A construction engineering cost data security protection method, system and medium

Abstract

The present application relates to the technical field of data security protection, and specifically to a method, system and medium for the security protection of construction project cost data. The method includes: obtaining historical documents, current documents and a numerical set of the current document; obtaining the intersection of word segmentation sets between documents after segmenting the documents, and obtaining sentence similarity and word order differences based on the difference in word number and sequence position; correcting sentence similarity based on word order differences to determine similar sentences of the current document sentence; clustering the data values ​​of the current document sentence and similar sentences, obtaining the abnormal value of the cluster based on the distance between the clustered clusters and the distance between the data value of the current document sentence and the cluster, deleting the data value based on the abnormal value to obtain the final numerical set and replacement range; determining the replacement value based on the replacement range, thereby obtaining a key, and encrypting the data with the key. The present application improves the rationality of encryption and increases the protection effect.

Description

Technical Field

[0001] The present application relates to the technical field of data security protection, and specifically to a method, system and medium for security protection of construction project cost data. Background Art

[0002] In the management of construction project cost data, since price information is directly related to the business secrets and competitive advantages of an enterprise, the price-related information in the construction cost data file is particularly important. Generally, the security protection in the engineering file or document is to use hidden encryption to directly hide the price-related information in the file. Although the data can be protected to a certain extent, once the encryption is cracked, the data may be leaked. The existing encryption algorithm usually directly encrypts the data without disguise. The encrypted data is too different from the data in the original document. Although it has encryption ability, it does not have disguise ability and is easily cracked by brute force, and the encryption effect is poor. Therefore, the present application encrypts the current document cost data through the previous cost data, so that the value of the encrypted ciphertext is reasonable with the normal value, and has corresponding authenticity, thereby protecting more real cost data. Summary of the invention

[0003] In order to solve the technical problem of poor encryption effect, this application provides a construction project cost data security protection method, system and medium. The technical solution adopted is as follows:

[0004] This application proposes a construction engineering cost data security protection method, system and medium, the method comprising the following steps:

[0005] Get the historical document, current document and all data values ​​of the current document;

[0006] The historical document and the current document are segmented according to punctuation to obtain several sentences; each sentence is segmented, and a historical segmentation set and a current segmentation set are obtained for each historical document and the current document respectively; the segmentations that are the same in the current segmentation set and the historical segmentation set constitute the segmentation set intersection; sentence similarity is obtained according to the difference in the number of segmentations in the segmentation set intersection and the current segmentation set; word order difference is obtained according to the difference in the sequence number of each segmentation in the segmentation set intersection in the historical segmentation set and the current segmentation set; sentence similarity is corrected according to the word order difference to obtain corrected sentence similarity; and similar sentences of the current document sentence are determined in this way;

[0007] Cluster the data value of the current document sentence with the data values ​​of all its similar sentences to obtain the current cluster and the neighborhood cluster; if the current document sentence has one data value, obtain the outlier of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster; delete some data values ​​in the neighborhood cluster according to the comparison between the outlier and the preset outlier threshold to obtain the final value set; if the current document sentence has multiple data values, the current cluster is the final value set, and the replacement range is obtained according to the maximum and minimum values ​​of the final value set;

[0008] Determine the replacement value based on the difference between each data value in the current document and each data value in the replacement range, and determine the key of the current document based on all data values ​​in the current document and their replacement values;

[0009] The project cost data is encrypted and protected according to the key.

[0010] In the above scheme, this application proposes a cost data protection method based on numerical disorder. By determining the replaceable data value in the numerical value of the current document according to the data range of similar sentence segments in historical projects and the difference between the replaceable data in the document and the current data, the data indicators in the encrypted document and the real document are displayed reasonably, and there are large differences, which are difficult to be identified, thereby protecting the real cost file.

[0011] In one embodiment, the method for obtaining sentence similarity based on the difference in the number of segmentation words between the intersection of the segmentation set and the current segmentation set is:

[0012] The ratio of the intersection of the word segmentation sets to the number of word segmentations in the current word segmentation set is taken as the sentence similarity between the sentence in the current document and the sentence in the historical document.

[0013] In one embodiment, the method for obtaining the word order difference according to the difference in the sequence number of each word in the intersection of the word sets in the historical word set and the current word set is:

[0014] Label all the segmentations in the current segmentation set and the historical segmentation set in order, calculate the absolute value of the difference between the serial numbers of each segmentation in the intersection of the segmentation sets in the current segmentation set and the historical segmentation set, and record the cumulative sum of the absolute values ​​of the difference of all the segmentations in the intersection of the segmentation sets as the word order difference.

[0015] In one embodiment, the method of correcting the sentence similarity according to the word order difference to obtain the corrected sentence similarity and determining the similar sentences of the current document sentence is as follows:

[0016] The expression of the corrected sentence similarity is:

[0017] , Indicates the similarity between the sentences in the current document and the sentences in the historical documents. Indicates the difference in word order between the current document and the historical document. is the normalization function, Indicates the corrected sentence similarity;

[0018] For any sentence in the current document, the maximum sentence similarity among all sentences in the remaining historical documents is taken as the similar sentence of the sentence in the current document.

[0019] In one embodiment, the method of clustering the data value of the current document sentence with the data values ​​of all similar sentences to obtain the current cluster and the neighborhood clusters is:

[0020] Cluster the data value of the current document sentence with the data values ​​of all its similar sentences; the cluster distance is the absolute value of the difference between the data values;

[0021] The cluster where the data value of the current document sentence is located is recorded as the current cluster; the clusters other than the current cluster are recorded as neighboring clusters.

[0022] In one embodiment, the method for obtaining the outlier value of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster is:

[0023] , Represents the data value of the cluster center of the current cluster b, represents the data value of the cluster center of the vth neighborhood cluster, Represents the data value of the current document statement, represents the normalization function, represents the outlier of the vth neighborhood cluster.

[0024] In one embodiment, the method of deleting data values ​​in some neighborhood clusters according to the comparison between the abnormal value and the preset abnormal threshold to obtain the final value set is:

[0025] If the abnormal value of the neighborhood cluster is greater than the preset abnormal threshold, it means that the data of the current neighborhood cluster is abnormal, and the data value in the neighborhood cluster is deleted from the value set;

[0026] Delete the data values ​​of all abnormal neighborhood clusters from the value set to obtain the final value set.

[0027] In one embodiment, the method of determining the replacement value according to the difference between each data value of the current document and each data value in the replacement range, and determining the key of the current document according to all data values ​​of the current document and their replacement values ​​is:

[0028] Record the data value of the current document statement as the current data value, calculate the absolute value of the difference between the current data value and each data value in the replacement range, and record the value with the largest absolute value of the difference as the replacement value of the current data value. Save the replacement value in the sequence position of the final value set;

[0029] Get the serial position of the current data value in the value set of the current document, and use the serial position of the current data value and the serial position of its corresponding replacement value as a two-dimensional point;

[0030] All 2D points in the current document form the key.

[0031] In a second aspect, the present application also provides a construction engineering cost data security protection system, the system comprising:

[0032] The data collection module is used to obtain historical documents, current documents and the value set of the current document;

[0033] A similar sentence acquisition module is used to segment the historical document and the current document according to punctuation marks to obtain several sentences; segment each sentence, and obtain a historical segmentation set and a current segmentation set for each historical document and the current document respectively; form a segmentation set intersection with the same segmentations in the current segmentation set and the historical segmentation set; obtain sentence similarity according to the difference in the number of segmentations in the segmentation set intersection and the current segmentation set; obtain word order difference according to the difference in the sequence number of each segmentation in the segmentation set intersection in the historical segmentation set and the current segmentation set; correct the sentence similarity according to the word order difference to obtain the corrected sentence similarity; and determine similar sentences accordingly;

[0034] The replacement range acquisition module is used to cluster the data value of the current document sentence with the data values ​​of all similar sentences to obtain the current cluster and the neighborhood cluster; obtain the abnormal value of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster; delete the data values ​​in some neighborhood clusters according to the comparison between the abnormal value and the preset abnormal threshold to obtain the final value set; obtain the replacement range according to the maximum and minimum values ​​of the final value set;

[0035] A key determination module determines a replacement value based on the difference between each data value of the current document and each data value within the replacement range, and determines the key of the current document based on all data values ​​of the current document and their replacement values;

[0036] The protection module encrypts and protects the engineering cost data according to the key.

[0037] In a third aspect, an embodiment of the present application 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 method for securely protecting construction project cost data as described in the first aspect is implemented.

[0038] The beneficial effects of this application are as follows:

[0039] This application proposes a cost data protection method based on numerical disorder. By determining the replaceable data value in the numerical value of the current document according to the data range of similar sentence segments in historical projects and the difference between the replaceable data in the document and the current data, the encrypted document and the data indicators in the real document are displayed reasonably, and there are large differences, which are difficult to be identified, thereby protecting the real cost file. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 creative work.

[0041] Figure 1 A flow chart of a construction project cost data security protection method provided by an embodiment of the present application;

[0042] Figure 2 The present invention is a flowchart of a construction engineering cost data security protection system. DETAILED DESCRIPTION

[0043] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of a construction project cost data security protection method, system and medium proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0044] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0045] An embodiment of a method for protecting construction project cost data security:

[0046] The following is a detailed description of a specific method for protecting the construction project cost data security provided by the present application in conjunction with the accompanying drawings.

[0047] See also Figure 1 , which shows a flow chart of a construction project cost data security protection method provided by an embodiment of the present application, the method comprising the following steps:

[0048] Step S001, obtaining historical documents, current documents and a value set of the current document.

[0049] Record the document to be encrypted in the construction project as the current document, obtain the current document in the construction project, and obtain the documents in the remaining construction projects as historical documents. Open the current document in the construction project through the Microsoft Office API and read its content. Use regular expressions to identify numerical data in the current document file, and gradually add all the identified numerical data to the collection according to the order of the numerical values ​​in the current document to obtain the current numerical collection.

[0050] At this point, the historical document, the current document, and the current value set of the current document are obtained.

[0051] Step S002, perform sentence segmentation on the historical document and the current document, obtain the word segments of the sentence, form the intersection of the word segmentation sets with the same word segments, obtain sentence similarity based on the difference in the number of word segmentations in the intersection of the word segmentation sets and the current document; obtain word order difference based on the difference in the sequence numbers of the word segments in the intersection of the word segmentation sets, and correct the sentence similarity based on the word order difference to obtain similar sentences of the current document sentence.

[0052] Since numerical values ​​represent certain physical meanings in text information, if they are randomly shuffled, their numerical values ​​may not match the text information and will lead to unreasonable numerical representation. Therefore, we can determine the data range of certain numerical values ​​in the context through sentence segments in historical documents that are similar to the current file, and further determine the most recent data value that can be replaced in the current document based on the data range.

[0053] Since the information contained in the engineering cost document is mostly similar, the value required for the sentence in the current document can be determined based on the value of the similar sentence segment in the historical document. If it is necessary to determine the sentence whose value needs to be replaced, the similar sentence segment can be determined in the historical document based on the keyword information in the current sentence.

[0054] For historical documents, the historical documents are segmented by each punctuation mark, and each sentence is identified by the symbol recognition algorithm, and all sentences that do not contain numerical data are deleted, and the sentences that contain numerical data are retained. Similarly, the current document is segmented by punctuation marks to obtain several sentences.

[0055] For each sentence in the historical document and the current document, use Jieba to segment the sentence, break the current complete sentence into multiple individual words, and add them to the word segmentation set corresponding to each sentence; denote the word segmentation set of each sentence in the current document as the current word segmentation set, and denote the word segmentation set of each sentence in the historical document as the historical word segmentation set. After word segmentation, determine the stop words in the word segmentation set according to the Chinese stop word library, and delete the stop words in the word segmentation set. Among them, stop words include "de", "zai", "he", etc.

[0056] For any current word segmentation set, calculate its similarity with each historical word segmentation set to obtain the sentence similarity between the sentences in the current document and the historical document.

[0057] Obtain the sentence similarity between the sentences in the current document and the historical document according to the difference between the number of identical words in the current word segmentation set and the historical word segmentation set and the number of words in the current word segmentation set.

[0058] The sentence similarity is positively correlated with the number of identical words and the number of words in the current word segmentation set.

[0059] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the change directions of the two variables are the same. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large; the specific relationship is determined by the actual application, and this application does not make special restrictions.

[0060] Preferably, in this embodiment, count the number of identical words in the current word segmentation set and the historical word segmentation set, denote it as the intersection of the word segmentation sets, and use the ratio of the intersection of the word segmentation sets to the number of words in the current word segmentation set as the sentence similarity between the sentences in the current document and the historical document.

[0061] Preferably, in this embodiment, count the number of identical words in the current word segmentation set and the historical word segmentation set, denote it as the intersection of the word segmentation sets, and use the absolute value of the difference between the intersection of the word segmentation sets and the number of words in the current word segmentation set as the sentence similarity between the sentences in the current document and the historical document.

[0062] Since the order of different words is different, the meaning expressed by the sentence may be different. Therefore, the sentence similarity can be corrected according to the order of word segmentation. Number all the words in the current word segmentation set and the historical word segmentation set in order, count the serial numbers of each word in the intersection of the word segmentation sets in the current word segmentation set and the historical word segmentation set, calculate the absolute value of the difference between the serial numbers of each word in the intersection of the word segmentation sets in the current word segmentation set and the historical word segmentation set, and denote the sum of the absolute values of the differences of all words in the intersection of the word segmentation sets as the word order difference;

[0063] The sentence similarity is corrected according to the word order difference to obtain the corrected sentence similarity.

[0064] The corrected sentence similarity is negatively correlated with word order differences.

[0065] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0066] Preferably, in this embodiment, the expression of the corrected sentence similarity is:

[0067] , Indicates the similarity between the sentences in the current document and the sentences in the historical documents. Indicates the difference in word order between the current document and the historical document. is the normalization function, Represents the corrected sentence similarity.

[0068] For any sentence in the current document, a corrected sentence similarity is calculated between it and each sentence in each historical document. Among the historical documents, the sentence with the maximum corrected sentence similarity to the sentence in the current document is selected as the similar sentence to the sentence in the current document.

[0069] At this point, the similar sentences of each sentence in the current document in each historical document are obtained.

[0070] Step S003, clustering the data value of the current document sentence with the data values ​​of all its similar sentences to obtain the current cluster and the neighborhood cluster; obtaining the outlier of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster; deleting the data values ​​in some neighborhood clusters according to the comparison between the outlier and the preset outlier threshold to obtain the final value set; obtaining the replacement range according to the maximum and minimum values ​​of the final value set.

[0071] The numerical replacement range of the data that can be replaced in the current document is determined based on the data values ​​in similar sentences. However, since some data may be too large or too small and obviously do not meet the replacement range of the current data, unreasonable replacement ranges can be further deleted through anomaly detection to determine the final replacement range value.

[0072] For any sentence in the current document, there is a similar sentence in each historical document. The number of historical documents is n, that is, the number of similar sentences to the sentence in the current document is n. In this embodiment, the number n is 50.

[0073] If there is only one data value in the sentence of the current document, the data values ​​of similar sentences corresponding to the sentence of the current document are formed into a set and recorded as a numerical set; the data value of the current document sentence and the data values ​​of all similar sentences are clustered through DBSCAN clustering, and the clustering distance is the absolute value of the difference between the data values. In this way, all data values ​​are divided into multiple clusters, and the cluster where the data value of the current document sentence is located is recorded as the current cluster, and the remaining clusters are recorded as neighborhood clusters. The data value of the current document sentence is recorded as the current data value.

[0074] The outlier value of each neighborhood cluster is obtained based on the distance between the current cluster and the neighborhood cluster and the distance between the current data value and the neighborhood cluster.

[0075] The expression of the outlier value of the domain cluster is:

[0076] , Represents the data value of the cluster center of the current cluster b, represents the data value of the cluster center of the vth neighborhood cluster, Represents the data value of the current document statement, represents the normalization function, represents the outlier of the vth neighborhood cluster.

[0077] Indicates the distance between the cluster center of the current cluster b and the cluster center of the neighboring cluster, Indicates the distance between the current data value and other cluster centers. The larger the two values ​​are, the more unreasonable the data in the neighborhood cluster is and the larger its outlier is.

[0078] The abnormal threshold is set to H. If the abnormal value of the neighborhood cluster is greater than the abnormal threshold, it means that the data of the current neighborhood cluster is abnormal, and the data value in the neighborhood cluster is deleted from the value set. In this embodiment, the value of H is 0.7.

[0079] Through the above steps, the neighborhood cluster with abnormal data is deleted, that is, the data value of this neighborhood cluster in the value set is deleted to obtain the final value set.

[0080] If there are multiple data values ​​in the sentence of the current document, after the data value of the current document sentence and the data values ​​of all similar sentences are clustered through DBSCAN clustering, the cluster where each data value in the sentence of the current document belongs is the final value set of the data value.

[0081] Select the maximum and minimum values ​​in the final set of values, and use the range from the minimum to the maximum value as the replacement range.

[0082] At this point, the replacement range of the current data value is obtained.

[0083] Step S004, determining a replacement value based on the difference between each data value of the current document and each data value within the replacement range, and determining the key of the current document based on all data values ​​of the current document and their replacement values.

[0084] The current data value is replaced with a data value in the replacement range. Since all data values ​​in the replacement range are obtained based on the data values ​​of similar statements corresponding to the current data value, it satisfies the authenticity, that is, each data value after replacement also satisfies the corresponding statement. Satisfying the authenticity has a more realistic effect, making the encryption effect better.

[0085] Then calculate the absolute value of the difference between the current data value and each data value in the replacement range, and record the value with the largest absolute value of the difference as the replacement value of the current data value. Save the replacement value in the serial position of the final value set.

[0086] For the current data value, obtain its serial position in the current value set, and use the serial position of the current data value and the serial position of its corresponding replacement value as a two-dimensional point. For example: the first data value in the current value set, the serial position of its corresponding replacement value in the corresponding final value set is 10, then the first data value in the current value set corresponds to [1, 10]; the second data value in the current value set, the serial position of its corresponding replacement value in the corresponding final value set is 5, then the second data value in the current value set corresponds to [2, 5].

[0087] All 2D points in the current document form the key.

[0088] At this point, the key of the current document has been obtained.

[0089] Step S005, encrypting and protecting the project cost data according to the key.

[0090] After determining the key of the current document, the value in the current document is replaced with the corresponding ciphertext according to the corresponding relationship of the key. The encrypted text is saved as a new document and the document is marked so that it can be identified as an encrypted document file.

[0091] If the encrypted file needs to be decrypted, it can be decrypted according to the corresponding relationship between the document data in the code book, so as to obtain the real file.

[0092] Based on the same inventive concept as the above method, an embodiment of the present invention further provides a construction engineering cost data security protection system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above construction engineering cost data security protection methods are implemented. The specific process is as follows: Figure 2 shown.

[0093] Based on the same concept as the method embodiment of the present application, a computer-readable storage medium is proposed, and the computer-readable storage medium stores a computer program. When the computer program is executed by the processor, it implements a method for securely protecting construction project cost data as described in the first aspect. Its specific functions and technical effects can be found in the method embodiment part, and will not be repeated here.

[0094] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0095] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for protecting construction project cost data security, characterized in that: The method comprises the following steps: Get the historical document, current document and all data values ​​of the current document; The historical document and the current document are segmented according to punctuation to obtain several sentences; each sentence is segmented, and a historical segmentation set and a current segmentation set are obtained for each historical document and the current document respectively; the segmentations that are the same in the current segmentation set and the historical segmentation set constitute the segmentation set intersection; sentence similarity is obtained according to the difference in the number of segmentations in the segmentation set intersection and the current segmentation set; word order difference is obtained according to the difference in the sequence number of each segmentation in the segmentation set intersection in the historical segmentation set and the current segmentation set; sentence similarity is corrected according to the word order difference to obtain corrected sentence similarity; and similar sentences of the current document sentence are determined in this way; Cluster the data value of the current document sentence with the data values ​​of all its similar sentences to obtain the current cluster and the neighborhood cluster; if the current document sentence has one data value, obtain the outlier of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster; delete some data values ​​in the neighborhood cluster according to the comparison between the outlier and the preset outlier threshold to obtain the final value set; if the current document sentence has multiple data values, the current cluster is the final value set, and the replacement range is obtained according to the maximum and minimum values ​​of the final value set; Determine the replacement value based on the difference between each data value in the current document and each data value in the replacement range, and determine the key of the current document based on all data values ​​in the current document and their replacement values; The project cost data is encrypted and protected according to the key.

2. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method for obtaining sentence similarity based on the difference in the number of segmentation words between the intersection of the segmentation set and the current segmentation set is: The ratio of the intersection of the word segmentation sets to the number of word segmentations in the current word segmentation set is taken as the sentence similarity between the sentence in the current document and the sentence in the historical document.

3. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method for obtaining the word order difference according to the difference in the sequence number of each word in the intersection of the word sets in the historical word set and the current word set is: Label all the segmentations in the current segmentation set and the historical segmentation set in order, calculate the absolute value of the difference between the serial numbers of each segmentation in the intersection of the segmentation sets in the current segmentation set and the historical segmentation set, and record the cumulative sum of the absolute values ​​of the difference of all the segmentations in the intersection of the segmentation sets as the word order difference.

4. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method of correcting the sentence similarity according to the word order difference to obtain the corrected sentence similarity and determining the similar sentences of the current document sentence is as follows: The expression of the corrected sentence similarity is: , Indicates the similarity between the sentences in the current document and the sentences in the historical documents. Indicates the difference in word order between the current document and the historical document. is the normalization function, Indicates the corrected sentence similarity; For any sentence in the current document, the maximum sentence similarity between it and all sentences in the historical documents is taken as the similar sentence of the sentence in the current document.

5. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method of clustering the data value of the current document sentence with the data values ​​of all similar sentences to obtain the current cluster and the neighborhood clusters is: Cluster the data value of the current document sentence with the data values ​​of all its similar sentences; the cluster distance is the absolute value of the difference between the data values; The cluster where the data value of the current document sentence is located is recorded as the current cluster; the clusters other than the current cluster are recorded as neighboring clusters.

6. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method for obtaining the outlier value of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster is: , Represents the data value of the cluster center of the current cluster b, represents the data value of the cluster center of the vth neighborhood cluster, Represents the data value of the current document statement, represents the normalization function, represents the outlier of the vth neighborhood cluster.

7. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method of deleting data values ​​in some neighborhood clusters according to the comparison between the abnormal value and the preset abnormal threshold value to obtain the final value set is: If the abnormal value of the neighborhood cluster is greater than the preset abnormal threshold, it means that the data of the current neighborhood cluster is abnormal, and the data value in the neighborhood cluster is deleted from the value set; Delete the data values ​​of all abnormal neighborhood clusters from the value set to obtain the final value set.

8. A construction engineering cost data security protection method as claimed in claim 1, characterized in that: The method of determining the replacement value according to the difference between each data value of the current document and each data value in the replacement range, and determining the key of the current document according to all data values ​​of the current document and their replacement values ​​is: Record the data value of the current document statement as the current data value, calculate the absolute value of the difference between the current data value and each data value in the replacement range, record the value with the largest absolute value of the difference as the replacement value of the current data value, and save the replacement value in the sequence position of the final value set; Get the serial position of the current data value in the value set of the current document, and use the serial position of the current data value and the serial position of its corresponding replacement value as a two-dimensional point; All 2D points in the current document form the key.

9. A construction engineering cost data security protection system, implementing a construction engineering cost data security protection method as claimed in claim 1, characterized in that: The system comprises: The data collection module is used to obtain historical documents, current documents and the value set of the current document; A similar sentence acquisition module is used to segment the historical document and the current document according to punctuation marks to obtain several sentences; segment each sentence, and obtain a historical segmentation set and a current segmentation set for each historical document and the current document respectively; form a segmentation set intersection with the same segmentations in the current segmentation set and the historical segmentation set; obtain sentence similarity according to the difference in the number of segmentations in the segmentation set intersection and the current segmentation set; obtain word order difference according to the difference in the sequence number of each segmentation in the segmentation set intersection in the historical segmentation set and the current segmentation set; correct the sentence similarity according to the word order difference to obtain the corrected sentence similarity; and determine similar sentences accordingly; The replacement range acquisition module is used to cluster the data value of the current document sentence with the data values ​​of all similar sentences to obtain the current cluster and the neighborhood cluster; obtain the abnormal value of the neighborhood cluster according to the distance between the current cluster and the neighborhood cluster and the distance between the data value of the current document sentence and the neighborhood cluster; delete the data values ​​in some neighborhood clusters according to the comparison between the abnormal value and the preset abnormal threshold to obtain the final value set; obtain the replacement range according to the maximum and minimum values ​​of the final value set; A key determination module, used to determine a replacement value according to the difference between each data value of the current document and each data value within the replacement range, and to determine the key of the current document according to all data values ​​of the current document and their replacement values; The protection module is used to encrypt and protect the engineering cost data according to the key.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a method for securely protecting construction project cost data as described in any one of claims 1 to 8.

Images