Big data resource query method and system based on Internet of Things

Abstract

The invention provides a big data resource query method and system based on the Internet of Things, and the method comprises the steps: carrying out the semantic extension of each query keyword through the semantic similarity between a data query text and resource identification information, and obtaining an extension keyword set of a query request; determining the semantic association degree between each extended keyword in the extended keyword set and the data query text; extracting interest indexes of the target user when the target user queries each resource identifier in the resource identifier information from a query map of the target user, and performing preference matching on the data query text through all the interest indexes and resource semantics of each query keyword to obtain interest preference characteristics of the query request; and constructing a confidence index of resource semantics in the data query text according to the interest preference characteristics and each semantic association degree, and performing semantic feedback on the query request of the target user by using the confidence index. Based on the scheme, confidence feedback of semantics in the query request of the target user can be realized.

Description

Technical Field

[0001] This application relates to the technical field of identification matching of big data resources. More specifically, this application relates to a method and system for querying big data resources based on the Internet of Things. Background Art

[0002] With the development of technologies such as artificial intelligence and cloud computing, the big data resources of the Internet of Things are growing rapidly and have become the core driving force for intelligent applications. The number of Internet of Things devices is still increasing continuously. Billions of sensors and terminals have been deployed globally, covering multiple fields such as industry, healthcare, transportation, and energy, generating massive amounts of structured and unstructured data every day, including sensing data, log information, and video streams, providing support for intelligent decision-making and automated control.

[0003] In the process of querying big data resources, the existing technology mainly relies on keyword matching, that is, directly comparing the query keywords input by the user with the index keywords in the database to determine the matching degree. However, this method has obvious limitations. Especially in complex semantic query scenarios, keyword matching cannot handle semantic transformations such as synonyms and near-synonyms, and keyword matching has weak dependence on context, cannot parse the semantic relationships in the query text, and cannot accurately understand the user's query intention, resulting in a low relevance of the query results. Therefore, how to achieve a confidence feedback of the semantics in the target user's query request has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a method and system for querying big data resources based on the Internet of Things, which can achieve a confidence feedback of the semantics in the target user's query request.

[0005] In a first aspect, this application provides a method for querying big data resources based on the Internet of Things, including: Obtain the resource identification information in the Internet of Things. When the target user issues a query request for the big data resources in the Internet of Things, collect the data query text of the query request, and then extract multiple query keywords from the data query text; Semantically expand each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then determine the semantic association degree between each extended keyword in the extended keyword set and the data query text; Extract the interest index when the target user queries each resource identifier in the resource identification information from the query graph of the target user, and perform preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request; Construct a confidence index for the resource semantics in the data query text based on the interest preference characteristics and each semantic relevance degree, and use the confidence index to perform semantic feedback on the query request of the target user.

[0006] In some embodiments, semantic expansion is performed on each query keyword through the semantic similarity between the data query text and the resource identification information, and the obtained extended keyword set of the query request specifically includes: Perform semantic similarity comparison between the data query text and the resource identification information to obtain the semantic similarity between the data query text and the resource identification information; For each query keyword, perform similarity expansion on the semantic features in the query keyword through the semantic similarity to obtain multiple extended keywords; Determine an extended keyword subset of the query keyword through all the extended keywords, and further obtain an extended keyword subset of each query keyword; Determine the extended keyword set of the query request according to all the extended keyword subsets.

[0007] In some embodiments, determining the semantic relevance degree between each extended keyword in the extended keyword set and the data query text specifically includes: Extract the text semantic features of the data query text; For each extended keyword in the extended keyword set, extract the semantic expansion features of the extended keyword; Determine the semantic relevance degree between the extended keyword and the data query text through the semantic expansion features and the text semantic features, and further obtain the semantic relevance degree between each extended keyword in the extended keyword set and the data query text.

[0008] In some embodiments, extracting the interest index when the target user queries each resource identifier in the resource identification information from the query graph of the target user specifically includes: Obtain the query graph of the target user; For each resource identifier in the resource identification information, extract the query frequency and structural priority of the resource identifier from the query graph; Determine the interest index when the target user queries the resource identifier through the query frequency and the structural priority, and further obtain the interest index when the target user queries each resource identifier in the resource identification information.

[0009] In some embodiments, performing preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference characteristics of the query request specifically includes: For each query keyword in the data query text, extract the resource semantics of the query keyword; Match the interest preference of the query keyword according to the resource semantics and all interest indices to obtain the preference matching value of the query keyword, and further obtain the preference matching values of each query keyword in the data query text; Determine the interest preference characteristics of the query request through all the preference matching values.

[0010] In some embodiments, constructing the confidence index of the resource semantics in the data query text according to the interest preference characteristics and each semantic association degree specifically includes: For each query keyword, determine the index association characteristics of the query keyword through all the semantic association degrees; Extract the preference matching value of the query keyword from the interest preference characteristics; Construct the semantic index of the query keyword through the preference matching value and the index association characteristics, and further obtain the semantic indices of each query keyword; Merge all the semantic indices into the confidence index of the resource semantics in the data query text.

[0011] In some embodiments, using the confidence index to perform semantic feedback on the query request of the target user specifically includes: Use the confidence index as the semantic query index of the target user's query request to complete the semantic feedback of the target user's query request.

[0012] In a second aspect, the present application provides a big data resource query system based on the Internet of Things, including: An acquisition module, configured to acquire resource identification information in the Internet of Things, and when the target user issues a query request for big data resources in the Internet of Things, collect the data query text of the query request, and further extract multiple query keywords in the data query text; A processing module, configured to perform semantic expansion on each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and further determine the semantic association degree between each extended keyword in the extended keyword set and the data query text; The processing module is further configured to extract the interest indices when the target user queries each resource identifier in the resource identification information from the query graph of the target user, and perform preference matching on the data query text through all the interest indices and the resource semantics of each query keyword to obtain the interest preference characteristics of the query request; An execution module, configured to construct a confidence index of the resource semantics in the data query text according to the interest preference feature and each semantic association degree, and use the confidence index to perform semantic feedback on the query request of the target user.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data resource query method based on the Internet of Things.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer is caused to execute the above-mentioned big data resource query method based on the Internet of Things.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In a big data resource query method and system based on the Internet of Things provided by the present application, resource identification information in the Internet of Things is obtained. When a target user issues a query request for big data resources in the Internet of Things, the data query text of the query request is collected, and then a plurality of query keywords in the data query text are extracted; semantic expansion is performed on each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then the semantic association degree between each extended keyword in the extended keyword set and the data query text is determined; the interest index when the target user queries each resource identifier in the resource identification information is extracted from the query graph of the target user, and preference matching is performed on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request; a confidence index of the resource semantics in the data query text is constructed according to the interest preference feature and each semantic association degree, and the confidence index is used to perform semantic feedback on the query request of the target user.

[0016] It can be seen that in this application, a confidence index of the resource semantics in the data query text is constructed based on the interest preference features and various semantic association degrees, and the confidence index is used to perform semantic feedback on the query request of the target user; First. The semantic association degree reflects the semantic relevance between the query keyword and the resource identification information, enabling the query system to identify similar query requirements under different expression forms. Determining the semantic association degree can effectively quantify the semantic similarity between the query text and the resource data, ensuring that the extended keyword set can accurately reflect the original query intention. When a high-association semantic mapping is established between the extended keyword of the query request and the resource identification information, the construction of the confidence index can be based on a more comprehensive keyword set, making the query feedback result more semantically accurate. The confidence feedback of semantics can more accurately recommend resources that meet the user's needs, improving the relevance and coverage of the query results; Then, determining the interest preference features can incorporate the user's personalized needs into the query process, making the query results more in line with the actual usage scenario of the target user. Through the matching of the interest preference features, the extended keywords of the query request can be filtered and sorted according to the user's preferences, ensuring that the keywords finally used to construct the confidence index can give priority to reflecting the user's main interest points. When the query keyword has a certain degree of ambiguity or ambiguity, it can still perform accurate matching based on historical data and user preferences, thereby improving the construction quality of the confidence index of the query request. The semantic feedback combined with the interest preference features can further achieve a higher-precision resource recommendation, making the query results more personalized and practical; In summary, based on the above solutions, the confidence feedback of semantics in the query request of the target user can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0018] Figure 1 is an exemplary flowchart of a big data resource query method based on the Internet of Things according to some embodiments of the present application; Figure 2 is an architecture diagram of an Internet of Things data platform according to some embodiments of the present application; Figure 3 is a schematic flowchart of determining a confidence index according to some embodiments of the present application; Figure 4 is a schematic structural diagram of a big data resource query system based on the Internet of Things according to some embodiments of the present application; Figure 5Schematic diagram of a computer device for implementing an Internet of Things-based big data resource query method according to some embodiments of the present application. Detailed implementation manners

[0019] To better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0020] Refer to Figure 1 , which is an exemplary flowchart of an Internet of Things-based big data resource query method according to some embodiments of the present application. The Internet of Things-based big data resource query method mainly includes the following steps: In step 101, obtain resource identification information in the Internet of Things. When a target user issues a query request for big data resources in the Internet of Things, collect the data query text of the query request, and then extract multiple query keywords from the data query text.

[0021] It should be noted that in the present application, the resource identification information represents the unique identifier and its associated attributes of the Internet of Things big data resources, and is used to distinguish and retrieve different resource entities; the data query text represents the text content input by the target user in the query request; the query keyword is the core vocabulary for determining the query intent and performing semantic matching.

[0022] In specific implementation, the resource identifiers of each data resource in the Internet of Things can be obtained from the database of big data resources, so as to use the set of all resource identifiers as the resource identification information in the Internet of Things. When a target user issues a query request for big data resources in the Internet of Things, the request text can be collected from the query request as the data query text of the query request, and then natural language processing technology (for example: word segmentation algorithm) can be used to split the query text into multiple query keywords.

[0023] In some embodiments, refer to Figure 2 as described, this figure is an architecture diagram of an Internet of Things data platform according to some embodiments of the present application. This figure shows the basic architecture of the Internet of Things data platform. This figure includes three main parts: the Internet of Things data platform, a processing device, and an acquisition device. The Internet of Things data platform is located at the top of the figure and is responsible for receiving data uploads from the processing device. The processing device is located in the middle layer and plays a role in connecting the data platform and the acquisition device. The processing device reads data from the acquisition device and uploads this data to the Internet of Things data platform.

[0024] The figure also shows two types of acquisition devices: mobile acquisition devices and fixed acquisition devices. Both acquisition devices collect information by reading data and upload the data to the processing device. Mobile acquisition devices may be used in scenarios that require flexible deployment, while fixed acquisition devices are installed at fixed positions for continuous monitoring of specific areas or devices. Through this hierarchical structure, the entire Internet of Things data platform realizes data collection, processing, and uploading, providing basic data support for Internet of Things applications.

[0025] In step 102, semantic expansion is performed on each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then the semantic association degree between each extended keyword in the extended keyword set and the data query text is determined.

[0026] In some embodiments, semantic expansion of each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request can be implemented by the following steps: Perform semantic similarity comparison between the data query text and the resource identification information to obtain the semantic similarity between the data query text and the resource identification information; For each query keyword, perform similarity expansion on the semantic features in the query keyword through the semantic similarity to obtain multiple extended keywords; Determine an extended keyword subset of the query keyword through all the extended keywords, and then obtain an extended keyword subset of each query keyword; Determine the extended keyword set of the query request according to all the extended keyword subsets.

[0027] In specific implementation, first, a semantic similarity comparison is made between the data query text and the resource identification information. The semantic similarity between the data query text and the resource identification information can be achieved in the following manner, namely: for each resource identification in the resource identification information, a word vector model is used to convert the resource identification and the data query text into vectors, and then the Euclidean distance between the two converted vectors is used as the semantic similarity between the resource identification and the data query text. Through the above method, the semantic similarity between each resource identification and the data query text can be obtained, and thus the set of all semantic similarities can be used as the semantic similarity between the data query text and the resource identification information. Secondly, for each query keyword, a similarity expansion of the semantic features in the query keyword is performed through the semantic similarity to obtain multiple extended keywords, which can be achieved in the following manner, namely: the historical surprise preset similarity threshold can be combined, and the resource identifications corresponding to the semantic similarities greater than the similarity threshold in the semantic similarity are obtained as extended resource identifications, and thus multiple extended resource identifications can be obtained. For each query keyword, a word vector model can be used to convert the resource identification and the data query text into vectors. Then, an extended keyword subset of the query keyword is determined through all the extended keywords, and further, an extended keyword subset of each query keyword can be obtained in the following manner, namely: the set of all extended keywords is used as the extended keyword subset of the query keyword. Through the above method, the extended keyword subset of each query keyword can be obtained. Finally, an extended keyword set of the query request is determined according to all the extended keyword subsets, which can be achieved in the following manner, namely: the set of all extended keyword subsets is used as the extended keyword set of the query request.

[0028] It should be noted that in this application, the extended keyword set represents the set of all extended keywords for the query request; the extended keyword subset represents the set of extended keywords generated for a specific query keyword; the extended keyword is a vocabulary used to enhance the semantic expression ability of the query; the semantic similarity represents the degree of semantic overlap between the data query text and the resource identification information.

[0029] In some embodiments, the semantic relevance degree between each extended keyword in the extended keyword set and the data query text can be determined by the following steps: Extract the text semantic features of the data query text; For each extended keyword in the extended keyword set, extract the semantic expansion features of the extended keyword; Determine the semantic relevance degree between the extended keyword and the data query text through the semantic expansion features and the text semantic features, and further obtain the semantic relevance degree between each extended keyword in the extended keyword set and the data query text.

[0030] In specific implementation, first, the text semantic features of the data query text can be extracted in the following way, that is: use the word embedding model in natural language processing (for example: Word2Vec) to extract the text semantic feature vector of the data query text as the text semantic feature of the data query text; then, for each extended keyword in the extended keyword set, the semantic extension features of the extended keyword can be extracted in the following way, that is: for each extended keyword in the extended keyword set, use the word embedding model in natural language processing (for example: Word2Vec) to extract the semantic feature vector of the extended keyword as the semantic extension feature of the extended keyword; finally, the semantic association degree between the extended keyword and the data query text is determined through the semantic extension feature and the text semantic feature, and further the semantic association degree between each extended keyword in the extended keyword set and the data query text can be obtained in the following way, that is: take the cosine similarity between the semantic extension feature and the text semantic feature as the semantic association degree between the extended keyword and the data query text. Through the above method, the semantic association degree between each extended keyword in the extended keyword set and the data query text can be obtained.

[0031] It should be noted that in this application, the semantic association degree represents the semantic matching degree between the query keyword and the data query text; the text semantic feature represents the feature of the semantic information in the data query text; the semantic extension feature represents the feature of the semantic information in the extended keyword.

[0032] In step 103, the interest index when the target user queries each resource identifier in the resource identifier information is extracted from the query graph of the target user, and the data query text is preferentially matched through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request.

[0033] In some embodiments, the interest index when the target user queries each resource identifier in the resource identifier information can be extracted from the query graph of the target user by the following steps: Obtain the query graph of the target user; For each resource identifier in the resource identifier information, extract the query frequency and structural priority of the resource identifier from the query graph; Determine the interest index when the target user queries the resource identifier through the query frequency and the structural priority, and further obtain the interest index when the target user queries each resource identifier in the resource identifier information.

[0034] In specific implementation, first, the query graph of the target user can be obtained in the following way: obtain the query records of the target user from the log database of the Internet of Things. The query records include query frequency, query index path, query target, and query time. Then, use the structured standard in the log database to model the query records as a graph, and further use the modeled graph as the query graph of the target user. Then, for each resource identifier in the resource identifier information, the query frequency and structural priority of the resource identifier can be extracted from the query graph in the following way: for each resource identifier in the resource identifier information, obtain all the query frequencies and all the query index paths corresponding to the data with the query target being the resource identifier from the query records. Thus, the average value of all the query frequencies can be used as the query frequency of the resource identifier. For each query index path, use graph theory metrics (such as PageRank) to calculate the node centrality of the query index path as the index priority of the query index path. Thus, the average value of all the index priorities can be used as the structural priority of the resource identifier. Finally, the interest index when the target user queries the resource identifier can be determined through the query frequency and the structural priority, and further the interest index when the target user queries each resource identifier in the resource identifier information can be obtained in the following way: use the product of the query frequency and the structural priority as the interest index when the target user queries the resource identifier. Through the above method, the interest index when the target user queries each resource identifier in the resource identifier information can be obtained.

[0035] It should be noted that in this application, the interest index represents the intensity of the user's query preference for a specific resource identifier; the query graph represents the structured knowledge representation of the user's historical query behavior; the query frequency represents the number of times the user queries a specific resource identifier; the structural priority represents the importance degree of different resource identifiers in the query graph.

[0036] In some embodiments, the interest preference feature of the query request can be obtained by performing preference matching on the data query text through all the interest indices and the resource semantics of each query keyword, which can be implemented by the following steps: For each query keyword in the data query text, extract the resource semantics of the query keyword. According to the resource semantics and all the interest indices, perform matching on the interest preference of the query keyword to obtain the preference matching value of the query keyword, and further obtain the preference matching values of each query keyword in the data query text. Determine the interest preference feature of the query request through all the preference matching values.

[0037] In specific implementation, first, for each query keyword in the data query text, the resource semantics of the query keyword can be extracted in the following way: for each query keyword in the data query text, use a word embedding model in natural language processing (e.g., Word2Vec) to extract the text semantic feature vector of the query keyword as the resource semantics of the query keyword; then, match the interest preference of the query keyword according to the resource semantics and all interest indices to obtain the preference matching value of the query keyword. Furthermore, the preference matching values of each query keyword in the data query text can be obtained in the following way: for each resource identifier in the resource identifier information, initialize a matching mapping model based on the attention mechanism, use the resource semantics as the input feature in this matching mapping model, use the interest index when the target user queries the resource identifier as the weight parameter in this mapping model, and use this matching mapping model to perform matching mapping on the semantic relevance between the query keyword and the resource identifier. Thus, the result of the matching mapping can be used as the matching mapping value between the query keyword and the resource identifier. Through the above method, the matching mapping values between the query keyword and each resource identifier can be obtained, and thus the set of all matching mapping values can be used as the value range of the preference matching value, and the preference matching value of the query keyword can be obtained. Through the above method, the preference matching values of each query keyword in the data query text can be obtained; finally, the interest preference characteristics of the query request can be determined through all the preference matching values in the following way: use the set of all preference matching values as the interest preference characteristics of the query request.

[0038] It should be noted that in this application, the interest preference characteristic represents the interest tendency and query preference of the target user for the query keyword; the resource semantics represents the semantic information of the Internet of Things big data resource; the preference matching value represents the matching degree between the query keyword and the user interest; the matching mapping model based on the attention mechanism is a deep learning method used to improve the model's ability to focus on key features, which can dynamically adjust the importance of different input features in the matching task. In the above matching mapping model, the resource semantics is used as the input feature, representing the information expression of the query keyword and the resource identifier, while the interest index when the target user queries the resource identifier is used as the weight parameter, representing the influence of the user's historical query preference on resource matching. This matching mapping model first calculates the preliminary matching score between the resource semantics and the query keyword, and then weights it through the attention weight (i.e., the interest index), dynamically adjusting the contribution of different resource semantic features to generate an optimized matching score; this process uses mechanisms such as self-attention, calculates the attention distribution of different resource semantics through softmax normalization, so that highly relevant features obtain higher weights. Finally, the model outputs the matching mapping value between the query keyword and the resource identifier to improve the accuracy of semantic matching and realize the intelligent adaptation to the query preference of the target user.

[0039] In step 104, a confidence index for the resource semantics in the data query text is constructed based on the interest preference feature and each semantic association degree, and the confidence index is used to perform semantic feedback on the query request of the target user.

[0040] In some embodiments, a confidence index for the resource semantics in the data query text is constructed based on the interest preference feature and each semantic association degree. Referring to Figure 3 as described, this figure is a schematic flowchart for determining the confidence index in some embodiments of the present application. In this embodiment, the determination of the confidence index can be implemented by the following steps: In step 1041, for each query keyword, the index association feature of the query keyword is determined through all semantic association degrees; In step 1042, the preference matching value of the query keyword is extracted from the interest preference feature; In step 1043, a semantic index of the query keyword is constructed through the preference matching value and the index association feature, and then the semantic indexes of all query keywords are obtained; In step 1044, all semantic indexes are merged into the confidence index for the resource semantics in the data query text.

[0041] In specific implementation, first, for each query keyword, the index association feature of the query keyword can be determined through all semantic association degrees in the following manner, that is, for each query keyword, an extended keyword subset of the query keyword is obtained from the extended keyword set, and the semantic association degrees of each extended keyword in the extended keyword subset are obtained from all semantic association degrees as index values, so as to use the set of all index values as the index association feature of the query keyword; second, the preference matching value of the query keyword can be extracted from the interest preference feature in the following manner, that is: the value range of the preference matching value of the query keyword in the interest preference feature is used as the preference matching value of the query keyword; then, the semantic index of the query keyword can be constructed through the preference matching value and the index association feature, and further the semantic index of each query keyword can be obtained in the following manner, that is: a multi-layer perceptron model based on a neural network is initialized, the value range of the preference matching value is used as the first input layer in the multi-layer perceptron model, the index association feature is used as the second input layer in the multi-layer perceptron model, and the multi-layer perceptron model is used to generate the semantic index of the query keyword. Through the above method, the semantic index of each query keyword can be obtained; finally, all semantic indexes can be merged into the confidence index of the resource semantics in the data query text in the following manner, that is, the frequency of each query keyword appearing in the historical query record can be used as a weight, and all semantic indexes are merged into the confidence index of the resource semantics in the data query text by means of weighted concatenation.

[0042] It should be noted that in this application, the confidence index is an index used for querying data resources in the data query text; the index association feature represents the association degree between the semantic information of the query keyword and the query text; the preference matching value represents the degree of the user's interest preference for the query keyword; the semantic index is an index used for querying the resource semantics of the query keyword; the multi-layer perceptron model is a feedforward neural network composed of multiple fully connected neuron layers, which can perform feature transformation and pattern mapping on the input data through a non-linear activation function. In the above process, the first input layer of the multi-layer perceptron model receives the value range of the preference matching value, representing the matching degree between the query keyword and the user's interest preference; the second input layer receives the index association feature, representing the semantic relevance of the query keyword in the data query text. The multi-layer perceptron model performs feature interaction and non-linear mapping through multiple hidden layers, extracts deep semantic relationships, and finally outputs the semantic index of the query keyword. This semantic index is used to construct the confidence index of the query request to improve the semantic matching degree of the query result and the adaptability of the user preference.

[0043] In some embodiments, the semantic feedback on the query request of the target user can be implemented by the following steps using the confidence index: Use the confidence index as the semantic query index of the target user's query request to complete the semantic feedback of the target user's query request.

[0044] In addition, on the other hand of the present application, in some embodiments, the present application provides a big data resource query system based on the Internet of Things. Refer to Figure 4 , this figure is a schematic structural diagram of a big data resource query system based on the Internet of Things shown according to some embodiments of the present application. The big data resource query system based on the Internet of Things includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described as follows: The acquisition module 201. In the present application, the acquisition module 201 is mainly used to acquire resource identification information in the Internet of Things. When the target user issues a query request for big data resources in the Internet of Things, collect the data query text of the query request, and then extract multiple query keywords in the data query text; The processing module 202. In the present application, the processing module 202 is used to semantically expand each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then determine the semantic association degree between each extended keyword in the extended keyword set and the data query text; It should be noted that the processing module 202 is also used to extract the interest index when the target user queries each resource identifier in the resource identification information from the query graph of the target user, and perform preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request; The execution module 203. In the present application, the execution module 203 is mainly used to construct a confidence index of the resource semantics in the data query text based on the interest preference feature and each semantic association degree, and use the confidence index to perform semantic feedback on the query request of the target user.

[0045] The above has introduced in detail the examples of the big data resource query method and system based on the Internet of Things provided by the embodiments of the present application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0046] In some embodiments, the present application further provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data resource query method based on the Internet of Things.

[0047] In some embodiments, referring to Figure 5 , the dashed line in this figure indicates that the unit or module is optional. This figure is a schematic structural diagram of a computer device for implementing the big data resource query method based on the Internet of Things according to an embodiment of the present application. The above-mentioned big data resource query method based on the Internet of Things can be implemented by Figure 5 the computer device shown. The computer device includes at least one processor 301, a memory 302, and at least one communication unit 305. The computer device can be a terminal device, a server, or a chip.

[0048] The processor 301 can be a general-purpose processor or a special-purpose processor. For example, the processor 301 can be a central processing unit (CPU). The CPU can be used to control the computer device, execute software programs, and process the data of software programs. The computer device can also include a communication unit 305 for realizing the input (reception) and output (transmission) of signals.

[0049] For example, the computer device can be a chip, and the communication unit 305 can be the input and / or output circuit of the chip, or the communication unit 305 can be the communication interface of the chip. The chip can be a component of a terminal device, a network device, or other devices.

[0050] Again, for example, the computer device can be a terminal device or a server, and the communication unit 305 can be the transceiver of the terminal device or the server, or the communication unit 305 can be the transceiver circuit of the terminal device or the server.

[0051] The computer device may include one or more memories 302, on which there is a program 304. The program 304 can be run by the processor 301 to generate instructions 303, so that the processor 301 executes the method described in the above method embodiments according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302. The data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0052] The processor 301 and the memory 302 can be separately provided or integrated together. For example, they can be integrated on a system on chip (SOC) of a terminal device.

[0053] It should be understood that the steps of the above method embodiments can be completed by a logic circuit in hardware form or an instruction in software form in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices. For example, discrete gate, transistor logic devices, or discrete hardware components.

[0054] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0055] For example, in some embodiments, the present application also provides a computer-readable storage medium. Instructions or code are stored in the computer-readable storage medium. When the instructions or code run on a computer, the computer is caused to execute the above-described method for querying big data resources based on the Internet of Things.

[0056] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0057] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for querying big data resources based on the Internet of Things, characterized in that It includes the following steps: Obtain the resource identification information in the Internet of Things. When the target user issues a query request for the big data resources in the Internet of Things, collect the data query text of the query request, and then extract multiple query keywords from the data query text; Semantically expand each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then determine the semantic association degree between each extended keyword in the extended keyword set and the data query text; Extract the interest index when the target user queries each resource identification in the resource identification information from the query graph of the target user, and perform preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request; Construct a confidence index for the resource semantics in the data query text based on the interest preference feature and each semantic association degree, and use the confidence index to perform semantic feedback on the query request of the target user.

2. The method according to claim 1, wherein Semantically expanding each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request specifically includes: Perform semantic similarity comparison between the data query text and the resource identification information to obtain the semantic similarity between the data query text and the resource identification information; For each query keyword, perform similarity expansion on the semantic features in the query keyword through the semantic similarity to obtain multiple extended keywords; Determine an extended keyword subset of the query keyword through all the extended keywords, and then obtain an extended keyword subset of each query keyword; Determine the extended keyword set of the query request according to all the extended keyword subsets.

3. The method according to claim 1, characterized in that, Determining the semantic association degree between each extended keyword in the extended keyword set and the data query text specifically includes: Extract the text semantic features of the data query text; For each extended keyword in the extended keyword set, extract the semantic expansion features of the extended keyword; Determine the semantic association degree between the extended keyword and the data query text through the semantic expansion features and the text semantic features, and then obtain the semantic association degree between each extended keyword in the extended keyword set and the data query text.

4. The method according to claim 1, characterized in that Extracting the interest index when the target user queries each resource identification in the resource identification information from the query graph of the target user specifically includes: Obtain the query graph of the target user; For each resource identification in the resource identification information, extract the query frequency and structural priority of the resource identification from the query graph; Determine the interest index when the target user queries the resource identification through the query frequency and the structural priority, and then obtain the interest index when the target user queries each resource identification in the resource identification information.

5. The method according to claim 1, characterized in that, Performing preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference feature of the query request specifically includes: For each query keyword in the data query text, extract the resource semantics of the query keyword; Match the interest preference of the query keyword according to the resource semantics and all interest indexes to obtain the preference matching value of the query keyword, and then obtain the preference matching values of each query keyword in the data query text; Determine the interest preference characteristics of the query request through all the preference matching values.

6. The method according to claim 1, wherein Constructing the confidence index of the resource semantics in the data query text based on the interest preference characteristics and each semantic association degree specifically includes: For each query keyword, determine the index association characteristics of the query keyword through all the semantic association degrees; Extract the preference matching value of the query keyword from the interest preference characteristics; Construct the semantic index of the query keyword through the preference matching value and the index association characteristics, and then obtain the semantic indexes of each query keyword; Merge all the semantic indexes into the confidence index of the resource semantics in the data query text.

7. The method according to claim 1, characterized in that, Using the confidence index to perform semantic feedback on the query request of the target user specifically includes: Use the confidence index as the semantic query index of the query request of the target user to complete the semantic feedback of the query request of the target user.

8. A big data resource query system based on the Internet of Things, characterized in that, Including: An acquisition module, configured to acquire resource identification information in the Internet of Things, and when a target user issues a query request for big data resources in the Internet of Things, collect the data query text of the query request, and then extract multiple query keywords in the data query text; A processing module, configured to perform semantic expansion on each query keyword through the semantic similarity between the data query text and the resource identification information to obtain an extended keyword set of the query request, and then determine the semantic association degree between each extended keyword in the extended keyword set and the data query text; The processing module is further configured to extract the interest indexes when the target user queries each resource identifier in the resource identification information from the query graph of the target user, and perform preference matching on the data query text through all the interest indexes and the resource semantics of each query keyword to obtain the interest preference characteristics of the query request; An execution module, configured to construct the confidence index of the resource semantics in the data query text based on the interest preference characteristics and each semantic association degree, and use the confidence index to perform semantic feedback on the query request of the target user.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the method for querying big data resources based on the Internet of Things according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Instructions or codes are stored in the computer-readable storage medium, and when the instructions or codes are run on a computer, the computer is caused to execute the method for querying big data resources based on the Internet of Things according to any one of claims 1 to 7.

Images