CN115775064A

CN115775064A - Engineering decision calculation result evaluation method and cloud platform

Info

Publication number: CN115775064A
Application number: CN202211375944.8A
Authority: CN
Inventors: 代亮亮; 卢小玉
Original assignee: Guizhou Weiyu Technology Co ltd
Current assignee: Guizhou Weiyu Technology Co ltd
Priority date: 2022-11-04
Filing date: 2022-11-04
Publication date: 2023-03-10

Abstract

According to the engineering decision-making result evaluation method and the cloud platform provided by the embodiment of the application, when the engineering decision-making log to be evaluated is obtained, a decision-making behavior expression array is extracted through a pre-deployed engineering decision-making analysis model, and then the engineering decision-making behavior compliance evaluation information of the engineering decision-making log to be evaluated is determined according to the obtained decision-making behavior compliance expression array and the focusing degree distribution factor corresponding to each engineering decision-making analysis point. Influence factors of decision-making behavior compliance expression arrays of different engineering decision-making analysis points are analyzed, and the decision-making behavior compliance expression array adjusted by the focusing degree distribution factor can reflect the compliance of engineering decision-making behavior compliance data more accurately, so that decision-making results which are identified as compliance but are actually non-compliant in decision-making behaviors can be greatly prevented from being considered as compliance results, and the engineering decision-making compliance behaviors are restrained.

Description

Engineering decision calculation result evaluation method and cloud platform

Technical Field

The application relates to the fields of engineering settlement, data processing and artificial intelligence, in particular to an engineering settlement result evaluation method and a cloud platform.

Background

The project settlement is an essential part for the acceptance check of the project completion, comprises all the actual expenses from the project completion to the whole process of the project completion, and comprises construction project expenses, installation project expenses, equipment and appliance purchase expenses, other expenses of the project construction, preparation expenses, tax expenditure expenses for adjusting the investment direction and the like. The decision result is related to the follow-up audit examination, so the compliance of the compilation is important. With the rise of the online office in the traditional industry, a large number of enterprises or units are helped to manage standardized operation, the project resolution is embedded into the online office, the flow node data compiled by the project resolution is collected, an evaluator can be helped to evaluate and analyze the compliance of the project resolution, and the non-compliance resolution behavior that only the result does not respect the process is stopped, so that the technical problem to be overcome is how to automatically and accurately analyze whether the data of the project resolution behavior is compliant or not. It is easy to understand that the above background technical contents are only for better understanding of the technical contents of the present application and can not be used as a basis for judging the novelty of the present application.

Disclosure of Invention

The invention aims to provide an engineering decision result evaluation method and a cloud platform to solve the technical problems.

In order to achieve the above purpose, the embodiments of the present application are implemented as follows:

in a first aspect, an embodiment of the present disclosure provides a method for evaluating an engineering decision result, where the method includes:

when the uploading of the project resolution result is completed, acquiring a project resolution compiling log to be evaluated, wherein the project resolution compiling log is contained in the project resolution result; and performing resolution calculation compiling behavior expression array extraction on the project resolution calculation compiling log to be evaluated through a pre-deployed project resolution analysis model to obtain a resolution calculation behavior compliance expression array of not less than two project resolution analysis points and a focusing degree distribution factor corresponding to each project resolution analysis point, and obtaining project resolution calculation compiling behavior compliance evaluation information of the project resolution calculation compiling log to be evaluated according to the resolution calculation behavior compliance expression array of not less than two project resolution analysis points and the focusing degree distribution factor corresponding to each project resolution analysis point.

According to the engineering settlement result evaluation method provided by the embodiment of the application, when the engineering settlement evaluation working log to be evaluated is obtained, settlement evaluation behavior expression arrays are extracted from the engineering settlement evaluation working log to be evaluated through an engineering settlement analysis model deployed in advance, and then the engineering settlement evaluation working behavior compliance evaluation information of the engineering settlement evaluation working log to be evaluated is determined according to the obtained settlement behavior compliance expression arrays of not less than two engineering settlement analysis points and the focus degree distribution factor corresponding to each engineering settlement analysis point. Influence factors of decision behavior compliance expression arrays of different engineering decision analysis points are analyzed through focus degree distribution factors, for example, a decision behavior compliance expression array with a low influence factor is distributed, a focus degree distribution factor with a small value is distributed, it can be understood that a focus degree distribution factor with a large value is distributed for a decision behavior compliance expression array with a high influence factor, and the decision behavior compliance expression array adjusted through the focus degree distribution factor can reflect the compliance of engineering decision behavior compliance data more accurately, so that the decision calculation compilation result which is identified as compliance but the decision calculation compilation behavior is actually non-compliance can be greatly prevented from being regarded as the compliance result, and the constraint engineering decision calculation compliance behavior is facilitated.

Optionally, the obtaining engineering resolution calculation compilation behavior compliance evaluation information of the engineering resolution compilation log to be evaluated according to the resolution behavior compliance expression arrays of not less than two engineering resolution analysis points and the focus degree distribution factor corresponding to each engineering resolution analysis point includes: performing expression array extrusion processing according to the decision behavior compliance expression array of not less than two engineering decision analysis points to obtain a decision behavior compliance expression array after the expression array of the engineering decision analysis points less than the engineering decision analysis points before extrusion is extruded; performing expression array excitation processing according to the decision-making behavior compliance expression array after the expression array is extruded to obtain a decision-making behavior compliance expression array after the excitation of the expression array, wherein the engineering decision-making analysis points are equal to the engineering decision-making analysis points before the extrusion; and determining engineering decision making behavior compliance evaluation information of the engineering decision making log to be evaluated according to the decision making behavior compliance expression array excited by the expression array and the focusing degree distribution factor corresponding to each engineering decision making analysis point.

Therefore, the decision behavior compliance expression arrays which are repeatedly invalid in at least two engineering decision analysis points are extruded according to the expression array, and then weight distribution summation is carried out according to the expression array excitation processing, so that the obtained engineering decision behavior compliance evaluation information is more accurate.

Optionally, the engineering resolution analysis model comprises an analysis network for performing engineering resolution compilation behavior compliance assessment; the step of obtaining the engineering settlement computing behavior compliance assessment information of the engineering settlement computing working log to be assessed according to the settlement computing behavior compliance expression arrays of not less than two engineering settlement analysis points and the focus degree distribution factor corresponding to each engineering settlement analysis point comprises the following steps: performing distribution operation according to the decision behavior compliance expression array of not less than two engineering decision analysis points and the focusing degree distribution factor corresponding to each engineering decision analysis point, adding the results after the distribution operation, and determining the added decision behavior compliance expression array; and loading the added decision behavior compliance expression array into the analysis network of the engineering decision analysis model to obtain the engineering decision behavior compliance evaluation information output by the analysis network.

Optionally, the optimization process of the engineering decision analysis model includes: acquiring a project resolution working log template and working behavior compliance indication information of the project resolution working log template, wherein the working behavior compliance indication information represents whether the project resolution working behavior data in the corresponding project resolution working log template is the project resolution working behavior compliance data covering counterfeit behaviors or not; and determining the engineering decision making log template as loading data of a to-be-optimized engineering decision making analysis model, determining the compiling behavior compliance indication information of the engineering decision making log template as constraint information of output information of the to-be-optimized engineering decision making analysis model, and performing multiple model parameter optimization on the to-be-optimized engineering decision making analysis model to obtain a pre-deployed engineering decision making analysis model. The engineering decision analysis model comprises an expression array acquisition network, a focus degree distribution network and an analysis network; the step of determining the engineering resolution working log template as the loading data of the engineering resolution analysis model to be optimized, determining the working behavior compliance indication information of the engineering resolution working log template as the constraint information of the output information of the engineering resolution analysis model to be optimized, and performing multiple model parameter optimization on the engineering resolution analysis model to be optimized comprises the following steps: loading the engineering resolution working log template into the expression array acquisition network of the engineering resolution analysis model to obtain a resolution action total scale board expression array which is output by the expression array acquisition network and is not less than two engineering resolution analysis points, and loading the resolution action total scale board expression array which is output by the expression array acquisition network and is not less than two engineering resolution analysis points into the focus degree distribution network of the engineering resolution analysis model to obtain a focus degree distribution factor which is output by the focus degree distribution network and corresponds to each engineering resolution analysis point; performing distribution operation between the decision behavior sum-scale board expression array of not less than two engineering decision analysis points and the focusing degree distribution factor corresponding to each engineering decision analysis point, adding the results after the distribution operation, and determining the added decision behavior sum-scale board expression array; loading the added decision behavior close-scale board expression array into the analysis network of the engineering decision analysis model, and determining compilation behavior close-scale prediction information obtained by inference of the analysis network; and performing multiple model parameter optimization on the project resolution analysis model to be optimized according to the compilation behavior compliance prediction information and compilation behavior compliance indication information of the project resolution compilation log template.

Based on the method, the optimization of the engineering decision-making analysis model can be completed through the engineering decision-making log template and the compiling behavior compliance indication information aiming at the engineering decision-making log template, and the optimized model has strong capability. The model is optimized through the added decision-making behavior combined scale board expression array, and the added decision-making behavior combined scale board expression array can reflect the engineering decision-making compilation behavior data more accurately, so that the obtained compilation behavior compliance prediction information has a more accurate result, and the accuracy of the obtained model is ensured.

Optionally, the engineering decision analysis model includes a plurality of expression arrays outputting different convolution strengths to obtain a network and an analysis network; the step of determining the project resolution working log template as the loading data of the project resolution analysis model to be optimized, determining the working behavior compliance indication information of the project resolution working log template as the constraint information of the output information of the project resolution analysis model to be optimized, and carrying out multiple model parameter optimization on the project resolution analysis model to be optimized comprises the following steps: loading the project settlement compilation log template into a plurality of expression array acquisition networks included in the project settlement analysis model to obtain a settlement behavior combined scale plate expression array output by each expression array acquisition network; acquiring a selected expression array extraction network with convolution intensity which is screened and output from the plurality of expression arrays and meets preset convolution intensity; loading a decision-making behavior close-size board expression array output by the selected expression array extraction network into the analysis network of the engineering decision-making analysis model to obtain compilation behavior close-size prediction information obtained by inference of the analysis network; and performing multiple model parameter optimization on the project resolution analysis model to be optimized according to the compiling behavior compliance prediction information and the compiling behavior compliance indication information of the project resolution compiling log template.

According to the method and the device, the decision-making behavior sum-scale plate expression arrays output by the network are extracted according to the multiple selected expression arrays with convolution intensity meeting the preset convolution intensity for carrying out model optimization, namely, the decision-making behavior template expression arrays with strong convolution intensity are not only used for expressing the arrays, but also used for carrying out model optimization, so that the analysis accuracy of the engineering decision-making analysis model obtained through optimization is higher.

Optionally, the performing multiple model parameter optimization on the to-be-optimized engineering resolution analysis model according to the compilation behavior compliance prediction information and the compilation behavior compliance indication information of the engineering resolution compilation log template includes: determining an error result of the project resolution analysis model to be optimized according to a similarity measurement result between the compiling behavior compliance prediction information and compiling behavior compliance indication information of the project resolution compiling log template; and carrying out multiple model parameter optimization on the project decision analysis model to be optimized according to the error result.

Optionally, the performing, by the error result, multiple model parameter optimizations on the engineering decision analysis model to be optimized includes: and if the secondary model optimization does not meet the optimization ending requirement, optimizing at least one model parameter of the network, the focusing degree distribution network and the analysis network obtained by the expression array included in the engineering decision analysis model to be optimized through the error result, carrying out the next model optimization process according to the optimized engineering decision analysis model, and stopping the optimization when the engineering decision analysis model meets the optimization ending requirement.

Optionally, the step of obtaining the compilation behavior compliance indication information of the engineering decision calculation compilation log template includes: carrying out counterfeit behavior analysis on the project resolution working log template, and determining a counterfeit behavior type corresponding to the project resolution working behavior data in the project resolution working log template; and determining compilation behavior compliance indication information for the engineering resolution compilation log template according to the type of the counterfeit behavior corresponding to the engineering resolution compilation behavior data in the engineering resolution compilation log template.

In the embodiment of the application, the annotation of the relevant engineering resolution calculation compilation behavior compliance data is completed based on the type of the counterfeit behavior, and for the engineering resolution calculation compilation behavior data of which the type of the counterfeit behavior is determined as the counterfeit, even if the engineering resolution calculation compilation log template is a compliance decision result, the engineering resolution calculation log template is annotated as a non-compliance result, so that the accuracy of the identification of the compliance behavior is ensured.

Optionally, the analyzing the obtained engineering resolution calculation compilation log template for the counterfeit behavior to determine the counterfeit behavior type corresponding to the engineering resolution calculation compilation behavior data in the engineering resolution calculation compilation log template includes: performing fake behavior analysis on the obtained engineering decision calculation compiling log template according to a preset fake behavior expression array extraction model, and determining a compiling fake behavior expression array of each layer extracted from the engineering decision calculation compiling log template; and determining the type of the counterfeit behavior corresponding to the project resolution calculation compiling behavior data in the project resolution calculation compiling log template according to the compiling counterfeit behavior expression array of each layer.

Optionally, different engineering decision making behavior data categories covered by the engineering decision making log to be evaluated correspond to decision making behavior compliance expression arrays of different engineering decision making analysis points, and a decision making behavior compliance expression value represented by a decision making behavior compliance expression array is positively associated with a focus degree distribution value represented by a focus degree distribution factor corresponding to the corresponding engineering decision making behavior data category.

Optionally, the decision-making behavior compliance expression arrays of different engineering decision-making analysis points at least comprise compiling counterfeit behavior expression array information and compiling behavior expression array information; and the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the compilation and counterfeiting behavior expression array information is reversely associated with the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the compilation and counterfeiting behavior expression array information.

In a second aspect, an embodiment of the present application provides a project management cloud platform, which includes a memory and a processor, where the memory stores a computer program, and when the processor runs the computer program, the method provided in the first aspect of the embodiment of the present application is implemented.

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples which follow.

Drawings

To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

The methods, systems, and/or programs of the figures will be further described in accordance with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which reference numerals represent similar mechanisms throughout the various views of the drawings.

Fig. 1 is a schematic diagram of an application scenario shown in accordance with some embodiments of the present application.

FIG. 2 is a schematic diagram illustrating hardware and software components in a project management cloud platform according to some embodiments of the present application.

FIG. 3 is a flow chart of a method of project resolution result evaluation according to some embodiments of the present application.

Fig. 4 is a schematic structural diagram of an engineering decision result evaluation apparatus according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.

In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, systems, compositions, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

These and other features, functions, methods of execution, and combination of functions and elements of related elements in the structure and economies of manufacture disclosed in the present application may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this application. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.

Flowcharts are used herein to illustrate the implementations performed by systems according to embodiments of the present application. It should be expressly understood that the processes performed by the flowcharts may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, at least one other implementation may be added to the flowchart. One or more implementations may be deleted from the flowchart.

Fig. 1 is a schematic view of an application scenario shown in some embodiments of the present application, where a project management cloud platform 100 communicates with a plurality of service interaction devices 200 in communication therewith, and the service interaction devices 200 may be smart devices such as a personal computer, a tablet computer, and a smart phone that can perform cloud office. The engineering resolution personnel complete the online engineering resolution behavior on the service interaction device 200, and perform data interaction with the project management cloud platform 100 based on the service interaction device 200. The project management cloud platform 100 may be a cloud server, for example, an independent physical server, a server cluster or a distributed system composed of a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform. The service interaction device 200 and the project management cloud platform 100 may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

In some embodiments, please refer to fig. 2, which is a schematic diagram of an architecture of a project management cloud platform 100, wherein the project management cloud platform 100 includes an engineering decision result evaluation apparatus 110, a memory 120, a processor 130, and a communication unit 140. The elements of the memory 120, the processor 130, and the communication unit 140 are electrically connected to each other, directly or indirectly, to enable the transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The engineering decision result evaluation device 110 includes at least one software function module which may be stored in the memory 120 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the project management cloud platform 100. The processor 130 is used for executing executable modules stored in the memory 120, such as software functional modules and computer programs included in the engineering decision result evaluation device 110.

The Memory 120 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 120 is used for storing a program, and the processor 130 executes the program after receiving the execution instruction. The communication unit 140 is configured to establish a communication connection between the project management cloud platform 100 and the service interaction device 200 through a network, and is configured to receive and transmit data through the network.

The processor may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP)), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It is to be understood that the configuration shown in FIG. 2 is merely illustrative and that project management cloud platform 100 may include more or fewer components than shown in FIG. 2 or have a different configuration than shown in FIG. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.

Fig. 3 is a flowchart of a method for evaluating engineering decision results according to some embodiments of the present application, where the method is applied to the project management cloud platform 100 in fig. 1, and specifically may include the following steps 100 to 300. On the basis of the following steps 100 to 300, some alternative embodiments will be described, which should be understood as examples and not as technical features essential for implementing the present solution.

Step 100: and when the uploading of the project settlement results is completed, acquiring a project settlement compiling log to be evaluated, wherein the project settlement compiling log is contained in the project settlement results.

Step 200: and performing resolution calculation compiling behavior expression array extraction on the project resolution calculation compiling log to be evaluated through a pre-deployed project resolution analysis model to obtain a resolution calculation behavior compliance expression array of not less than two project resolution analysis points and a focusing degree distribution factor corresponding to each project resolution analysis point.

Step 300: and obtaining engineering decision calculation compiling behavior compliance evaluation information of the engineering decision calculation compiling log to be evaluated according to the decision calculation behavior compliance expression arrays of not less than two engineering decision calculation analysis points and the focusing degree distribution factor corresponding to each engineering decision calculation analysis point.

The engineering settlement result evaluation method provided by the embodiment of the application is applied to an on-line engineering settlement scene, for example, the engineering settlement staff carries out related settlement making through an on-line engineering settlement system, so that a trace can be left on the making process of the engineering settlement staff, the settlement behavior data generated in the engineering settlement staff carrying out the engineering settlement process is generated after the settlement of the engineering settlement file, and an engineering settlement making log is generated and contains all the making behavior data of the engineering settlement staff from the beginning to the end of the engineering settlement, such as material collection uploading, material comparison labeling, cost accounting, settlement material making, report filling and the like. When the engineering settlement personnel upload the engineering settlement results and finish the compiling behaviors on behalf of the engineering settlement personnel, the compiling results and the compiling process can be evaluated and analyzed. In the engineering decision calculation making process, the making personnel may have non-compliant making behaviors, such as missing necessary links in data checking, forging intermediate data, omitting necessary data and the like, so that the final decision calculation data may correspond to the original decision calculation data, but the material itself is non-compliant, which is not beneficial to the audit and feasibility study of the follow-up audit department.

In the embodiment of the application, a decision making behavior expression array (machine vector expression of making behavior) is extracted from a project decision making analysis model which is deployed in advance, so that a decision making behavior compliance expression array of not less than two project decision making analysis points and a focusing degree distribution factor corresponding to each project decision making analysis point are obtained, wherein in order to obtain accurate project decision making behavior compliance data, when the decision making behavior compliance expression array of not less than two project decision making analysis points is extracted through the project decision making analysis model, a focusing degree distribution factor corresponding to each project decision making analysis point can be determined (for example, an attention eccentricity factor is obtained based on an attention mechanism), the focusing degree distribution factor of the project decision making analysis point can reflect an influence factor (importance degree) of the corresponding decision making behavior compliance expression array, a larger focusing degree distribution factor can be distributed to the decision making behavior compliance expression array with a larger influence factor, for example, false decision making calculation, and a smaller focusing degree distribution factor, for example, a material focusing degree distribution factor can be distributed to the decision making behavior compliance expression array with a smaller influence factor. Therefore, the important data expression array of the engineering decision-making analysis points can be well highlighted, the data expression array of the engineering decision-making analysis points with low importance is limited, the decision-making behavior compliance expression array can better express the decision-making behavior, and the identification of the engineering decision-making behavior compliance data is facilitated. The final settlement behavior compliance expression arrays of at least two project final settlement analysis points can be final settlement behavior compliance expression arrays obtained by corresponding different dimensions, such as cost checking times, cost checking time, material preparation specifications and other analysis points.

In the embodiment of the application, the decision behavior compliance expression array of different engineering decision analysis points can comprise compiling counterfeiting behavior expression array information and compiling behavior expression array information, when the quantity of the compiling behavior expression array information is insufficient, the focusing degree distribution value for compiling the counterfeiting behavior expression array information can be improved, and the focusing degree distribution value for compiling the behavior expression array information is reduced; when the compiled fake behavior expression array information is not obvious, the focusing degree distribution value of the compiled behavior expression array information can be improved, and the focusing degree distribution value of the compiled fake behavior expression array information is reduced; if the information indicating capabilities of compiling the fake behavior expression array and compiling the fake behavior expression array are close, the focusing degree distribution values can be equally divided. In addition, different project resolution compilation behavior data categories may be associated with different project resolution analysis points, such as sort data types (e.g., collecting check files), check data types (e.g., drawing check), calculate data types (e.g., project cost calculation update), and write data types (e.g., resolution instruction write).

As an implementation manner, the engineering decision result evaluation method provided in the embodiment of the present application performs expression capability enhancement processing on an expression array before performing the focus degree evaluation, and specifically may be performed based on a dependency relationship between modeling expression arrays, for example, refer to the following steps I to III:

step I: and performing expression array extrusion processing according to the decision behavior compliance expression array of not less than two engineering decision analysis points to obtain a decision behavior compliance expression array after the expression array of the engineering decision analysis points less than the engineering decision analysis points before extrusion is extruded.

Step II: and carrying out expression array excitation processing according to the decision behavior compliance expression array after the expression array is extruded to obtain a decision behavior compliance expression array after the expression array excitation, wherein the engineering decision analysis point number is equal to the engineering decision analysis point number before the extrusion.

Step III: and determining engineering decision making behavior compliance evaluation information of the engineering decision making log to be evaluated according to the decision making behavior compliance expression array excited by the expression array and the focusing degree distribution factor corresponding to each engineering decision making analysis point.

In the embodiment of the application, the SENET network model is adopted to realize the steps, in the process of expressing array extrusion (global information embedding), expression array extrusion processing is carried out along the dimension of the engineering decision-making analysis point, the expression arrays of the cross-space dimension are aggregated to obtain the descriptor of the engineering decision-making analysis point, the global space information is compressed into the descriptor of the engineering decision-making analysis point, and the descriptor of the engineering decision-making analysis point is adopted by the input layer, such as global average implementation. In specific implementation, m · i · 2 · 2 (corresponding to a decision behavior compliance expression array of not less than two engineering decision analysis points) can be transformed into an expression array (corresponding to a decision behavior compliance expression array after the expression array is extruded) of m · j · 2 · 2 by a linear transformation unit (such as a convolution unit), wherein m is equal to the number of engineering decision making logs to be evaluated; i. j is corresponding to the quantity of the engineering decision calculation analysis points before and after the expression array is extruded respectively, and j is less than i, so that the simplified extrusion of the engineering decision calculation analysis points is completed. The expression array excitation transforms the scale of m.j.22222222222220m (corresponding to the decision behavior compliance expression array after the expression array excitation), wherein m is the number of engineering decision making logs to be evaluated; j. and i corresponds to the number of the engineering resolution analysis points before the excitation of the expression array and after the excitation of the expression array, and j is less than i, so that the self-adaptive adjustment (expansion) of the dimensionality of the engineering resolution analysis points is completed. And finally, distributing the focusing degree distribution factors for each expression array, and distributing the obtained i focusing degree distribution values to each engineering decision analysis point respectively to complete the mining of the influence degree of the expression arrays. Before the expression array is extruded, the dimension of the decision behavior of at least two engineering decision analysis points which are loaded can be reduced according to the scale of the expression array by adopting downsampling processing, useless or repeated information is cleaned, calculation cost is relieved, and the model speed is increased.

The above-mentioned acquisition of each expression array is executed through an expression array mining network of the engineering decision analysis model, the expression array mining network is used for extracting the expression array, and a layer at the tail of the expression array mining network can be connected with the analysis network of the engineering decision analysis model to perform engineering decision compilation behavior compliance data analysis. In the embodiment of the application, weight values of the excited decision-making behavior compliance expression array and the focusing degree distribution factor corresponding to each engineering decision-making analysis point are distributed and added, and then the decision-making behavior compliance expression array obtained through addition is loaded into the analysis network of the engineering decision-making analysis model, so that engineering decision-making behavior compliance evaluation information output by the analysis network is obtained. The analysis network is used for analyzing whether the loaded project resolution compilation behavior data in the project resolution compilation log to be evaluated is project resolution compilation behavior compliance data or not to obtain confidence coefficients of two categories, and the category with the high confidence coefficient is taken as project resolution compilation behavior compliance evaluation information.

The following describes an optimization process of the engineering decision analysis model, which includes:

step I: and acquiring an engineering resolution working log template and working behavior compliance indication information of the engineering resolution working log template, wherein the working behavior compliance indication information represents whether the engineering resolution working behavior data in the corresponding engineering resolution working log template is the engineering resolution working behavior compliance data covering the counterfeit behaviors.

Step II: determining the project resolution working log template as the loading data of the project resolution analysis model to be optimized, determining the working behavior compliance indication information of the project resolution working log template as the constraint information of the output information of the project resolution analysis model to be optimized, and carrying out multiple model parameter optimization on the project resolution analysis model to be optimized to obtain the project resolution analysis model deployed in advance.

In this embodiment, the written behavior compliance indication information may be obtained by annotating in advance, and whether the engineering resolution written behavior data in the engineering resolution written log template is the engineering resolution written behavior compliance data may be annotated in advance for the engineering resolution written log template. Whether the decision making behavior has a fake trace or not needs to be considered, and fake information is jointly made to evaluate the engineering decision making behavior compliance data, so that each engineering decision making flow node is singly determined to meet the specified requirements, namely the node is regarded as an expression array of the engineering decision making behavior compliance data, the fake information needs to be considered for evaluation, even if the making result and/or the node meet the requirements, but the decision making process has the fake trace, the node is not regarded as the compliance behavior data, and more accurate annotation information of the engineering decision making behavior compliance data is obtained.

In the embodiment of the application, the counterfeit behavior analysis can be performed on the obtained engineering resolution working log template, and the counterfeit behavior type corresponding to the engineering resolution working behavior data in the engineering resolution working log template is determined, so that the working behavior compliance indication information can be determined according to the counterfeit behavior type.

In the embodiment of the application, the obtained engineering decision calculation compilation log template can be subjected to counterfeit behavior analysis according to a pre-deployed counterfeit behavior expression array extraction model, the compilation counterfeit behavior expression array of each layer extracted from the engineering decision calculation compilation log template is determined, and then the counterfeit behavior type is determined according to the compilation counterfeit behavior expression array of each layer. The compiling counterfeiting behavior expression array of each layer can be a related engineering decision calculation compiling behavior data expression array indicating the counterfeiting behavior in each dimension, such as a cost accounting rule, an accounting node, an accounting data source and the like, different compiling counterfeiting behavior expression arrays can be combined to identify different counterfeiting behavior types, the counterfeiting behavior types include node missing counterfeiting, data source counterfeiting and calculation mode counterfeiting, and when no counterfeiting behavior exists, the counterfeiting behavior type is not counterfeiting. For example, if it is determined that the type of the forgery is a loss forgery, the compilation behavior compliance indication information is annotated as an unconventional result even if the result of the project resolution compilation behavior data is a compliant result that is expected.

In the method for evaluating the engineering decision result provided by the embodiment of the application, the engineering decision analysis model may include an expression array acquisition network for mining expression arrays, a focus degree distribution network for determining significance information, and an analysis network for performing an analysis process. To obtain a more complete data expression array, expression array mining may be performed through a multi-expression array acquisition network. And directly obtaining the expression array obtained by network mining according to the last expression array to evaluate the engineering decision calculation compilation behavior compliance data, or obtaining the expression array extracted by the network by combining a plurality of expression arrays to evaluate the engineering decision calculation compilation behavior compliance data.

As an implementation manner, the following steps may be taken to complete model optimization in the embodiment of the present application:

step I: and loading the engineering resolution calculation making log template into an expression array acquisition network included in the engineering resolution calculation analysis model to obtain a resolution action combined scale board expression array of not less than two engineering resolution analysis points output by the expression array acquisition network, and loading the resolution action combined scale board expression array of not less than two engineering resolution analysis points output by the expression array acquisition network into a focusing degree distribution network included in the engineering resolution analysis model to obtain a focusing degree distribution factor corresponding to each engineering resolution analysis point output by the focusing degree distribution network.

Step II: and performing distribution operation (multiplying the distribution factors of the focusing degrees) between the decision behavior close-size board expression array of not less than two engineering decision analysis points and the focusing degree distribution factor corresponding to each engineering decision analysis point, adding the results after the distribution operation, and determining the added decision behavior close-size expression array.

Step III: and loading the added decision behavior combined scale board expression array into the analysis network of the engineering decision analysis model, and determining compilation behavior compliance prediction information obtained by network inference.

Step IV: and performing multiple model parameter optimization on the project resolution analysis model to be optimized according to the compiling behavior compliance prediction information and the compiling behavior compliance indication information of the project resolution compiling log template.

In the embodiment of the application, the expression array obtaining network can carry out expression array mining on the engineering decision calculation making log template to obtain a decision calculation behavior combined scale board expression array of not less than two engineering decision calculation analysis points, so as to complete the obtaining of the focusing degree distribution factor corresponding to each engineering decision calculation analysis point through the focusing degree distribution network, and when the distribution operation is carried out between the decision calculation behavior combined scale board expression array of not less than two engineering decision calculation analysis points and the focusing degree distribution factor corresponding to each engineering decision calculation analysis point and the distribution operation is carried out, the added decision calculation behavior combined scale board expression array is loaded to the analysis network to carry out multiple model parameter optimization of the engineering decision calculation analysis model.

In the embodiment of the application, different engineering decision making behavior data types covered by the engineering decision making log to be evaluated correspond to decision making behavior compliance expression arrays of different engineering decision making analysis points, and a decision making behavior compliance expression value represented by the decision making behavior compliance expression array is in forward correlation with a focusing degree distribution value represented by a focusing degree distribution factor corresponding to the corresponding engineering decision making behavior data type; the settlement behavior compliance expression arrays of different engineering settlement analysis points at least comprise the information of compiling the fake behavior expression array and the information of compiling the behavior expression array; and establishing a reverse association between the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the fake behavior expression array information and the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the fake behavior expression array information.

In the embodiment of the present application, when the summed decision behavior compliance board expression array is loaded into the analysis network, an error result of the to-be-optimized engineering decision analysis model may be determined according to a similarity measurement result between compilation behavior compliance prediction information output by the analysis network and compilation behavior compliance indication information for the engineering decision log template, and then, the to-be-optimized engineering decision analysis model may be subjected to multiple model parameter optimizations according to the error result. For example, through multiple model optimizations, after a first model optimization, it is determined whether the first model optimization meets an optimization ending requirement (for example, the number of times of the optimization reaches a threshold, the prediction accuracy of the model reaches the threshold, or an error result does not change greatly, if the error result is less than a preset change rate), and when it is determined that the first model optimization does not meet the optimization ending requirement, back propagation is performed according to the error result determined by the first optimization to complete parameter optimization of the engineering decision-making analysis model, the engineering decision-making log template is loaded into the optimized engineering decision-making analysis model, a second optimization is started, the above processes are repeated, and when the engineering decision-making analysis model meets the optimization ending requirement, the optimization is stopped, so as to obtain a previously deployed engineering decision-making analysis model.

When the engineering decision calculation analysis model is optimized, model parameters of at least one of the expression array acquisition network, the focus degree distribution network and the analysis network can be optimized and adjusted, joint optimization of each network module is completed, and accuracy of engineering decision calculation compiling behavior compliance evaluation information is improved.

As another implementation manner, the optimization process of the engineering decision analysis model in the embodiment of the present application may include:

step I: and loading the project resolution calculation log template into a plurality of expression array acquisition networks included in the project resolution calculation analysis model to obtain a resolution calculation behavior combined scale board expression array output by each expression array acquisition network.

Step II: and selecting the expression array extraction network in which the convolution intensity screened and output from the plurality of expression array acquisition networks meets the preset convolution intensity.

Step III: and loading the decision-making behavior close-size board expression array output by the selected expression array extraction network into the analysis network of the engineering decision-making analysis model, and determining compilation behavior close-size prediction information obtained by inference of the analysis network.

In this embodiment, the expression array obtaining network may include a plurality of expression array obtaining networks, the plurality of expression array obtaining networks obtain decision-making behavior close-size plate expression arrays with different convolution strengths (convolution abstraction degrees), and the decision-making behavior close-size plate expression arrays expressed by the decision-making behaviors with different convolution strengths have different hierarchies.

If the expression array with higher convolution strength and higher abstract degree is directly obtained for compliance information evaluation during analysis and evaluation, the shallow expression array is ignored and is not beneficial to accurate evaluation by means of the useful shallow expression array, the shallow expression array is simultaneously connected to the analysis network to carry out inference of engineering decision making behavior compliance data, decision making behavior compliance board expression arrays meeting preset convolution strength are screened to carry out engineering decision making behavior compliance evaluation, and the accuracy of engineering decision making behavior compliance data evaluation is improved.

In summary, based on the engineering decision-making result evaluation method provided in the embodiment of the present application, when the engineering decision-making log to be evaluated is obtained, a decision-making behavior expression array may be extracted from the engineering decision-making log to be evaluated through a previously deployed engineering decision-making analysis model, and then the engineering decision-making behavior compliance evaluation information for the engineering decision-making log to be evaluated is determined according to the obtained decision-making behavior compliance expression array of at least two engineering decision-making analysis points and the focus degree distribution factor corresponding to each engineering decision-making analysis point. Influence factors of decision behavior compliance expression arrays of different engineering decision analysis points are analyzed through focus degree distribution factors, for example, a decision behavior compliance expression array with a low influence factor is distributed, a focus degree distribution factor with a small value is distributed, it can be understood that a focus degree distribution factor with a large value is distributed for a decision behavior compliance expression array with a high influence factor, and the decision behavior compliance expression array adjusted through the focus degree distribution factor can reflect the compliance of engineering decision behavior compliance data more accurately, so that the decision calculation compilation result which is identified as compliance but the decision calculation compilation behavior is actually non-compliance can be greatly prevented from being regarded as the compliance result, and the constraint engineering decision calculation compliance behavior is facilitated.

Referring to fig. 4, a schematic diagram of a functional module architecture of the engineering decision result evaluation device 110 according to an embodiment of the present invention is shown, where the engineering decision result evaluation device 110 is configured to execute an engineering decision result evaluation method, where the engineering decision result evaluation device 110 includes:

and a log obtaining module 111, configured to obtain a project resolution making log to be evaluated included in the project resolution result when the project resolution result is uploaded.

An array extraction module 112, configured to perform resolution calculation making behavior expression array extraction on the project resolution calculation making log to be evaluated through a project resolution analysis model deployed in advance, so as to obtain a resolution calculation behavior compliance expression array of not less than two project resolution analysis points and a focus degree allocation factor corresponding to each project resolution analysis point.

And a compliance evaluation module 113, configured to obtain engineering resolution calculation compilation behavior compliance evaluation information for the engineering resolution compilation log to be evaluated according to the resolution behavior compliance expression array of at least two engineering resolution analysis points and the focus degree allocation factor corresponding to each engineering resolution analysis point.

Wherein, the log obtaining module 111 is configured to perform step 100; the array extraction module 112 is operable to perform step 200; the compliance assessment module 113 may be used to perform step 300.

Since the engineering decision result evaluation method provided in the embodiment of the present invention has been described in detail in the above embodiment, and the principle of the engineering decision result evaluation device 110 is the same as that of the method, the implementation principle of each module of the engineering decision result evaluation device 110 is not described herein again.

It should be understood that, for technical terms that are not noun-interpreted in the above, a person skilled in the art can deduce to determine the meaning of the reference unambiguously from the above disclosure, for example, for some terms such as threshold, coefficient, parameter, etc., a person skilled in the art can deduce and determine from the logical relationship before and after, and the value range of these values can be selected according to the actual situation, for example, 0.1 to 1, for example, 1 to 10, and for example, 50 to 100, which are not limited herein.

The skilled person can determine some preset, reference, predetermined, set and preference labels of technical features/technical terms, such as threshold, threshold interval, threshold range, etc., without any doubt according to the above disclosure. For some technical characteristic terms which are not explained, the skilled person is fully capable of reasonably and unambiguously deriving the technical solution based on the logical relations between the preceding and following terms, so as to clearly and completely implement the technical solution. The prefixes of non-explained technical-feature terms, such as "first", "second", "selected", "target", etc., may be unambiguously derived and determined from the context. Suffixes of technical feature terms not explained, such as "set", "value", etc., can also be derived and determined unambiguously from the foregoing and the following.

The above disclosure of the embodiments of the present application will be apparent to those skilled in the art from the above disclosure. It should be understood that the derivation and analysis of technical terms, which are not explained, by those skilled in the art based on the above disclosure are based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered as illustrative and not restrictive of the application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific terminology to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of at least one embodiment of the present application may be combined as appropriate.

In addition, those skilled in the art will recognize that the various aspects of the application may be illustrated and described in terms of several patentable species or contexts, including any new and useful combination of procedures, machines, articles, or materials, or any new and useful modifications thereof. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as a "unit", "component", or "system". Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in at least one computer readable medium.

A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the execution of aspects of the present application may be written in any combination of one or more programming languages, including object oriented programming, such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, or similar conventional programming languages, such as the "C" programming language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages, such as Python, ruby, and Groovy, or other programming languages. The programming code may execute entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order of the process elements and sequences described herein, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods unless otherwise indicated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it should be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware means, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

It should also be appreciated that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. However, this method of disclosure is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Claims

1. A project decision result evaluation method is applied to a project management cloud platform and comprises the following steps:

when the uploading of the project settlement results is completed, acquiring project settlement compiling logs to be evaluated, wherein the project settlement compiling logs are contained in the project settlement results;

performing resolution calculation compiling behavior expression array extraction on the project resolution calculation compiling log to be evaluated through a project resolution analysis model deployed in advance to obtain a resolution calculation behavior compliance expression array of not less than two project resolution analysis points and a focusing degree distribution factor corresponding to each project resolution analysis point;

and obtaining engineering decision making behavior compliance evaluation information of the engineering decision making log to be evaluated according to the decision making behavior compliance expression arrays of at least two engineering decision making analysis points and the focusing degree distribution factor corresponding to each engineering decision making analysis point.

2. A method as recited in claim 1, wherein said obtaining engineering resolution behavior compliance assessment information for said engineering resolution compilation log to be assessed based on said resolution behavior compliance expression arrays for not less than two engineering resolution analysis points and a focus degree allocation factor corresponding to each engineering resolution analysis point comprises:

performing expression array extrusion processing according to the decision behavior compliance expression array of not less than two engineering decision analysis points to obtain a decision behavior compliance expression array after the expression array of the engineering decision analysis points less than the engineering decision analysis points before extrusion is extruded;

performing expression array excitation processing according to the decision-making behavior compliance expression array after the expression array is extruded to obtain a decision-making behavior compliance expression array after the excitation of the expression array, wherein the engineering decision-making analysis points are equal to the engineering decision-making analysis points before the extrusion;

and determining engineering decision making behavior compliance evaluation information of the engineering decision making log to be evaluated according to the decision making behavior compliance expression array excited by the expression array and the focusing degree distribution factor corresponding to each engineering decision making analysis point.

3. The method of claim 2, wherein the engineering resolution analysis model comprises an analysis network for engineering resolution behavioral compliance assessment;

the step of obtaining the engineering resolution calculation compiling behavior compliance evaluation information of the engineering resolution calculation compiling log to be evaluated according to the resolution behavior compliance expression arrays of not less than two engineering resolution analysis points and the focusing degree distribution factor corresponding to each engineering resolution analysis point comprises the following steps:

performing distribution operation according to the decision behavior compliance expression array of at least two engineering decision analysis points and the focusing degree distribution factor corresponding to each engineering decision analysis point, adding the results after the distribution operation, and determining the added decision behavior compliance expression array;

and loading the added decision behavior compliance expression array into the analysis network of the engineering decision analysis model to obtain the engineering decision behavior compliance evaluation information output by the analysis network.

4. The method of claim 3, wherein the optimization process of the engineering decision analysis model comprises:

acquiring a project resolution working log template and working behavior compliance indication information of the project resolution working log template, wherein the working behavior compliance indication information represents whether the project resolution working behavior data in the corresponding project resolution working log template is the project resolution working behavior compliance data covering counterfeit behaviors or not;

determining the engineering resolution working log template as loading data of a to-be-optimized engineering resolution analysis model, determining working behavior compliance indication information of the engineering resolution working log template as constraint information of output information of the to-be-optimized engineering resolution analysis model, and performing multiple model parameter optimization on the to-be-optimized engineering resolution analysis model to obtain the pre-deployed engineering resolution analysis model;

the engineering decision analysis model comprises an expression array acquisition network, a focusing degree distribution network and an analysis network; the step of determining the project resolution working log template as the loading data of the project resolution analysis model to be optimized, determining the working behavior compliance indication information of the project resolution working log template as the constraint information of the output information of the project resolution analysis model to be optimized, and carrying out multiple model parameter optimization on the project resolution analysis model to be optimized comprises the following steps:

loading the project resolution compilation log template into an expression array acquisition network included in the project resolution analysis model to obtain a resolution action total scale board expression array of not less than two project resolution analysis points output by the expression array acquisition network;

loading a settlement behavior sum-scale board expression array which is output by the expression array acquisition network and is not less than two engineering settlement analysis points into the focusing degree distribution network of the engineering settlement analysis model to obtain a focusing degree distribution factor which is output by the focusing degree distribution network and corresponds to each engineering settlement analysis point;

performing distribution operation according to the decision behavior combined scale board expression array of not less than two engineering decision analysis points and the focusing degree distribution factor corresponding to each engineering decision analysis point, and adding the results after the distribution operation to obtain an added decision behavior combined scale board expression array;

loading the added decision behavior close-scale board expression array into the analysis network of the engineering decision analysis model, and determining compilation behavior close-scale prediction information obtained by inference of the analysis network;

and performing multiple model parameter optimization on the project decision analysis model to be optimized according to the compiling behavior compliance prediction information and the compiling behavior compliance indication information of the project decision log template.

5. The method of claim 4, wherein the engineering decision analysis model comprises an acquisition network and an analysis network for acquiring a plurality of expression arrays of different convolution strengths;

the step of determining the project resolution working log template as the loading data of the project resolution analysis model to be optimized, the step of determining the working behavior compliance indication information of the project resolution working log template as the constraint information of the output information of the project resolution analysis model to be optimized, and the step of carrying out multiple model parameter optimization on the project resolution analysis model to be optimized comprises the following steps:

loading the project settlement compilation log template into a plurality of expression array acquisition networks included in the project settlement analysis model to obtain a settlement behavior combined scale plate expression array output by each expression array acquisition network;

selecting an expression array extraction network in which the convolution intensity screened and output from the plurality of expression array acquisition networks meets the preset convolution intensity;

loading a decision-making behavior close-size board expression array output by the selected expression array extraction network into the analysis network of the engineering decision-making analysis model to obtain compilation behavior close-size prediction information obtained by inference of the analysis network;

6. The method as claimed in claim 5, wherein said performing a plurality of model parameter optimizations on said project resolution analysis model to be optimized according to said compilation behavior compliance prediction information and compilation behavior compliance indication information for said project resolution logging template, comprises:

determining an error result of the project resolution analysis model to be optimized according to a similarity measurement result between the compiling behavior compliance prediction information and compiling behavior compliance indication information of the project resolution compiling log template;

performing multiple model parameter optimization on the project decision analysis model to be optimized according to the error result;

the multiple model parameter optimization of the project decision analysis model to be optimized through the error result comprises the following steps:

if the current model optimization does not meet the optimization ending requirement, optimizing model parameters of at least one of the network for obtaining the expression array of the project decision analysis model to be optimized, the focusing degree distribution network and the analysis network through the error result;

and carrying out the next model optimization process according to the optimized engineering decision analysis model, and stopping optimization when the engineering decision analysis model meets the optimization ending requirement.

7. The method as claimed in claim 6, wherein the compilation behavior compliance indication information of the engineering resolution logging template is obtained by the following steps:

carrying out counterfeit behavior analysis on the project resolution working log template, and determining a counterfeit behavior type corresponding to the project resolution working behavior data in the project resolution working log template;

and determining compilation behavior compliance indication information of the project resolution compilation log template according to the counterfeit behavior type corresponding to the project resolution compilation behavior data in the project resolution compilation log template.

8. The method according to claim 7, wherein the step of performing the counterfeit analysis on the engineering resolution working log template to determine the type of the counterfeit corresponding to the engineering resolution working behavior data in the engineering resolution working log template comprises:

performing fake behavior analysis on the project resolution working log template according to a preset fake behavior expression array extraction model, and determining working fake behavior expression arrays of each layer extracted from the project resolution working log template;

and determining the type of the counterfeit behavior corresponding to the project resolution calculation compiling behavior data in the project resolution calculation compiling log template according to the compiling counterfeit behavior expression array of each layer.

9. The method as claimed in claim 8, wherein the different engineering resolution calculation working behavior data categories covered by the engineering resolution calculation working log to be evaluated correspond to resolution behavior compliance expression arrays of different engineering resolution analysis points, and the resolution behavior compliance expression values represented by the resolution behavior compliance expression arrays are positively associated with the focus degree distribution values represented by the focus degree distribution factors corresponding to the corresponding engineering resolution calculation working behavior data categories; the settlement behavior compliance expression arrays of different engineering settlement analysis points at least comprise compiling counterfeiting behavior expression array information and compiling behavior expression array information; and the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the compiling and counterfeiting behavior expression array information is reversely associated with the focusing degree distribution value represented by the focusing degree distribution factor corresponding to the compiling behavior expression array information.

10. A project management cloud platform comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the method of any one of claims 1 to 9.