Engineering management BIM system evaluation method and system based on artificial intelligence

Abstract

The present invention discloses an evaluation method and system for a BIM system for engineering management based on artificial intelligence, and belongs to the technical field of BIM systems for engineering management, and comprises: constructing a data firewall, and dividing the data firewall into a building material information data firewall, a building design information data firewall and a building construction information data firewall; collecting data features of the data firewall, and performing data backup, and acquiring task information corresponding to each data feature at the same time; the present invention utilizes artificial intelligence analysis and evaluation technology to construct a firewall system based on construction operation data, and distinguishes and manages the constituent data in the data firewall, analyzes the correlation influence between each data after being invaded, and predicts and analyzes the change rules of each IP address text data, and when the prediction result is that an invasion is determined, a firewall early warning signal is issued to protect the data from being stolen and tampered with.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering management BIM system, in particular to an engineering management BIM system evaluation method and system based on artificial intelligence. Background Art

[0002] In engineering project management, the BIM (Building Information Modeling) system is a building information model management system based on cloud computing technology. It can help project teams coordinate and manage BIM data, including architectural and engineering design, building materials, construction plans, and maintenance plans. The BIM management system can be used for various types of construction projects, including residential, commercial, and public facilities. In real life, the application of BIM management systems is becoming more and more popular. Among them, the technical application number CN202310851568.3 provides an artificial intelligence-based engineering project data analysis system and method. This technical application analyzes the material selection scheme of the engineering project, constructs an engineering material priority sequence model, and analyzes the impact of mechanical equipment related to each construction link on the progress of the construction link. , Construct a risk assessment model, and combine the scheme adopted by the current engineering project for rationality judgment, thereby improving the rationality of the construction plan of the engineering project and reducing the cost of the engineering project. However, with the widespread application of BIM management technology, the security issues of the large amount of data and information involved in the project management process have gradually emerged. Since BIM management technology involves a large amount of project information and data, the above-mentioned technical application is difficult to eliminate the risk of data leakage and unauthorized access, and then in the case of insufficient data security protection, it will lead to information leakage or tampering, bringing risks to the project. Summary of the invention

[0003] In view of the above problems existing in the existing engineering management BIM system, the present invention is proposed.

[0004] Therefore, one of the purposes of the present invention is to provide an engineering management BIM system evaluation method and system based on artificial intelligence, which utilizes artificial intelligence analysis and evaluation technology to construct a firewall system based on construction operation data, and distinguishes and manages the constituent data in the data firewall, collects information characteristics of different data being invaded, analyzes the correlation impact between the data after the invasion, and formulates a corresponding hierarchical management plan. At the same time, by collecting the text data characteristics of the invading IP address and counting the total number of invading IP addresses, the invading text data characteristics of each IP address are given as abnormal data characteristics, and the change rules of the text data of each IP address are analyzed. Based on the change rules, a text data change trend prediction model is generated, and then the text data characteristics of the IP address accessing the data firewall can be predicted in the future period. When the prediction result is a judgment of invasion, a firewall warning signal can be issued to protect the data from being stolen and tampered with.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In one aspect, the present invention provides an engineering management BIM system evaluation method based on artificial intelligence, comprising:

[0007] S10: constructing a data firewall, and dividing the data firewall into a building material information data firewall, a building design information data firewall, and a building construction information data firewall;

[0008] S20: collecting data features of the data firewall, performing data backup, and acquiring task information corresponding to each data feature;

[0009] S30: Divide the data components of the data firewall, obtain information features of different data components encountering intrusion, and generate a cloud database;

[0010] S40: Evaluate the data loss each time an intrusion occurs, analyze the data capacity characteristics of the lost data, and obtain the corresponding data components based on the lost data, and collect the number of intrusions of each data component according to the obtained data components, and sort the data components according to the probability of being susceptible to intrusion according to the number of intrusions;

[0011] S50: Monitor and analyze the loss data to obtain changes in the impact of the loss data on the progress of the construction work, and formulate a corresponding hierarchical management plan based on the changes in the impact.

[0012] As a preferred solution of the present invention, in said S20, task information corresponding to each data feature is obtained, and the task information is decomposed, and the task information decomposition includes refining the building status planning and refining the building status progress.

[0013] As a preferred solution of the present invention, wherein: in the S30, the data composition of the data firewall is divided, including dividing the data composition into early data, mid-term data and late data, wherein the early data includes survey and analysis data of the topography, landform, geology, surrounding environment and traffic conditions of the construction site;

[0014] The interim data include project progress, quality assessment, cost analysis, benefit assessment and construction fund management. The quality assessment includes inspection and testing data of building structure, material usage and construction technology;

[0015] The later data includes safety record data, acceptance data and maintenance data. The safety record data includes production data, safety inspection report data and accident handling data; the acceptance data includes project acceptance record data and project completion acceptance report data.

[0016] As a preferred solution of the present invention, in said S30, the information features of different data encountering intrusions include the time of the first encounter with intrusion and the subsequent intrusion time change features, as well as the text features of the intruder, virus implantation data and denial of service attacks. The denial of service attacks include sending information exceeding the system load to the target server or email address of the BIM management system, causing the BIM management system to be overloaded, network blocked and crashed. In said S30, it also includes:

[0017] S301: Obtaining the intruder IP address and different data components of the intrusion corresponding to the first intrusion, and obtaining the corresponding intrusion residence time from the different data components of the intrusion;

[0018] S302: Based on the early data in the data composition, analyze the associated changes formed by the intruder on the mid-term data and / or the late data after each intrusion access, and obtain the change characteristics therein. When the data changes in the data composition in the future period are the same as the change characteristics after the intrusion access, it is determined that the data firewall is attacked by the intrusion, and a firewall warning signal is issued. Otherwise, no determination is made;

[0019] S303: Based on the intruder IP address obtained each time the intruder intrudes, analyze the associated features of the intrusion text data of each IP address, and use Wireshark and / or Tcpdump network analysis technology to analyze the attack behavior corresponding to the intrusion text data.

[0020] As a preferred solution of the present invention, the text data of each intrusion is marked and stored, and the intrusion text data is uploaded to the cloud database, the cloud database is updated and optimized, and in S303, the associated features of the intrusion text data of each IP address are obtained according to , , ..., To distinguish, Indicates The correlation features are determined, and the proportion of the IP address intrusion text data under different correlation features to the early data, mid-term data and / or late data in different data compositions is analyzed; when the proportion of different IP address text data accessing the early data, mid-term data and / or late data in the future time period is consistent with the proportion of data at the time of intrusion access, it is determined that the data firewall has been attacked by intrusion, and a firewall early warning signal is issued; otherwise, no determination is made.

[0021] As a preferred solution of the present invention, the total number of invading IP addresses is counted based on the previous data in the data composition, the invading text data features of each IP address are used as abnormal data features, and artificial intelligence assisted processing is performed through abnormal feature recognition technology and multi-dimensional information fusion fault judgment technology. The auxiliary processing includes using data cleaning technology and standardization processing to generate a cleaned data set based on the abnormal data features. When the text data features of the IP address accessing the data firewall in the future period are consistent with the abnormal data features in the data set, a firewall warning signal is issued and the access path of the data firewall is closed.

[0022] As a preferred solution of the present invention, the total number of invading IP addresses counted by the previous data in the data composition is used to sort the acquired invading IP addresses in a forward-to-backward order, and a Monte Carlo tree search update strategy is used to analyze the change pattern of the IP address text data from front to back, and a text data change trend prediction model is generated based on the change pattern, and at the same time, the IP address text data change in the future time period is predicted. When the text data characteristics of the IP address accessing the data firewall in the future time period are consistent with the predicted IP address text data change, a firewall warning signal is issued, and the access path of the data firewall is closed.

[0023] A terminal includes a processor, an input interface, an output interface and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute an engineering management BIM system evaluation method based on artificial intelligence.

[0024] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes an engineering management BIM system evaluation method based on artificial intelligence.

[0025] On the other hand, the present invention provides a system for an engineering management BIM system evaluation method based on artificial intelligence, comprising:

[0026] A security construction module is used to construct a data firewall, and divide the data firewall into a building material information data firewall, a building design information data firewall and a building construction information data firewall;

[0027] A feature collection module is used to collect data features of the data firewall and perform data backup, and at the same time obtain task information corresponding to each data feature and decompose the task information, including detailed building status planning and detailed building status progress;

[0028] An LSTM network fusion analysis module, used to divide the data composition of the data firewall based on the LSTM network, obtain information features of different data compositions encountering intrusion, and generate a cloud database. The LSTM network fusion analysis module includes a division module, a calculation module, and an analysis module. The information features include the IP address of the intruder.

[0029] The division module is used to divide the data composition of the data firewall into early data, mid-term data and late data;

[0030] The calculation module responds to the division module to divide the data components to obtain the division data, and the calculation module is used to obtain the intruder IP address and different data components of the intrusion corresponding to the first intrusion, and calculate the corresponding intrusion residence time in the different data components of the intrusion;

[0031] The analysis module is used to analyze the proportion of the text data volume of different intrusion IP addresses to the early data, mid-term data and / or late data in different data compositions. When the proportion of the text data of different IP addresses accessing the early data, mid-term data and / or late data in the future period is consistent with the proportion of the data at the time of intrusion access, it is determined that the data firewall is attacked by intrusion and a firewall warning signal is issued. Otherwise, no determination is made.

[0032] The prediction and discrimination module is used to sort the acquired invading IP addresses in a forward-to-backward order based on the total number of invading IP addresses counted by the previous data in the data composition, and at the same time use a Monte Carlo tree search update strategy to analyze the change pattern of the IP address text data from front to back, and generate a text data change trend prediction model based on the change pattern.

[0033] The present invention utilizes artificial intelligence analysis and evaluation technology to construct a firewall system based on construction operation data, and distinguishes and manages the constituent data in the data firewall, collects information features of different data being invaded, analyzes the correlation impact between the data after being invaded, and formulates corresponding hierarchical management plans. At the same time, by collecting text data features of invading IP addresses and counting the total number of invading IP addresses, the invading text data features of each IP address are given as abnormal data features, and the change rules of the text data of each IP address are analyzed. A text data change trend prediction model is generated based on the change rules, and then the text data features of the IP addresses accessing the data firewall can be predicted in the future time period. When the prediction result is that an invasion is determined, a firewall warning signal is issued to protect the data from being stolen and tampered with. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0035] Figure 1 A schematic diagram of a modular structure of a system according to an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a method flow of an embodiment of the present invention;

[0037] Figure 3 It is a schematic diagram of the process structure of an embodiment of the present invention.

[0038] Numbers in the figure: 110 - security construction module; 120 - feature collection module; 130 - LSTM network fusion analysis module; 1301 - partitioning module; 1302 - calculation module; 1303 - analysis module; 140 - prediction and discrimination module. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0040] Because existing technologies are difficult to eliminate the risk of data leakage and unauthorized access when involving a large amount of project information and data, insufficient data security may lead to information leakage or tampering, posing risks to the project.

[0041] Based on this, the present invention proposes an engineering management BIM system evaluation method and system based on artificial intelligence, which utilizes artificial intelligence analysis and evaluation technology to construct a firewall system based on construction operation data, and manages the component data separately in the data firewall, collects information characteristics of different data being invaded, analyzes the correlation impact between the data after the invasion, and simultaneously analyzes the change pattern of the text data of each IP address, and generates a text data change trend prediction model based on the change pattern. When the prediction result is an intrusion, a firewall warning signal is issued to protect the data from being stolen and tampered with.

[0042] The present invention is further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0043] Reference Figures 1 to 3 , is an embodiment of the present invention, which provides an engineering management BIM system evaluation method based on artificial intelligence, including:

[0044] S10: construct a data firewall, and divide the data firewall into a building material information data firewall, a building design information data firewall, and a building construction information data firewall;

[0045] S20: Collect data features of the data firewall, perform data backup, and obtain task information corresponding to each data feature;

[0046] It should be noted that in this embodiment, obtaining task information corresponding to each data feature further includes decomposing the task information, and the task information decomposition includes refining the building status planning and refining the building status progress;

[0047] S30: Divide the data components of the data firewall, obtain information features of different data components encountering intrusion, and generate a cloud database;

[0048] Specifically, the data composition of the data firewall is divided into early data, mid-term data and late data, wherein the early data includes survey and analysis data of the topography, landform, geology, surrounding environment and traffic conditions of the construction site;

[0049] Mid-term data include project progress, quality assessment, cost analysis, benefit assessment and construction fund management. Quality assessment includes inspection and test data of building structure, material use and construction technology.

[0050] The later data includes safety record data, acceptance data and maintenance data. The safety record data includes production data, safety inspection report data and accident handling data. The acceptance data includes project acceptance record data and project completion acceptance report data.

[0051] Furthermore, the present embodiment obtains information features of intrusions encountered by different data, including the time of the first intrusion, and subsequent intrusion time change features, as well as text features of the intruder, virus implantation data, and denial of service attacks. Denial of service attacks include sending information that exceeds the system load to the target server or email address of the BIM management system, causing system overload, network congestion, and system crash;

[0052] On the basis of the above, this embodiment also includes the following implementation steps:

[0053] S301: Obtaining the intruder IP address and different data components of the intrusion corresponding to the first intrusion, and obtaining the corresponding intrusion residence time from the different data components of the intrusion;

[0054] S302: Based on the previous data in the data composition, analyze the associated changes formed by the intruder on the mid-term data and / or the later data after each intrusion access, and obtain the change characteristics therein. When the data change in the future period data composition is the same as the change characteristics after the intrusion access, it is determined that the data firewall is attacked by the intrusion and a firewall warning signal is issued. Otherwise, no determination is made;

[0055] S303: Analyze the associated features of the intrusion text data of each IP address based on the intruder IP address obtained each time the intruder intrudes and use Wireshark and / or Tcpdump network analysis technology to analyze the attack behavior corresponding to the intrusion text data;

[0056] It should be emphasized in this embodiment that each intrusion text data is marked and stored, and the intrusion text data is uploaded to the cloud database, the cloud database is updated and optimized, and in S303, the associated features of the intrusion text data of each IP address are obtained according to , , ..., To distinguish, Indicates The said correlation features are analyzed, and the proportion of the amount of IP address intrusion text data under different correlation features to the early data, mid-term data and / or late data in different data compositions is analyzed. When the proportion of different IP address text data accessing the said early data, mid-term data and / or late data in the future period is consistent with the proportion of data accessed during the intrusion, it is determined that the said data firewall is attacked by intrusion, and a firewall warning signal is issued. Otherwise, it is not determined;

[0057] This embodiment further counts the total number of intruding IP addresses based on the previous data in the data composition, gives the intrusion text data features of each IP address as abnormal data features, and performs artificial intelligence-assisted processing through abnormal feature recognition technology and multi-dimensional information fusion fault discrimination technology. The auxiliary processing includes using data cleaning technology and standardization processing to generate a cleaned data set based on abnormal data features. When the text data features of the IP addresses accessing the data firewall in the future period are consistent with the abnormal data features in the data set, a firewall warning signal is issued, and the access path of the data firewall is closed;

[0058] It should be noted that, based on the above, this embodiment further includes: based on the total number of intruding IP addresses counted by the previous data in the data composition, the acquired intruding IP addresses are sorted in a front-to-back order, and the change law of the IP address text data is analyzed from front to back using the Monte Carlo tree search update strategy, a text data change trend prediction model is generated based on the change law, and the IP address text data change in the future period is predicted. When the IP address text data characteristics of the access to the data firewall in the future period meet the predicted IP address text data changes, a firewall warning signal is issued, and the access path of the data firewall is closed;

[0059] S40: Evaluate the data loss each time an intrusion occurs, analyze the data capacity characteristics of the lost data, and obtain the corresponding data components based on the lost data. At the same time, according to the obtained data components, collect the number of intrusions of each data component, and sort the data components according to the probability of being susceptible to intrusion according to the number of intrusions.

[0060] S50: Monitor and analyze the loss data to obtain changes in the impact of the loss data on the progress of the construction work, and formulate a corresponding hierarchical management plan based on the changes in the impact.

[0061] A terminal includes a processor, an input interface, an output interface and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute an engineering management BIM system evaluation method based on artificial intelligence.

[0062] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes an engineering management BIM system evaluation method based on artificial intelligence.

[0063] Based on the above, this application uses artificial intelligence analysis and evaluation technology to build a firewall system based on construction work data, and manages the constituent data in the data firewall, collects information characteristics of different data being invaded, and analyzes the correlation and impact between the data after the invasion. At the same time, it analyzes the change pattern of the text data of each IP address, and generates a text data change trend prediction model based on the change pattern. When the prediction result is an intrusion, a firewall warning signal is issued to protect the data from being stolen and tampered with.

[0064] This embodiment combines the above-mentioned engineering management BIM system evaluation method based on artificial intelligence and also proposes a working system of the evaluation method, as follows:

[0065] The security construction module 110 is used to construct a data firewall, and divide the data firewall into a building material information data firewall, a building design information data firewall and a building construction information data firewall;

[0066] The feature collection module 120 is used to collect data features of the data firewall and perform data backup, and at the same time obtain task information corresponding to each data feature and decompose the task information, including detailed building status planning and detailed building status progress.

[0067] The LSTM network fusion analysis module 130 is used to divide the data composition of the data firewall based on the LSTM network, obtain information features of different data compositions encountering intrusion, and generate a cloud database. The LSTM network fusion analysis module includes a division module 1301, a calculation module 1302 and an analysis module 1303. The information features include the IP address of the intruder;

[0068] The division module 1301 is used to divide the data composition of the data firewall into early data, mid-term data and late data;

[0069] The calculation module 1302 responds to the divided data obtained by dividing the data composition by the division module 1301, and the calculation module is used to obtain the intruder IP address and different data compositions of the intrusion corresponding to the first intrusion, and calculate the corresponding intrusion residence time in the different data compositions of the intrusion;

[0070] The analysis module 1303 is used to analyze the proportion of the text data volume of different intrusion IP addresses to the early data, mid-term data and / or late data in different data compositions. When the proportion of the text data of different IP addresses accessing the early data, mid-term data and / or late data in the future period is consistent with the proportion of the data during the intrusion access, it is determined that the data firewall is attacked by the intrusion and a firewall warning signal is issued. Otherwise, no determination is made.

[0071] The prediction and judgment module 140 is used to sort the acquired invading IP addresses in a forward-to-backward order based on the total number of invading IP addresses counted by the previous data in the data composition, and at the same time use the Monte Carlo tree search update strategy to analyze the change pattern of the IP address text data from front to back, and generate a text data change trend prediction model based on the change pattern.

[0072] In summary, the present invention utilizes artificial intelligence analysis and evaluation technology to construct a firewall system based on construction operation data, and distinguishes and manages the constituent data in the data firewall, collects information features of different data being invaded, analyzes the correlation impact between the data after being invaded, and formulates corresponding hierarchical management plans. At the same time, by collecting the text data features of the invading IP addresses and counting the total number of invading IP addresses, the invading text data features of each IP address are given as abnormal data features, and the change rules of the text data of each IP address are analyzed. A text data change trend prediction model is generated based on the change rules, and then the text data features of the IP addresses accessing the data firewall can be predicted in the future time period. When the prediction result is that an invasion is determined, a firewall warning signal is issued to protect the data from being stolen and tampered with.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The evaluation method of engineering management BIM system based on artificial intelligence is characterized by: include: S10: constructing a data firewall, and dividing the data firewall into a building material information data firewall, a building design information data firewall, and a building construction information data firewall; S20: collecting data features of the data firewall, performing data backup, and acquiring task information corresponding to each data feature; S30: Divide the data components of the data firewall, obtain information features of different data components encountering intrusion, and generate a cloud database; The information features of different data encountering intrusions are obtained, including the time of the first intrusion and the subsequent intrusion time change features, as well as the text features of the intruder, virus implantation data and denial of service attacks. The denial of service attacks include sending information that exceeds the system load to the target server or email address of the BIM management system, causing the BIM management system to be overloaded, network blocked and crashed. In the S30, it also includes: S301: Obtaining the intruder IP address and different data components of the intrusion corresponding to the first intrusion, and obtaining the corresponding intrusion residence time from the different data components of the intrusion; S302: Based on the early data in the data composition, analyze the associated changes formed by the intruder on the mid-term data and / or the late data after each intrusion access, and obtain the change characteristics therein. When the data changes in the data composition in the future period are the same as the change characteristics after the intrusion access, it is determined that the data firewall is attacked by the intrusion, and a firewall warning signal is issued. Otherwise, no determination is made; S303: Analyze the associated features of the intrusion text data of each IP address based on the intruder IP address obtained each time the intruder intrudes and use Wireshark and / or Tcpdump network analysis technology to analyze the attack behavior corresponding to the intrusion text data; Each time the text data encountered intrusion is marked and stored, the intrusion text data is uploaded to the cloud database, the cloud database is updated and optimized, and in S303, the associated features of the intrusion text data of each IP address are obtained according to To distinguish, Indicate the nth said correlation feature, and analyze the proportion of the amount of IP address intrusion text data under different correlation features to the early data, mid-term data and / or late data in different data compositions. When the proportion of different IP address text data accessing the early data, mid-term data and / or late data in the future period is consistent with the proportion of data at the time of intrusion access, it is determined that the data firewall is attacked by intrusion, and a firewall warning signal is issued. Otherwise, no determination is made; S40: Evaluate the data loss each time an intrusion occurs, analyze the data capacity characteristics of the lost data, and obtain the corresponding data components based on the lost data, and collect the number of intrusions of each data component according to the obtained data components, and sort the data components according to the probability of being susceptible to intrusion according to the number of intrusions; S50: Monitor and analyze the loss data to obtain changes in the impact of the loss data on the progress of the construction work, and formulate a corresponding hierarchical management plan based on the changes in the impact.

2. The method for evaluating the engineering management BIM system based on artificial intelligence according to claim 1, characterized in that: In the S20, task information corresponding to each data feature is obtained, and the task information is decomposed, and the task information decomposition includes detailed building status planning and detailed building status progress.

3. The method for evaluating the engineering management BIM system based on artificial intelligence according to claim 1, characterized in that: In the S30, the data composition of the data firewall is divided, including dividing the data composition into early data, mid-term data and late data, wherein the early data includes survey and analysis data of the topography, landform, geology, surrounding environment and traffic conditions of the construction site; The interim data include project progress, quality assessment, cost analysis, benefit assessment and construction fund management. The quality assessment includes inspection and testing data of building structure, material usage and construction technology; The later data includes safety record data, acceptance data and maintenance data. The safety record data includes production data, safety inspection report data and accident handling data; the acceptance data includes project acceptance record data and project completion acceptance report data.

4. The method for evaluating the engineering management BIM system based on artificial intelligence as claimed in claim 3, characterized in that: The total number of invading IP addresses is counted based on the previous data in the data composition, the invading text data features of each IP address are used as abnormal data features, and artificial intelligence-assisted processing is performed through abnormal feature recognition technology and multi-dimensional information fusion fault judgment technology. The auxiliary processing includes using data cleaning technology and standardization processing to generate a cleaned data set based on the abnormal data features. When the text data features of the IP addresses accessing the data firewall in the future period are consistent with the abnormal data features in the data set, a firewall warning signal is issued, and the access path of the data firewall is closed.

5. The method for evaluating the engineering management BIM system based on artificial intelligence as claimed in claim 4, characterized in that: Based on the total number of invading IP addresses counted by the previous data in the data composition, the acquired invading IP addresses are sorted in a forward-to-backward order, and a Monte Carlo tree search update strategy is used to analyze the change pattern of the IP address text data from front to back. A text data change trend prediction model is generated based on the change pattern, and the IP address text data change in the future time period is predicted. When the text data characteristics of the IP address accessing the data firewall in the future time period are consistent with the predicted IP address text data change, a firewall warning signal is issued, and the access path of the data firewall is closed.

6. A terminal comprising a processor, an input interface, an output interface and a memory, wherein: The memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 5.

7. A computer-readable storage medium storing a computer program, wherein the computer program comprises program instructions, and when the program instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 5.

8. A system for evaluating the engineering management BIM system based on artificial intelligence, applied to the method according to any one of claims 1 to 5, characterized in that: include: A security construction module is used to construct a data firewall, and divide the data firewall into a building material information data firewall, a building design information data firewall and a building construction information data firewall; A feature collection module is used to collect data features of the data firewall and perform data backup, and at the same time obtain task information corresponding to each data feature and decompose the task information, including detailed building status planning and detailed building status progress; An LSTM network fusion analysis module, used to divide the data composition of the data firewall based on the LSTM network, obtain information features of different data compositions encountering intrusion, and generate a cloud database. The LSTM network fusion analysis module includes a division module, a calculation module, and an analysis module. The information features include the IP address of the intruder. The division module is used to divide the data composition of the data firewall into early data, mid-term data and late data; The calculation module responds to the division module to divide the data components to obtain the division data, and the calculation module is used to obtain the intruder IP address and different data components of the intrusion corresponding to the first intrusion, and calculate the corresponding intrusion residence time in the different data components of the intrusion; The analysis module is used to analyze the proportion of the text data volume of different intrusion IP addresses to the early data, mid-term data and / or late data in different data compositions. When the proportion of the text data of different IP addresses accessing the early data, mid-term data and / or late data in the future period is consistent with the proportion of the data at the time of intrusion access, it is determined that the data firewall is attacked by intrusion and a firewall warning signal is issued. Otherwise, no determination is made. The prediction and discrimination module is used to sort the acquired invading IP addresses in a forward-to-backward order based on the total number of invading IP addresses counted by the previous data in the data composition, and at the same time use a Monte Carlo tree search update strategy to analyze the change pattern of the IP address text data from front to back, and generate a text data change trend prediction model based on the change pattern.

Images