Engineering work order auditing duplicate checking method and device, storage medium and program product

Abstract

The invention discloses an engineering work order auditing duplicate checking method and device, a storage medium and a program product, and the method comprises the following steps: obtaining to-be-audited engineering work order information, calculating the geographic position similarity, the engineering content similarity, the work order name similarity, the workload sheet similarity, the field photo similarity and the engineering drawing similarity of the to-be-audited engineering work order and each approved engineering work order; calculating the comprehensive similarity between the to-be-audited project work order and each approved project work order according to the geographic position similarity, the project content similarity, the work order name similarity, the workload table similarity, the field photo similarity and the project drawing similarity; and taking the approved project work order of which the comprehensive similarity is greater than a preset threshold as a project work order repeated with the project work order to be audited. The method is high in efficiency and high in accuracy.

Description

Technical Field

[0001] The present invention relates to engineering audit, and in particular to an audit and duplicate checking method, equipment, storage medium and program product for engineering work orders. Background Art

[0002] At present, engineering construction and maintenance often involve patchwork projects. For example, a telecommunications network operator has about 1,000 patchwork projects in a city in a year, and the number of patchwork projects in the province is as high as tens of thousands. The cost of a single patchwork project is not too high, generally between tens of thousands and hundreds of thousands of yuan, but calculated over the whole year, this cost is also very considerable. In order to avoid repeated calculation of related workload in daily patchwork projects, there is an urgent need for a means to distinguish repeated and false related workload or repeated reports to avoid repeated settlement.

[0003] At present, the audit of repeated false reports related to sporadic projects is mainly carried out by manual one-to-one comparison, which involves a lot of project-related data, and the number is large and complex. The workload of manual review is very large, the efficiency is low, and the accuracy is relatively low. Summary of the invention

[0004] In view of the problems existing in the prior art, the purpose of the present invention is to provide a method, equipment, storage medium and program product for auditing and checking duplicate works in engineering work orders with high efficiency and high accuracy.

[0005] An audit and duplicate checking method for an engineering work order comprises the following steps:

[0006] Obtaining the engineering work order information to be audited, the engineering work order information including the work order name, engineering content, geographic location, workload table, on-site photos and engineering drawings;

[0007] According to the geographical locations of the engineering work order to be audited and each approved engineering work order, the geographical location similarity between the engineering work order to be audited and each approved engineering work order is calculated;

[0008] According to the engineering contents of the engineering work order to be audited and each approved engineering work order, the similarity of the engineering contents of the engineering work order to be audited and each approved engineering work order is calculated by using the semantic recognition method;

[0009] According to the work order names of the engineering work order to be audited and each approved engineering work order, the similarity between the work order names of the engineering work order to be audited and each approved engineering work order is calculated by using a semantic recognition method;

[0010] According to the workload tables of the engineering work order to be audited and each approved engineering work order, calculate the similarity of the workload table names between the engineering work order to be audited and each approved engineering work order. If the similarity of the workload table names is greater than the similarity threshold of the measurement table names, calculate the workload ratio value between the engineering work order to be audited and each approved engineering work order as the workload table similarity.

[0011] According to the on-site photos of the engineering work order to be audited and each approved engineering work order, calculate the similarity of the on-site photos between the engineering work order to be audited and each approved engineering work order.

[0012] According to the engineering drawings of the engineering work order to be audited and each approved engineering work order, calculate the similarity of the engineering drawings between the engineering work order to be audited and each approved engineering work order.

[0013] Calculate the comprehensive similarity between the engineering work order to be audited and each approved engineering work order according to the following formula:

[0014]

[0015] In the formula, S represents the comprehensive similarity, k1, k2, k3, k4, k5 are weights, D1 is the geographical location similarity, A1 is the engineering content similarity, C2 is the workload table similarity, A2 is the work order name similarity, F1 is the on-site photo similarity, F2 is the engineering drawing similarity, C1 is the workload table name similarity, and R is the similarity threshold of the measurement table.

[0016] Take the approved engineering work orders with a comprehensive similarity greater than the preset threshold as the engineering work orders that are duplicates of the engineering work order to be audited.

[0017] Further, the calculation method of the geographical location similarity specifically includes:

[0018] Calculate the distance difference between the geographical locations of the engineering work order to be audited and the approved engineering work order.

[0019] According to the distance difference, calculate the geographical location similarity according to the following formula:

[0020]

[0021] In the formula, D1 represents the geographical location similarity, x represents the distance difference, represents rounding down, with the unit of meter.

[0022] Further, the calculation method of the engineering content similarity specifically includes:

[0023] Divide the description texts in the engineering content of the engineering work order to be audited and the approved engineering work order into several words respectively to obtain the word sets of each engineering work order.

[0024] Create a whitelist database for storing whitelist words without semantics.

[0025] Delete the whitelist words in the whitelist database from the word sets of the engineering work order to be audited and the approved engineering work order.

[0026] Convert the word sets of the engineering work order to be audited and the approved engineering work order into vector forms to obtain the word frequency vectors of the engineering work order to be audited and each approved engineering work order.

[0027] Calculate the cosine value of the included angle between the word frequency vectors of the engineering work order to be audited and the approved engineering work order as the similarity of the engineering content. Among them, if the cosine value of the included angle is 1, it means exactly the same; 0 means no relationship; -1 means exactly the opposite.

[0028] Furthermore, the calculation method of the work order name similarity and the calculation method of the workload form name similarity are the same as the calculation method of the engineering content similarity.

[0029] Furthermore, the workload ratio value is specifically the ratio value of the total workloads in the two workload forms.

[0030] Furthermore, the calculation method of the on-site photo similarity specifically includes:

[0031] Perform grayscale processing on the on-site photos of the engineering work order to be audited and the approved engineering work order respectively.

[0032] Use the ORB algorithm to extract several key point feature descriptors from the grayscale on-site photos of the engineering work order to be audited and the approved engineering work order.

[0033] Use a brute-force matcher to match each key point feature descriptor of the engineering work order to be audited and the approved engineering work order to obtain the matching result.

[0034] According to the matching result of the brute-force matcher, calculate the coincidence ratio of the matching result as the on-site photo similarity.

[0035] Furthermore, the calculation method of the engineering drawing similarity is the same as the calculation method of the on-site photo similarity.

[0036] A computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the above method.

[0037] A computer-readable storage medium stores a computer program / instructions, and the computer program / instructions implement the above method when executed by a processor.

[0038] A computer program product, comprising a computer program / instructions, characterized in that when the computer program / instructions are executed by a processor, the above method is implemented.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can be automatically audited and checked for duplication by a computer, with high efficiency and high accuracy, and is not prone to errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of the method for auditing and checking for duplication of engineering work orders provided by an embodiment of the present invention;

[0041] Figure 2 It is a schematic flow chart of the method for calculating the geographical location similarity provided by an embodiment of the present invention;

[0042] Figure 3 It is a schematic flow chart of the method for calculating the similarity of work schedules provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0044] Embodiment 1

[0045] The embodiment of the present invention provides a method for auditing and checking for duplication of engineering work orders, as Figure 1 shown, including the following steps:

[0046] S101. Obtain the information of the engineering work order to be audited.

[0047] Among them, the engineering work order information includes the work order name, engineering content, geographical location, work schedule, on-site photos, and engineering drawings. The engineering content is specifically the description of the construction content, materials used, etc. The geographical location is specifically the longitude and latitude of the work order construction location. The work schedule is mainly the workload of the construction. The on-site photos are the photos of the construction site. The engineering drawings are the planning drawings before the engineering construction.

[0048] S102. Calculate the geographical location similarity between the engineering work order to be audited and each approved engineering work order according to the geographical locations of the engineering work order to be audited and each approved engineering work order.

[0049] Among them, as Figure 2 shown, the specific calculation method of the geographical location similarity includes:

[0050] Calculate the distance difference x between the geographical locations of the engineering work order to be audited and the approved engineering work order; according to the distance difference x, calculate the geographical location similarity according to the following formula:

[0051]

[0052] In the formula, D1 represents the geographical location similarity, and x represents the distance difference, with the unit of meter.

[0053] In the calculation of the geographical location similarity, it is set that the similarity is 100% within the range where the distance difference before and after is 0 - 20m. For every subsequent 20m difference, the coefficient decreases by 1%. If the difference distance is greater than 2km, the value is zero.

[0054] S103. According to the project content of the work order to be audited and each approved work order, through the semantic recognition method, calculate the project content similarity between the work order to be audited and each approved work order.

[0055] Among them, the calculation method of the project content similarity specifically includes:

[0056] Divide the description texts in the project content of the work order to be audited and the approved work order into several words respectively to obtain the word set of each work order.

[0057] Establish a whitelist database for storing whitelist words without semantics, such as high-frequency words like place names, facility names, quantifiers, and other words without semantics.

[0058] Delete the whitelist words in the whitelist database from the word sets of the work order to be audited and the approved work order, so as to eliminate interference and increase the accuracy of calculation.

[0059] Convert the word sets of the work order to be audited and the approved work order into vector forms to obtain the word frequency vectors of the work order to be audited and each approved work order.

[0060] Calculate the cosine value of the included angle between the word frequency vectors of the work order to be audited and the approved work order as the project content similarity. Among them, if the cosine value of the included angle is 1, it means exactly the same; 0 means no relationship; -1 means exactly the opposite.

[0061] S104. According to the work order names of the work order to be audited and each approved work order, through the semantic recognition method, calculate the work order name similarity between the work order to be audited and each approved work order.

[0062] Among them, the work order name similarity is calculated using the same method as the calculation method of the project content similarity, which will not be elaborated here.

[0063] S105. Calculate the similarity of the work order name between the work order to be audited and each approved work order according to the work order of the project to be audited and the workload table of each approved work order. If the similarity of the work order name is greater than the threshold of the similarity of the measurement table name, calculate the workload ratio value between the work order to be audited and each approved work order as the similarity of the workload table.

[0064] Among them, the similarity of the work order name is calculated by the same method as the calculation method of the similarity of the project content. As Figure 3 shown, after calculating the similarity of the work order name, if the similarity of the work order name is less than or equal to the threshold of the similarity of the measurement table name, which is 50%, the workload ratio value will not be included in the result. If it is greater than 50%, calculate the workload ratio value, and the workload ratio value is specifically the ratio value of the total workload in the two workload tables as the similarity of the workload table.

[0065] S106. Calculate the similarity of the on-site photos between the work order to be audited and each approved work order according to the on-site photos of the work order to be audited and each approved work order.

[0066] Among them, the calculation method of the similarity of the on-site photos specifically includes:

[0067] Perform grayscale processing on the on-site photos of the work order to be audited and the approved work order respectively;

[0068] Use the ORB algorithm to extract several key point feature descriptors from the grayscale on-site photos of the work order to be audited and the approved work order;

[0069] Use a brute-force matcher to match each key point feature descriptor of the work order to be audited and the approved work order to obtain a matching result;

[0070] According to the matching result of the brute-force matcher, calculate the coincidence ratio of the matching result as the similarity of the on-site photos.

[0071] S107. Calculate the similarity of the engineering drawings between the work order to be audited and each approved work order according to the engineering drawings of the work order to be audited and each approved work order.

[0072] Among them, the calculation method of the similarity of the engineering drawings is the same as the calculation method of the similarity of the on-site photos.

[0073] S108. Calculate the comprehensive similarity between the work order to be audited and each approved work order according to the following formula:

[0074]

[0075] Wherein, S represents the comprehensive similarity, k1, k2, k3, k4, and k5 are weights, D1 is the geographical location similarity, A1 is the engineering content similarity, C2 is the work scale similarity, A2 is the work order name similarity, F1 is the on-site photo similarity, F2 is the engineering drawing similarity, C1 is the work scale name similarity, and R is the similarity threshold of the scale name, specifically 50%.

[0076] S109. Use the approved engineering work orders with a comprehensive similarity greater than the preset threshold as the engineering work orders that are duplicates of the work orders to be audited.

[0077] The present invention can automatically extract the engineering work orders for repeated audits with high accuracy and high efficiency.

[0078] Embodiment 2

[0079] The embodiment of the present invention provides a computer device, and the embodiment of the present invention provides services for the implementation of the method in the above-mentioned Embodiment 1 of the present invention. The device may include: a memory storing computer-executable programs; a processor coupled to the memory 301; the processor calls the computer-executable programs stored in the memory for executing the steps in the method described in Embodiment 1.

[0080] The memory may include a computer system-readable medium in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as "hard disk drives"). Programs / utilities with a set of (at least one) program modules may be stored in, for example, the memory, and such program modules include but are not limited to an operating system, one or more application programs, other program modules, and program data. The implementation of the network environment may be included in each or some combination of these examples. The computer-executable programs of the program modules generally execute the functions and / or methods in the embodiments described in the present invention.

[0081] The processor executes various functional applications and data processing by running the programs stored in the memory, such as implementing the method provided in Embodiment 1 of the present invention.

[0082] The code of the computer-executable programs may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages.

[0083] Embodiment 3

[0084] An embodiment of the present invention provides a storage medium containing computer-executable programs, and the computer-executable programs are used to execute the method of Embodiment 1 when executed by a computer processor.

[0085] The storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0086] Of course, for the storage medium containing computer-executable programs provided by the embodiment of the present invention, its computer-executable programs are not limited to the above method operations, and can also execute relevant operations in the methods provided by any embodiment of the present invention.

[0087] Embodiment 4

[0088] The embodiment of the present invention also provides a computer product, such as an app on a mobile phone or a tablet, an installation program on a computer, etc. The product includes computer programs / instructions, and the computer programs / instructions implement the method described in Embodiment 1 when executed by a processor. The code of the computer-executable program for executing the operations of the present invention can be written in one or more programming languages or a combination thereof. The programming languages include object-oriented programming languages, such as Java, Smalltalk, C++, and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0089] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0090] It should be understood that the above embodiments and the description in the specification are only the principles, main features and advantages of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the protection scope of the present invention.

Claims

1. A method for auditing and checking duplicate work orders, characterized in that: The steps include: Obtaining the engineering work order information to be audited, the engineering work order information including the work order name, engineering content, geographic location, workload table, on-site photos and engineering drawings; According to the geographical locations of the engineering work order to be audited and each approved engineering work order, the geographical location similarity between the engineering work order to be audited and each approved engineering work order is calculated; According to the engineering contents of the engineering work order to be audited and each approved engineering work order, the similarity of the engineering contents of the engineering work order to be audited and each approved engineering work order is calculated by using the semantic recognition method; According to the work order names of the engineering work order to be audited and each approved engineering work order, the similarity between the work order names of the engineering work order to be audited and each approved engineering work order is calculated by using a semantic recognition method; According to the workload tables of the engineering work order to be audited and each approved engineering work order, the similarity of the workload table names of the engineering work order to be audited and each approved engineering work order is calculated. If the workload table name similarity is greater than the table name similarity threshold, the workload ratio value of the engineering work order to be audited and each approved engineering work order is calculated as the workload table similarity; Based on the on-site photos of the engineering work order to be audited and each approved engineering work order, the similarity between the on-site photos of the engineering work order to be audited and each approved engineering work order is calculated; Based on the engineering drawings of the engineering work order to be audited and each approved engineering work order, the similarity between the engineering work order to be audited and each approved engineering work order is calculated; The comprehensive similarity between the engineering work order to be audited and each approved engineering work order is calculated according to the following formula: In the formula, S represents the comprehensive similarity, k1, k2, k3, k4, and k5 are weights, D1 is the geographical location similarity, A1 is the engineering content similarity, C2 is the work scale similarity, A2 is the work order name similarity, F1 is the site photo similarity, F2 is the engineering drawing similarity, C1 is the work scale name similarity, and R is the scale name similarity threshold; Approved engineering work orders with a comprehensive similarity greater than a preset threshold are regarded as engineering work orders that are duplicates of the engineering work orders to be audited.

2. The method for auditing and checking duplicate work orders according to claim 1, characterized in that: The method for calculating the geographical location similarity specifically includes: Calculate the distance difference between the geographical locations of the engineering work orders to be audited and the approved engineering work orders; Based on the distance difference, the geographic location similarity is calculated according to the following formula: In the formula, D1 represents the geographical location similarity, x represents the distance difference, Indicates rounding down, the unit is meter.

3. The method for auditing and checking duplicate works in engineering work orders according to claim 1, characterized in that: The method for calculating the engineering content similarity specifically includes: The description texts in the engineering contents of the engineering work orders to be audited and the approved engineering work orders are divided into a number of words respectively, and a word set of each engineering work order is obtained; Establish a whitelist database to store semantically meaningless whitelist words; Delete the whitelist words in the whitelist database from the word sets of the engineering work orders to be audited and the approved engineering work orders; The word sets of the engineering work orders to be audited and the approved engineering work orders are converted into vector form to obtain the word frequency vectors of the engineering work orders to be audited and each approved engineering work order; The cosine value of the angle between the word frequency vectors of the engineering work order to be audited and the approved engineering work order is calculated as the engineering content similarity. If the cosine value of the angle is 1, it means they are exactly the same, 0 means there is no relationship, and -1 means they are completely opposite.

4. The method for auditing and checking duplicate works in engineering work orders according to claim 3, characterized in that: The work order name similarity and the workload table name similarity are calculated using the same method as the project content similarity calculation method.

5. The method for auditing and checking duplicate work orders according to claim 1, characterized in that: The workload ratio value is specifically a ratio value of the total workload in the two workload tables.

6. The method for auditing and checking duplicate works in engineering work orders according to claim 1, characterized in that: The method for calculating the similarity of the on-site photos specifically includes: Grayscale the on-site photos of the engineering work orders to be audited and the approved engineering work orders respectively; The ORB algorithm is used to extract several key point feature descriptors from the grayscale on-site photos of the engineering work orders to be audited and the approved engineering work orders; Use a brute force matcher to match each key feature descriptor of the audited engineering work order with the approved engineering work order to obtain a matching result; According to the matching results of the brute force matcher, the overlap ratio of the matching results is calculated as the similarity of the scene photos.

7. The method for auditing and checking duplicate works in engineering work orders according to claim 6, characterized in that: The method for calculating the similarity of the engineering drawings is the same as the method for calculating the similarity of the on-site photos.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the computer program to implement the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: The computer program / instructions, when executed by a processor, implement the method of any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images