Methods, devices, equipment, and media for identifying duplicate instructions issued in engineering projects.

Abstract

This invention relates to the field of application development technology and provides a method for identifying duplicate change orders in engineering projects. First, engineering information is correlated and integrated to obtain an intermediate dataset with a logical order of project implementation. Text extraction and data cleaning are then performed on the intermediate dataset to form change order text data. Next, the change order text data are paired based on instruction keywords to form an instruction control group. Then, a dual-thread similarity framework is used to calculate the similarity between two change order text data in the instruction control group to obtain first and second similarity data. If the first and second similarity data meet the duplication condition, the instruction control group is considered as a duplicate change order. In this way, duplicate change orders can be automatically identified, allowing for timely detection of problems and mitigation of company losses.

Description

Technical Field

[0001] This invention relates to the field of engineering management technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for identifying repeatedly issued instructions in engineering projects. Background Technology

[0002] Project management is one of the core businesses of construction companies. During the project management process, the owner communicates adjustments to the project scope, changes in construction content, or replacement of construction materials by issuing project instructions. The issuance of project instructions affects the settlement amount and project cost. In this process, there is room and motivation for relevant personnel of the owner and the construction unit to collude to create false changes and repeatedly issue change instructions to obtain benefits, thereby harming the interests of the owner and needlessly increasing project costs.

[0003] In traditional engineering audits, audit experts in the engineering industry use their professional experience to extract high-risk samples and manually review processes such as the issuance of engineering instructions, execution of change orders, and payment of engineering funds. Due to the large sample size, this method carries a high sampling risk, which, combined with the high error rate of manual review, results in a high level of audit risk.

[0004] Currently, by managing engineering instructions through information systems, a relatively comprehensive and reliable data foundation has been formed.

[0005] Therefore, there is an urgent need for an information management system that can be integrated with existing engineering management systems to automatically identify whether duplicate instructions have been issued, thereby achieving a comprehensive and accurate automated monitoring system for engineering instructions and a method for regularly issuing warnings about high-risk data containing errors or fraud risks in engineering projects that have been issued duplicate instructions. Summary of the Invention

[0006] This invention provides a method for identifying duplicate instructions issued in engineering projects. This addresses the problem in traditional engineering audits where audit experts rely on their professional experience to extract high-risk samples and manually review processes such as instruction issuance, change order execution, and payment of project funds. Due to the large sample size, this method carries high sampling risk, which, combined with the high error rate of manual review, results in a high level of overall audit risk.

[0007] To achieve the above objectives, the present invention provides a method for identifying repeatedly issued instructions in engineering projects, comprising:

[0008] The project information of each sub-project in the overall project is obtained through a pre-set information management program;

[0009] The project information is associated and integrated using a preset data association component to obtain an intermediate dataset with a logical order of project implementation. The intermediate dataset is then subjected to text extraction and data cleaning to form change instruction text data.

[0010] Based on preset keyword extraction rules, the command keywords of the change command text data are extracted, and the change command text data are combined in pairs according to the command keywords to form a command control group.

[0011] The two change instruction text data in the instruction control group are calculated using a pre-trained dual-thread similarity framework to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0012] Optionally, the project information includes the project name, contract information, change order information, and settlement information of the project sub-project.

[0013] Optionally, the step of obtaining project information for each sub-project within the overall project through a preset information management program includes:

[0014] Obtain the project name, retrieve the data packet of the sub-project with the project name from the database of the preset online project management system, and retrieve the change instruction information of the sub-project with the project name from each node in the online project management system.

[0015] At least the contract information and settlement information corresponding to the name of the project should be extracted from the data packet.

[0016] Optionally, the step of extracting text and cleaning data from the intermediate dataset to form change instruction text data includes:

[0017] The intermediate dataset is extracted using a preset text extraction plugin to convert the fields in the intermediate dataset into text and numeric data, and the text and numeric data is used as the dataset to be cleaned.

[0018] The dataset to be cleaned is cleaned by a preset data cleaning component according to preset data cleaning conditions, so as to retain only the data before the instruction change, the data after the instruction change, and the data after the instruction change, and the data before the instruction change, the data after the instruction change, and the data after the instruction change are used as the change instruction text.

[0019] Optionally, the step of extracting instruction keywords from the change instruction text data based on preset keyword extraction rules, and combining the change instruction text data in pairs according to the instruction keywords to form an instruction control group, includes:

[0020] Based on preset keyword extraction rules, extract instruction keywords related to instruction characteristics from the change instruction text data;

[0021] If any two change instruction text data contain the same instruction keyword, then the two change instruction text data with the same instruction keyword are combined in pairs to form an instruction control group; otherwise, the two change instruction text data with the same category of instruction keyword are combined in pairs to form an instruction control group.

[0022] Optionally, the dual-threaded similarity framework includes a text similarity calculation thread and a TF-IDF algorithm thread; wherein, the dual-threaded similarity calculation of two change instruction text data in the instruction control group using the pre-trained dual-threaded similarity framework to obtain first similarity data and second similarity data, and if the first similarity data and the second similarity data satisfy the duplication condition, then the instruction control group is used as a duplicate change instruction, including:

[0023] The text similarity calculation thread calculates the similarity between two change instruction text data in the instruction control group to obtain first similarity data; simultaneously, the TF-IDF algorithm thread calculates the similarity between the two change instruction text data in the instruction control group to obtain second similarity data; wherein...

[0024] If the first similarity data is higher than a preset first threshold and the second similarity data is higher than a preset second threshold, then the instruction control group will be used as a repeatedly issued change instruction.

[0025] Optionally, the step of calculating the similarity between two change instruction text data in the instruction control group through a text similarity calculation thread to obtain first similarity data includes:

[0026] The word segmentation unit in the text similarity calculation thread segments the two change instruction text data in the instruction control group into two sets of word sequences, and vectorizes the two sets of word sequences to generate two sets of word vectors corresponding to the word sequences.

[0027] The word vector of each word is encoded at the word level by the encoding unit in the text similarity calculation thread to obtain the first encoding information and the second encoding information of the two word sequences respectively;

[0028] The attention units in the text similarity calculation thread perform regularization processing on the first encoded information and the second encoded information respectively to obtain the first weight and the second weight, and then assign the first weight and the second weight to obtain the first attention vector and the second attention vector respectively.

[0029] The attention unit in the text similarity calculation thread calculates the similarity probability of two change instruction text data in the control group based on the first attention vector and the second attention vector, and uses the similarity probability as the first similarity data.

[0030] To address the aforementioned problems, the present invention also provides a device for identifying repeatedly issued instructions in engineering projects, the device comprising:

[0031] The project information acquisition module is used to acquire project information of various sub-projects in the overall project through a preset information management program.

[0032] The text generation module is used to associate and integrate the engineering information through a preset data association component to obtain an intermediate dataset with a logical order of engineering implementation, and to extract text and clean the intermediate dataset to form change instruction text data.

[0033] The instruction comparison module is used to extract instruction keywords from the change instruction text data based on preset keyword extraction rules, and to combine the change instruction text data in pairs according to the instruction keywords to form an instruction control group.

[0034] A dual-thread similarity framework is used to perform dual-thread similarity calculation on two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0035] To address the above problems, the present invention also provides an electronic device, characterized in that the electronic device comprises:

[0036] At least one processor; and,

[0037] A memory communicatively connected to the at least one processor; wherein,

[0038] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the steps in the identification method for repeatedly issuing instructions for engineering projects as described above.

[0039] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the method for identifying repeatedly issued instructions for engineering projects as described above.

[0040] This invention first acquires project information for each sub-project within the overall project using a pre-set information management program, and then generates change order text data based on this information. This facilitates subsequent determination of whether two highly similar orders exist, and identifies these two highly similar orders as duplicate orders. Specifically, during the similarity determination, the change order text data first acquires the order keywords, and then performs pairwise pairwise combinations based on these keywords to form an order control group. Further, a pre-trained dual-thread similarity framework is used to further analyze the two change order text data in the order control group. A dual-threaded similarity calculation is performed to obtain first and second similarity data. Further, based on these two data, it is determined whether the duplicate conditions are met. If the duplicate conditions are met, the instruction control group is considered as a duplicate change instruction. Thus, through preliminary and further similarity assessments, duplicate change instructions can be automatically identified in a timely manner. Business experts can then compare the abnormal data involving duplicate instructions to evaluate and inspect the engineering instruction issuance, change order execution, and engineering payment processes. This allows for a more comprehensive and rapid audit of the engineering project change procedures, enabling timely detection of problems and mitigation of company losses. Attached Figure Description

[0041] Figure 1 A flowchart illustrating a method for identifying repeatedly issued instructions in an engineering project, as provided in an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a module for identifying repeatedly issued instructions in an engineering project, provided in an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the internal structure of an electronic device for a method of identifying repeatedly issued instructions in an engineering project, as provided in an embodiment of the present invention.

[0044] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0046] In traditional engineering audits, audit experts in the engineering industry use their professional experience to extract high-risk samples and manually review processes such as the issuance of engineering instructions, execution of change orders, and payment of engineering funds. Due to the large sample size, this method carries a high sampling risk, which, combined with the high error rate of manual review, results in a high level of audit risk.

[0047] To address the aforementioned problems, this invention provides a method for identifying repeatedly issued instructions in engineering projects.

[0048] like Figure 1 As shown, in this embodiment, the method for identifying repeatedly issued instructions in an engineering project includes:

[0049] S1: Obtain engineering information for each sub-project in the overall project through a pre-set information management program;

[0050] S2: The engineering information is associated and integrated through a preset data association component to obtain an intermediate dataset with a logical order of engineering implementation, and the intermediate dataset is subjected to text extraction and data cleaning to form change instruction text data.

[0051] S3: Extract instruction keywords from the change instruction text data based on preset keyword extraction rules, and combine the change instruction text data in pairs according to the instruction keywords to form an instruction control group;

[0052] S4: The two change instruction text data in the instruction control group are calculated using a pre-trained dual-thread similarity framework to obtain the first similarity data and the second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0053] exist Figure 1 In the embodiment shown, step S1 is the process of obtaining engineering information of each engineering sub-project in the overall project through a preset information management program. In this process, the engineering information includes the engineering project name, contract information, change instruction information and settlement information of the engineering sub-project.

[0054] Specifically, in this embodiment, engineering information for each sub-project in the overall project is obtained through a preset information management program, including:

[0055] Obtain the project name, retrieve the data packet of the sub-project with the project name from the database of the preset online project management system, and retrieve the change instruction information of the sub-project with the project name from each node in the online project management system.

[0056] At least the contract information and settlement information corresponding to the name of the project should be extracted from the data packet.

[0057] More specifically, in this embodiment, based on the degree of online management of engineering projects, the information on type I and type II instruction change details can be directly extracted from the database of the online management system for engineering projects. This includes engineering projects, contract information, change instruction information, settlement information, etc.

[0058] exist Figure 1 In the embodiment shown, step S2 is the process of associating and integrating the engineering information through a preset data association component to obtain an intermediate dataset with an engineering implementation logical order, and extracting text and cleaning the intermediate dataset to form change instruction text data.

[0059] In this process, after acquiring information such as project details, contract information, change order information, and settlement information, the original dataset can be linked and integrated to generate an intermediate dataset based on business logic settings. Rules are extracted using expert experience, textual information is cleaned according to rules, and the intermediate dataset is filtered based on conditions. Paired change order combinations are generated through certain pairing conditions to form the final change order text data. The process of linking and integrating project information in step S2 is not specifically limited; it involves organizing all process information related to the project sub-projects into a sequentially ordered intermediate dataset (fields). Then, text extraction and data cleaning are performed on this intermediate dataset to form the change order text data. The specific data cleaning method is not specifically limited; in this embodiment, it involves removing unclear statements or words and retaining only valid information about the change orders for the project sub-project, such as the data preceding the change order, the change order data, and the data following the change order.

[0060] Specifically, text extraction and data cleaning are performed on the intermediate dataset to form change instruction text data, including:

[0061] S21: The intermediate dataset is extracted using a preset text extraction plugin to convert the fields in the intermediate dataset into text and numeric data, and the text and numeric data is used as the dataset to be cleaned.

[0062] S22: The dataset to be cleaned is cleaned by a preset data cleaning component according to preset data cleaning conditions to retain only the data before the instruction change, the data after the instruction change, and the data after the instruction change, and the data before the instruction change, the data after the instruction change, and the data after the instruction change are used as the change instruction text.

[0063] This will allow you to obtain all relevant information about the project sub-projects related to the change orders.

[0064] In this embodiment, step S3 involves extracting instruction keywords from the change instruction text data based on preset keyword extraction rules, and then combining the change instruction text data in pairs according to the instruction keywords to form an instruction control group; in step S3,

[0065] Based on preset keyword extraction rules, instruction keywords are extracted from the change instruction text data. Then, the change instruction text data is paired according to these keywords to form instruction control groups, including:

[0066] S31: Extract instruction keywords related to instruction characteristics from the change instruction text data based on preset keyword extraction rules;

[0067] S32: Iterate through the change instruction text data to see if there are two change instruction text data containing the same instruction keyword. If so, combine the two change instruction text data with the same instruction keyword in pairs as an instruction control group; if not, combine the two change instruction text data with the same type of instruction keyword in pairs as an instruction control group.

[0068] In this embodiment, step S31 is the process of obtaining instruction keywords. The keyword extraction rule is to automatically extract keywords from the statement through a preset keyword extraction model, such as keywords related to instruction changes, such as "signing", "construction", and "cost".

[0069] Step S32 involves pairwise combination of two similar change instruction text data. First, it is necessary to iterate through the change instruction text data to see if there are two change instruction text data containing the same instruction keyword. If so, the two change instruction texts are extremely similar, and the two change instruction text data with the same instruction keyword are combined as instruction control group. If not, the two change instruction text data with the same category of instruction keywords are combined as instruction control group. This category can be that the two change instruction texts have instruction keywords that are synonyms of each other. In this way, two similar change instruction texts can be found even if it is only a second choice.

[0070] Step S4 involves using a pre-trained dual-thread similarity framework to perform dual-thread similarity calculations on the two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, then the instruction control group is used as a process for repeatedly issuing change instructions.

[0071] In step S4, the dual-threaded similarity framework includes a text similarity calculation thread and a TF-IDF algorithm thread; wherein, the dual-threaded similarity calculation of two change instruction text data in the instruction control group is performed using the pre-trained dual-threaded similarity framework to obtain first similarity data and second similarity data, and if the first similarity data and the second similarity data meet the duplication condition, then the instruction control group is used as a duplicate change instruction, including:

[0072] S41: The text similarity calculation thread calculates the similarity between two change instruction text data in the instruction control group to obtain first similarity data; simultaneously, the TF-IDF algorithm thread calculates the similarity between two change instruction text data in the instruction control group to obtain second similarity data; wherein...

[0073] S42: If the first similarity data is higher than a preset first threshold and the second similarity data is higher than a preset second threshold, then the instruction control group is used as a repeated change instruction.

[0074] Step S41 involves simultaneously calculating the similarity of the change instruction text data using two threads to obtain first similarity data and second similarity data. In this embodiment, the text similarity calculation thread employs a text similarity algorithm. Specifically, the text similarity calculation thread calculates the similarity of the two change instruction text data in the instruction control group to obtain the first similarity data, including:

[0075] The word segmentation unit in the text similarity calculation thread segments the two change instruction text data in the instruction control group into two sets of word sequences, and vectorizes the two sets of word sequences to generate two sets of word vectors corresponding to the word sequences.

[0076] The word vector of each word is encoded at the word level by the encoding unit in the text similarity calculation thread to obtain the first encoding information and the second encoding information of the two word sequences respectively;

[0077] The attention unit in the text similarity calculation thread performs regularization processing on the first and second encoded information to obtain the first weight and the second weight, respectively, and assigns the first weight and the second weight to obtain the first attention vector and the second attention vector, respectively; the formula for obtaining the attention vector is s = ∑i*Hi, where s is the attention vector, i is the weight, and Hi is the encoded information.

[0078] The attention unit in the text similarity calculation thread calculates the similarity probability of two change instruction text data in the control group based on the first attention vector and the second attention vector, and uses the similarity probability as the first similarity data.

[0079] This TF-IDF algorithm thread calculates similarity using the TF-IDF algorithm, a statistical algorithm that uses a command keyword to evaluate the degree of similarity of the command text data. The importance of the command keyword increases with the frequency of its occurrence. Thus, a similarity parameter is obtained from two command text data, and this similarity parameter is used as the second similarity data. The more similar the two command text data are, the larger the value of the second similarity data.

[0080] Furthermore, this embodiment also includes a feedback optimization iteration process. Specifically, after the instruction control group is used as a duplicate change instruction, the relevant data of the reread change instruction is pushed to the internal control auditors to make them issue a duplicate instruction change warning. The internal control auditors then process the results and summarize the rules for the valid and invalid cases to adjust the first or second threshold. For example, if too many non-duplicate change instructions are treated as duplicate change instructions, the first or second threshold is appropriately increased. If there are few duplicate change instructions, the first or second threshold is appropriately decreased to make the determination of duplicate change instructions more accurate.

[0081] In this embodiment, the server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0082] As described above, the method for identifying duplicate engineering project instructions provided in this embodiment of the invention first obtains engineering information of various engineering sub-projects in the overall project through a preset information management program. Then, the engineering information is correlated and integrated to obtain an intermediate dataset with an engineering implementation logical order. The intermediate dataset is then subjected to text extraction and data cleaning to form change instruction text data. Next, the instruction keywords of the change instruction text data are extracted, and the change instruction text data are paired according to the instruction keywords to form an instruction control group. Then, a pre-trained dual-thread similarity framework is used to perform dual-thread similarity calculation on the two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is regarded as a duplicate change instruction. In this way, duplicate change instructions can be automatically identified in a timely manner. Business experts can evaluate and check the engineering instruction issuance, change order execution, and engineering payment links involved by comparing the abnormal data of duplicate instructions. This allows for a more comprehensive and rapid audit of the engineering project change process, timely detection of problems, and mitigation of company losses.

[0083] like Figure 2 As shown, this invention provides a device 100 for identifying repeatedly issued instructions in engineering projects. This invention can be installed in an electronic device. Depending on the functions implemented, the device 100 may include an engineering information acquisition module 101, a text generation module 102, an instruction comparison module 103, and a dual-thread similarity framework 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0084] In this embodiment, the functions of each module / unit are as follows:

[0085] The project information acquisition module 101 is used to acquire project information of various sub-projects in the overall project through a preset information management program;

[0086] The text generation module 102 is used to associate and integrate the engineering information through a preset data association component to obtain an intermediate dataset with an engineering implementation logical order, and to extract text and clean the intermediate dataset to form change instruction text data.

[0087] The instruction comparison module 103 is used to extract instruction keywords from the change instruction text data based on preset keyword extraction rules, and to combine the change instruction text data in pairs according to the instruction keywords to form an instruction control group.

[0088] A dual-threaded similarity framework 104 is used to perform dual-threaded similarity calculation on two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0089] The project information acquisition module 101 acquires project information for each sub-project in the overall project through a preset information management program, including:

[0090] Obtain the project name, retrieve the data packet of the sub-project with the project name from the database of the preset online project management system, and retrieve the change instruction information of the sub-project with the project name from each node in the online project management system.

[0091] At least the contract information and settlement information corresponding to the name of the project should be extracted from the data packet.

[0092] The text generation module 102 integrates the engineering information through a preset data association component to obtain an intermediate dataset with a logical order of engineering implementation, and performs text extraction and data cleaning on the intermediate dataset to form change instruction text data, including:

[0093] The intermediate dataset is extracted using a preset text extraction plugin to convert the fields in the intermediate dataset into text and numeric data, and the text and numeric data is used as the dataset to be cleaned.

[0094] The dataset to be cleaned is cleaned by a preset data cleaning component according to preset data cleaning conditions, so as to retain only the data before the instruction change, the data after the instruction change, and the data after the instruction change, and the data before the instruction change, the data after the instruction change, and the data after the instruction change are used as the change instruction text.

[0095] The instruction comparison module 103 extracts instruction keywords from the change instruction text data based on preset keyword extraction rules, and combines the change instruction text data in pairs according to the instruction keywords to form an instruction control group. The process includes:

[0096] Based on preset keyword extraction rules, extract instruction keywords related to instruction characteristics from the change instruction text data;

[0097] If any two change instruction text data contain the same instruction keyword, then the two change instruction text data with the same instruction keyword are combined in pairs to form an instruction control group; otherwise, the two change instruction text data with the same category of instruction keyword are combined in pairs to form an instruction control group.

[0098] The dual-threaded similarity framework 104 performs dual-threaded similarity calculations on the two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a process for repeatedly issuing change instructions, including:

[0099] The text similarity calculation thread calculates the similarity between two change instruction text data in the instruction control group to obtain first similarity data; simultaneously, the TF-IDF algorithm thread calculates the similarity between the two change instruction text data in the instruction control group to obtain second similarity data; wherein...

[0100] If the first similarity data is higher than a preset first threshold and the second similarity data is higher than a preset second threshold, then the instruction control group will be used as a repeatedly issued change instruction.

[0101] As described above, the method for identifying repeatedly issued instructions in engineering projects provided by the present invention first obtains engineering information of various sub-projects in the overall project through a preset information management program using the engineering information acquisition module 101. Then, the text generation module 102 integrates and correlates the engineering information to obtain an intermediate dataset with a logical order of project implementation. The intermediate dataset undergoes text extraction and data cleaning to form change instruction text data. Next, the instruction comparison module 103 extracts instruction keywords from the change instruction text data and combines the change instruction text data in pairs based on the instruction keywords to form instruction control groups. Finally, the method... The dual-thread similarity framework 104 performs dual-thread similarity calculations on the text data of two change instructions in the instruction control group to obtain the first similarity data and the second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is regarded as a duplicate change instruction. In this way, duplicate change instructions can be automatically identified in time. Business experts can evaluate and check the engineering instruction issuance, change order execution, engineering payment and other links involved by comparing the abnormal data of duplicate instructions. This allows for a more comprehensive and rapid audit of the engineering project change process, timely discovery of problems and mitigation of company losses.

[0102] like Figure 3 As shown, the present invention provides an electronic device 1 for identifying methods of repeatedly issuing instructions in engineering projects.

[0103] The electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as an identification program 12 for repeatedly issuing instructions for engineering projects.

[0104] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 can include both internal and external storage units of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as application development code for identifying repeatedly issued instructions in engineering projects, but also to temporarily store data that has been output or will be output.

[0105] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a program for identifying repeatedly issued instructions in an engineering project) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0106] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0107] Figure 3 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0108] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0109] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0110] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0111] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0112] The identification program 12 for repeatedly issuing engineering project instructions stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0113] The project information of each sub-project in the overall project is obtained through a pre-set information management program;

[0114] The project information is associated and integrated using a preset data association component to obtain an intermediate dataset with a logical order of project implementation. The intermediate dataset is then subjected to text extraction and data cleaning to form change instruction text data.

[0115] Based on preset keyword extraction rules, the command keywords of the change command text data are extracted, and the change command text data are combined in pairs according to the command keywords to form a command control group.

[0116] The two change instruction text data in the instruction control group are calculated using a pre-trained dual-thread similarity framework to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0117] It should be emphasized that, in order to further ensure the privacy and security of identifying repeated instructions for the aforementioned engineering projects, the data for identifying repeated instructions for the aforementioned engineering projects is stored in the nodes of the blockchain where this server cluster is located.

[0118] A server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0119] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0120] This invention also provides a computer-readable storage medium, which may be non-volatile or volatile, and stores a computer program that is implemented when executed by a processor:

[0121] The project information of each sub-project in the overall project is obtained through a pre-set information management program;

[0122] The project information is associated and integrated using a preset data association component to obtain an intermediate dataset with a logical order of project implementation. The intermediate dataset is then subjected to text extraction and data cleaning to form change instruction text data.

[0123] Based on preset keyword extraction rules, the command keywords of the change command text data are extracted, and the change command text data are combined in pairs according to the command keywords to form a command control group.

[0124] The two change instruction text data in the instruction control group are calculated using a pre-trained dual-thread similarity framework to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

[0125] Specifically, the specific implementation method when the computer program is executed by the processor can be referred to the description of the relevant steps in the embodiment of the identification method for repeatedly issuing instructions based on engineering projects, which will not be repeated here.

[0126] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0127] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0129] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0130] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0131] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0132] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The term "second class" is used to indicate names and does not indicate any specific order.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for identifying repeatedly issued instructions in an engineering project, characterized in that, include: The project information of each sub-project in the overall project is obtained through a pre-set information management program; The project information is associated and integrated using a preset data association component to obtain an intermediate dataset with a logical order of project implementation. The intermediate dataset is then subjected to text extraction and data cleaning to form change instruction text data. Based on preset keyword extraction rules, instruction keywords are extracted from the change instruction text data, and the change instruction text data are paired according to the instruction keywords to form an instruction control group; wherein, instruction keywords related to instruction characteristics are extracted from the change instruction text data based on preset keyword extraction rules. If there are two change instruction text data containing the same instruction keyword, then the two change instruction text data with the same instruction keyword are combined in pairs as an instruction control group; otherwise, the two change instruction text data with the same category of instruction keyword are combined in pairs as an instruction control group. The text data of two change instructions in the instruction control group are calculated using a pre-trained dual-thread similarity framework to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

2. The method for identifying repeatedly issued instructions in an engineering project as described in claim 1, characterized in that, The project information includes the project name, contract information, change order information, and settlement information of the project sub-projects.

3. The method for identifying repeatedly issued instructions in an engineering project as described in claim 2, characterized in that, The process of obtaining project information for each sub-project within the overall project through a pre-set information management program includes: Obtain the project name, retrieve the data packet of the sub-project with the project name from the database of the preset online project management system, and retrieve the change instruction information of the sub-project with the project name from each node in the online project management system. At least the contract information and settlement information corresponding to the name of the project should be extracted from the data packet.

4. The method for identifying repeatedly issued instructions in an engineering project as described in claim 3, characterized in that, The step of extracting text and cleaning data from the intermediate dataset to form change instruction text data includes: The intermediate dataset is extracted using a preset text extraction plugin to convert the fields in the intermediate dataset into text and numeric data, and the text and numeric data is used as the dataset to be cleaned. The dataset to be cleaned is cleaned by a preset data cleaning component according to preset data cleaning conditions, so as to retain only the data before the instruction change, the data after the instruction change, and the data after the instruction change, and the data before the instruction change, the data after the instruction change, and the data after the instruction change are used as the change instruction text.

5. The method for identifying repeatedly issued instructions in an engineering project as described in claim 4, characterized in that, The dual-threaded similarity framework includes a text similarity calculation thread and a TF-IDF algorithm thread; wherein, the dual-threaded similarity calculation of two change instruction text data in the instruction control group is performed using the pre-trained dual-threaded similarity framework to obtain first similarity data and second similarity data; if the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction, including: The text similarity calculation thread calculates the similarity between two change instruction text data in the instruction control group to obtain first similarity data; simultaneously, the TF-IDF algorithm thread calculates the similarity between two change instruction text data in the instruction control group to obtain second similarity data; wherein... If the first similarity data is higher than a preset first threshold and the second similarity data is higher than a preset second threshold, then the instruction control group will be used as a repeatedly issued change instruction.

6. The method for identifying repeatedly issued instructions in an engineering project as described in claim 5, characterized in that, The step of calculating the similarity between two change instruction text data in the instruction control group through a text similarity calculation thread to obtain first similarity data includes: The word segmentation unit in the text similarity calculation thread segments the two change instruction text data in the instruction control group into two sets of word sequences, and vectorizes the two sets of word sequences to generate two sets of word vectors corresponding to the word sequences. The word vector of each word is encoded at the word level by the encoding unit in the text similarity calculation thread to obtain the first encoding information and the second encoding information of the two word sequences respectively; The attention units in the text similarity calculation thread perform regularization processing on the first encoded information and the second encoded information respectively to obtain the first weight and the second weight, and then assign the first weight and the second weight to obtain the first attention vector and the second attention vector respectively. The attention unit in the text similarity calculation thread calculates the similarity probability of two change instruction text data in the control group based on the first attention vector and the second attention vector, and uses the similarity probability as the first similarity data.

7. A device for identifying repeatedly issued instructions in an engineering project, characterized in that, The device includes: The project information acquisition module is used to acquire project information of various sub-projects in the overall project through a preset information management program. The text generation module is used to associate and integrate the engineering information through a preset data association component to obtain an intermediate dataset with a logical order of engineering implementation, and to extract text and clean the intermediate dataset to form change instruction text data. The instruction comparison module is used to extract instruction keywords from the change instruction text data based on preset keyword extraction rules, and to combine the change instruction text data in pairs according to the instruction keywords to form an instruction control group; wherein, instruction keywords related to instruction characteristics are extracted from the change instruction text data based on preset keyword extraction rules. If there are two change instruction text data containing the same instruction keyword, then the two change instruction text data with the same instruction keyword are combined in pairs as an instruction control group; otherwise, the two change instruction text data with the same category of instruction keyword are combined in pairs as an instruction control group. A dual-thread similarity framework is used to perform dual-thread similarity calculation on two change instruction text data in the instruction control group to obtain first similarity data and second similarity data. If the first similarity data and the second similarity data meet the duplication condition, the instruction control group is used as a duplicate change instruction.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the steps in the identification method for repeatedly issuing instructions for engineering projects as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for identifying repeatedly issued instructions for engineering projects as described in any one of claims 1 to 6.

Images