A data security collection system and method based on artificial intelligence

Abstract

The present invention discloses a data security collection system and method based on artificial intelligence. The data security collection system includes a project information acquisition module, an associated project information selection module, an associated file information selection module and a reference file push module. The project information acquisition module is used to obtain project information to be processed and project information that has been processed historically. The associated project information selection module selects associated project information of the project information to be processed from the project information that has been processed historically. The associated file information selection module collects file information that has been read when the associated project information was processed historically as candidate file information, analyzes the candidate file information and selects associated file information therefrom. The reference file push module uses the associated file information as a reference file for the project information to be processed and pushes it to a terminal.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based data security collection system and method. Background Art

[0002] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. AI aims to create intelligent machines that can respond in a manner similar to human intelligence. The application of AI can help reduce workloads and improve efficiency.

[0003] In the process of carrying out a project, it is often necessary to collect some information. The existing process of collecting information is mostly done manually, but the workload of this method of collecting information is very large. There is a situation in the existing technology that the historical collected information is used to establish a database, but in this case, people still need to manually search for relevant information when carrying out the project.

[0004] Therefore, this application proposes an artificial intelligence-based data security collection system and method to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a data security collection system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a data security collection system based on artificial intelligence, the data security collection system includes a project information acquisition module, an associated project information selection module, an associated file information selection module and a reference file push module, the project information acquisition module is used to obtain the project information to be processed and the historically processed project information, the associated project information selection module selects the associated project information of the project information to be processed from the historically processed project information, the associated file information selection module collects the file information that has been read when the associated project information was processed historically as candidate file information, analyzes the candidate file information and selects associated file information therefrom, and the reference file push module uses the associated file information as a reference file for the project information to be processed and pushes it to the terminal.

[0007] Furthermore, the associated project information selection module includes an associated similarity acquisition module, a processing similarity acquisition module and a similarity comparison module. The associated similarity acquisition module sets the historically processed project information as the project to be referenced, and uses artificial intelligence to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the associated similarity of the project to be referenced. The processing similarity acquisition module uses artificial intelligence to analyze the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed as the processing similarity of the project to be referenced. The similarity comparison module compares the associated similarity of each project to be referenced with the associated similarity threshold, and compares the processing similarity of each project to be referenced with the processing similarity threshold. If the associated similarity of a certain project to be referenced is greater than or equal to the associated similarity threshold and the processing similarity of the project to be referenced is greater than the processing similarity threshold, then the project to be referenced is the associated project information of the project information to be processed.

[0008] Furthermore, the associated file information selection module includes an effective index calculation module and an effective index comparison module. The effective index calculation module calculates the effective index of each candidate file information based on the status information of the candidate file during the associated project information processing. The effective index comparison module compares the effective index of each candidate file information with the effective threshold. When the effective index of a candidate file information is greater than the effective threshold, the candidate file is defined as the associated file information.

[0009] Furthermore, the effective index calculation module includes a sequence sorting acquisition module, an information classification module, a first index calculation module, a second index calculation module, a third index calculation module, a topic similarity acquisition module and an effective index acquisition module. The sequence sorting acquisition module sets the candidate file information as the information to be analyzed, counts the total number of all related project information as n, and sorts each related project information in the order of processing time to obtain a sequence sorting. The information classification module determines whether the information to be analyzed has been opened during the processing of each related project information in the order of sequence sorting. If the information to be analyzed has been opened during the processing of a certain related project information, then the information to be analyzed is opened. The associated item information is the first information of the information to be analyzed. Otherwise, the associated item information is the second information of the information to be analyzed. The first index calculation module counts the average value c of the number of second information between two adjacent first information in the order of sorting, then the first index R of the information to be analyzed is 1-c / (n-1). The second index calculation module counts the number d of associated item information in the order of sorting that is the first information of the information to be analyzed, then the second index S of the information to be analyzed is d / n. The third index calculation module collects data when the information to be analyzed is opened during the first information processing period, and calculates the third index of the information to be analyzed based on the data. ,in, Indicates the first in the order of sorting The first information, , For the The total time that the information page to be analyzed is open during the first information processing period, For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during a first information processing period. When the information to be analyzed is opened at a certain time during a first information processing period, the page of the information to be analyzed is directly switched to the page of the first analysis. Then, this time is the effective number of times the information to be analyzed is opened. The topic similarity acquisition module collects the similarity U between the content of the information to be analyzed and the topic of the project information to be processed. The effective index acquisition module obtains the effective index W=0.12*R+0.12*S+0.26*T+0.5*U of the information to be analyzed.

[0010] A data security collection method based on artificial intelligence, the data security collection method comprising the following steps:

[0011] Obtaining the project information to be processed and the project information that has been processed in the past, and selecting the project information related to the project information to be processed from the project information that has been processed in the past;

[0012] The file information that has been read when collecting historical processing of related project information is used as candidate file information. The candidate file information is analyzed to select related file information, and the related file information is used as a reference file for the project information to be processed and pushed to the terminal.

[0013] Furthermore, the selecting of associated project information of the project information to be processed from the historically processed project information includes:

[0014] Assume that the project information that has been processed in the past is the project to be referenced. Use artificial intelligence to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the associated similarity of the project to be referenced. Analyze the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed as the processing similarity of the project to be referenced. If the associated similarity of a project to be referenced is greater than or equal to the associated similarity threshold and the processing similarity of the project to be referenced is greater than the processing similarity threshold, then the project to be referenced is the associated project information of the project information to be processed.

[0015] Furthermore, analyzing the candidate file information and selecting related file information therefrom includes:

[0016] Calculate the validity index of each candidate file information separately, wherein the calculation of the validity index of a candidate file information includes the following:

[0017] Assume that the candidate file information is the information to be analyzed, count the total number of all related project information as n, sort each related project information in chronological order of processing time to obtain a priority ranking, and determine in sequence whether each related project information has been opened during the processing of the information to be analyzed. If the information to be analyzed has been opened during the processing of a certain related project information, then the related project information is the first information to be analyzed; otherwise, the related project information is the second information to be analyzed; count the average value c of the number of second information between two adjacent first information in the priority ranking order, and then the first index R of the information to be analyzed is R = 1-c / (n-1); count the number d of related project information that is the first information to be analyzed in the priority ranking order, and then the second index S of the information to be analyzed is S = d / n;

[0018] Collect data when the information to be analyzed is opened during the first information processing period, and calculate the third index of the information to be analyzed based on the data ,in, Indicates the first in the order of sorting The first information, , For the The total time that the information page to be analyzed is open during the first information processing period, For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during a first information processing period. When the information to be analyzed is opened once during a first information processing period, if the page of the information to be analyzed is directly switched to the page of the first analysis, then this time is considered a valid number of times the information to be analyzed is opened;

[0019] Collect the similarity U between the content of the information to be analyzed and the subject of the project information to be processed, then the validity index of the information to be analyzed is W=0.12*R+0.12*S+0.26*T+0.5*U; compare the validity index of each candidate file information with the validity threshold. If the validity index of a candidate file information is greater than the validity threshold, then the candidate file is associated file information.

[0020] Furthermore, the data security collection method further includes:

[0021] De-duplicate the reference file before pushing it to the terminal.

[0022] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention selects appropriate historically processed projects as associated project information in advance according to the subject of the project to be processed and the situation of the assigned personnel, and then uses the file information that has been read when the associated project information is generated as candidate file information. The status information of the candidate files during the associated project information processing is then analyzed to calculate the validity index of each candidate file information to determine whether the candidate file information belongs to the type of information that needs to be collected for the project to be processed. Finally, when it is determined that the candidate file information belongs to the type of information that needs to be collected for the project to be processed, it is directly pushed to the terminal for direct review by the user, thereby reducing the workload of people in collecting and obtaining relevant information when carrying out project information and improving the work efficiency of carrying out project information. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0024] Figure 1 It is a module schematic diagram of the data security acquisition system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 The present invention provides a technical solution: a data security collection system based on artificial intelligence, the data security collection system includes a project information acquisition module, an associated project information selection module, an associated file information selection module and a reference file push module, the project information acquisition module is used to obtain the project information to be processed and the project information that has been processed historically, the associated project information selection module selects the associated project information of the project information to be processed from the project information that has been processed historically, the associated file information selection module collects the file information that has been read when the associated project information was processed historically as candidate file information, analyzes the candidate file information and selects associated file information therefrom, and the reference file push module uses the associated file information as a reference file for the project information to be processed and pushes it to the terminal.

[0027] The associated project information selection module includes an associated similarity acquisition module, a processing similarity acquisition module and a similarity comparison module. The associated similarity acquisition module sets historically processed project information as the project to be referenced, and uses artificial intelligence to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the associated similarity of the project to be referenced. The processing similarity acquisition module uses artificial intelligence to analyze the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed as the processing similarity of the project to be referenced. The similarity comparison module compares the associated similarity of each project to be referenced with the associated similarity threshold, and compares the processing similarity of each project to be referenced with the processing similarity threshold. If the associated similarity of a certain project to be referenced is greater than or equal to the associated similarity threshold and the processing similarity of the project to be referenced is greater than the processing similarity threshold, then the project to be referenced is the associated project information of the project information to be processed.

[0028] The associated file information selection module includes an effective index calculation module and an effective index comparison module. The effective index calculation module calculates the effective index of each candidate file information based on the status information of the candidate file during the associated project information processing. The effective index comparison module compares the effective index of each candidate file information with the effective threshold. When the effective index of a candidate file information is greater than the effective threshold, the candidate file is determined to be associated file information.

[0029] The effective index calculation module includes a sequence ranking acquisition module, an information classification module, a first index calculation module, a second index calculation module, a third index calculation module, a topic similarity acquisition module and an effective index acquisition module. The sequence ranking acquisition module sets the candidate file information as the information to be analyzed, counts the total number of all related project information as n, and sorts each related project information in the order of processing time to obtain a sequence ranking. The information classification module determines whether the information to be analyzed has been opened during the processing of each related project information in the order of sequence ranking. If the information to be analyzed has been opened during the processing of a certain related project information, then the related project information is opened. The associated item information is the first information of the information to be analyzed; otherwise, the associated item information is the second information of the information to be analyzed. The first index calculation module counts the average value c of the number of second information between two adjacent first information in the order of sorting, then the first index R of the information to be analyzed is 1-c / (n-1). The second index calculation module counts the number d of associated item information that is the first information of the information to be analyzed in the order of sorting, then the second index S of the information to be analyzed is d / n. The third index calculation module collects data when the information to be analyzed is opened during the first information processing period, and calculates the third index of the information to be analyzed based on the data. ,in, Indicates the first in the order of sorting The first information, , For the The total time that the information page to be analyzed is open during the first information processing period, For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during a first information processing period. When the information to be analyzed is opened at a certain time during a first information processing period, the page of the information to be analyzed is directly switched to the page of the first analysis. Then, this time is the effective number of times the information to be analyzed is opened. The topic similarity acquisition module collects the similarity U between the content of the information to be analyzed and the topic of the project information to be processed. The effective index acquisition module obtains the effective index W=0.12*R+0.12*S+0.26*T+0.5*U of the information to be analyzed.

[0030] A data security collection method based on artificial intelligence, the data security collection method comprising the following steps:

[0031] Obtaining the project information to be processed and the project information that has been processed in the past, and selecting the project information related to the project information to be processed from the project information that has been processed in the past;

[0032] The selecting of associated project information of the project information to be processed from the historically processed project information includes:

[0033] Assuming that the project information that has been processed in the past is the project to be referenced, artificial intelligence is used to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the association similarity of the project to be referenced, and the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed is analyzed as the processing similarity of the project to be referenced. This application takes into account that different project processing personnel have different tendencies when referring to and collecting relevant data, so in this application, the similarity of the assigned personnel is also used as a selection factor for the associated project information, so that the reference files pushed to project staff are more targeted;

[0034] If the association similarity of a certain to-be-referenced item is greater than or equal to the association similarity threshold and the processing similarity of the to-be-referenced item is greater than the processing similarity threshold, then the to-be-referenced item is associated item information of the to-be-processed item information.

[0035] The file information read during the historical processing of the associated project information is collected as candidate file information, and the candidate file information is analyzed to select associated file information therefrom; the analyzing the candidate file information to select associated file information therefrom includes: calculating the validity index of each candidate file information respectively, wherein the calculation of the validity index of a candidate file information includes the following:

[0036] Assume that the candidate file information is the information to be analyzed, count the total number of all related project information as n, sort each related project information in the order of processing time to obtain a priority sort, and judge in order whether each related project information has been opened during the processing of each related project information. If the information to be analyzed has been opened during the processing of a certain related project information, then the related project information is the first information of the information to be analyzed. If the information to be analyzed has not been opened during the processing of a certain related project information, then the related project information is the second information of the information to be analyzed; count the average value c of the number of second information between two adjacent first information in the priority sort order, then the first index R of the information to be analyzed is R = 1-c / (n-1). For example, in the priority sort of the information to be analyzed, the related project information is opened according to the order of the first information. The order is first information, first information, second information, second information, first information, first information, first information, first information, then the number of second information between two adjacent first information is 0, 2, 0, 0, then the average value c is (0+2+0+0) / 4=0.5, then the first index R=1-c / (n-1)=1-0.5 / (7-1)=11 / 12; the larger the number of second information between two adjacent first information (the smaller the first index R), the less frequently the information to be analyzed is used, indicating a lower probability of using the information to be analyzed when processing the information of the project to be processed; the smaller the number of second information between two adjacent first information (the larger the first index R), the more frequently the information to be analyzed is used, indicating a higher probability of using the information to be analyzed when processing the information of the project to be processed;

[0037] The number d of the first information whose associated project information is the information to be analyzed in the order of priority is counted, and the second index S of the information to be analyzed is S = d / n; the greater the number d, the greater the probability that the information to be analyzed will be used when processing the project information to be processed;

[0038] Collect data when the information to be analyzed is opened during the first information processing period, and calculate the third index of the information to be analyzed based on the data ,in, Indicates the first in the order of sorting The first information, , For the The total time that the information page to be analyzed is open during the first information processing period, For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during the first information processing period. When the information to be analyzed is opened at a certain time during the first information processing period, it is directly switched from the page of the information to be analyzed to the page of the first analysis, then this time is the effective time of opening the information to be analyzed; this application takes into account that not every time the information to be analyzed is opened, the project staff may not necessarily obtain relevant data information from it, and not every time the information file to be analyzed is opened is helpful for processing the project information, so this application further analyzes the page switching situation to improve the accuracy of the analysis results; at the same time, this application will As a weight, the rationality of the calculated third index is further improved.

[0039] When judging whether a certain opening of the information to be analyzed is a valid time, for example, when a project staff member is processing the first information, he opens the first information to be analyzed page and the second information to be analyzed page. The main page of the terminal is first on the first information to be analyzed page, then switches from the first information to be analyzed page to the second information to be analyzed page, and then switches from the second information to be analyzed page to the first information page. In this case, the opening of the second information to be analyzed page is not a valid time, but the opening of the second information to be analyzed page is a valid time.

[0040] Collect the similarity U between the content of the information to be analyzed and the subject of the project information to be processed. The higher the similarity U, the greater the probability that the information to be analyzed will be used when processing the project information to be processed.

[0041] Then the validity index of the information to be analyzed is W = 0.12*R + 0.12*S + 0.26*T + 0.5*U. The validity index of each candidate file information is compared with the validity threshold. If the validity index of a candidate file information is greater than the validity threshold, then the candidate file information is the associated file information;

[0042] The associated file information is used as a reference file for the project information to be processed, and the reference file is deduplicated before being pushed to the terminal.

[0043] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0044] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A data security collection system based on artificial intelligence, characterized in that: The data security collection system includes a project information acquisition module, a related project information selection module, a related file information selection module, and a reference file push module. The project information acquisition module is used to acquire project information to be processed and project information that has been processed historically. The related project information selection module selects related project information of the project information to be processed from the project information that has been processed historically. The related file information selection module collects file information that has been read during the historical processing of related project information as candidate file information, analyzes the candidate file information, and selects related file information therefrom. The reference file push module uses the related file information as a reference file for the project information to be processed and pushes it to the terminal. The associated file information selection module includes an effective index calculation module and an effective index comparison module. The effective index calculation module calculates the effective index of each candidate file information based on the status information of the candidate file during the associated project information processing. The effective index comparison module compares the effective index of each candidate file information with the effective threshold. When the effective index of a candidate file information is greater than the effective threshold, the candidate file is determined to be associated file information. The effective index calculation module includes a sequence ranking acquisition module, an information classification module, a first index calculation module, a second index calculation module, a third index calculation module, a topic similarity acquisition module and an effective index acquisition module. The sequence ranking acquisition module sets a certain candidate file information as the information to be analyzed, counts the total number of all related project information as n, and sorts each related project information in the order of processing time to obtain a sequence ranking. The information classification module determines whether the information to be analyzed has been opened during the processing of each related project information in the order of sequence ranking. If the information to be analyzed has been opened during the processing of a certain related project information, then the related project information is opened. The associated item information is the first information of the information to be analyzed; otherwise, the associated item information is the second information of the information to be analyzed. The first index calculation module counts the average value c of the number of second information between two adjacent first information in the order of sorting, then the first index R of the information to be analyzed is 1-c / (n-1). The second index calculation module counts the number d of associated item information that is the first information of the information to be analyzed in the order of sorting, then the second index S of the information to be analyzed is d / n. The third index calculation module collects data when the information to be analyzed is opened during the first information processing period, and calculates the third index of the information to be analyzed based on the data. ,in, Indicates the first The first information, , H is the total time that the information page to be analyzed is open during the i-th first information processing period in the order of chronological order; z is the total time duration that the page of the information to be analyzed is open during all first information processing periods. For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during the first information processing period; When the information to be analyzed is opened at a certain time during a first information processing period, the page of the information to be analyzed is directly switched to the page of the first information, then this time is the effective time of opening the information to be analyzed, the subject similarity acquisition module collects the similarity U between the content of the information to be analyzed and the subject of the project information to be processed, and the effective index acquisition module obtains the effective index W=0.12*R+0.12*S+0.26*T+0.5*U of the information to be analyzed.

2. The artificial intelligence-based data security acquisition system according to claim 1, characterized in that: The associated project information selection module includes an associated similarity acquisition module, a processing similarity acquisition module and a similarity comparison module. The associated similarity acquisition module sets historically processed project information as the project to be referenced, and uses artificial intelligence to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the associated similarity of the project to be referenced. The processing similarity acquisition module uses artificial intelligence to analyze the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed as the processing similarity of the project to be referenced. The similarity comparison module compares the associated similarity of each project to be referenced with the associated similarity threshold, and compares the processing similarity of each project to be referenced with the processing similarity threshold. If the associated similarity of a certain project to be referenced is greater than or equal to the associated similarity threshold and the processing similarity of the project to be referenced is greater than the processing similarity threshold, then the project to be referenced is the associated project information of the project information to be processed.

3. A method for secure data collection based on artificial intelligence, applied to a secure data collection system based on artificial intelligence according to any one of claims 1-2, characterized in that: The data security collection method comprises the following steps: Obtaining the project information to be processed and the project information that has been processed in the past, and selecting the project information related to the project information to be processed from the project information that has been processed in the past; The file information that has been read when collecting historical processing of related project information is used as candidate file information. The candidate file information is analyzed to select related file information, and the related file information is used as a reference file for the project information to be processed and pushed to the terminal.

4. The method for secure data collection based on artificial intelligence according to claim 3, characterized in that: The selecting of associated project information of the project information to be processed from the historically processed project information includes: Suppose that the project information that has been processed historically is the project to be referenced. Use artificial intelligence to analyze the similarity between the subject of each project to be referenced and the subject of the project information to be processed as the associated similarity of the project to be referenced. Analyze the similarity between the assigned personnel of each project to be referenced and the assigned personnel of the project information to be processed as the processing similarity of the project to be referenced. If the associated similarity of a project to be referenced is greater than or equal to the associated similarity threshold and the processing similarity of the project to be referenced is greater than the processing similarity threshold, then the project to be referenced is the associated project information of the project information to be processed.

5. The method for secure data collection based on artificial intelligence according to claim 4, characterized in that: The analyzing the candidate file information and selecting the associated file information therefrom includes: Calculate the validity index of each candidate file information separately, wherein the calculation of the validity index of a candidate file information includes the following: Assume that a certain candidate file information is the information to be analyzed, count the total number of all related project information as n, and sort each related project information in order of processing time to obtain a priority ranking; determine in order of priority whether each related project information has been opened during the processing of the information to be analyzed; if the information to be analyzed has been opened during the processing of a certain related project information, then the related project information is the first information to be analyzed; otherwise, the related project information is the second information to be analyzed; count the average value c of the number of second information between two adjacent first information in the priority ranking order, then the first index R of the information to be analyzed is 1-c / (n-1); count the number d of related project information that is the first information to be analyzed in the priority ranking order, then the second index S of the information to be analyzed is d / n; Collect data when the information to be analyzed is opened during the first information processing period, and calculate the third index of the information to be analyzed based on the data ,in, Indicates the first The first information, , H is the total time that the information page to be analyzed is open during the i-th first information processing period in the order of chronological order; z is the total time duration that the page of the information to be analyzed is open during all first information processing periods. For the The valid number of times the information to be analyzed is opened during the first information processing period, For the The total number of times the information to be analyzed is opened during a first information processing period. When the information to be analyzed is opened once during a first information processing period, the user directly switches from the page of the information to be analyzed to the page of the first information, and this time is considered a valid number of times the information to be analyzed is opened. Collect the similarity U between the content of the information to be analyzed and the subject of the project information to be processed. Then the validity index of the information to be analyzed is W=0.12*R+0.12*S+0.26*T+0.5*U. Compare the validity index of each candidate file information with the validity threshold. If the validity index of a candidate file information is greater than the validity threshold, then the candidate file is associated file information.

6. The method for secure data collection based on artificial intelligence according to claim 5, characterized in that: The data security collection method further includes: De-duplicate the reference file before pushing it to the terminal.

Images