An incomplete data query method and related equipment based on agricultural Internet of Things

By extracting and converting agricultural IoT data flows and calculating similarity mapping data, the low query accuracy and data security problems caused by data flow incompleteness in agricultural IoT are solved, and efficient data query and privacy protection are achieved .

CN118820544BActive Publication Date: 2024-11-19HUNAN FULLRIVER INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411298879.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-19
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

The incompleteness of data flows in the agricultural Internet of Things leads to low accuracy of data query, existing methods are difficult to deal with in outsourcing scenarios, and there are data leakage and privacy protection issues.

Method used

By obtaining the feature extraction and transformation of agricultural data flow, compute similarity mapping data, query and filtering of target data flow, improve the security and query accuracy of data flow, and realize data privacy protection.

Benefits of technology

It improves the query accuracy and security of agricultural data flows, ensures data privacy protection, and solves the query problems of incomplete data flows and data security challenges in outsourcing scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118820544B_ABST
    Figure CN118820544B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of agricultural data privacy protection, and provides an incomplete data query method based on the agricultural Internet of Things and related equipment. The method includes: extracting features from an agricultural data stream to obtain data features; converting the agricultural data stream into a first data stream and a second data stream, and converting the data features into a first data feature and a second data feature; extracting features from a retrieval data stream to obtain retrieval data features, and converting the retrieval data stream into a first retrieval data stream and a second retrieval data stream, and converting the retrieval data features into a first retrieval data feature and a second retrieval data feature; calculating first mapping data and second mapping data; determining a target agricultural data stream from all agricultural data streams according to the first mapping data, the second mapping data, the first data stream, and the second data stream; and sending the target agricultural data stream to a target user. The method can improve the query accuracy and security of agricultural data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of agricultural data privacy protection, and in particular to an incomplete data query method and related equipment based on the agricultural Internet of Things. Background Art

[0002] The agricultural Internet of Things can collect a large amount of biological and environmental data, such as geographic location, light, humidity, temperature, soil composition, crop growth, etc., by integrating various sensors, controllers, actuators and other devices, providing rich information support for agricultural production. Due to various reasons (such as sensor failure, network interruption, etc.), the data stream in the agricultural Internet of Things may be incomplete. These incomplete data streams may mislead the making of agricultural production decisions, so an effective query method is needed to process these incomplete data. General data query methods require preset weights of each attribute or clear rules for retrieval and optimization, but each attribute usually shows correlation, and these preset conditions are difficult to generalize. Skyline query is to filter out a data subset that is not dominated by any other data point from a given data set, that is, to find samples that perform well in multiple key attributes, and provide scientific decision support for agricultural production, such as safety production warning or planting yield recommendation, that is, to allow users to enter the attribute data and decision preferences of the query sample, and the skyline retrieves excellent data that is close enough to the query sample in some dimensions, and then returns relevant agricultural features.

[0003] As the number of query responses increases, more and more data owners choose to outsource their data to cloud servers to take advantage of their extensive computing and storage capabilities, enabling authorized users to retrieve skyline samples from these outsourced agricultural data. However, agricultural data is an important asset for agricultural producers, and these data have been cultivated and studied for a long time and have high value. If these data are leaked or abused, it will cause huge losses to agricultural producers, so the data of these organisms needs to be protected from illegal acquisition by cloud servers and other unauthorized users.

[0004] At present, secure skyline query methods are mainly performed on complete data sets. The incompleteness of data streams brings new challenges, where missing data hinders the dominance comparison of data items and destroys the transitive properties implied by the skyline, resulting in cyclic dominance between data. In a plaintext environment, these incomplete dimensions can be simply marked and skipped. However, in an outsourcing scenario, these intermediate operations and results mean that even if the exact data is protected, more indirect information about the data can potentially be revealed. At the same time, since the transitivity of dominance is not applicable to incomplete data, most transitivity-based skyline algorithms cannot be applied. It can be seen that the existing agricultural data query methods have the problem of low query accuracy of agricultural data. Summary of the invention

[0005] The present application provides an incomplete data query method and related equipment based on the agricultural Internet of Things, which can solve the problem of low query accuracy of agricultural data.

[0006] In the first aspect, the present application provides an incomplete data query method based on the agricultural Internet of Things, the query method comprising:

[0007] Acquire multiple agricultural data streams, and perform feature extraction on each agricultural data stream to obtain data features of each agricultural data stream; the agricultural data stream includes multiple dimensions, the multiple dimensions correspond to multiple agricultural data one by one, and the data features are used to describe the missing status of agricultural data in the agricultural data stream;

[0008] For each agricultural data stream, convert the agricultural data stream into a first data stream and a second data stream, and convert the data features of the agricultural data stream into a first data feature and a second data feature;

[0009] Acquire a search data stream of a target user, perform feature extraction on the search data stream, obtain search data features, convert the search data stream into a first search data stream and a second search data stream, and convert the search data features into first search data features and second search data features; the search data stream includes multiple dimensions, and the multiple dimensions correspond to the multiple search data one by one;

[0010] Based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, first mapping data and second mapping data of each agricultural data stream are calculated; the first mapping data is used to describe the similarity between the first data stream and the first search data stream, and the second mapping data is used to describe the similarity between the second data stream and the second search data stream;

[0011] According to all the first mapping data, all the second mapping data, all the first data streams, and the second data streams, a query is performed in all the agricultural data streams to determine a plurality of target agricultural data streams;

[0012] Send all targeted agricultural data streams to targeted users.

[0013] Optionally, feature extraction is performed on each agricultural data stream to obtain data features of each agricultural data stream, including:

[0014] For each agricultural data stream, perform the following steps:

[0015] For each dimension in the agricultural data stream, if the dimension has corresponding agricultural data, the characteristic value of the dimension is set to 1; if the dimension does not have corresponding agricultural data, the characteristic value of the dimension is set to 0;

[0016] The characteristic values ​​of all dimensions are integrated to obtain the data characteristics of the agricultural data stream.

[0017] Optionally, based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, the first mapping data and the second mapping data of each agricultural data stream are calculated, including:

[0018] For each agricultural data stream respectively, based on the first data stream, the second data stream, the first retrieval data stream and the second retrieval data stream of the agricultural data stream, the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream are calculated; and based on the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream, the first mapping data and the second mapping data of the agricultural data stream are calculated.

[0019] Optionally, based on the first data stream, the second data stream, the first search data stream, and the second search data stream of the agricultural data stream, calculating the Euclidean distance between the first data stream and the first search data stream and the Euclidean distance between the second data stream and the second search data stream comprises:

[0020] By formula:

[0021] ;

[0022] ;

[0023] ;

[0024] Calculate the The Euclidean distance between the first data stream and the first search data stream and The Euclidean distance between the second data stream and the second search data stream ;

[0025] in, represents the first multiplication algorithm for secret sharing, Indicates The first data stream The agricultural data of the first dimension and the first retrieval data stream The Euclidean distance between the retrieved data in dimensions, Indicates The second data stream The agricultural data of the second dimension and the The Euclidean distance between the retrieved data in dimensions, Indicates The first data stream The value of the dimension, Indicates The second data stream The value of the dimension, Indicates the first search data stream The value of the dimension, Indicates the second search data stream The value of the dimension, represents the modulus, represents the number of agricultural data streams, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, Indicates The Euclidean distance between the value of the first dimension of the first data stream and the value of the first dimension of the first search data stream, Indicates The first data stream The value of the dimension is the same as the value of the first retrieval data stream. The Euclidean distance between the values ​​of the dimensions, Indicates The Euclidean distance between the value of the first dimension of the second data stream and the value of the first dimension of the second search data stream, Indicates The second data stream The value of the dimension is the same as the value of the The Euclidean distance between the values ​​in the dimension.

[0026] Calculating first mapping data and second mapping data of the agricultural data stream based on the Euclidean distance between the first data stream and the first search data stream and the Euclidean distance between the second data stream and the second search data stream includes:

[0027] By formula:

[0028] ;

[0029] ;

[0030] ;

[0031] Calculate the First mapping data and Second mapping data ;

[0032] in, represents the second multiplication algorithm for secret sharing, Indicates The first mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates the first search data feature The value of the dimension, Indicates the second search data feature The value of the dimension, Indicates the value of the first dimension in the first mapping data of the first data stream, Indicates The first mapping data of the first data stream The value of the dimension, Indicates The value of the first dimension in the second mapping data, Indicates The second mapping data The value of a dimension.

[0033] Optionally, according to all the first mapping data, all the second mapping data, all the first data streams, and the second data streams, a query is performed in all the agricultural data streams to determine a plurality of target agricultural data streams, including:

[0034] For each agricultural data stream, respectively, calculate the first attribute sum and the second attribute sum of the agricultural data stream according to the first mapping data, the second mapping data, the first data feature, and the second data feature corresponding to the agricultural data stream;

[0035] According to the sum of all first attributes and the sum of all second attributes, all agricultural data streams are sorted from small to large to obtain a sorting result, and the first multiple agricultural data streams in the sorting result are used as a filtering sequence;

[0036] All first data streams corresponding to the filter sequence are used as the first filter sequence, and all second data streams corresponding to the filter sequence are used as the second filter sequence;

[0037] Based on the first filtering sequence and the second filtering sequence, calculating a first incomplete dominance result between every two first data streams in the first filtering sequence and a second incomplete dominance result between every two second data streams in the second filtering sequence;

[0038] For each agricultural data stream in the filtering sequence, multiple domination results are calculated based on all first incomplete domination results and all second incomplete domination results corresponding to the agricultural data stream. If there is a domination result whose value is equal to 1, the agricultural data stream is removed. If there is no domination result whose value is equal to 1, the agricultural data stream is used as a target data stream.

[0039] Optionally, calculating the first attribute sum and the second attribute sum of the agricultural data stream according to the first mapping data, the second mapping data, the first data feature, and the second data feature corresponding to the agricultural data stream includes:

[0040] By formula:

[0041]

[0042] Calculate the The first attribute of the agricultural data stream and and The second attribute of the agricultural data stream and ;

[0043] in, represents the third multiplication algorithm for secret sharing, Indicates The first data feature The value of the dimension, Indicates The first mapping data The value of the dimension, Indicates The second data feature The value of the dimension, Indicates The second mapping data The value of the dimension, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, represents the number of agricultural data streams, Indicates the modulus.

[0044] Optionally, based on the first filtering sequence and the second filtering sequence, calculating a first incomplete dominance result between every two first data streams in the first filtering sequence and a second incomplete dominance result between every two second data streams in the second filtering sequence includes:

[0045] By formula:

[0046]

[0047]

[0048]

[0049]

[0050]

[0051]

[0052] Calculate the The first data stream and the The first incomplete dominance result between the first data streams and The second data stream and the The second incomplete type dominance result between the second data streams ;

[0053] in, represents the fourth multiplication algorithm for secret sharing, represents the comparison algorithm for secret sharing, represents the fifth multiplication algorithm for secret sharing, Indicates The first data stream and the The strict dominance results between the first data streams, Indicates that under the public complete dimension, Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result, Indicates The second data stream and the The strict dominance result between the second data streams, Indicates that under the public complete dimension, Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, represents the modulus, Indicated in The first data stream is affected by The complete properties of the first data stream and, Indicated in The first data stream is affected by The complete properties of the first data stream and, Indicated in The second data stream is affected by The complete properties of the second data stream and, Indicated in The second data stream is affected by The complete properties of the second data stream and, Indicated in The first data stream is affected by The common integrity characteristics of the first data stream, Indicated in The second data stream is affected by The common integrity characteristics of the second data stream, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, Indicated in Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result, Indicated in Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, Indicates The first mapping data The value of the dimension, Indicates The first mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, , , Indicates the number of agricultural data streams in the filtered sequence.

[0054] Optionally, based on all first incomplete domination results and all second incomplete domination results corresponding to the agricultural data stream, multiple domination results are calculated, including:

[0055] By formula:

[0056]

[0057] Calculate the Agricultural data streams are Domination results under the influence of data flow ;

[0058] in, Indicates The first data stream of the agricultural data stream and the The first incomplete type dominates the result between the data streams, Indicates The second data stream of the agricultural data stream is The second incomplete type between the second data streams dominates the result.

[0059] In a second aspect, an embodiment of the present application provides an incomplete data query device based on the agricultural Internet of Things, comprising:

[0060] The feature extraction module obtains multiple agricultural data streams and performs feature extraction on each agricultural data stream to obtain data features of each agricultural data stream; the agricultural data stream includes multiple dimensions, and the multiple dimensions correspond to multiple agricultural data one by one. The data features are used to describe the missing status of agricultural data in the agricultural data stream;

[0061] A first conversion module, for each agricultural data stream, converts the agricultural data stream into a first data stream and a second data stream, and converts data features of the agricultural data stream into first data features and second data features;

[0062] The second conversion module obtains the search data stream of the target user, performs feature extraction on the search data stream, obtains search data features, and converts the search data stream into a first search data stream and a second search data stream, and converts the search data features into first search data features and second search data features; the search data stream includes multiple dimensions, and the multiple dimensions correspond to the multiple search data one by one;

[0063] A calculation module, based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, calculates the first mapping data and the second mapping data of each agricultural data stream; the first mapping data is used to describe the similarity between the first data stream and the first search data stream, and the second mapping data is used to describe the similarity between the second data stream and the second search data stream;

[0064] A query module, querying among all agricultural data streams according to all first mapping data, all second mapping data, all first data streams, and second data streams, and determining a plurality of target agricultural data streams;

[0065] The sending module sends all target agricultural data streams to target users.

[0066] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned incomplete data query method based on the agricultural Internet of Things when executing the above-mentioned computer program.

[0067] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned incomplete data query method based on the agricultural Internet of Things.

[0068] The above solution of the present application has the following beneficial effects:

[0069] In an embodiment of the present application, multiple agricultural data streams are obtained, and feature extraction is performed on each agricultural data stream to obtain data features of each agricultural data stream. Then, for each agricultural data stream, the agricultural data stream is converted into a first data stream and a second data stream, and the data features of the agricultural data stream are converted into first data features and second data features. Then, the retrieval data stream of the target user is obtained, and feature extraction is performed on the retrieval data stream to obtain retrieval data features, and the retrieval data stream is converted into a first retrieval data stream and a second retrieval data stream, and the retrieval data features are converted into first retrieval data features and second retrieval data features. Then, based on all first data streams, all second data streams, first retrieval data streams and second retrieval data streams, first mapping data and second mapping data of each agricultural data stream are calculated. Then, based on all first mapping data, all second mapping data, all first data streams and second data streams, queries are performed in all agricultural data streams to determine multiple target agricultural data streams, and finally all target agricultural data streams are sent to target users. Among them, obtaining the data characteristics of the agricultural data stream can describe the data missing status of the agricultural data stream. The accuracy and rationality of the mapping data calculated under the consideration of the data missing status are improved. The target agricultural data stream is determined according to the mapping data with high accuracy and rationality, which realizes the query of incomplete data streams, improves the accuracy of the target agricultural data stream, and further improves the query accuracy of agricultural data.

[0070] In addition, converting the agricultural data stream and the retrieval data stream into two data streams can improve the security of the agricultural data stream and the retrieval data stream, and can facilitate the transmission of the two data streams to two devices for processing respectively. A single device only has a part of the data after the data stream is converted, and cannot know the complete information of the data stream, thereby achieving privacy protection for the agricultural data stream and the retrieval data stream.

[0071] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 A flowchart of an incomplete data query method based on the agricultural Internet of Things provided in one embodiment of the present application;

[0074] Figure 2 A specific flow chart of an incomplete data query method based on the agricultural Internet of Things provided in one embodiment of the present application;

[0075] Figure 3 A schematic diagram of the structure of an incomplete data query device based on the agricultural Internet of Things provided in one embodiment of the present application;

[0076] Figure 4 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0077] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0078] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0079] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0080] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0081] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0082] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0083] In response to the problem of low query accuracy of existing agricultural data, the present application provides an incomplete data query method based on the agricultural Internet of Things. The incomplete data query method obtains multiple agricultural data streams and performs feature extraction on each agricultural data stream to obtain data features of each agricultural data stream, and then converts the agricultural data stream into a first data stream and a second data stream for each agricultural data stream, and converts the data features of the agricultural data stream into first data features and second data features, then obtains the retrieval data stream of the target user, and performs feature extraction on the retrieval data stream to obtain retrieval data features, and converts the retrieval data stream into a first retrieval data stream and a second retrieval data stream, and converts the retrieval data features into first retrieval data features and second retrieval data features, and then based on all first data streams, all second data streams, first retrieval data streams and second retrieval data streams, calculate the first mapping data and second mapping data of each agricultural data stream, and then query all agricultural data streams based on all first mapping data, all second mapping data, all first data streams, and second data streams to determine multiple target agricultural data streams, and finally send all target agricultural data streams to the target user. Among them, obtaining the data characteristics of the agricultural data stream can describe the data missing status of the agricultural data stream. The accuracy and rationality of the mapping data calculated under the consideration of the data missing status are improved. The target agricultural data stream is determined according to the mapping data with high accuracy and rationality, which realizes the query of incomplete data streams, improves the accuracy of the target agricultural data stream, and further improves the query accuracy of agricultural data.

[0084] In addition, converting the agricultural data stream into a first data stream and a second data stream can improve the security of the agricultural data stream, and can facilitate the transmission of the first data stream and the second data stream to two devices for processing respectively. A single device only has a part of the data after the agricultural data stream is converted, and cannot know the complete information of the agricultural data stream, thereby achieving privacy protection of the agricultural data stream.

[0085] Next, an exemplary description is given of the incomplete data query method based on the agricultural Internet of Things provided in this application.

[0086] like Figure 1 As shown, the incomplete data query method based on agricultural Internet of Things provided by this application includes the following steps:

[0087] Step 11, obtain multiple agricultural data streams, and perform feature extraction on each agricultural data stream to obtain data features of each agricultural data stream.

[0088] The above agricultural data stream includes multiple dimensions, which correspond to multiple agricultural data one by one. The data features are used to describe the missing status of agricultural data in the agricultural data stream. Agricultural data can be agricultural-related data such as geographic location, light, temperature, soil composition, etc. Each agricultural data stream can include multiple agricultural data.

[0089] In some embodiments of the present application, multiple agricultural data streams can be obtained by using sensors, illuminometers and other equipment. The above steps of extracting features from each agricultural data stream to obtain data features of each agricultural data stream are specifically as follows:

[0090] For each agricultural data stream, perform the following steps:

[0091] First, for each dimension in the agricultural data stream, if there is corresponding agricultural data for the dimension, the characteristic value of the dimension is set to 1; if there is no corresponding agricultural data for the dimension, the characteristic value of the dimension is set to 0.

[0092] Then, the characteristic values ​​of all dimensions are integrated to obtain the data characteristics of the agricultural data stream.

[0093] It should be noted that all agricultural data streams have the same dimension.

[0094] For example, the first agricultural data stream is {30°C, soil moisture 40%, [air], light 3 lumens, southern Asia}, including 5 dimensions, but only 4 agricultural data, of which the agricultural data corresponding to the third dimension is missing, then the data feature of the agricultural data stream is {1, 1, 0, 1, 1}. The obtained agricultural data stream can be uploaded to the agricultural Internet of Things, and the data features can be obtained in the agricultural Internet of Things.

[0095] It is worth mentioning that obtaining the data characteristics of the agricultural data stream can describe the data missing status of the agricultural data stream and provide data missing information for subsequent steps.

[0096] Step 12: for each agricultural data stream, convert the agricultural data stream into a first data stream and a second data stream, and convert the data features of the agricultural data stream into a first data feature and a second data feature.

[0097] Specifically, an encoder is used to convert each agricultural data in the agricultural data stream into a positive integer, and then the data stream is divided into a first data stream and a second data stream, and the data feature is divided into a first data feature and a second data feature, and the sum of the first data stream and the second data stream is equal to the agricultural data stream, and the sum of the first data feature and the second data feature is equal to the data feature, that is:

[0098]

[0099]

[0100] in, Indicates Agricultural data stream The value of the dimension, Indicates The first data stream The value of the dimension, Indicates The second data stream The value of the dimension, Indicates The first data feature The value of the dimension, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, represents the modulus, represents the number of agricultural data streams, Represents the number of dimensions of the agricultural data stream and the retrieval data stream.

[0101] It should be noted that in the first data stream and the second data stream Dimensional existence Dimension, which contains additional information and does not participate in the calculation of subsequent steps. The additional information contains a random part of the agricultural data stream corresponding to the first data stream, and the sum of the additional information of the first data stream and the additional information of the second data stream of the agricultural data stream is the agricultural data stream. When segmenting the agricultural data stream and data features, the segmentation of each dimension is random. If the agricultural data stream is {4, 12, 0, 7, 6}, the first data stream can be {4, 6, 0, 3, 1}, and the second data stream can be {0, 6, 0, 4, 5}, which satisfies the condition that the sum of the first data stream and the second data stream is equal to the agricultural data stream. The data features of the above agricultural data stream are {1, 1, 0, 1, 1}, the first data feature is {1, 0, 0, 1, 0}, and the second data feature is {0, 1, 0, 0, 1}, which satisfies the condition that the sum of the first data feature and the second data feature is equal to the data feature.

[0102] Exemplarily, after obtaining the first data stream and the second data stream, the first data feature and the second data feature, the first data stream and the first data feature may be sent to the first server, and the second data stream and the second data feature may be sent to the second server for subsequent processing.

[0103] It is worth mentioning that converting the agricultural data stream into a first data stream and a second data stream can improve the security of the agricultural data stream, and can facilitate the transmission of the first data stream and the second data stream to two devices for processing respectively. A single device only has a part of the data after the agricultural data stream is converted, and cannot know the complete information of the agricultural data stream, thereby achieving privacy protection of the agricultural data stream.

[0104] Step 13: Based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, the first mapping data and the second mapping data of each agricultural data stream are calculated.

[0105] The above retrieval data stream includes multiple dimensions, and the multiple dimensions correspond to multiple retrieval data one by one. The dimension of the retrieval data stream is the same as the dimension of the agricultural data stream. The retrieval data is the agricultural data that the user needs to query. For example, if the user needs to query the agricultural data stream related to temperature 30°C and soil moisture 50%, the retrieval data is 30°C and soil moisture 50%.

[0106] Specifically, the above-mentioned process of extracting features from the retrieval data stream to obtain retrieval data features is the same as the process in step 11, that is, for each dimension in the retrieval data stream, if there is corresponding retrieval data for the dimension, the feature value of the dimension is set to 1; if there is no corresponding retrieval data for the dimension, the feature value of the dimension is set to 0; then, the feature values ​​of all dimensions are integrated to obtain the data features of the retrieval data stream.

[0107] The specific process of converting the retrieval data stream into the first retrieval data stream and the second retrieval data stream, and converting the retrieval data feature into the first retrieval data feature and the second retrieval data feature is the same as the process in step 12, that is, the retrieval data stream is divided into the first retrieval data stream and the second retrieval data stream, and the retrieval data feature is divided into the first retrieval data feature and the second retrieval data feature, and the sum of the first retrieval data stream and the second retrieval data stream is equal to the retrieval data stream, and the sum of the first retrieval data feature and the second retrieval data feature is equal to the retrieval data feature.

[0108] It should be noted that when the retrieval data stream is segmented, the segmentation of each dimension is random.

[0109] Exemplarily, after obtaining the first retrieval data stream and the second retrieval data stream, the first retrieval data feature and the second retrieval data feature, the first retrieval data stream and the first retrieval data feature can be sent to the first server, and the second retrieval data stream and the second retrieval data feature can be sent to the second server for subsequent processing.

[0110] It is worth mentioning that by converting the retrieval data stream into the first retrieval data stream and the second retrieval data stream, the security of the retrieval data stream can be improved and the privacy protection of the retrieval data stream can be achieved.

[0111] Step 14: Based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, the first mapping data and the second mapping data of each agricultural data stream are calculated.

[0112] The first mapping data is used to describe the similarity between the first data stream and the first search data stream, and the second mapping data is used to describe the similarity between the second data stream and the second search data stream.

[0113] In some embodiments of the present application, the steps of calculating the first mapping data and the second mapping data of each agricultural data stream based on all the first data streams, all the second data streams, the first search data stream and the second search data stream are:

[0114] For each agricultural data stream, perform the following steps:

[0115] In the first step, based on the first data stream, the second data stream, the first retrieval data stream and the second retrieval data stream of the agricultural data stream, the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream are calculated.

[0116] Specifically, through the formula:

[0117] ;

[0118] ;

[0119] ;

[0120] Calculate the The Euclidean distance between the first data stream and the first search data stream and The Euclidean distance between the second data stream and the second search data stream ;

[0121] in, represents the first multiplication algorithm for secret sharing, Indicates The first data stream The agricultural data of the first dimension and the first retrieval data stream The Euclidean distance between the retrieved data in dimensions, Indicates The second data stream The agricultural data of the second dimension and the The Euclidean distance between the retrieved data in dimensions, Indicates The first data stream The value of the dimension, Indicates The second data stream The value of the dimension, Indicates the first search data stream The value of the dimension, Indicates the second search data stream The value of the dimension, represents the modulus, represents the number of agricultural data streams, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, Indicates The Euclidean distance between the value of the first dimension of the first data stream and the value of the first dimension of the first search data stream, Indicates The first data stream The value of the dimension is the same as the value of the first retrieval data stream. The Euclidean distance between the values ​​of the dimensions, Indicates The Euclidean distance between the value of the first dimension of the second data stream and the value of the first dimension of the second search data stream, Indicates The second data stream The value of the dimension is the same as the value of the The Euclidean distance between the values ​​in the dimension.

[0122] In the second step, based on the Euclidean distance between the first data stream and the first search data stream and the Euclidean distance between the second data stream and the second search data stream, the first mapping data and the second mapping data of the agricultural data stream are calculated.

[0123] By formula:

[0124] ;

[0125] ;

[0126] ;

[0127] Calculate the First mapping data and Second mapping data ;

[0128] in, represents the second multiplication algorithm for secret sharing, Indicates The first mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates the first search data feature The value of the dimension, Indicates the second search data feature The value of the dimension, Indicates the value of the first dimension in the first mapping data of the first data stream, Indicates The first mapping data of the first data stream The value of the dimension, Indicates The value of the first dimension in the second mapping data, Indicates The second mapping data The value of a dimension.

[0129] It should be noted that the expression of the first multiplication algorithm of the above secret sharing is:

[0130]

[0131] The second multiplication algorithm of secret sharing is multiplication calculation, and the expression can be:

[0132]

[0133] in, Indicates The first data stream The agricultural data of the first dimension and the first retrieval data stream The Euclidean distance between the retrieved data in the dimension, or The second data stream The agricultural data of the second dimension and the The Euclidean distance between the retrieved data in dimensions, Indicates The first data stream The value of the dimension, or The second data stream The value of the dimension, Indicates the first search data stream The value of the dimension, or the value of the second retrieval data stream The value of the dimension, Indicates First mapping data or Second mapping data No. The value of the dimension, Indicates the first search data feature The value of the dimension, or the value of the second retrieval data feature The value of a dimension.

[0134] Exemplarily, if the data is sent to the first server and the second server in the above steps, then in this step, based on the secret sharing method, the first server and the second server and the first multiplication algorithm and the second multiplication algorithm of the secret sharing above can be used to obtain the first mapping data and the second mapping data of each agricultural data stream, and the first mapping data is stored in the first server and the second mapping data is stored in the second server.

[0135] It is worth mentioning that the accuracy and rationality of the mapping data calculated considering the data missing condition are improved, and the similarity between the retrieval data stream and the agricultural data stream can be accurately described.

[0136] Step 15, querying among all agricultural data streams based on all first mapping data, all second mapping data, all first data streams, and second data streams to determine a plurality of target agricultural data streams.

[0137] In some embodiments of the present application, a plurality of target agricultural data streams may be determined using a skyline query method. The above step of querying among all agricultural data streams based on all first mapping data, all second mapping data, all first data streams, and second data streams to determine a plurality of target agricultural data streams includes:

[0138] In the first step, for each agricultural data stream, the first attribute sum and the second attribute sum of the agricultural data stream are calculated according to the first mapping data, the second mapping data, the first data feature and the second data feature corresponding to the agricultural data stream.

[0139] Specifically, through the formula:

[0140]

[0141] Calculate the The first attribute of the agricultural data stream and and The second attribute of the agricultural data stream and ;

[0142] in, represents the third multiplication algorithm for secret sharing, Indicates The first data feature The value of the dimension, Indicates The first mapping data The value of the dimension, Indicates The second data feature The value of the dimension, Indicates The second mapping data The value of the dimension, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, represents the number of agricultural data streams, Indicates the modulus.

[0143] It should be noted that the third multiplication algorithm of the above secret sharing is a cumulative multiplication calculation, and the expression can be:

[0144]

[0145] in, Indicates The first attribute of the agricultural data stream and or The second attribute of the agricultural data stream and .

[0146] It should be noted that, according to the nature of skyline queries, the sum of the attributes of each dimension of the data stream is associated with the dominance of the data stream.

[0147] In the second step, all agricultural data streams are sorted from small to large according to the sum of all first attributes and the sum of all second attributes to obtain a sorting result, and the first multiple agricultural data streams in the sorting result are used as a filtering sequence.

[0148] Exemplarily, the first server and the second server sort all agricultural data streams based on the sum of all first attributes and the sum of all second attributes according to the secret sharing method and using a secret sharing algorithm (such as a comparison algorithm in multi-party secure computing).

[0149] It should be noted that, in the sorting process of this step, the agricultural data stream is sorted using its identification tag (such as ID), that is, in the filtering sequence, there is only the identification tag of the agricultural data stream, rather than the actual data information of the agricultural data stream.

[0150] In the third step, all first data streams corresponding to the filter sequence are used as the first filter sequence, and all second data streams corresponding to the filter sequence are used as the second filter sequence.

[0151] The fourth step is to calculate, based on the first filtering sequence and the second filtering sequence, a first incomplete dominance result between every two first data streams in the first filtering sequence and a second incomplete dominance result between every two second data streams in the second filtering sequence.

[0152] Specifically, through the formula:

[0153]

[0154]

[0155]

[0156]

[0157]

[0158]

[0159] Calculate the The first data stream and the The first incomplete dominance result between the first data streams and The second data stream and the The second incomplete type dominance result between the second data streams ;

[0160] in, represents the fourth multiplication algorithm for secret sharing, represents the comparison algorithm for secret sharing, represents the fifth multiplication algorithm for secret sharing, Indicates The first data stream and the The strict dominance results between the first data streams, Indicates that under the public complete dimension, Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result, Indicates The second data stream and the The strict dominance result between the second data streams, Indicates that under the public complete dimension, Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, represents the modulus, Indicated in The first data stream is affected by The complete properties of the first data stream and, Indicated in The first data stream is affected by The complete properties of the first data stream and, Indicated in The second data stream is affected by The complete properties of the second data stream and, Indicated in The second data stream is affected by The complete properties of the second data stream and, Indicated in The first data stream is affected by The common integrity characteristics of the first data stream, Indicated in The second data stream is affected by The common integrity characteristics of the second data stream, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, Indicated in The The first data stream and the The relaxation between the first data streams dominates the result, Indicated in Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, Indicates The first mapping data The value of the dimension, Indicates The first mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, , , Indicates the number of agricultural data streams in the filtered sequence.

[0161] It should be noted that the expressions of the fourth multiplication algorithm of secret sharing, the comparison algorithm of secret sharing, and the fifth multiplication algorithm of secret sharing can be respectively:

[0162]

[0163]

[0164]

[0165] in, Indicates The first data stream and the The first incomplete type domination result between the first data streams, or the first The second data stream and the The second incomplete type dominating result between the second data streams, Indicates The first data stream and the The strict dominance between the first data stream or the The second data stream and the The strict dominance result between the second data streams, Indicates that under the public complete dimension, Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result or the first Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, Indicated in The first data stream is affected by The complete properties of the first data stream and, or The first data stream is affected by The complete properties of the first data stream and, Indicated in The second data stream is affected by The complete properties of the second data stream and, or in The second data stream is affected by The complete properties of the second data stream and, Indicated in Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result, or Weizhongdi The second data stream and the The relaxation between the second data streams dominates the result, Indicated in Weizhongdi The first data stream and the The relaxation between the first data streams dominates the result, or Weizhongdi The second data stream and the The slack between the second data streams dominates the results.

[0166] The fifth step is to calculate multiple domination results for each agricultural data stream in the filtering sequence based on all the first incomplete domination results and all the second incomplete domination results corresponding to the agricultural data stream. If there is a domination result with a value equal to 1, the agricultural data stream will be removed. If there is no domination result with a value equal to 1, the agricultural data stream will be used as a target data stream.

[0167] Specifically, through the formula:

[0168]

[0169] Calculate the Agricultural data streams are Domination results under the influence of data flow .

[0170] in, Indicates The first data stream of the agricultural data stream and the The first incomplete type dominates the result between the data streams, Indicates The second data stream of the agricultural data stream is The second incomplete type between the second data streams dominates the result.

[0171] Exemplarily, based on a secret sharing method, the target agricultural data stream may be obtained by utilizing the first server and the second server and the plurality of secret sharing algorithms described above.

[0172] It is worth mentioning that the target agricultural data stream is determined based on the mapping data with high accuracy and rationality, which enables the query of incomplete data streams and improves the accuracy of the target agricultural data stream.

[0173] Step 16: Send all target agricultural data streams to target users.

[0174] Specifically, for each target agricultural data stream, the first data stream and the second data stream corresponding to the target agricultural data stream are sent to the device of the target user, and the first data stream and the second data stream at this time include the first The target user's device reconstructs the first data stream and the second data stream to obtain the target agricultural data stream.

[0175] It should be noted that, through the formula:

[0176]

[0177] Obtain target agricultural data stream .

[0178] in, Indicates the first data stream corresponding to the target agricultural data stream. Additional information about the dimension, Indicates the first Additional information about the dimension.

[0179] Exemplarily, the device that sends the first data stream of the target agricultural data may be the first server, and the device that sends the second data stream of the target agricultural data may be the second server. After the target user obtains all the target agricultural data streams, all the target agricultural data streams can be used to participate in practical tasks, such as production early warning, yield prediction, and other tasks.

[0180] It is worth mentioning that obtaining the data characteristics of the agricultural data stream can describe the data missing status of the agricultural data stream. The accuracy and rationality of the mapping data calculated under the consideration of the data missing status are improved. The target agricultural data stream is determined based on the mapping data with high accuracy and rationality, which realizes the query of incomplete data streams and improves the accuracy of the target agricultural data stream.

[0181] In addition, converting the agricultural data stream into a first data stream and a second data stream can improve the security of the agricultural data stream, and can facilitate the transmission of the first data stream and the second data stream to two devices for processing respectively. A single device only has a part of the data after the agricultural data stream is converted, and cannot know the complete information of the agricultural data stream, thereby achieving privacy protection of the agricultural data stream.

[0182] The following is an illustrative example of the incomplete data query method based on the agricultural Internet of Things of the present application.

[0183] like Figure 2As shown, the agricultural Internet of Things shares the agricultural data stream with the first server and the second server, and the user device shares the retrieval data stream with the first server and the second server. After the first server and the second server obtain all the data streams, they perform secure mapping retrieval data (i.e., the step of obtaining the first mapping data and the second mapping number). Then, the first server and the second server perform the steps of securely calculating the filtering sequence, securely filtering the dominant data, and generating the skyline index (i.e., the step of querying all the agricultural data streams and determining multiple target agricultural data streams). Then, the first server and the second server respond to the skyline share and send the first data stream and the second data stream corresponding to the target agricultural data stream to the user, and the user performs auxiliary evaluation based on the target agricultural data stream (i.e., making all the target agricultural data streams participate in the actual task).

[0184] The following is an exemplary description of the incomplete data query device based on the agricultural Internet of Things provided by this application.

[0185] like Figure 3 As shown, the embodiment of the present application provides an incomplete data query device based on the agricultural Internet of Things, and the incomplete data query device 300 includes:

[0186] The feature extraction module 301 obtains multiple agricultural data streams and performs feature extraction on each agricultural data stream to obtain data features of each agricultural data stream; the agricultural data stream includes multiple dimensions, the multiple dimensions correspond to multiple agricultural data one by one, and the data features are used to describe the missing status of agricultural data in the agricultural data stream;

[0187] The first conversion module 302 converts the agricultural data stream into a first data stream and a second data stream, and converts the data features of the agricultural data stream into a first data feature and a second data feature, respectively for each agricultural data stream;

[0188] The second conversion module 303 obtains the search data stream of the target user, performs feature extraction on the search data stream, obtains search data features, and converts the search data stream into a first search data stream and a second search data stream, and converts the search data features into a first search data feature and a second search data feature; the search data stream includes multiple dimensions, and the multiple dimensions correspond to the multiple search data one by one;

[0189] The calculation module 304 calculates the first mapping data and the second mapping data of each agricultural data stream based on all the first data streams, all the second data streams, the first search data stream and the second search data stream; the first mapping data is used to describe the similarity between the first data stream and the first search data stream, and the second mapping data is used to describe the similarity between the second data stream and the second search data stream;

[0190] A query module 305 performs a query in all agricultural data streams according to all first mapping data, all second mapping data, all first data streams, and second data streams to determine a plurality of target agricultural data streams;

[0191] The sending module 306 sends all target agricultural data streams to target users.

[0192] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0193] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0194] like Figure 4 As shown, an embodiment of the present application provides a terminal device. The terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 4 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.

[0195] Specifically, when the processor D100 executes the computer program D102, it obtains multiple agricultural data streams and performs feature extraction on each agricultural data stream to obtain data features of each agricultural data stream, and then converts the agricultural data stream into a first data stream and a second data stream for each agricultural data stream, and converts the data features of the agricultural data stream into first data features and second data features, then obtains the retrieval data stream of the target user, and performs feature extraction on the retrieval data stream to obtain retrieval data features, and converts the retrieval data stream into a first retrieval data stream and a second retrieval data stream, and converts the retrieval data features into first retrieval data features and second retrieval data features, and then calculates the first mapping data and the second mapping data of each agricultural data stream based on all the first data streams, all the second data streams, the first retrieval data stream and the second retrieval data stream, and then queries are performed in all agricultural data streams based on all the first mapping data, all the second mapping data, all the first data streams, and the second data streams to determine multiple target agricultural data streams, and finally all the target agricultural data streams are sent to the target user. Among them, obtaining the data characteristics of the agricultural data stream can describe the data missing status of the agricultural data stream. The accuracy and rationality of the mapping data calculated under the consideration of the data missing status are improved. The target agricultural data stream is determined according to the mapping data with high accuracy and rationality, which realizes the query of incomplete data streams, improves the accuracy of the target agricultural data stream, and further improves the query accuracy of agricultural data.

[0196] In addition, converting the agricultural data stream and the retrieval data stream into two data streams can improve the security of the agricultural data stream and the retrieval data stream, and can facilitate the transmission of the two data streams to two devices for processing respectively. A single device only has a part of the data after the data stream is converted, and cannot know the complete information of the data stream, thereby achieving privacy protection for the agricultural data stream and the retrieval data stream.

[0197] The processor D100 may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0198] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. equipped on the terminal device D10. Further, the memory D101 may also include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0199] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0200] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0201] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the incomplete data query method device / terminal device based on the agricultural Internet of Things, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0202] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0203] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0204] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An incomplete data query method based on agricultural Internet of Things, characterized in that: include: Acquire multiple agricultural data streams, and perform feature extraction on each of the agricultural data streams to obtain data features of each of the agricultural data streams; The agricultural data stream includes multiple dimensions, the multiple dimensions correspond to multiple agricultural data one by one, and the data feature is used to describe the missing status of agricultural data in the agricultural data stream; For each of the agricultural data streams, convert the agricultural data stream into a first data stream and a second data stream, and convert the data features of the agricultural data stream into a first data feature and a second data feature; Acquire a search data stream of a target user, perform feature extraction on the search data stream to obtain search data features, convert the search data stream into a first search data stream and a second search data stream, and convert the search data features into a first search data feature and a second search data feature; The retrieval data stream includes multiple dimensions, and the multiple dimensions correspond to the multiple retrieval data one by one; Based on all first data streams, all second data streams, the first retrieval data stream and the second retrieval data stream, first mapping data and second mapping data of each agricultural data stream are calculated; the first mapping data is used to describe the similarity between the first data stream and the first retrieval data stream, and the second mapping data is used to describe the similarity between the second data stream and the second retrieval data stream; According to all the first mapping data, all the second mapping data, all the first data streams, and the second data streams, a query is performed in all the agricultural data streams to determine a plurality of target agricultural data streams; All target agricultural data streams are sent to the target users.

2. The incomplete data query method according to claim 1, characterized in that: The extracting features of each agricultural data stream to obtain data features of each agricultural data stream includes: For each of the agricultural data streams, perform the following steps: For each dimension in the agricultural data stream, if the dimension has corresponding agricultural data, the characteristic value of the dimension is set to 1; if the dimension does not have corresponding agricultural data, the characteristic value of the dimension is set to 0; The characteristic values ​​of all dimensions are integrated to obtain the data characteristics of the agricultural data stream.

3. The incomplete data query method according to claim 1, characterized in that: The first mapping data and the second mapping data of each agricultural data stream are calculated based on all the first data streams, all the second data streams, the first search data stream and the second search data stream, including: For each of the agricultural data streams, respectively, based on the first data stream, the second data stream, the first retrieval data stream and the second retrieval data stream of the agricultural data stream, the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream are calculated; and based on the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream, the first mapping data and the second mapping data of the agricultural data stream are calculated.

4. The incomplete data query method according to claim 3, characterized in that: The method of calculating the Euclidean distance between the first data stream and the first retrieval data stream and the Euclidean distance between the second data stream and the second retrieval data stream based on the first data stream, the second data stream, the first retrieval data stream and the second retrieval data stream comprises: By formula: ; ; ; Calculate the The Euclidean distance between the first data stream and the first search data stream and The Euclidean distance between the second data stream and the second search data stream ; in, represents the first multiplication algorithm for secret sharing, Indicates the The first data stream The agricultural data of the first dimension and the first retrieval data stream The Euclidean distance between the retrieved data in dimensions, Indicates the The second data stream The agricultural data of the second dimension and the second retrieval data stream The Euclidean distance between the retrieved data in dimensions, Indicates the The first data stream The value of the dimension, Indicates the The second data stream The value of the dimension, The first retrieved data stream is represented by The value of the dimension, The second retrieved data stream is represented by The value of the dimension, represents the modulus, represents the number of agricultural data streams, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, Indicates the The Euclidean distance between the value of the first dimension of the first data stream and the value of the first dimension of the first search data stream, Indicates the The first data stream The value of the dimension is the same as the value of the first retrieval data stream. The Euclidean distance between the values ​​of the dimensions, Indicates the The Euclidean distance between the value of the first dimension of the second data stream and the value of the first dimension of the second search data stream, Indicates the The second data stream The value of the dimension is the same as the value of the The Euclidean distance between the values ​​of the dimensions; The calculating the first mapping data and the second mapping data of the agricultural data stream based on the Euclidean distance between the first data stream and the first search data stream and the Euclidean distance between the second data stream and the second search data stream comprises: By formula: ; ; ; Calculate the First mapping data and Second mapping data ; in, represents the second multiplication algorithm for secret sharing, Indicates the The first mapping data The value of the dimension, Indicates the The second mapping data The value of the dimension, Indicates the first search data feature The value of the dimension, Indicates the second search data feature The value of the dimension, Indicates the the value of the first dimension in the first mapping data of the first data stream, Indicates the The first mapping data of the first data stream The value of the dimension, Indicates the The value of the first dimension in the second mapping data, Indicates the The second mapping data The value of a dimension.

5. The incomplete data query method according to claim 1, characterized in that: The query is performed in all agricultural data streams according to all first mapping data, all second mapping data, all first data streams, and second data streams to determine multiple target agricultural data streams, including: For each agricultural data stream, respectively, according to the first mapping data, the second mapping data, the first data feature, and the second data feature corresponding to the agricultural data stream, calculate the first attribute sum and the second attribute sum of the agricultural data stream; According to the sum of all first attributes and the sum of all second attributes, all agricultural data streams are sorted from small to large to obtain a sorting result, and the first multiple agricultural data streams in the sorting result are used as a filtering sequence; Taking all first data streams corresponding to the filtering sequence as the first filtering sequence, and taking all second data streams corresponding to the filtering sequence as the second filtering sequence; Based on the first filtering sequence and the second filtering sequence, calculating a first incomplete dominance result between every two first data streams in the first filtering sequence and a second incomplete dominance result between every two second data streams in the second filtering sequence; For each agricultural data stream in the filtering sequence, multiple domination results are calculated based on all first incomplete domination results and all second incomplete domination results corresponding to the agricultural data stream. If there is a domination result whose value is equal to 1, the agricultural data stream is removed. If there is no domination result whose value is equal to 1, the agricultural data stream is used as a target data stream.

6. The incomplete data query method according to claim 5, characterized in that: The calculating the first attribute sum and the second attribute sum of the agricultural data stream according to the first mapping data, the second mapping data, the first data feature, and the second data feature corresponding to the agricultural data stream includes: By formula: Calculate the The first attribute of the agricultural data stream and and The second attribute of the agricultural data stream and ; in, represents the third multiplication algorithm for secret sharing, Indicates The first data feature The value of the dimension, Indicates the The first mapping data The value of the dimension, Indicates The second data feature The value of the dimension, Indicates the The second mapping data The value of the dimension, Represents the number of dimensions of the agricultural data stream and the retrieval data stream, represents the number of agricultural data streams, Indicates the modulus.

7. The incomplete data query method according to claim 5, characterized in that: The step of calculating, based on the first filtering sequence and the second filtering sequence, a first incomplete dominance result between every two first data streams in the first filtering sequence and a second incomplete dominance result between every two second data streams in the second filtering sequence comprises: By formula: Calculate the The first data stream and the The first incomplete dominance result between the first data streams and The second data stream and the The second incomplete type dominance result between the second data streams ; in, represents the fourth multiplication algorithm for secret sharing, represents the comparison algorithm for secret sharing, represents the fifth multiplication algorithm for secret sharing, Indicates the a first data stream and the The strict dominance results between the first data streams, Indicates that under the public complete dimension, The a first data stream and the The relaxation between the first data streams dominates the result, Indicates the a second data stream and the The strict dominance result between the second data streams, Indicates that under the public complete dimension, The a second data stream and the The relaxation between the second data streams dominates the result, represents the modulus, Indicated in the The first data stream is affected by The complete properties of the first data stream and, Indicated in the The first data stream is affected by The complete properties of the first data stream and, Indicated in the The second data stream is affected by The complete properties of the second data stream and, Indicated in the The second data stream is affected by The complete properties of the second data stream and, Indicated in the The first data stream is affected by The common integrity characteristics of the first data stream, Indicated in the The second data stream is affected by The common integrity characteristics of the second data stream, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, Indicated in The a first data stream and the The relaxation between the first data streams dominates the result, Indicated in The a second data stream and the The relaxation between the second data streams dominates the result, Indicates The first mapping data The value of the dimension, Indicates The first mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The second mapping data The value of the dimension, Indicates The first data feature The value of the dimension, Indicates The second data feature The value of the dimension, , , Indicates the number of agricultural data streams in the filtered sequence.

8. The incomplete data query method according to claim 7, characterized in that: The calculating of multiple domination results based on all first incomplete domination results and all second incomplete domination results corresponding to the agricultural data stream includes: By formula: Calculate the Agricultural data streams are Domination results under the influence of data flow ; in, Indicates The first data stream of the agricultural data stream and the The first incomplete type dominates the result between the data streams, Indicates The second data stream of the agricultural data stream is The second incomplete type between the second data streams dominates the result.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the incomplete data query method based on the agricultural Internet of Things as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the incomplete data query method based on the agricultural Internet of Things as described in any one of claims 1 to 8 is implemented.