A cross-departmental device naming consistency assessment method and system

Abstract

The application discloses a cross-department equipment naming consistency evaluation method and system, and relates to the field of intelligent supervision.The method comprises the following steps: according to multi-label annotation data of equipment samples, a semantic label matrix is constructed by adopting a label splicing vectorization method; according to the semantic label matrix, the average similarity between different equipment samples is determined by adopting cosine similarity and Jaccard similarity; according to the semantic label matrix, the hash signature between different equipment samples is determined by adopting a standard local sensitive hashing algorithm and a privacy protection mechanism; the privacy protection mechanism is that the hash signature bits are randomly flipped according to the privacy level of the equipment; the similarity of the hash signature between different equipment samples is determined, and the similarity is corrected by using the privacy level. The application can guarantee efficient integration and intelligent management of equipment cataloging data.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent supervision, in particular to a cross-departmental equipment naming consistency evaluation method and system. BACKGROUND

[0002] Equipment cataloging is a basic and preparatory link of equipment data resource construction and management. Cataloging data is the core and key data for realizing equipment data governance and utilization, and its data quality is directly related to the credibility and effectiveness of equipment data resource utilization. When different departments conduct equipment cataloging, experts assign specific equipment with variety names based on benchmark names and equipment attributes. If the degree of expert communication and cooperation is low, it will lead to the problem of inconsistent naming of the same equipment variety across departments. For example, a certain equipment is labeled as "reconnaissance unmanned aerial vehicle" or "airborne surveillance platform" in different data systems, but it is essentially the same type of equipment. In the cross-departmental scenario, it is also an important requirement to ensure the consistency of equipment cataloging data while preventing sensitive data leakage during data sharing and integration.

[0003] Currently, the solution to cross-departmental equipment naming consistency evaluation mainly relies on expert knowledge, which is high in labor cost, time-consuming and low in efficiency, seriously restricting the quality of equipment cataloging data construction. SUMMARY

[0004] The purpose of the present application is to provide a cross-departmental equipment naming consistency evaluation method and system, which can effectively solve the problems of strong manual dependence, low efficiency and great difficulty in cross-departmental collaboration in traditional methods, and ensure efficient integration and intelligent management of equipment cataloging data.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides a cross-departmental equipment naming consistency evaluation method, which comprises:

[0007] According to the multi-label annotation data of the equipment samples, a label splicing vectorization method is used to construct a semantic label matrix;

[0008] According to the semantic label matrix, cosine similarity and Jaccard similarity are used to determine the average similarity between different equipment samples;

[0009] According to the semantic label matrix, a standard local sensitive hashing algorithm and a privacy protection mechanism are used to determine the hash signature between different equipment samples; the privacy protection mechanism is to randomly flip the hash signature bit according to the privacy level of the equipment;

[0010] The similarity of the hash signature between different equipment samples is determined, and the similarity is corrected using the privacy level.

[0011] Optionally, the multi-label annotation data of the device samples is used to construct a semantic label matrix by using a label splicing vectorization method, and specifically includes:

[0012] A multi-annotator label splicing vector is constructed by using a formula ;

[0013] A semantic label matrix is constructed by using ;

[0014] wherein, is a label vector of the device sample annotated by an annotator , n is the number of annotators, is a category of the device sample, is the number of device samples, represents a splicing operation of a vector, and a superscript T represents transposition. Optionally, the multi-label annotation data of the device samples is used to construct a semantic label matrix by using a label splicing vectorization method, and before the step, the method further includes:

[0015] Error detection is performed on the multi-label annotation data.

[0016]

[0017] Optionally, according to the semantic label matrix, cosine similarity and Jaccard similarity are used to determine average similarity between different device samples, and specifically includes:

[0018] According to the semantic label matrix, cosine similarity and Jaccard similarity between two device samples are determined respectively;

[0019] According to the cosine similarity and the Jaccard similarity between the two device samples, a weighted average method is used to determine the average similarity.

[0020] Optionally, according to the cosine similarity and the Jaccard similarity between the two device samples, a weighted average method is used to determine the average similarity, and specifically includes:

[0021] The average similarity between the device sample and the device sample is determined by using a formula ;

[0022] wherein, is a weighted coefficient, is the cosine similarity between the device sample and the device sample , and​​​​​ device samples and device samples between the Jaccard similarity.

[0023] Optionally, the hash signatures between different device samples are determined according to the semantic label matrix, a standard local sensitive hashing algorithm and a privacy protection mechanism, and specifically include:

[0024] The hash signature of the device sample i is determined by using the formula

[0025] According to the privacy protection level A vector of randomly flipping the hash bits in the hash signature is generated

[0026] The flipped hash signature is determined by using the formula

[0027] wherein, is the hash bit generated after k times of random projection of the device sample i, represents a bitwise XOR operation, and each element of the random vector is generated by an independent Bernoulli random variable with a probability of the privacy protection level .

[0028] Optionally, the similarity of the hash signatures between different device samples is determined, and the similarity is corrected by using the privacy level, and specifically includes:

[0029] The similarity of the hash signatures between different device samples is determined by using the formula

[0030] The corrected similarity of the hash signatures is determined by using the formula

[0031] wherein, and indicate the privacy-protected hash values of two device samples or annotators, is the number of bits of the hash signature, is an indicator function, which is 1 if , and 0 otherwise, used to count the matching of two hash signatures at each hash bit, is the privacy protection level, indicating how many hash bits are randomly flipped.

[0032] In a second aspect, the present application provides a cross-department device naming consistency evaluation system, which comprises:​​​​​​​​​​​

[0033] a label semantic vectorization module configured to construct a semantic label matrix by using a label concatenation vectorization method according to multi-label annotation data of the device samples;

[0034] a consistency evaluation module configured to determine average similarity between different device samples according to the semantic label matrix by using cosine similarity and Jaccard similarity;

[0035] a privacy protection hash matching module configured to determine hash signatures between different device samples according to the semantic label matrix by using a standard locality-sensitive hashing algorithm and a privacy protection mechanism; the privacy protection mechanism is to randomly flip hash signature bits according to a privacy level of the device;

[0036] a consistency evaluation and privacy protection similarity correction module configured to determine similarity of the hash signatures between different device samples and correct the similarity by using the privacy level.

[0037] According to the specific embodiments provided in the present application, the present application has the following technical effects:

[0038] The present application provides a cross-department device naming consistency evaluation method and system. By using a label concatenation vectorization method to construct a semantic label matrix according to multi-label annotation data of the device samples, the original device label data is converted into a high-dimensional semantic vector to support subsequent consistency evaluation. On the basis of hash signatures of a standard locality-sensitive hashing algorithm (Locality-Sensitive Hashing, LSH), efficient approximate similarity calculation of the high-dimensional semantic vector is realized, and a random disturbance mechanism is introduced to randomly flip signature bits according to a set privacy level, thereby desensitizing and encrypting the naming data. In view of the error caused by the disturbance, a corresponding numerical correction model is constructed to repair the deviation of the disturbed similarity, so as to restore the original semantic consistency distribution. Through the implementation of this scheme, the sensitive device data protection is realized while the data integration efficiency is improved when performing cross-department data consistency evaluation, and the data ambiguity and misjudgment risk caused by inconsistent naming are greatly reduced. The problems of strong manual dependence, low efficiency and great difficulty in cross-department cooperation in the traditional method can be effectively solved, thereby providing strong support for efficient integration and intelligent management of device cataloging data. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 A cross-department device naming consistency evaluation method flowchart for an embodiment of the present application;

[0041] Figure 2 A cross-department device naming consistency evaluation method flowchart for an embodiment of the present application;

[0042] Figure 3 A cross-department device naming consistency evaluation system structure diagram for an embodiment of the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0044] The above purposes, features and advantages of the present application can be more obvious and easy to understand. The present application will be described in further detail below with reference to the drawings and specific embodiments.

[0045] In an exemplary embodiment, as shown in Figure 1 and Figure 2 , a cross-department device naming consistency evaluation method is provided, which comprises:

[0046] S101, according to the multi-label annotation data of the device sample, a label splicing vectorization method is used to construct a semantic label matrix.

[0047] According to the multi-label annotation data of the device sample, a dataset is constructed, which has device samples, categories, annotators. Each device sample can be annotated by multiple annotators, and the annotation of the device sample by an annotator is represented as a label set :

[0048] .

[0049] A multi-annotator label splicing vector is constructed using the formula .

[0050] wherein, is the label vector of the device sample annotated by the annotator , if , then ​​Otherwise, the value is 0; This represents the concatenation operation of vectors; for example, vectors... ,vector concatenation of two vectors This forms a dimension. New vector: .

[0051] For all After generating multi-annotator label concatenated vectors from each device sample, using Constructing a semantic tag matrix ; where the superscript T is transpose.

[0052] Semantic tag matrix As input to the semantic representation of the label for the entire dataset, it is used for subsequent hash mapping or consistency calculation.

[0053] To ensure the generated semantic label matrix can be correctly input into subsequent hash mapping or consistency calculation processes, any illegal annotations are detected within the generated semantic label matrix, and a skipping strategy is implemented. For any illegal annotations (such as label values...) (or non-integer types), execute the skip strategy and fill the vector with zeros. For missing values ​​(such as those not labeled by the annotator), define their label vector as: To maintain the dimensional consistency and alignment of the spliced ​​vectors.

[0054] S102, based on the semantic label matrix, the average similarity between samples from different devices is determined using cosine similarity and Jaccard similarity; the cosine similarity and Jaccard similarity are used to comprehensively evaluate the similarity between the original samples.

[0055] Using formula Determine equipment samples and equipment samples Cosine similarity between .

[0056] in, The dot product of two vectors. and They are respectively and The Euclidean norm of the similarity measure. The range of this similarity measure is... 1 indicates perfect similarity, 0 indicates no similarity, and -1 indicates complete opposites.

[0057] Using formula Determine equipment samples and equipment samples Jaccard similarity between .

[0058] wherein, and respectively represent semantic label matrices of device samples and device samples .

[0059] The Jaccard similarity and the cosine similarity are combined by weighted average, and the weight of the two indicators is controlled by a weighted coefficient to obtain the average similarity between the two samples :

[0060] .

[0061] S103, according to the semantic label matrix, a standard local sensitive hashing algorithm and a privacy protection mechanism are used to determine the hash signature between different device samples; the privacy protection mechanism is to randomly flip the hash signature bit according to the privacy level of the device.

[0062] The standard LSH method is used to calculate the hash signature of each device sample, and the high-dimensional data is mapped to a low-dimensional space by random projection, and then the hash signature of each device sample is calculated. Given an input vector (multi-annotator label splicing vector) wherein, represents the label semantic vector of the device sample, which contains various attribute information of the device (device type, model, specification parameter, functional characteristic). The calculation process of the standard hash is as follows:

[0063] (1) Random projection generation: a hyperplane in a high-dimensional space is randomly generated, which divides the data points into two parts, i.e. one side and the other side of the hyperplane. Through this hyperplane, the data is projected into a one-dimensional space. For a given input vector , a random vector is selected, and the dot product of the input vector is calculated, and the calculation formula is as follows:

[0064] .

[0065] wherein, represents a sign function, which maps the result of the dot product to a binary value, returning or .

[0066] (2) Multiple projection generation: in order to improve the effect of hash, multiple random projections are performed, i.e. multiple random vectors are used to generate multiple hash functions. Each hash function calculates the input vector The dot product between the vector and the corresponding random vector is then used to generate a hash bit using a sign function.

[0067] .

[0068] (3) Generate hash signature: The hash value of each input vector consists of multiple hash bits. It is dimensional binary vector hash signature , representing the input vector Mapping in low-dimensional space:

[0069] .

[0070] To effectively prevent the leakage of original sensitive equipment data during cross-departmental sharing, based on privacy protection levels... (Range from 0 to 1), randomly select bits from the hash signature and flip them. The flipping process is performed using a randomly generated vector. To execute: the reversed hash signature for:

[0071] .

[0072] in, This indicates a bitwise XOR operation. It is a random vector representing the bits that need to be flipped. Each element is generated by an independent Bernoulli random variable with probability . .

[0073] S104 determines the similarity of hash signatures between samples from different devices and corrects the similarity using privacy levels. This involves comparing the average similarity with the similarity after combining hash signatures to analyze whether adding privacy protection affects the similarity assessment. For similarity errors introduced by privacy protection, while ensuring data irreversibility, the true similarity level is effectively restored, improving the practicality and credibility of the results.

[0074] S104 specifically includes:

[0075] Using formula Determine the similarity of hash signatures between samples from different devices. .

[0076] If two identical samples have The probability bits are different, and different samples have different probability bits. If the probability bits are different, then the formula is used. Determine the similarity of the corrected hash signatures. .

[0077] wherein, and denote the privacy-protected hash values of two device samples or annotators, is the number of bits of the hash signature, is an indicator function, which is 1 if and 0 otherwise, used to count the matching of two hash signatures at each hash bit, is the privacy level, indicating how many hash bits are randomly flipped.

[0078] After S104, further comprising: performing consistency comparison to determine whether different devices remain consistent in semantic features; then performing clustering or grouping operation based on the corrected similarity matrix to realize organization and feature aggregation of device samples; finally, these results can be used as input for subsequent anomaly detection and behavior modeling, thereby improving the practicability and credibility of the method.

[0079] Based on the same inventive concept, the embodiments of the present application also provide a cross-department device naming consistency evaluation system for implementing the cross-department device naming consistency evaluation method described above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, so the specific limitations in one or more cross-department device naming consistency evaluation system embodiments provided below can be referred to the limitations of the cross-department device naming consistency evaluation method in the above, which will not be repeated here.

[0080] In one exemplary embodiment, a cross-department device naming consistency evaluation system is provided, comprising:

[0081] a label semantic vectorization module configured to construct a semantic label matrix by using a label concatenation vectorization method according to multi-label annotation data of device samples;

[0082] a consistency evaluation module configured to determine the average similarity between different device samples by using cosine similarity and Jaccard similarity according to the semantic label matrix;

[0083] a privacy-protected hash matching module configured to determine the hash signature between different device samples by using a standard local sensitive hash algorithm and a privacy protection mechanism according to the semantic label matrix; the privacy protection mechanism is to randomly flip the hash signature bits according to the privacy level of the device;

[0084] a consistency evaluation and privacy-protected similarity correction module configured to determine the similarity of the hash signature between different device samples and correct the similarity by using the privacy level.

[0085] As Figure 3As shown, the label semantic vectorization module function is to convert multi-label annotation data into high-dimensional semantic vectors to support subsequent consistency evaluation. The input is multi-label annotation data anno_data provided by multiple annotators, which is parsed by data structure and spliced by vectorization method, and after error detection, a unified semantic label matrix, i.e. high-dimensional semantic label matrix vectors, is generated for subsequent hash mapping or consistency calculation.

[0086] The function of the consistency evaluation module is to evaluate the consistency of the generated semantic label matrix vectors. The average similarity between different device samples is calculated using cosine similarity and Jaccard similarity. The input is the semantic label matrix vectors output by the label semantic vectorization module. The similarity average value between samples is obtained by weighted average of cosine similarity and Jaccard similarity.

[0087] The function of the privacy protection hash matching module is to process the label semantic matrix with local sensitive hash (LSH) and introduce a privacy protection mechanism to avoid revealing sensitive information by perturbing the hash signature. The input is the semantic label matrix vectors output by the label semantic vectorization module. After multiple random projections, the dot product between the data point and the random vector is calculated to obtain the hash signature. The output is the hash signature privacy_hashed_signatures calculated using local sensitive hash (LSH). The LSH algorithm is introduced to map high-dimensional label data to low-dimensional hash space, which greatly reduces the time complexity of similarity calculation between samples and has good calculation performance and real-time response ability.

[0088] The function of the consistency evaluation and privacy protection similarity correction module is to calculate the similarity between hash signatures with privacy protection and correct the errors introduced by privacy protection. The input is the hash signature privacy_hashed_signatures generated by the privacy protection hash matching module, which uses the similarity calculation formula and corrects the similarity value according to the privacy level The similarity calculation value is corrected, and the output is the similarity value corrected_similarity calculated by the privacy protection similarity correction formula and the error caused by privacy protection is corrected.

[0089] The consistency evaluation index combination in the present application can be flexibly extended according to actual needs, such as introducing Hamming distance, Manhattan distance or point mutual information as supplementary indexes to adapt to different types of label data characteristics. The local sensitive hashing mechanism used can be replaced by SimHash, MinHash and other efficient hashing algorithms in specific scenarios to improve the adaptability and performance of different types of similarity tasks. It can be generalized to other data governance fields that require multi-label integration, semantic consistency judgment and privacy protection

[0090] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0091] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to a memory, database or other medium used in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (Read-Only Memory, ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), a ferroelectric memory (Ferroelectric Random Access Memory, FRAM), a phase change memory (Phase Change Memory, PCM), a graphene memory, etc. The volatile memory can include a random access memory (Random Access Memory, RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

[0092] The database involved in each embodiment provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, and the like, without being limited thereto. The processor involved in each embodiment provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, and the like, without being limited thereto.

[0093] In the present application, all actions of obtaining signals, information or data are performed in compliance with the corresponding data protection regulations and policies of the country where the device is located, and on the premise of obtaining authorization from the owner of the corresponding device.

[0094] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but it should be considered that any combination of the technical features is within the scope of the present disclosure as long as there is no contradiction.

[0095] The principles and implementation modes of the present application are described by applying specific examples herein, and the above embodiments are only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, the specific implementation modes and application ranges can be changed according to the idea of the present application. In summary, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A method for assessing cross-departmental equipment naming consistency, characterized in that, The cross-department equipment naming consistency evaluation method comprises: According to the multi-label annotation data of the equipment samples, a label splicing vectorization method is used to construct a semantic label matrix; According to the semantic label matrix, cosine similarity and Jaccard similarity are used to determine the average similarity between different equipment samples; According to the semantic label matrix, a standard local sensitive hashing algorithm and a privacy protection mechanism are used to determine the hash signature between different equipment samples; the privacy protection mechanism is to randomly flip the hash signature bit according to the privacy level of the equipment; The similarity of the hash signatures between different equipment samples is determined, and the similarity is corrected by using the privacy level. According to the semantic label matrix, a standard local sensitive hashing algorithm and a privacy protection mechanism are used to determine the hash signature between different equipment samples, specifically comprising: Using the formula determining the hash signature of the device sample i ; According to a privacy protection level Generating a vector of hash bits to flip in a hash signature ; Using the formula Determining the flipped hash signature ; wherein, is the hash bit generated after k random projections for device sample i, denotes the bitwise XOR operation, and the random vector is generated by independent Bernoulli random variables with probability privacy level The similarity of the hash signatures between different equipment samples is determined, and the similarity is corrected by using the privacy level, specifically comprising: Using the formula Determining similarity of hash signatures between different device samples ; Using the formula Determining similarity of corrected hash signatures ; wherein, and denote the privacy-protected hash values of two device samples or annotators, is the number of bits of the hash signature, is an indicator function, which is 1 if and 0 otherwise, used to count the matching of two hash signatures at each hash bit, is the privacy protection level, indicating how many hash bits are randomly flipped.

2. The cross-departmental device naming consistency assessment method of claim 1, wherein, According to the multi-label annotation data of the equipment samples, a label splicing vectorization method is used to construct a semantic label matrix, specifically comprising: Using the formula Constructing multi-annotator label stitching vectors ; Utilizing constructing a semantic tag matrix ; wherein, is the number of annotators, is the number of device samples, is the label vector of the device sample, is the number of annotators, is the class of the device sample, is the number of device samples, denotes the concatenation operation of vectors, and the superscript T denotes the transpose.

3. The cross-departmental device naming consistency assessment method of claim 1, wherein, According to the multi-label annotation data of the equipment samples, a label splicing vectorization method is used to construct a semantic label matrix, and further comprising: Error detection is performed on the multi-label annotation data.

4. The cross-departmental device naming consistency assessment method of claim 1, wherein, According to the semantic label matrix, cosine similarity and Jaccard similarity are used to determine the average similarity between different equipment samples, specifically comprising: According to the semantic label matrix, the cosine similarity and Jaccard similarity between two equipment samples are determined respectively; According to the cosine similarity and Jaccard similarity between two equipment samples, a weighted average method is used to determine the average similarity.

5. The cross-departmental device naming consistency assessment method of claim 4, wherein, According to the cosine similarity and Jaccard similarity between two equipment samples, a weighted average method is used to determine the average similarity, specifically comprising: The average similarity between the device samples is determined using the formula ;​​​ wherein, is a weighting factor, is a device sample and a cosine similarity between device samples is a Jaccard similarity between device samples is a Jaccard similarity between device samples​​ 6. A cross-departmental device naming consistency assessment system for implementing the cross-departmental device naming consistency assessment method of any one of claims 1-5, characterized in that, The cross-department equipment naming consistency evaluation system comprises: A label semantic vectorization module is configured to construct a semantic label matrix according to multi-label annotation data of equipment samples by using a label splicing vectorization method; A consistency evaluation module is configured to determine the average similarity between different equipment samples according to the semantic label matrix by using cosine similarity and Jaccard similarity; A privacy protection hash matching module is configured to determine the hash signature between different equipment samples according to the semantic label matrix by using a standard local sensitive hashing algorithm and a privacy protection mechanism; the privacy protection mechanism is to randomly flip the hash signature bit according to the privacy level of the equipment; A consistency evaluation and privacy protection similarity correction module is configured to determine the similarity of the hash signatures between different equipment samples, and correct the similarity by using the privacy level.

Images