An artificial intelligence-based project completion file archiving method and cloud platform

Abstract

The artificial intelligence-based project completion archive archiving method and cloud platform provided in the embodiments of the present application respectively obtains a positioning description array and a positioning code array based on the original archive description array. The positioning code array and the positioning description array contain the same expression meaning. Then, two project completion archives containing similar positioning description arrays also have similar positioning code arrays. At the same time, when the positioning description array is obtained, the positioning code array is also obtained, which alleviates the error during code generation and increases the efficiency of optimization. Based on this, when archiving, the first standardized array of the positioning description array and the corresponding positioning code array is used as the basis, and the positioning description array is used as a collaborative element for correlation comparison and then archiving, thereby improving the rationality and efficiency of archiving the project completion archive.

Description

Technical Field

[0001] The present application relates to the fields of data processing and artificial intelligence, and more specifically, to an artificial intelligence-based project completion archive archiving method and cloud platform. Background Art

[0002] In the management of highway projects, for example, project completion archives are engineering materials compiled in strict accordance with specifications. Project completion archives are a summary and summary of the construction process, and the management of project completion archives is an important part of project document management. For the management of project completion archives, it is not only necessary to inspect the completeness and standardization of the content of the project completion archives, but also to classify and store similar project completion archives according to actual needs and the set archiving rules, so as to achieve orderly archiving and facilitate subsequent retrieval. At present, the archiving and storage process is based on manual labor, which not only occupies human resources, but also human archiving is often extremely inefficient and prone to errors. How to automatically archive project completion archives and ensure the accuracy and efficiency of archiving is a technical problem that needs to be solved urgently. Summary of the Invention

[0003] The purpose of the present invention is to provide an artificial intelligence-based project completion archive archiving method and cloud platform to improve the above-mentioned problems.

[0004] In order to achieve the above objectives, the implementation of the embodiments of the present application is as follows:

[0005] In a first aspect, an embodiment of the present application provides an artificial intelligence-based project completion file archiving method for a project management cloud platform, the method comprising:

[0006] Obtaining the project completion file to be archived and at least one preset archiving element;

[0007] Obtaining an original file description array of the file content associated with the at least one preset filing element in the project completion file to be filed;

[0008] Performing description array projection processing on the original file description array of the project completion file to be archived to obtain a positioning description array of the project completion file to be archived;

[0009] Performing code generation processing on the original file description array of the to-be-archived project completion file to obtain a positioning code array corresponding to the to-be-archived project completion file;

[0010] Standardizing the positioning code array of the to-be-archived project completion archive to obtain a first standardized array of the positioning code array of the to-be-archived project completion archive;

[0011] Comparing the similarity of a plurality of candidate archived project completion files using the location description array of the to-be-archived project completion file and the first standardized array of the to-be-archived project completion file to obtain a candidate archived project completion file associated with the to-be-archived project completion file;

[0012] The to-be-archived project completion files are classified and stored in the storage space where the associated candidate archived project completion files are located.

[0013] As an embodiment, the positioning description array of the to-be-archived project completion archive and the positioning code array of the to-be-archived project completion archive are obtained based on the retrieved project completion archive archiving model. Before obtaining the original archive description array of the to-be-archived project completion archive, the method further includes:

[0014] Extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence and the positioning code array of the project completion archive debugging sequence;

[0015] Determine the error result through the positioning description array of the project completion file debugging sequence to obtain the file description array distance error result of the project completion file debugging sequence;

[0016] Determine the error result by using the positioning code array of the engineering completion file debugging sequence to obtain the code array distance error result and the code array error result of the engineering completion file debugging sequence;

[0017] Merging at least two of the file description array distance error result, the code array distance error result, and the code array error result of the project completion file debugging sequence, and determining the error result obtained after the merger as the first error result corresponding to the project completion file archiving model;

[0018] The project completion archive model is optimized by using a first error result corresponding to the project completion archive model.

[0019] In one embodiment, the project completion file debugging sequence includes a reference debugging project completion file, a true value debugging project completion file, and a false value debugging project completion file, a matching score between the true value debugging project completion file and the reference debugging project completion file is greater than a first preset matching score, a matching score between the false value debugging project completion file and the reference debugging project completion file is less than a second preset matching score, and the first preset matching score is greater than the second preset matching score;

[0020] The project completion archive filing model includes a common description array extraction unit, a positioning description array processing unit, and a positioning code array processing unit;

[0021] The method of extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence and the positioning code array of the project completion archive debugging sequence includes:

[0022] Based on the common description array extraction unit, common file description arrays are extracted from the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively, to obtain original file description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively;

[0023] Based on the positioning code array processing unit, the original file description arrays of the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file are respectively subjected to numerical description array projection processing to obtain positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file respectively;

[0024] Based on the positioning description array processing unit, description array projection processing is performed on the original file description arrays of the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file, respectively, to obtain the positioning description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file, respectively.

[0025] As an embodiment, determining the error result by using the positioning description array of the project completion file debugging sequence to obtain the file description array distance error result of the project completion file debugging sequence includes:

[0026] Determine a first positioning description array difference between the positioning description array of the reference debugging project completion file and the positioning description array of the true value debugging project completion file, and simultaneously determine a second positioning description array difference between the positioning description array of the reference debugging project completion file and the positioning description array of the false value debugging project completion file;

[0027] Obtaining a first addition result of the first positioning description array difference and a first preset error result, and simultaneously determining a first subtraction result between the first addition result and the second positioning description array difference;

[0028] If the first subtraction result is greater than 0, determining the first subtraction result as the file description array distance error result;

[0029] If the first subtraction result is less than or equal to 0, the file description array distance error result is determined to be 0.

[0030] As an embodiment, determining the error result by using the positioning code array of the engineering completion file debugging sequence to obtain the code array distance error result of the engineering completion file debugging sequence includes:

[0031] Obtaining a first positioning description array difference between the positioning code array of the reference debugging project completion file and the positioning code array of the true value debugging project completion file, and simultaneously determining a second positioning description array difference between the positioning code array of the reference debugging project completion file and the positioning code array of the false value debugging project completion file;

[0032] Determine a second addition result of the first location description array difference and a second preset error result, and simultaneously determine a second subtraction result between the second addition result and the second location description array difference;

[0033] If the second subtraction result is greater than 0, determining the second subtraction result as the code array distance error result;

[0034] If the second subtraction result is less than or equal to 0, a value of 0 is determined as the code array distance error result.

[0035] As an embodiment, determining the error result by using the positioning code array of the engineering completion file debugging sequence to obtain the code array error result of the engineering completion file debugging sequence includes:

[0036] Performing optimization and standardization processing on the positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively, to obtain an optimized value corresponding to each element in each positioning code array;

[0037] Determine a subtraction result between each element in each positioning code array and the corresponding optimized value;

[0038] The subtraction results corresponding to each of the elements are summed to obtain the code array error result of the engineering completion file debugging sequence.

[0039] As an embodiment, the optimizing the project completion archive model by using the first error result corresponding to the project completion archive model includes:

[0040] If the first error result is obtained through the archive description array distance error result, the code array distance error result, and the code array error result, optimizing the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit through the first error result;

[0041] or optimizing the parameters of the positioning code array processing unit and the parameters of the positioning description array processing unit based on the first error result;

[0042] If the first error result is obtained through the code array distance error result and the code array error result, the parameter of the positioning code array processing unit is optimized according to the first error result.

[0043] As an embodiment, the positioning description array of the project completion file to be archived and the positioning code array of the project completion file to be archived are obtained by retrieving a project completion file archiving model. The project completion file archiving model includes a common description array extraction unit, a positioning code array processing unit, and a positioning description array processing unit. Before obtaining the original file description array of the project completion file to be archived, the method further includes:

[0044] Optimizing the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit until the second error result corresponding to the project completion archive filing model meets the preset change requirements;

[0045] Optimizing the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit until a third error result corresponding to the project completion archive archiving model meets the preset change requirement;

[0046] The optimizing the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit includes:

[0047] Extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence;

[0048] Determining an error result through the positioning description array of the project completion file debugging sequence to obtain a distance error result of the file description array of the project completion file debugging sequence, and determining the file description array distance error result as a second error result corresponding to the project completion file archiving model;

[0049] The parameters of the common description array extraction unit and the parameters of the positioning description array processing unit are optimized by corresponding to the second error result of the project completion archive archiving model.

[0050] In one embodiment, the method of performing similarity comparison on a plurality of candidate archived project completion files using the location description array of the to-be-archived project completion file and the first standardized array of the to-be-archived project completion file to obtain a candidate archived project completion file associated with the to-be-archived project completion file includes:

[0051] Obtaining, through the second standardized arrays of the plurality of candidate archived project completion files, a correspondence between the second standardized arrays and the candidate archived project completion files, wherein each second standardized array corresponds to one or more candidate archived project completion files;

[0052] Determine a search standardized array from a plurality of second standardized arrays using the first standardized array, and determine the candidate archived project completion file corresponding to the search standardized array as the selected project completion file;

[0053] Obtaining a vector difference between the positioning description array of the candidate archived project completion file corresponding to the search standardization array and the positioning description array of the project completion file to be archived, and determining the candidate archived project completion file whose vector difference is greater than a preset vector difference as the selected project completion file;

[0054] Before the step of obtaining the corresponding relationship between the second standardized array and the candidate archived project completion files, the method further includes:

[0055] Determine the original file description array of the plurality of candidate archived project completion files;

[0056] Performing code generation processing on the original file description arrays of the plurality of candidate archived project completion files to obtain positioning code arrays corresponding to the plurality of candidate archived project completion files;

[0057] performing standardization processing on the positioning code arrays of the plurality of candidate archived project completion files to obtain a second standardized array of the positioning code arrays of the plurality of candidate archived project completion files;

[0058] Before the step of obtaining the vector difference between the positioning description array of the candidate archived project completion file corresponding to the search standardization array and the positioning description array of the to-be-archived project completion file, the method further includes:

[0059] The original file description arrays of the plurality of candidate archived project completion files are subjected to description array projection processing to obtain positioning description arrays of the plurality of candidate archived project completion files.

[0060] In the second aspect, an embodiment of the present application provides a project management cloud platform, comprising at least one memory and at least one processor; the memory stores a program, the processor is used to call the program stored in the memory, and the program is used to implement the above-mentioned artificial intelligence-based engineering completion file archiving method.

[0061] The artificial intelligence-based project completion archive archiving method and cloud platform provided in the embodiment of the present application obtains a positioning description array and a positioning code array based on the original archive description array. In this way, the positioning code array and the positioning description array contain the same expression meaning, and then two project completion archives containing similar positioning description arrays also have similar positioning code arrays. At the same time, when the positioning description array is obtained, the positioning code array is also obtained, which alleviates the error during code generation and increases the efficiency of optimization. Based on this, when archiving the first standardized array of the positioning description array and the corresponding positioning code array, the first standardized array is used as the basis, and the positioning description array is used as a collaborative element for correlation comparison and then archiving, thereby improving the rationality and efficiency of archiving the project completion archive.

[0062] In the following description, other features will be partially set forth. Those skilled in the art will partially discover these features upon inspection of the following description and the accompanying drawings, or may learn these features through production or use. The features of the present application can be realized and obtained by practicing or using various aspects of the methods, tools, and combinations listed in the detailed examples described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0064] The methods, systems, and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein reference numerals represent similar structures in the various views of the drawings.

[0065] Figure 1 This is a schematic diagram of the hardware and software components of a project management cloud platform according to some embodiments of the present application.

[0066] Figure 2 This is a flowchart of an artificial intelligence-based project completion file archiving method according to some embodiments of the present application.

[0067] Figure 3 This is a schematic diagram of the architecture of the project completion file archiving device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0069] In the following detailed description, numerous specific details are set forth by way of example in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application can be practiced without these details. In other instances, well-known methods, procedures, systems, compositions, and / or circuits have been described at a relatively high level, without detail, to avoid unnecessarily obscuring aspects of the present application.

[0070] These and other features, the functions disclosed in the present application, the methods of performing them, the functions of the related elements in the structure and the combination of parts and the economics of production 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. However, it is to be understood that the drawings are for illustration and description purposes only and are not intended to limit the scope of this application. It should be understood that these drawings are not drawn to scale. However, it should be clearly understood that the drawings are for illustration and description purposes only and are not intended to limit the scope of this application. It should be understood that these drawings are not drawn to scale.

[0071] Flowcharts are used in this application to illustrate the execution processes performed by the system according to the embodiments of the present application. It should be clearly understood that the execution processes of the flowcharts may not be executed in sequence. Instead, these execution processes may be executed in reverse order or simultaneously. In addition, at least one additional execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0072] The artificial intelligence-based project completion file archiving method provided in this application embodiment is applied to the project management cloud platform. Please refer to Figure 1, is a schematic diagram of the architecture of the project management cloud platform 100, which includes a project completion archive archiving device 110, a memory 120, a processor 130 and a communication unit 140. The memory 120, the processor 130 and the communication unit 140 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The project completion archive archiving device 110 includes at least one software function module that can be stored in the memory 120 in the form of software or firmware or solidified in the operating system (OS) of the project management cloud platform 100. The processor 130 is used to execute executable modules stored in the memory 120, such as the software function modules and computer programs included in the project completion archive archiving device 110.

[0073] 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 programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory 120 is used to store programs, and the processor 130 executes the programs after receiving execution instructions. The communication unit 140 is used to establish a communication connection between the project management cloud platform 100 and the business interaction device through the network, and is used to send and receive data through the network, such as scanned electronic files.

[0074] The processor may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it 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, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor.

[0075] I understand. Figure 1The structure shown is for illustration only. The project management cloud platform 100 may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0076] The artificial intelligence-based project completion file archiving method provided in the embodiment of the present application is executed through a preset project completion file archiving model. It can be understood that the model architecture of the project completion file archiving model is not limited, such as a convolutional neural network framework, a deep learning network framework, a residual network framework, etc.

[0077] The project completion archive model includes a common description array extraction unit, a positioning description array processing unit and a positioning code array processing unit.

[0078] The common description array extraction unit may include multiple filters containing different convolution matrices connected in sequence. The number of filters, the matrix rank of the convolution matrix, the number of channels, and the moving distance are determined according to actual conditions, and the embodiments of the present application do not limit this.

[0079] The positioning description array processing unit includes a downsampling unit (such as a maximum pooling unit), a normalization unit (such as configuring a normalized exponential function) and a classification mapping unit (including multiple fully connected layers).

[0080] The positioning code array processing unit may also include a downsampling unit, a normalization unit, and a classification mapping unit.

[0081] During the optimization process of the project completion archive archiving model, the project completion archive debugging sequence is input into the project completion archive archiving model, and multiple convolutions are performed based on the common description array extraction unit to obtain the original archive description array of each project completion archive in the project completion archive debugging sequence (it can be understood that the archive content associated with the preset archiving elements is extracted), and the original archive description array of each project completion archive is processed based on the positioning description array processing unit to obtain the positioning description array, such as the description array projection processing (feature mapping) of the archive description array, and the original archive description array of each project completion archive is processed based on the positioning code array processing unit to obtain the positioning code array, such as If code generation processing is performed (implemented through quantitative coding), the positioning description array and the positioning code array are obtained based on the original file description array, so that the positioning code array and the positioning description array have the same expression meaning. Then, the two project completion files containing the associated positioning description array also contain the matching positioning code array. The two project completion files containing the matching positioning description array will not be divided because of the different positioning code arrays. When the positioning description array is obtained, the positioning code array is obtained at the same time. There is no need to optimize after the positioning description array is determined. This eliminates the need for multiple optimizations to increase useless processes and the generation of multiple errors, that is, description array errors and errors in the code generation process. The file description array distance error result is obtained through the positioning description array, the code array distance error result and the code array error result are obtained through the positioning code array, and the total error result is obtained through the file description array distance error result, the code array distance error result and the code array error result, so as to optimize the parameters of the project completion file archiving model through the total error result.

[0082] In the artificial intelligence-based project completion file archiving method provided in the embodiment of the present application, the positioning description array of the project completion file to be archived and the positioning code array of the project completion file to be archived are extracted using the above-mentioned project completion file archiving model. The optimization process of the project completion file archiving model can include the following steps 110 to 150.

[0083] Step 110: extracting the file description array of the project completion file debugging sequence based on the project completion file archiving model to obtain the positioning description array of the project completion file debugging sequence and the positioning code array of the project completion file debugging sequence.

[0084] Regarding the project completion archive, its specific contents include but are not limited to the design plan (including the submission and approval parts), review records, commencement report, technical briefing, building materials, equipment inspection report, operation records, completion acceptance report, completion drawings, etc. When archiving the project completion archive, it is often necessary to archive similar project completion archives according to the preset archiving rules. The preset archiving rules of different units may be different. For example, when archiving by similarity, the reference archiving elements may be different. For example, the reference archiving elements may include one or more of the above contents, such as the archiving element is the completion acceptance report.

[0085] When optimizing the project completion archive archiving model to be optimized, the project completion archive debugging sequence is used as a template for training optimization. The project completion archive debugging sequence includes reference debugging project completion archives, true value debugging project completion archives, and false value debugging project completion archives.

[0086] The matching score (used to measure the degree of matching) between the true value debugging project completion file and the reference debugging project completion file is greater than the first preset matching score, the matching score between the false value debugging project completion file and the reference debugging project completion file is less than the second preset matching score, and the first preset matching score is greater than the second preset matching score.

[0087] The project completion archive model includes a common description array extraction unit, a positioning description array processing unit, and a positioning code array processing unit.

[0088] In step 110, based on the project completion file archiving model, the file description array of the project completion file debugging sequence is extracted to obtain the positioning description array of the project completion file debugging sequence and the positioning code array of the project completion file debugging sequence, which specifically include:

[0089] Based on the common description array extraction unit, the common file description arrays of the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are extracted respectively, and the original file description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are obtained respectively; based on the positioning code array processing unit, the original file description arrays of the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are projected with numerical description arrays respectively, and the positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are obtained respectively; based on the positioning description array processing unit, the original file description arrays of the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are projected with description arrays respectively, and the positioning description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file are obtained respectively.

[0090] Among them, among the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file included in the project completion file debugging sequence, if the reference debugging project completion file and the true value debugging project completion file are similar project completion files, then the matching score between the reference debugging project completion file and the true value debugging project completion file is greater than the first preset matching score.

[0091] If the reference debugging project completion file and the dummy value debugging project completion file are dissimilar project completion files, then the matching score between the reference debugging project completion file and the dummy value debugging project completion file is less than the second preset matching score. The first preset matching score is greater than the second preset matching score.

[0092] In addition, the project completion file debugging sequence can also be obtained through similar project completion file groups. For example, if there are 15 project completion file groups, for any project completion file group I, any project completion file I-1 in the project completion file group I and any project completion file in each of the remaining 14 project completion file groups are matched and scored to obtain 14 matching scores.

[0093] The 14 project completion file groups are arranged in descending order according to the matching scores, and a random project completion file in the project completion file group with a middle ranking is determined as a false value debugging project completion file, and any project completion file in the project completion file group I is determined as a reference debugging project completion file, and the remaining project completion files in the project completion file group I are determined as true value debugging project completion files. The project completion file with a middle ranking can be determined based on the third preset matching score.

[0094] The matching score between the reference commissioning project completion file and the fake commissioning project completion file is less than the second preset matching score but greater than the third preset matching score, and the third preset matching score is less than the second preset matching score. The resulting fake commissioning project completion file serves as a project completion file template of appropriate difficulty, which can be optimized to create a more generalizable project completion file archiving model.

[0095] As an implementation method, a common file description array extraction unit is used to extract the common file description array of the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively, to obtain the original file description array of the reference debugging project completion file, the original file description array of the true value debugging project completion file, and the original file description array of the false value debugging project completion file. Based on the positioning code array processing unit, the original file description array of the reference debugging project completion file, the original file description array of the true value debugging project completion file, and the original file description array of the false value debugging project completion file are respectively processed. The value description array is projected to obtain the positioning code array of the reference debugging project completion file, the positioning code array of the true value debugging project completion file and the positioning code array of the false value debugging project completion file. Based on the positioning description array processing unit, the original file description array of the reference debugging project completion file, the original file description array of the true value debugging project completion file and the original file description array of the false value debugging project completion file are respectively projected to obtain the positioning description array of the reference debugging project completion file, the positioning description array of the true value debugging project completion file and the positioning description array of the false value debugging project completion file.

[0096] Step 120: Determine the error result through the positioning description array of the engineering completion file debugging sequence to obtain the file description array distance error result of the engineering completion file debugging sequence.

[0097] In one implementation of an embodiment of the present application, in step 120, an error result is determined by using the positioning description array of the project completion file debugging sequence to obtain the file description array distance error result of the project completion file debugging sequence, including: obtaining a first positioning description array difference (i.e., array distance) between the positioning description array of the reference debugging project completion file and the positioning description array of the true value debugging project completion file, and simultaneously determining a second positioning description array difference between the reference debugging project completion file and the false value debugging project completion file; obtaining a first addition result of the first positioning description array difference and a first preset error result, and simultaneously determining a first subtraction result between the first addition result and the second positioning description array difference; if the first subtraction result is greater than 0, determining the first subtraction result as the file description array distance error result; if the first subtraction result is less than or equal to 0, determining a value of 0 as the file description array distance error result.

[0098] In one implementation of an embodiment of the present application, in step 120, an error result is determined by using the positioning code array of the project completion file debugging sequence to obtain a code array distance error result of the project completion file debugging sequence, including: determining a first positioning description array difference between the positioning code array of the reference debugging project completion file and the positioning code array of the true value debugging project completion file, and simultaneously determining a second positioning description array difference between the reference debugging project completion file and the false value debugging project completion file; determining a second addition result of the first positioning description array difference and a second preset error result, and simultaneously determining a second subtraction result between the second addition result and the second positioning description array difference; if the second subtraction result is greater than 0, determining the second subtraction result as the code array distance error result; if the second subtraction result is less than or equal to 0, determining the code array distance error result as 0.

[0099] Step 130: Determine the error result through the positioning code array of the engineering completion file debugging sequence to obtain the code array distance error result and the code array error result of the engineering completion file debugging sequence.

[0100] In one implementation of the embodiment of the present application, in step 130, the error result is determined by the positioning code array of the project completion file debugging sequence to obtain the code array error result of the project completion file debugging sequence, including: standardizing the positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, completing the normalization of the values, and obtaining the optimized value corresponding to each element in each positioning code array; obtaining the subtraction result of each element in each positioning code array and the corresponding optimized value, the preset calculation result is, for example, the difference between each element and the optimized value, and determining the absolute value of the difference; adding the absolute value of the difference corresponding to each element to obtain the code array error result of the project completion file debugging sequence, or, in another implementation, the absolute value of each element can be squared and added to obtain the code array error result of the project completion file debugging sequence.

[0101] Step 140: Merge at least two of the file description array distance error results, the code array distance error results, and the code array error results of the project completion file debugging sequence, and determine the error result obtained after the merger as the first error result corresponding to the project completion file archiving model.

[0102] When optimizing the project completion archive archiving model, all parameters of the project completion archive archiving model are determined to be in a state to be optimized. During the optimization process, each project completion archive of the project completion archive debugging sequence is calculated to obtain a positioning description array and a positioning code array. The archive description array distance error result is calculated based on the positioning description array of the project completion archive debugging sequence, the code array distance error result is calculated through the positioning code array of the project completion archive debugging sequence, and the code array error result is calculated through the positioning code array of the project completion archive debugging sequence. The three error results are summed to obtain a total error result.

[0103] Step 150: Optimize the project completion archive model using the first error result corresponding to the project completion archive model.

[0104] In the implementation scheme of the embodiment of the present application, in step 150, the project completion archive archiving model is optimized by the first error result corresponding to the project completion archive archiving model, including: if the first error result is obtained through the archive description array distance error result, the code array distance error result and the code array error result, then the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit and the parameters of the positioning description array processing unit are optimized through the first error result, or the parameters of the positioning code array processing unit and the parameters of the positioning description array processing unit are optimized through the first error result; if the first error result is obtained through the code array distance error result and the code array error result, then the parameters of the positioning code array processing unit are optimized through the first error result.

[0105] For example, in the process of optimizing the parameters of the project completion archive model using the total error result, all parameters or local parameters of the project completion archive model can be optimized. During the optimization process, the positioning code array processing unit and the positioning description array processing unit can be learned simultaneously. The parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit can be optimized using the first error result, or the parameters of the positioning code array processing unit and the parameters of the positioning description array processing unit can be optimized using the first error result. In addition, only the positioning code array processing unit can be optimized, and the positioning description array processing unit can be not optimized.

[0106] In one implementation of an embodiment of the present application, the positioning description array of the project completion archive to be archived and the positioning code array of the project completion archive to be archived are obtained based on retrieving the project completion archive archiving model. The project completion archive archiving model includes a common description array extraction unit, a positioning code array processing unit, and a positioning description array processing unit. Before obtaining the original archive description array of the project completion archive to be archived based on retrieving the project completion archive archiving model, the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit are optimized until the second error result of the corresponding project completion archive archiving model meets the preset change requirements; the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit are optimized until the third error result of the corresponding project completion archive archiving model meets the preset change requirements. The above-mentioned preset condition is, for example, that the change of the error result is less than the preset value.

[0107] In one implementation of an embodiment of the present application, the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit are optimized, for example, including: extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence; determining the error result through the positioning description array of the project completion archive debugging sequence to obtain the archive description array distance error result of the project completion archive debugging sequence, and determining the archive description array distance error result as the second error result corresponding to the project completion archive archiving model; optimizing the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit through the second error result corresponding to the project completion archive archiving model.

[0108] For example, optimize the parameters of the common description array extraction unit and the positioning description array processing unit, only obtain the archive description array distance error result, extract the archive description array of the reference debugging project completion archive, the true value debugging project completion archive and the false value debugging project completion archive based on the project completion archive archiving model, and obtain the positioning description array of the reference debugging project completion archive, the positioning description array of the true value debugging project completion archive and the positioning description array of the false value debugging project completion archive. Determine the error result by using the positioning description array of the reference debugging project completion archive, the positioning description array of the true value debugging project completion archive and the positioning description array of the false value debugging project completion archive to obtain the archive description array distance error result.

[0109] Please refer to Figure 2 The method for archiving project completion files based on artificial intelligence provided in the embodiment of the present application includes the following steps 10 to 70.

[0110] Step 10: Obtain the project completion file to be archived and at least one preset archiving element.

[0111] The project completion files to be archived are project completion files that need to be classified and stored in the corresponding storage space. It can be understood that the project completion files to be archived are electronic files, such as scanned copies obtained by scanning paper project completion files, or for enterprises with a high degree of electronicization, the project completion files are directly generated electronic files. This application does not limit this.

[0112] Step 20: Get the original file description array of the project completion file to be archived.

[0113] For example, the project completion archive archiving model provided in an embodiment of the present application includes a common description array extraction unit, a positioning description array processing unit, and a positioning code array processing unit. The positioning description array processing unit and the positioning code array processing unit are both connected to the common description array extraction unit. Based on the common description array extraction unit of the project completion archive archiving model, the original archive description array of the project completion archive to be archived is obtained.

[0114] Step 30: Perform description array projection processing on the original file description array of the project completion file to be archived to obtain the positioning description array of the project completion file to be archived.

[0115] In one implementation of an embodiment of the present application, the description array projection processing can be performed based on a positioning description array processing unit, which may include a downsampling module I (such as maximum pooling), a regularization module I, and a fully connected module I.

[0116] In step 30, description array projection processing is performed on the original file description array of the project completion archive to be archived to obtain the positioning description array of the project completion archive to be archived, including: pooling the original file description array of the project completion archive to be archived based on the downsampling module I to obtain the pooling value I of the original file description array; normalizing the pooling value I based on the regularization module I to obtain the regularization value of the original file description array; and classifying and mapping the regularized value based on the full connection module I to obtain the positioning description array of the project completion archive to be archived.

[0117] Step 40: Perform code generation processing on the original file description array of the project completion file to be archived to obtain a positioning code array corresponding to the project completion file to be archived.

[0118] In one implementation of an embodiment of the present application, the code generation process is obtained based on a positioning code array processing unit, and the positioning code array processing unit includes a downsampling module II, a regularization module II, and a fully connected module II. In step 40, the original file description array of the project completion file to be archived is subjected to code generation processing to obtain a positioning code array corresponding to the project completion file to be archived, including: pooling the original file description array of the project completion file to be archived based on the downsampling module II to obtain a pooling value II of the original file description array; normalizing the pooling value II based on the regularization module II to obtain a regularized value of the original file description array; and classifying and mapping the regularized value based on the fully connected module II to obtain a positioning code array of the project completion file to be archived.

[0119] Step 50: Standardize the array of positioning codes of the project completion archive to be archived to obtain a first standardized array of the array of positioning codes of the project completion archive to be archived.

[0120] The standardization process in the embodiment of the present application is a normalization process, which completes the binary encoding and normalizes the values ​​less than 0 in the positioning code array to 0, and the values ​​greater than or equal to 0 to 1. For example, the positioning code array is [0.33, -0.22, 0.11], and the normalization process is performed to obtain the first normalized array [1, 0, 1].

[0121] Step 60: performing similarity comparison on multiple candidate archived project completion files using the location description array of the to-be-archived project completion file and the first standardized array of the to-be-archived project completion file to obtain a candidate archived project completion file associated with the to-be-archived project completion file.

[0122] In one implementation of an embodiment of the present application, in step 60, a similarity comparison is performed on multiple candidate archived project completion files through the positioning description array of the project completion file to be archived and the first standardized array of the project completion file to be archived, and the candidate archived project completion file associated with the project completion file to be archived is obtained, which may include the following steps 61-63.

[0123] Step 61: Determine the correspondence between the second standardized array and the candidate archived project completion files through the second standardized array of the plurality of candidate archived project completion files.

[0124] In step 61, each second standardized array corresponds to one or more candidate archived project completion files. For example, if there are 20 candidate archived project completion files, each candidate archived project completion file contains a second standardized array. If some candidate archived project completion files contain the same second standardized array, then each different second standardized array will have one or more candidate archived project completion files, resulting in a one-to-many correspondence.

[0125] Step 62: Identify a search standardized array from a plurality of second standardized arrays using the first standardized array, and determine the candidate archived project completion file corresponding to the search standardized array as the selected project completion file.

[0126] In one embodiment of the present application, identifying a search standardized array from among the plurality of second standardized arrays using the first standardized array in step 62 includes: obtaining an array distance between each second standardized array and the first standardized array, and determining a second array distance whose array distance is less than a preset array distance as the search standardized array. Alternatively, the first standardized array is converted according to the preset array distance to obtain a converted standardized array, and determining a second array distance from the plurality of second standardized arrays that is consistent with the converted standardized array as the search standardized array.

[0127] Step 63: Determine the vector difference between the positioning description array of the candidate archived project completion file corresponding to the search standardized array and the positioning description array of the project completion file to be archived, and determine the candidate archived project completion file whose vector difference is greater than the preset vector difference as the selected project completion file.

[0128] In step 63 of the embodiment of the present application, the retrieval standardized array corresponds to one or more candidate archived project completion files, for example, the retrieval standardized array A corresponds to the candidate archived project completion file I, and the retrieval standardized array B corresponds to the candidate archived project completion files II and III, and the vector difference between the positioning description arrays of the candidate archived project completion file I, the candidate archived project completion file II and the candidate archived project completion file III and the positioning description array of the project completion file to be archived is determined, and the candidate archived project completion file whose vector difference is greater than the preset vector difference is determined as the selected project completion file.

[0129] In another embodiment, the candidate archived project completion files corresponding to the search standardized array can be directly determined as the selected project completion files, and the matching results can be arranged in order according to the magnitude of the vector difference. This embodiment of the application directly determines the first array distance of the positioning code array obtained in steps 20, 40, and 50 as the basis for commonality matching, eliminating unnecessary computational overhead and improving efficiency. At the same time, during the model optimization process, the reliance on storage space is relatively small, and the optimization process can be repeated in small batches.

[0130] In one implementation scheme of the embodiment of the present application, before the step 61 of determining the correspondence between the second standardized array and the candidate archived project completion archives, the original file description arrays of the multiple candidate archived project completion archives are obtained; code generation processing is performed on the original file description arrays of the multiple candidate archived project completion archives to obtain positioning code arrays corresponding to the multiple candidate archived project completion archives; the positioning code arrays of the multiple candidate archived project completion archives are standardized to obtain a second standardized array of the positioning code arrays of the multiple candidate archived project completion archives; before determining in step 63 the vector difference between the positioning description array of the candidate archived project completion archive corresponding to the retrieved standardized array and the positioning description array of the project completion archive to be archived, description array projection processing is performed on the original file description arrays of the multiple candidate archived project completion archives to obtain positioning description arrays of the multiple candidate archived project completion archives.

[0131] For example, the candidate archived project completion files are first compared, and multiple candidate archived project completion files are respectively input into the project completion file archiving model to obtain the encoding results of the positioning description array and the positioning code array. After the positioning code array processing unit obtains the positioning code array, a second standardized array is obtained through standardization processing, and the correspondence between the candidate archived project completion files and the positioning description array is saved. The multiple second standardized arrays are deduplicated to obtain multiple different normalized values, which are associated with the candidate archived project completion files.

[0132] In one embodiment of the present application, in order to optimize the project completion file archiving model, it is necessary to pre-organize the project completion file debugging sequence. The project completion file debugging sequence can be obtained based on the project completion file group. The project completion file group has been annotated to indicate whether it is the same project completion file. During the matching score optimization process, the optimization is performed based on the matched project completion file group. In order to optimize the obtained positioning code array to represent the matching score between the project completion file groups, the positioning code array can be optimized based on the same project completion file group.

[0133] In the embodiment of the present application, the project completion file archiving model is optimized based on the project completion file debugging sequence. Using similar project completion file groups as model input information, a triplet of project completion file templates is extracted from multiple project completion file groups in each generation. For example, for project completion file group I, any one project completion file is selected from each of the remaining multiple project completion file groups, and the matching status between the determined project completion file and any one of the project completion files in project completion file group I is obtained. The first portion of the determined project completion file is then cleared. This portion of the project completion file may be a similar project completion file to that in project completion file group I and therefore needs to be cleared.

[0134] The project completion file group can only reflect that the two project completion files contained in the project completion file group are similar, and does not mean that different project completion file groups are similar. Therefore, each generation may determine that project completion file group I and project completion file group B are similar, and the remaining top P project completion files are selected as false value templates. The false value templates and the project completion file group I constitute a project completion file debugging sequence. Any project completion file in the project completion file group I is a true value template, and the other project completion file is a reference template. Then, each project completion file group I can obtain P project completion file debugging sequences, and finally obtain P×Q project completion file debugging sequences, where Q is the number of project completion file groups in one generation of optimization.

[0135] In one implementation of an embodiment of the present application, the project completion archive archiving model includes a common description array extraction unit, a positioning description array processing unit, and a positioning code array processing unit. The common description array extraction unit, the positioning description array processing unit, and the positioning code array processing unit are as described above.

[0136] In the model application, the output of the positioning code array processing unit is activated, the common description array extraction unit can be a residual network, the positioning description array processing unit and the positioning code array processing unit can be other networks, and the two networks are combined and connected with the fully connected module to obtain the output of the positioning code array processing unit, which can include a fully connected module (F) and an activation unit (A). The combined network can include a FAFAF structure, and the activation function of A is not limited. When the positioning description array is obtained by adopting the above structure, the positioning code array can be obtained at the same time. The positioning code array is generated into code through the activation algorithm, eliminating the need for multiple learning and adding additional processes. Through the parallel optimization of the common description array extraction unit, the numerical results of the positioning description array and the positioning code array are simultaneously generated in the engineering completion file archiving model. Two engineering completion files with matching positioning description arrays will not be separated due to different positioning code arrays.

[0137] Step 70: Classify and store the to-be-archived project completion files into the storage space where the associated candidate archived project completion files are located.

[0138] In summary, in one implementation scheme of the embodiment of the present application, when the project completion file archiving model is forward transferred, all parameters are set to be optimized. During the optimization process, each project completion file of the input project completion file debugging sequence is processed to obtain a positioning description array and a positioning code array. The file description array distance error result is obtained through the positioning description array of the project completion file debugging sequence, the code array distance error result is obtained through the positioning code array of the project completion file debugging sequence, and the code array error result is obtained through the positioning code array of the project completion file debugging sequence. The three error results are summed to obtain a total error result.

[0139] Please refer to Figure 3 , is a functional module architecture diagram of a project completion file archiving device 110 provided in an embodiment of the present invention. The project completion file archiving device 110 can be used to execute a project completion file archiving method based on artificial intelligence, wherein the project completion file archiving device 110 includes:

[0140] The basic data acquisition module 111 is used to acquire the completed project archive to be archived and at least one preset archiving element;

[0141] The original array acquisition module 112 is used to obtain the original file description array of the file content associated with the at least one preset archiving element in the completed project file to be archived;

[0142] The description array projection module 113 is used to perform description array projection processing on the original file description array of the project completion file to be archived to obtain the positioning description array of the project completion file to be archived;

[0143] The code array generation module 114 is used to perform code generation processing on the original file description array of the project completion file to be archived, so as to obtain a positioning code array corresponding to the project completion file to be archived;

[0144] The annotation array generation module 115 is used to perform standardization processing on the positioning code array of the to-be-archived project completion archive to obtain a first standardized array of the positioning code array of the to-be-archived project completion archive;

[0145] The associated file determination module 116 is configured to perform a similarity comparison on a plurality of candidate archived project completion files using the location description array of the to-be-archived project completion file and the first normalized array of the to-be-archived project completion file, to obtain a candidate archived project completion file associated with the to-be-archived project completion file;

[0146] The project archive storage module 117 is used to classify and store the to-be-archived project completion archives into the storage space where the associated candidate archived project completion archives are located.

[0147] Among them, the basic data acquisition module 111 can be used to execute step 10; the original array acquisition module 112 can be used to execute step 20; the description array projection module 113 can be used to execute step 30; the code array generation module 114 can be used to execute step 40; the annotation array generation module 115 can be used to execute step 50; the associated file determination module 116 can be used to execute step 60; and the engineering file storage module 117 can be used to execute step 70.

[0148] Since the artificial intelligence-based project completion file archiving method provided by the embodiment of the present invention has been introduced in detail in the above embodiment, and the principle of the project completion file archiving device 110 is the same as that of the method, the execution principle of each module of the project completion file archiving device 110 will not be repeated here.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a portion of code, and the module, program segment or a portion of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0150] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0151] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0152] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0153] It should be understood that for technical terms that are not explained in the above content, those skilled in the art can deduce the meanings thereof without any doubt based on the above disclosed content. The above content disclosed in the embodiments of the present application is clear and complete for those skilled in the art. It should be understood that the process of deriving and analyzing the unexplained technical terms based on the above disclosed content by those skilled in the art is based on the content recorded in the application, and therefore the above content is not a judgment on the creativity of the overall solution.

[0154] The basic concepts have been described above. It will be apparent to those skilled in the art that the detailed disclosure provided above is merely illustrative and does not limit the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to the present application. Such modifications, improvements, and amendments are suggested in the present application and remain within the spirit and scope of the exemplary embodiments of the present application.

[0155] It should also be understood that, in order to simplify the presentation of this disclosure and thereby facilitate understanding of at least one embodiment of the invention, the foregoing description of the embodiments of this application sometimes combines multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this application requires more features than those recited in the claims. In fact, an embodiment may have fewer features than the totality of the features of a single disclosed embodiment.

Claims

1. A method for archiving completed project files based on artificial intelligence, characterized in that: Applied to a project management cloud platform, the method includes: Obtaining the project completion file to be archived and at least one preset archiving element; Obtaining an original file description array of the file content associated with the at least one preset filing element in the project completion file to be filed; Performing description array projection processing on the original file description array of the project completion file to be archived to obtain a positioning description array of the project completion file to be archived; Performing code generation processing on the original file description array of the to-be-archived project completion file to obtain a positioning code array corresponding to the to-be-archived project completion file; Standardizing the positioning code array of the to-be-archived project completion archive to obtain a first standardized array of the positioning code array of the to-be-archived project completion archive; Comparing the similarity of a plurality of candidate archived project completion files using the location description array of the to-be-archived project completion file and the first standardized array of the to-be-archived project completion file to obtain a candidate archived project completion file associated with the to-be-archived project completion file; The to-be-archived project completion files are classified and stored in the storage space where the associated candidate archived project completion files are located.

2. The method according to claim 1, characterized in that The positioning description array of the to-be-archived project completion archive and the positioning code array of the to-be-archived project completion archive are obtained based on the retrieved project completion archive archiving model. Before obtaining the original archive description array of the to-be-archived project completion archive, the method further includes: Extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence and the positioning code array of the project completion archive debugging sequence; Determine the error result through the positioning description array of the project completion file debugging sequence to obtain the file description array distance error result of the project completion file debugging sequence; Determine the error result by using the positioning code array of the engineering completion file debugging sequence to obtain the code array distance error result and the code array error result of the engineering completion file debugging sequence; Merging at least two of the file description array distance error result, the code array distance error result, and the code array error result of the project completion file debugging sequence, and determining the error result obtained after the merger as the first error result corresponding to the project completion file archiving model; The project completion archive model is optimized by using a first error result corresponding to the project completion archive model.

3. The method according to claim 2, characterized in that The project completion file debugging sequence includes a reference debugging project completion file, a true value debugging project completion file, and a false value debugging project completion file, the matching score between the true value debugging project completion file and the reference debugging project completion file is greater than a first preset matching score, the matching score between the false value debugging project completion file and the reference debugging project completion file is less than a second preset matching score, and the first preset matching score is greater than the second preset matching score; The project completion archive filing model includes a common description array extraction unit, a positioning description array processing unit, and a positioning code array processing unit; The method of extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence and the positioning code array of the project completion archive debugging sequence includes: Based on the common description array extraction unit, common file description arrays are extracted from the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively, to obtain original file description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively; Based on the positioning code array processing unit, the original file description arrays of the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file are respectively subjected to numerical description array projection processing to obtain positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file respectively; Based on the positioning description array processing unit, description array projection processing is performed on the original file description arrays of the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file, respectively, to obtain the positioning description arrays corresponding to the reference debugging project completion file, the true value debugging project completion file and the false value debugging project completion file, respectively.

4. The method according to claim 3, characterized in that The error result is determined by using the positioning description array of the project completion file debugging sequence to obtain the file description array distance error result of the project completion file debugging sequence, including: Determine a first positioning description array difference between the positioning description array of the reference debugging project completion file and the positioning description array of the true value debugging project completion file, and simultaneously determine a second positioning description array difference between the positioning description array of the reference debugging project completion file and the positioning description array of the false value debugging project completion file; Obtaining a first addition result of the first positioning description array difference and a first preset error result, and simultaneously determining a first subtraction result between the first addition result and the second positioning description array difference; If the first subtraction result is greater than 0, determining the first subtraction result as the file description array distance error result; If the first subtraction result is less than or equal to 0, the file description array distance error result is determined to be 0.

5. The method according to claim 3, characterized in that The error result is determined by using the positioning code array of the engineering completion file debugging sequence to obtain the code array distance error result of the engineering completion file debugging sequence, including: Obtaining a first positioning description array difference between the positioning code array of the reference debugging project completion file and the positioning code array of the true value debugging project completion file, and simultaneously determining a second positioning description array difference between the positioning code array of the reference debugging project completion file and the positioning code array of the false value debugging project completion file; Determine a second addition result of the first location description array difference and a second preset error result, and simultaneously determine a second subtraction result between the second addition result and the second location description array difference; If the second subtraction result is greater than 0, determining the second subtraction result as the code array distance error result; If the second subtraction result is less than or equal to 0, a value of 0 is determined as the code array distance error result.

6. The method according to claim 3, characterized in that Determining the error result by using the positioning code array of the engineering completion file debugging sequence to obtain the code array error result of the engineering completion file debugging sequence includes: Performing optimization and standardization processing on the positioning code arrays corresponding to the reference debugging project completion file, the true value debugging project completion file, and the false value debugging project completion file, respectively, to obtain an optimized value corresponding to each element in each positioning code array; Determine a subtraction result between each element in each positioning code array and the corresponding optimized value; The subtraction results corresponding to each of the elements are summed to obtain the code array error result of the engineering completion file debugging sequence.

7. The method according to claim 3, characterized in that Optimizing the project completion archive model by using the first error result corresponding to the project completion archive model includes: If the first error result is obtained through the archive description array distance error result, the code array distance error result, and the code array error result, optimizing the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit through the first error result; or optimizing the parameters of the positioning code array processing unit and the parameters of the positioning description array processing unit based on the first error result; If the first error result is obtained through the code array distance error result and the code array error result, the parameter of the positioning code array processing unit is optimized according to the first error result.

8. The method according to claim 1, characterized in that The project completion archive archiving model is retrieved based on the positioning description array of the project completion archive to be archived and the positioning code array of the project completion archive to be archived. The project completion archive archiving model includes a common description array extraction unit, a positioning code array processing unit, and a positioning description array processing unit. Before obtaining the original archive description array of the project completion archive to be archived, the method further includes: Optimizing the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit until the second error result corresponding to the project completion archive filing model meets the preset change requirements; Optimizing the parameters of the common description array extraction unit, the parameters of the positioning code array processing unit, and the parameters of the positioning description array processing unit until a third error result corresponding to the project completion archive archiving model meets the preset change requirement; The optimizing the parameters of the common description array extraction unit and the parameters of the positioning description array processing unit includes: Extracting the archive description array of the project completion archive debugging sequence based on the project completion archive archiving model to obtain the positioning description array of the project completion archive debugging sequence; Determining an error result through the positioning description array of the project completion file debugging sequence to obtain a distance error result of the file description array of the project completion file debugging sequence, and determining the file description array distance error result as a second error result corresponding to the project completion file archiving model; The parameters of the common description array extraction unit and the parameters of the positioning description array processing unit are optimized by corresponding to the second error result of the project completion archive archiving model.

9. The method according to claim 1, characterized in that The method of performing similarity comparison on a plurality of candidate archived project completion files using the location description array of the to-be-archived project completion file and the first standardized array of the to-be-archived project completion file to obtain a candidate archived project completion file associated with the to-be-archived project completion file includes: Obtaining, through the second standardized arrays of the plurality of candidate archived project completion files, a correspondence between the second standardized arrays and the candidate archived project completion files, wherein each second standardized array corresponds to one or more candidate archived project completion files; Determine a search standardized array from a plurality of second standardized arrays using the first standardized array, and determine the candidate archived project completion file corresponding to the search standardized array as the selected project completion file; Obtaining a vector difference between the positioning description array of the candidate archived project completion file corresponding to the search standardization array and the positioning description array of the project completion file to be archived, and determining the candidate archived project completion file whose vector difference is greater than a preset vector difference as the selected project completion file; Before the step of obtaining the corresponding relationship between the second standardized array and the candidate archived project completion files, the method further includes: Determine the original file description array of the plurality of candidate archived project completion files; Performing code generation processing on the original file description arrays of the plurality of candidate archived project completion files to obtain positioning code arrays corresponding to the plurality of candidate archived project completion files; performing standardization processing on the positioning code arrays of the plurality of candidate archived project completion files to obtain a second standardized array of the positioning code arrays of the plurality of candidate archived project completion files; Before the step of obtaining the vector difference between the positioning description array of the candidate archived project completion file corresponding to the search standardization array and the positioning description array of the to-be-archived project completion file, the method further includes: The original file description arrays of the plurality of candidate archived project completion files are subjected to description array projection processing to obtain positioning description arrays of the plurality of candidate archived project completion files.

10. A project management cloud platform, characterized in that: It includes at least one memory and at least one processor; the memory stores a program, the processor is used to call the program stored in the memory, and the program is used to implement the artificial intelligence-based engineering completion file archiving method as described in any one of claims 1 to 9.

Images