An Artificial Intelligence-Based Engineering Management Method and System

Abstract

This invention provides an artificial intelligence-based engineering management method and system. The method includes: acquiring worker attendance data; preprocessing the attendance data to obtain a worker feature matrix; inputting the worker feature matrix into an engineering progress recognition model, which is constructed based on an artificial intelligence algorithm; and determining the engineering progress based on the output of the engineering progress recognition model. This invention eliminates the need for on-site visits by engineering management personnel to determine engineering progress, significantly improving the efficiency of engineering progress management.

Description

Technical Field

[0001] This invention relates to the fields of engineering management and artificial intelligence technology, and more specifically, to an engineering management method, system, electronic device, and computer storage medium based on artificial intelligence. Background Technology

[0002] Schedule management is a crucial aspect of project management. Timely and accurate monitoring of project progress enables project managers to make decisions that facilitate the smooth progress of the project. However, in practice, managers typically determine project progress through project schedules and communication with specific construction personnel. However, project progress involves multiple factors and is subject to gradual changes. The aforementioned methods are insufficient for accurately determining project progress and are also difficult to be timely, thus failing to meet actual project management needs. Summary of the Invention

[0003] In order to at least solve the technical problems existing in the background art, the present invention provides an engineering management method, system, electronic device and computer storage medium based on artificial intelligence.

[0004] The first aspect of the present invention provides an artificial intelligence-based engineering management method, comprising the following steps:

[0005] Obtain worker attendance data and preprocess the attendance data to obtain a worker feature matrix;

[0006] The worker feature matrix is ​​input into the project progress recognition model, which is constructed based on an artificial intelligence algorithm.

[0007] The project progress is determined based on the output of the project progress identification model.

[0008] Further, the preprocessing of the attendance data to obtain the worker feature matrix includes:

[0009] The check-in data is sorted according to the check-in time, and the sorted check-in data is discretized according to the first time interval to obtain the first check-in data set.

[0010] A stability analysis is performed on each sub-data set in the first check-in data set. When the stability analysis result of the sub-data set meets the first preset condition, the sub-data set is discretized according to the second time interval.

[0011] Obtain the second set of attendance data, and obtain the worker feature matrix based on the second set of attendance data;

[0012] Wherein, the first time interval is greater than the second time interval.

[0013] Furthermore, the method also includes a pre-training step for the project progress recognition model:

[0014] Obtain workers' historical attendance data, and discretize the historical attendance data based on the manually decomposed and labeled project progress data to obtain a third attendance data set;

[0015] The third check-in data set is reorganized to obtain a training set; wherein the training set includes several data pairs, each data pair includes progress core feature data and progress connection feature data, and the progress core feature data and progress connection feature data in each data pair are temporally adjacent; and each data pair is associated with the project progress data.

[0016] The data pairs in the training set are input into the project progress recognition model to train it until the training monitoring indicators are met.

[0017] Further, the step of inputting each data pair from the training set into the project progress recognition model to train it until the training monitoring indicators are met includes:

[0018] The data pairs in the training set are input into the project progress recognition model, which outputs project progress recognition data. The equivalent deviation value between the project progress recognition data and the manually decomposed and labeled project progress data is calculated.

[0019] d i =α[∑(x ij -z ij ) 2 ]+β[∑(y ij -z ij ) 2 ]

[0020] In the formula, d i x is the equivalent deviation value between the project progress identification data output by the i-th data pair after inputting it into the project progress identification model and the corresponding project progress data; ij and y ij z is the j-th data value of a single sub-data in the i-th data pair; ij The j-th data value in the project progress data corresponding to the project progress identification data; α and β are weighting coefficients;

[0021] If d iIf the number / proportion of the data pairs input to the project progress identification model is less than or equal to the first threshold and meets the second predetermined condition, then cumulative calculation is performed. If the cumulative calculation meets the third predetermined condition, it is determined that the training monitoring index is met and training is stopped.

[0022] Furthermore, the weighting coefficients α and β are determined in the following manner:

[0023] If the data pair is [schedule core feature data, schedule connection feature data], then set α < β, and α + β = 1;

[0024] If the data pair is [schedule connection feature data, schedule core feature data], then set α>β, and α+β=1;

[0025] If the data pair is [Schedule Core Feature Data, Schedule Core Feature Data], then set α = β, and α + β = 1;

[0026] If the data pair is [schedule connection feature data, schedule connection feature data], then set α = β, and α + β > 1.

[0027] Further, determining the project progress based on the output of the project progress identification model includes:

[0028] Based on the output results, the project progress attributes are determined, and the project progress attributes are compared with the preset project progress data to determine whether there is any project reversal.

[0029] If not, the project progress is determined based on the project progress attribute.

[0030] Furthermore, when it is determined that there is reverse engineering, the data of the engineering materials entering the site is obtained;

[0031] Based on the project progress attributes, the target project materials are determined, and the latest record time in the project material arrival record data that the target project materials meet the fourth preset condition is determined;

[0032] Calculate the time interval between the recorded time and the current time. If the time interval is less than or equal to a second threshold, then determine that the project progress is the latest previous project progress; otherwise, determine the project progress based on the project progress attribute.

[0033] A second aspect of the present invention provides an artificial intelligence-based engineering management system, including an acquisition module, a processing module, and a storage module; the processing module is connected to the acquisition module and the storage module.

[0034] The storage module is used to store executable computer program code;

[0035] The acquisition module is used to acquire workers' clock-in data and transmit it to the processing module;

[0036] The processing module is configured to execute the method described in the preceding one by invoking the executable computer program code in the storage module.

[0037] A third aspect of the present invention provides an electronic device comprising: a memory storing executable program code; a processor coupled to the memory; the processor invoking the executable program code stored in the memory to perform the method as described in any of the preceding claims.

[0038] A fourth aspect of the present invention provides a computer storage medium storing a computer program that, when executed by a processor, performs the method described in any of the preceding claims.

[0039] The present invention involves acquiring worker attendance data, preprocessing the data to obtain a worker feature matrix, inputting the feature matrix into a project progress recognition model (built based on an artificial intelligence algorithm), and determining the project progress based on the output of the model. This invention indirectly analyzes the current construction progress based on worker attendance data. Specifically, the attendance data is input into a project progress recognition model built using an artificial intelligence algorithm, which outputs corresponding recognition results, thereby accurately determining the current project progress. Clearly, the present invention eliminates the need for on-site visits by project management personnel to determine project progress, significantly improving the efficiency of project progress management. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating an artificial intelligence-based engineering management method disclosed in an embodiment of the present invention;

[0042] Figure 2 This is a schematic diagram of the structure of an artificial intelligence-based engineering management system disclosed in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0045] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0046] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0047] It should be understood that although the terms first, second, third, etc., may be used to describe ... in the embodiments of this application, these ... should not be limited to these terms. These terms are only used to distinguish .... For example, without departing from the scope of the embodiments of this application, first ... can also be referred to as second ..., and similarly, second ... can also be referred to as first ....

[0048] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0049] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0050] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0051] Example 1

[0052] Please see Figure 1 , Figure 1 This is a flowchart illustrating an artificial intelligence-based engineering management method disclosed in an embodiment of the present invention. Figure 1 As shown in the figure, an artificial intelligence-based engineering management method according to an embodiment of the present invention includes the following steps:

[0053] Obtain worker attendance data and preprocess the attendance data to obtain a worker feature matrix;

[0054] The worker feature matrix is ​​input into the project progress recognition model, which is constructed based on an artificial intelligence algorithm.

[0055] The project progress is determined based on the output of the project progress identification model.

[0056] In this embodiment of the invention, referring to the background description, in the prior art, engineering managers typically determine project progress through traditional methods such as comparing project schedules and communicating with specific construction personnel. This traditional method clearly cannot meet the timeliness, efficiency, and accuracy requirements of modern construction management. To address this, the present invention indirectly analyzes the current construction progress based on worker attendance data. Specifically, the attendance data is input into a project progress recognition model built using artificial intelligence algorithms. The project progress recognition model can output corresponding recognition results, thereby accurately determining the current project progress. Obviously, the solution of the present invention eliminates the need for engineering managers to conduct on-site visits to determine project progress, greatly improving the efficiency of project progress management.

[0057] The attendance data involved in this invention generally refers to the card-swiping attendance data of workers when entering the construction area. This card-swiping attendance can be achieved using technologies such as process communication (e.g., RFID, NFC), positioning technologies (e.g., comparing positioning data from GPS / BeiDou / Galileo / GLONASS systems with a pre-set electronic fence for the construction area), and fingerprint / iris / facial recognition technologies, etc. Specific details will not be elaborated further. Therefore, the management server configured with the construction project can obtain this data, and then analyze and identify the current project progress using a project progress recognition model, outputting it to project management personnel to assist in decision-making and implementation in project scheduling, supervision, etc.

[0058] Furthermore, the artificial intelligence algorithm involved in this invention can be any algorithm selected from neural network algorithms, deep learning algorithms, decision tree algorithms, or clustering algorithms. Since neural network algorithms, deep learning algorithms, decision tree algorithms, or clustering algorithms are well-known to those skilled in the art, they will not be described in detail here.

[0059] Further, the preprocessing of the attendance data to obtain the worker feature matrix includes:

[0060] The check-in data is sorted according to the check-in time, and the sorted check-in data is discretized according to the first time interval to obtain the first check-in data set.

[0061] A stability analysis is performed on each sub-data set in the first check-in data set. When the stability analysis result of the sub-data set meets the first preset condition, the sub-data set is discretized according to the second time interval.

[0062] Obtain the second set of attendance data, and obtain the worker feature matrix based on the second set of attendance data;

[0063] Wherein, the first time interval is greater than the second time interval.

[0064] In this embodiment of the invention, worker attendance data is associated with attendance time. Based on this, the attendance data can be sorted by time and then segmented to achieve discretization. The first time interval used for discretization can be days, months, weeks, etc., which can be freely determined by project managers according to project attributes, and will not be elaborated further here. Simultaneously, this invention also provides targeted processing for the transition areas between project progress stages. Specifically, when a sub-data set is identified as a transition area through stability analysis, it can be further discretized in a more refined manner, thereby improving the accuracy of project progress identification. For example, the main participating trades in Project Progress 1 are earthmoving workers, and the main participating trades in Project Progress 2 are concrete pouring workers. During a certain period, earthmoving and concrete pouring are carried out simultaneously. Therefore, in the transition area between Project Progress 1 and Project Progress 2, earthmoving workers and concrete pouring workers will coexist. At this time, the corresponding sub-data set exhibits reduced stability, thus identifying it as a transition area, which can then be further subdivided.

[0065] Furthermore, the method also includes a pre-training step for the project progress recognition model:

[0066] Obtain workers' historical attendance data, and discretize the historical attendance data based on the manually decomposed and labeled project progress data to obtain a third attendance data set;

[0067] The third check-in data set is reorganized to obtain a training set; wherein the training set includes several data pairs, each data pair includes progress core feature data and progress connection feature data, and the progress core feature data and progress connection feature data in each data pair are temporally adjacent; and each data pair is associated with the project progress data.

[0068] The data pairs in the training set are input into the project progress recognition model to train it until the training monitoring indicators are met.

[0069] In this embodiment of the invention, the project progress recognition model needs to be pre-trained. The invention uses historical worker attendance data to construct a training set. Specifically, project progress data is first obtained through manual annotation. Based on this, the historical worker attendance data can be discretized to obtain a third attendance data set. Simultaneously, the characteristics of adjacent data in the third attendance data set are identified to extract core progress feature data and progress connection feature data. These are then paired into data sets, where each data pair may contain only core progress feature data or progress connection feature data, or both. Finally, each data pair is associated with the project progress data to obtain a complete training set, which is then progressively input into the project progress recognition model to complete the training.

[0070] It should be noted that the historical check-in data used for component training sets in this invention can be obtained from other projects with the same or similar attributes as the current project, thereby ensuring the availability of training results.

[0071] Further, the step of inputting each data pair from the training set into the project progress recognition model to train it until the training monitoring indicators are met includes:

[0072] The data pairs in the training set are input into the project progress recognition model, which outputs project progress recognition data. The equivalent deviation value between the project progress recognition data and the manually decomposed and labeled project progress data is calculated.

[0073] d i =α[∑(x ij -z ij ) 2 ]+β[∑(y ij -z ij ) 2 ]

[0074] In the formula, d ix is the equivalent deviation value between the project progress identification data output by the i-th data pair after inputting it into the project progress identification model and the corresponding project progress data; ij and y ij z is the j-th data value of a single sub-data in the i-th data pair; ij The j-th data value in the project progress data corresponding to the project progress identification data; α and β are weighting coefficients;

[0075] If d i If the number / proportion of the data pairs input to the project progress identification model is less than or equal to the first threshold and meets the second predetermined condition, then cumulative calculation is performed. If the cumulative calculation meets the third predetermined condition, it is determined that the training monitoring index is met and training is stopped.

[0076] In this embodiment of the invention, the project progress recognition model is trained in the form of data pairs. Compared with the traditional training method that uses a single data set, the training method of this invention also considers the correlation between adjacent data, which can better reflect the gradual change characteristics of project progress, and makes the trained project progress recognition model have a more accurate recognition capability.

[0077] It should be noted that the first threshold and the second predetermined condition can be determined based on experimental measurements or empirical values, and the present invention does not limit this. Furthermore, the third predetermined condition can also be determined based on stability analysis; for example, the cumulative count reaches a minimum limit and the skip rate (i.e., the case where cumulative count is not performed due to not meeting the aforementioned conditions) is lower than a predetermined value.

[0078] Furthermore, the weighting coefficients α and β are determined in the following manner:

[0079] If the data pair is [schedule core feature data, schedule connection feature data], then set α < β, and α + β = 1;

[0080] If the data pair is [schedule connection feature data, schedule core feature data], then set α>β, and α+β=1;

[0081] If the data pair is [Schedule Core Feature Data, Schedule Core Feature Data], then set α = β, and α + β = 1;

[0082] If the data pair is [schedule connection feature data, schedule connection feature data], then set α = β, and α + β > 1.

[0083] In this embodiment of the invention, the weight coefficients α and β are adjusted according to the different attributes of the sub-data included in the data pair. Specifically, for the first and second cases, the weight of the progress connection feature data is set higher to increase the deviation corresponding to the progress connection feature data, thereby improving the training rigor of the progress connection feature data. For the third case, since all are core progress feature data, the sub-data in the data pair are not significantly different and all reflect the most core features of the project progress, so no specific adjustment of their deviation values ​​is needed. For the fourth case, the data pair is entirely within the progress connection area, so the sum of the weight coefficients α and β is increased to increase the deviation corresponding to the progress connection feature data, further improving the training rigor of the progress connection feature data. Through the above-described case-specific adjustments to the weight coefficients α and β, the project progress recognition model can accurately identify the project progress corresponding to progress connection areas without obvious distinguishing features.

[0084] Further, determining the project progress based on the output of the project progress identification model includes:

[0085] Based on the output results, the project progress attributes are determined, and the project progress attributes are compared with the preset project progress data to determine whether there is any project reversal.

[0086] If not, the project progress is determined based on the project progress attribute.

[0087] In this embodiment of the invention, under normal circumstances, the progress of a project will not be reversed. However, certain abnormal situations, such as reworking substandard work, can lead to a reversal. Therefore, after the project progress identification model outputs its results, the invention first determines whether a project reversal exists. If not, the output result is directly accepted, and the project progress is determined accordingly.

[0088] Furthermore, when it is determined that there is reverse engineering, the data of the engineering materials entering the site is obtained;

[0089] Based on the project progress attributes, the target project materials are determined, and the latest record time in the project material arrival record data that the target project materials meet the fourth preset condition is determined;

[0090] Calculate the time interval between the recorded time and the current time. If the time interval is less than or equal to a second threshold, then determine that the project progress is the latest previous project progress; otherwise, determine the project progress based on the project progress attribute.

[0091] In this embodiment of the invention, when a reverse engineering situation is determined, it is further determined whether it is a rework situation or an inherent design of the project. For example, in a tunnel construction project involving bifurcated tunnels, the construction procedures for the main tunnel A and the bifurcated tunnel B are the same, and the construction is sequential, but the check-in data is completed at the same entrance. In this case, a reverse engineering situation will occur. In view of this, the present invention queries the arrival records of the target engineering materials required for the project progress attribute corresponding to the output result. If the arrival record of the target engineering material is very recent, it indicates that the pre-preparation of the target engineering material is low and the temporary nature is high, which can be judged as a rework situation, not a true reverse engineering situation. In this case, the project progress does not need to be updated, and the most recently determined project progress is still used. Conversely, it indicates that the pre-preparation of the target engineering material is high and the temporary nature is low, which can be judged as a normal cyclical construction arrangement. The project progress is directly determined and updated based on the output result of the project progress identification model.

[0092] Example 2

[0093] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an artificial intelligence-based engineering management system disclosed in an embodiment of the present invention. Figure 2 As shown, an artificial intelligence-based engineering management system according to an embodiment of the present invention includes an acquisition module (101), a processing module (102), and a storage module (103); the processing module (102) is connected to the acquisition module (101) and the storage module (103);

[0094] The storage module (103) is used to store executable computer program code;

[0095] The acquisition module (101) is used to acquire the workers' clock-in data and transmit it to the processing module (102);

[0096] The processing module (102) is configured to execute the method described in Embodiment 1 by calling the executable computer program code in the storage module (103).

[0097] The specific functions of the artificial intelligence-based engineering management system in this embodiment refer to those in Embodiment 1 above. Since the system in this embodiment adopts all the technical solutions of the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be described in detail here.

[0098] Example 3

[0099] Please see Figure 3 , Figure 3This invention discloses an electronic device comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method described in Embodiment 1.

[0100] Example 4

[0101] This invention also discloses a computer storage medium storing a computer program, which is executed by a processor as described in Embodiment 1.

[0102] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0103] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, system, or device.

[0104] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0105] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, all of which fall within the scope of protection of the present invention.

Claims

1. An engineering management method based on artificial intelligence, characterized in that, Includes the following steps: Obtain worker attendance data and preprocess the attendance data to obtain a worker feature matrix; the attendance data refers to the attendance data of workers swiping their cards at the entrance when entering the construction area. The worker feature matrix is ​​input into the project progress recognition model, which is constructed based on an artificial intelligence algorithm. The project progress is determined based on the output of the project progress identification model. The preprocessing of the attendance data to obtain the worker feature matrix includes: The check-in data is sorted according to the check-in time, and the sorted check-in data is discretized according to the first time interval to obtain the first check-in data set. A stability analysis is performed on each sub-data set in the first check-in data set. When the stability analysis result of the sub-data set meets the first preset condition, the sub-data set is discretized according to the second time interval. Obtain the second set of attendance data, and obtain the worker feature matrix based on the second set of attendance data; Wherein, the first time interval is greater than the second time interval; The method further includes a pre-training step for the project progress identification model: Obtain workers' historical attendance data, and discretize the historical attendance data based on the manually decomposed and labeled project progress data to obtain a third attendance data set; The third check-in data set is reorganized to obtain a training set; wherein the training set includes several data pairs, each data pair includes progress core feature data and progress connection feature data, and the progress core feature data and progress connection feature data in each data pair are temporally adjacent; and each data pair is associated with the project progress data. Each of the data pairs in the training set is input into the project progress recognition model to train it until the training monitoring indicators are met. Determining the project progress based on the output of the project progress identification model includes: Based on the output results, the project progress attributes are determined, and the project progress attributes are compared with the preset project progress data to determine whether there is any project reversal. If not, then the project progress is determined based on the project progress attribute; When it is determined that there is reverse engineering, obtain the data of the engineering material entry records; Based on the project progress attributes, the target project materials are determined, and the latest record time in the project material arrival record data that the target project materials meet the fourth preset condition is determined; Calculate the time interval between the recorded time and the current time. If the time interval is less than or equal to a second threshold, then determine that the project progress is the latest previous project progress; otherwise, determine the project progress based on the project progress attribute.

2. The engineering management method based on artificial intelligence according to claim 1, characterized in that: The step of inputting each data pair from the training set into the project progress recognition model to train it until the training monitoring indicators are met includes: The data pairs in the training set are input into the project progress recognition model, which outputs project progress recognition data. The equivalent deviation between the project progress recognition data and the manually decomposed and labeled project progress data is calculated. d i <α[∑(x ij -z ij ) 2 ]+β[∑(y ij -z ij ) 2 ] In the formula, d i x is the equivalent deviation value between the project progress identification data output by the i-th data pair after inputting it into the project progress identification model and the corresponding project progress data; ij and y ij z is the j-th data value of a single sub-data in the i-th data pair; ij The j-th data value in the project progress data that corresponds to the project progress identification data; α and β are weighting coefficients; If d i If the number / proportion of the data pairs input to the project progress identification model is less than or equal to the first threshold and meets the second predetermined condition, then cumulative calculation is performed. If the cumulative calculation meets the third predetermined condition, it is determined that the training monitoring index is met and training is stopped.

3. The engineering management method based on artificial intelligence according to claim 2, characterized in that: The weighting coefficients α and β are determined as follows: If the data pair is [schedule core feature data, schedule connection feature data], then set α < β, and α + β = 1; If the data pair is [schedule connection feature data, schedule core feature data], then set α>β, and α+β=1; If the data pair is [Schedule Core Feature Data, Schedule Core Feature Data], then set α = β, and α + β = 1; If the data pair is [schedule connection feature data, schedule connection feature data], then set α = β, and α + β > 1.

4. An artificial intelligence-based engineering management system, comprising an acquisition module, a processing module, and a storage module; the processing module is connected to the acquisition module and the storage module; the storage module is used to store executable computer program code; the acquisition module is used to acquire worker attendance data and transmit it to the processing module; characterized in that: The processing module is configured to execute the method as described in any one of claims 1-3 by calling the executable computer program code in the storage module.

5. An electronic device, comprising: Memory containing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to perform the method as described in any one of claims 1-3.

6. A computer storage medium storing a computer program, characterized in that: The computer program is executed by the processor to perform the method as described in any one of claims 1-3.

Images