Data processing method and device for engineering purchase management

Abstract

The invention discloses a data processing method and device for engineering purchase management. The method comprises the following steps: acquiring purchase-related application data sent by a user side; sending the purchase-related application data to a corresponding approval user side to generate approval data, and sending the approval data to a corresponding execution user side to obtain corresponding execution result data; obtaining a reconciliation request of a reconciliation user side for the target purchase project; and generating account checking result data based on a preset account checking algorithm combination model according to the input bill data and the bill attachment image which are sent by the account checking user side and aim at the target purchase item and the execution result data corresponding to the target purchase item. Therefore, the method can greatly improve the efficiency and effect of project purchase, reduces the error of the purchase account, and provides help for the smooth development of project purchase.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data processing method and device for engineering procurement management. Background Art

[0002] With the development of construction engineering technology, the types and quantities of materials required in the project have also increased significantly. The existing project management system is facing more and more complex procurement needs. Although the existing technology partially uses data processing technology to summarize the procurement data, it still relies on manual purchasers to fill in and operate to a large extent, and does not fully consider the automation advantages of the application approval process and the subsequent execution and data processing characteristics in the reconciliation process. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a data processing method and device for engineering procurement management, which can greatly improve the efficiency and effect of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a data processing method for engineering procurement management, the method comprising: Obtain purchase-related application data sent by the user; Sending the procurement-related application data to the corresponding approval user terminal to generate approval data, and sending the approval data to the corresponding execution user terminal to obtain corresponding execution result data; Obtain the reconciliation request for the target procurement project from the reconciliation user end; Reconciliation result data is generated based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item.

[0005] As an optional embodiment, in the first aspect of the present invention, the procurement-related application data includes at least one of material application data, planned procurement application data, actual procurement application data, transfer application data, leasing application data, warehousing application data, material collection application data, return application data and material return and lease return application data.

[0006] As an optional implementation, in the first aspect of the present invention, the execution result data includes at least one of procurement result data, transfer result data, leasing result data, material picking result data and inventory result data.

[0007] As an optional implementation, in the first aspect of the present invention, sending the procurement-related application data to the corresponding approval user terminal to generate approval data, sending the approval data to the corresponding execution user terminal to obtain corresponding execution result data, includes: Obtain the inventory approval instructions for the target procurement items input by the approval user; Generate inventory approval data according to the procurement-related application data corresponding to the target procurement item and preset inventory approval rules; Obtaining an inventory execution instruction for the target procurement item input by an execution user terminal; Acquire the actual inventory data and inventory attachments input by the executing user terminal; the inventory attachments include at least one of inventory text, inventory image, and inventory video; The inventory result data is generated according to the inventory approval data, the actual inventory data and the inventory attachments, and the preset inventory execution rules.

[0008] As an optional implementation, in the first aspect of the present invention, generating reconciliation result data based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item includes: Acquire the input bill data for the target procurement item sent by the reconciliation user terminal; Acquire the document attachment image for the target procurement item sent by the reconciliation user terminal, and generate document attachment image data according to a preset data processing rule; Input the document attachment image data into a trained classification neural network model to obtain a validity judgment result; the validity judgment result is valid or invalid; if the validity judgment result is valid, the document attachment image is processed according to a preset OCR image recognition rule to generate document supporting data; Generate system bill data according to the execution result data corresponding to the target procurement project and the preset association rules; Reconciliation result data is generated based on the input bill data, the document supporting data and the system bill data corresponding to the target procurement project, as well as preset three-party data comparison rules.

[0009] As an optional embodiment, in the first aspect of the present invention, the comparison data items corresponding to the three-party data comparison rules include project number, document number, document type, material name, specification model, material receipt quantity, purchase unit price, confirmed unit price, tax, total price including tax, paid material fee amount, unpaid material fee amount, application reconciliation amount and at least one of the actual bill amount.

[0010] As an optional embodiment, in the first aspect of the present invention, the classification neural network model is a CNN network model developed and tested under the Pytorch deep learning framework; and / or, the classification neural network model is trained according to the following steps: Determine a training data set and a training classification model including a plurality of training document attachment images annotated with the validity type; the training classification model includes the classification neural network model and a loss function calculation layer; the loss function of the loss function calculation layer is a cross entropy cost function; The training document attachment images and the validity type annotations in the training data set are input into the training classification model in the form of paired labels for training, and the stochastic gradient descent method is used during the training process to continuously reduce the loss function value calculated by the loss function calculation layer, and the training network model is optimized until convergence to obtain the trained classification neural network model.

[0011] As an optional implementation, in the first aspect of the present invention, the stochastic gradient descent method is used in the training process to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain the trained classification neural network model, including: The SGD stochastic gradient descent algorithm is used to optimize the model parameters of the training network model, with a total of 200 iterations, an initial learning rate of 0.001, a momentum of 0.5, and a decrease in the learning rate every 50 rounds so that the loss function value calculated by the loss function calculation layer continues to decrease so that the training network model reaches the optimal value.

[0012] A second aspect of an embodiment of the present invention discloses a data processing system for engineering procurement management, the system comprising: The acquisition module is used to obtain the purchase-related application data sent by the user; An execution module, used for sending the procurement-related application data to a corresponding approval user terminal to generate approval data, and sending the approval data to a corresponding execution user terminal to obtain corresponding execution result data; The application module is used to obtain the reconciliation request of the reconciliation user for the target procurement project; The reconciliation module is used to generate reconciliation result data based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement project sent by the reconciliation user terminal and the execution result data corresponding to the target procurement project.

[0013] As an optional embodiment, in the second aspect of the present invention, the procurement-related application data includes at least one of material application data, planned procurement application data, actual procurement application data, transfer application data, leasing application data, warehousing application data, material collection application data, return application data and material return and lease return application data.

[0014] As an optional implementation, in the second aspect of the present invention, the execution result data includes at least one of procurement result data, transfer result data, leasing result data, material picking result data and inventory result data.

[0015] As an optional implementation, in the second aspect of the present invention, the execution module sends the procurement-related application data to the corresponding approval user terminal to generate approval data, and sends the approval data to the corresponding execution user terminal to obtain the corresponding execution result data, including: Obtain the inventory approval instructions for the target procurement items input by the approval user; Generate inventory approval data according to the procurement-related application data corresponding to the target procurement item and preset inventory approval rules; Obtaining an inventory execution instruction for the target procurement item input by an execution user terminal; Acquire the actual inventory data and inventory attachments input by the executing user terminal; the inventory attachments include at least one of inventory text, inventory image, and inventory video; The inventory result data is generated according to the inventory approval data, the actual inventory data and the inventory attachments, and the preset inventory execution rules.

[0016] As an optional implementation, in the second aspect of the present invention, the reconciliation module generates the reconciliation result data based on the preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item, including: Acquire the input bill data for the target procurement item sent by the reconciliation user terminal; Acquire the document attachment image for the target procurement item sent by the reconciliation user terminal, and generate document attachment image data according to a preset data processing rule; Input the document attachment image data into a trained classification neural network model to obtain a validity judgment result; the validity judgment result is valid or invalid; if the validity judgment result is valid, the document attachment image is processed according to a preset OCR image recognition rule to generate document supporting data; Generate system bill data according to the execution result data corresponding to the target procurement project and the preset association rules; Reconciliation result data is generated based on the input bill data, the document supporting data and the system bill data corresponding to the target procurement project, as well as preset three-party data comparison rules.

[0017] As an optional embodiment, in the second aspect of the present invention, the comparison data items corresponding to the three-party data comparison rules include project number, document number, document type, material name, specification model, received material quantity, purchase unit price, confirmed unit price, tax, total price including tax, paid material fee amount, unpaid material fee amount, application reconciliation amount and at least one of the actual bill amount.

[0018] As an optional embodiment, in the second aspect of the present invention, the classification neural network model is a CNN network model developed and tested under the Pytorch deep learning framework; and / or, the classification neural network model is trained according to the following steps: Determine a training data set and a training classification model including a plurality of training document attachment images annotated with the validity type; the training classification model includes the classification neural network model and a loss function calculation layer; the loss function of the loss function calculation layer is a cross entropy cost function; The training document attachment images and the validity type annotations in the training data set are input into the training classification model in the form of paired labels for training, and the stochastic gradient descent method is used during the training process to continuously reduce the loss function value calculated by the loss function calculation layer, and the training network model is optimized until convergence to obtain the trained classification neural network model.

[0019] As an optional implementation, in the second aspect of the present invention, the stochastic gradient descent method is used in the training process to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain the trained classification neural network model, including: The SGD stochastic gradient descent algorithm is used to optimize the model parameters of the training network model, with a total of 200 iterations, an initial learning rate of 0.001, a momentum of 0.5, and a decrease in the learning rate every 50 rounds so that the loss function value calculated by the loss function calculation layer continues to decrease so that the training network model reaches the optimal value.

[0020] The third aspect of the present invention discloses another data processing system for engineering procurement management, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the data processing method for engineering procurement management disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the data processing method for engineering procurement management disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can complete the approval and execution of procurement applications by leveraging the automation advantages of the application approval process, and combine the reconciliation algorithm combination model to realize automatic reconciliation based on the bill and attachment images, thereby greatly improving the efficiency and effectiveness of engineering procurement, reducing procurement account errors, and providing assistance for the smooth development of engineering procurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a data processing method for engineering procurement management disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of a data processing system for engineering procurement management disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another data processing system for engineering procurement management disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a data processing method and device for engineering procurement management, which can complete the approval and execution of procurement applications by taking advantage of the automation of the application approval process, and realize automatic reconciliation based on bills and attachment images by combining a reconciliation algorithm combination model, thereby greatly improving the efficiency and effect of engineering procurement, reducing procurement book errors, and providing assistance for the smooth development of engineering procurement. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 This is a flow chart of a data processing method for engineering procurement management disclosed in an embodiment of the present invention. Figure 1 The data processing method for engineering procurement management described herein can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the data processing method for engineering procurement management may include the following operations: 101. Obtain the procurement-related application data sent by the user.

[0032] 102. Send the procurement-related application data to the corresponding approval user end to generate approval data, and send the approval data to the corresponding execution user end to obtain the corresponding execution result data. 103. Obtain a reconciliation request from the reconciliation client for the target procurement project. 104. Generate reconciliation result data based on the preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement project sent by the reconciliation user terminal and the execution result data corresponding to the target procurement project.

[0033] It can be seen that the above-mentioned invention embodiments can complete the approval and execution of procurement applications by leveraging the automation advantages of the application approval process, and combine the reconciliation algorithm combination model to realize automatic reconciliation based on the bill and attachment images, thereby greatly improving the efficiency and effectiveness of engineering procurement, reducing procurement book errors, and providing assistance for the smooth development of engineering procurement.

[0034] As an optional embodiment, in the above steps, the procurement-related application data includes at least one of material application data, planned procurement application data, actual procurement application data, transfer application data, leasing application data, warehousing application data, material collection application data, return application data and material return and lease return application data.

[0035] It can be seen that through the above optional implementation examples, the types of procurement-related applications are clarified, and more comprehensive procurement function management can be achieved, which can help significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0036] As an optional embodiment, in the above steps, the execution result data includes at least one of procurement result data, transfer result data, leasing result data, material picking result data and inventory result data.

[0037] It can be seen that through the above optional embodiments, the type of execution result data is clarified, which can achieve more comprehensive execution result acquisition, thereby helping to significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0038] As an optional embodiment, in the above steps, sending the procurement-related application data to the corresponding approval user end to generate approval data, sending the approval data to the corresponding execution user end, and obtaining the corresponding execution result data include: Obtain the inventory approval instructions for the target procurement items input by the approval user; Generate inventory approval data based on the purchase-related application data corresponding to the target procurement project and the preset inventory approval rules; Obtaining and executing the inventory execution instruction for the target procurement item input by the execution user; Acquire actual inventory data and inventory attachments input by the execution user; optionally, the inventory attachments include at least one of inventory text, inventory image, and inventory video; Generate inventory result data based on inventory approval data, actual inventory data and inventory attachments, as well as preset inventory execution rules.

[0039] It can be seen that through the above-mentioned optional embodiments, inventory execution is realized based on inventory approval rules, and inventory results are generated according to relevant data, which can realize automated and accurate procurement inventory, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0040] As an optional embodiment, in the above steps, based on the input bill data and document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item, based on the preset reconciliation algorithm combination model, generating the reconciliation result data includes: Obtain the input bill data for the target procurement project sent by the reconciliation user end; Obtain the document attachment image for the target procurement project sent by the reconciliation user end, and generate the document attachment image data according to the preset data processing rules; Input the document attachment image data into the trained classification neural network model to obtain the validity judgment result; optionally, the validity judgment result is valid or invalid; if the validity judgment result is valid, the document attachment image is processed according to the preset OCR image recognition rules to generate document supporting data; Generate system bill data based on the execution result data corresponding to the target procurement project and the preset association rules; Reconciliation result data is generated based on the input bill data, document supporting data and system bill data corresponding to the target procurement project, as well as the preset three-party data comparison rules.

[0041] It can be seen that through the above-mentioned optional embodiments, the validity judgment of the acquired bill data and attachment images is realized based on the neural network, and the reconciliation results are generated according to the judgment results and corresponding data rules, which can realize automated and accurate procurement reconciliation, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0042] As an optional embodiment, in the above steps, the comparison data items corresponding to the three-party data comparison rules include project number, document number, document type, material name, specification model, material receipt quantity, purchase unit price, confirmed unit price, tax, total price including tax, paid material fee amount, unpaid material fee amount, application reconciliation amount and at least one of the actual bill amount.

[0043] It can be seen that through the above optional implementation examples, the comparison data items of the three-party data comparison rules are clarified, which can improve the precision and accuracy of the comparison, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0044] As an optional embodiment, in the above steps, the classification neural network model is a CNN network model developed and tested under the Pytorch deep learning framework; and / or, the classification neural network model is trained according to the following steps: Determine a training data set and a training classification model including a plurality of training document attachment images labeled with validity types; optionally, the training classification model includes a classification neural network model and a loss function calculation layer; the loss function of the loss function calculation layer is a cross entropy cost function; The training document attachment images and validity type annotations in the training data set are input into the training classification model in the form of paired labels for training. During the training process, the stochastic gradient descent method is used to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain a trained classification neural network model.

[0045] It can be seen that through the above optional embodiments, the type of neural network is clarified and specific training steps are provided to achieve training to obtain a better effectiveness judgment neural network, which can help significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement account errors, and provide assistance for the smooth development of engineering procurement.

[0046] As an optional embodiment, in the above steps, the stochastic gradient descent method is used during the training process to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain a trained classification neural network model, including: The SGD stochastic gradient descent algorithm is used to optimize the model parameters of the training network model. A total of 200 rounds of iterations are performed, the initial learning rate is 0.001, the momentum is set to 0.5, and the learning rate is reduced every 50 rounds so that the loss function value calculated by the loss function calculation layer continues to decrease so that the training network model reaches the optimal value.

[0047] It can be seen that through the above optional embodiments, the training optimization details in the training steps of the neural network are clarified to achieve training to obtain a better effectiveness judgment neural network, which can help to significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement account errors, and provide assistance for the smooth development of engineering procurement.

[0048] Embodiment 2 See also Figure 2 , Figure 21 is a schematic diagram of a data processing system for engineering procurement management disclosed in an embodiment of the present invention. Figure 2 The data processing system for engineering procurement management described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the data processing system for engineering procurement management may include: The acquisition module 201 is used to acquire the purchase-related application data sent by the user.

[0049] The execution module 202 is used to send the procurement-related application data to the corresponding approval user end to generate approval data, and send the approval data to the corresponding execution user end to obtain corresponding execution result data. The application module 203 is used to obtain a reconciliation request from the reconciliation user terminal for the target procurement item. The reconciliation module 204 is used to generate reconciliation result data based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement project sent by the reconciliation user terminal and the execution result data corresponding to the target procurement project.

[0050] It can be seen that the above-mentioned invention embodiments can complete the approval and execution of procurement applications by leveraging the automation advantages of the application approval process, and combine the reconciliation algorithm combination model to realize automatic reconciliation based on the bill and attachment images, thereby greatly improving the efficiency and effectiveness of engineering procurement, reducing procurement book errors, and providing assistance for the smooth development of engineering procurement.

[0051] As an optional embodiment, the procurement-related application data includes at least one of material application data, planned procurement application data, actual procurement application data, transfer application data, lease application data, warehousing application data, material collection application data, return application data and material return and lease return application data.

[0052] It can be seen that through the above optional implementation examples, the types of procurement-related applications are clarified, and more comprehensive procurement function management can be achieved, which can help significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0053] As an optional embodiment, the execution result data includes at least one of procurement result data, transfer result data, leasing result data, material picking result data and inventory result data.

[0054] It can be seen that through the above optional embodiments, the type of execution result data is clarified, which can achieve more comprehensive execution result acquisition, thereby helping to significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0055] As an optional embodiment, the execution module sends the procurement-related application data to the corresponding approval user end to generate approval data, and sends the approval data to the corresponding execution user end to obtain the corresponding execution result data, including: Obtain the inventory approval instructions for the target procurement items input by the approval user; Generate inventory approval data based on the purchase-related application data corresponding to the target procurement project and the preset inventory approval rules; Obtaining and executing the inventory execution instruction for the target procurement item input by the execution user; Acquire actual inventory data and inventory attachments input by the execution user; optionally, the inventory attachments include at least one of inventory text, inventory image, and inventory video; Generate inventory result data based on inventory approval data, actual inventory data and inventory attachments, as well as preset inventory execution rules.

[0056] It can be seen that through the above-mentioned optional embodiments, inventory execution is realized based on inventory approval rules, and inventory results are generated according to relevant data, which can realize automated and accurate procurement inventory, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0057] As an optional embodiment, the reconciliation module generates the reconciliation result data based on the input bill data and document attachment image for the target procurement project sent by the reconciliation user terminal and the execution result data corresponding to the target procurement project, based on the preset reconciliation algorithm combination model, in a specific manner including: Obtain the input bill data for the target procurement project sent by the reconciliation user end; Obtain the document attachment image for the target procurement project sent by the reconciliation user end, and generate the document attachment image data according to the preset data processing rules; Input the document attachment image data into the trained classification neural network model to obtain the validity judgment result; optionally, the validity judgment result is valid or invalid; if the validity judgment result is valid, the document attachment image is processed according to the preset OCR image recognition rules to generate document supporting data; Generate system bill data based on the execution result data corresponding to the target procurement project and the preset association rules; Reconciliation result data is generated based on the input bill data, document supporting data and system bill data corresponding to the target procurement project, as well as the preset three-party data comparison rules.

[0058] It can be seen that through the above-mentioned optional embodiments, the validity judgment of the acquired bill data and attachment images is realized based on the neural network, and the reconciliation results are generated according to the judgment results and corresponding data rules, which can realize automated and accurate procurement reconciliation, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0059] As an optional embodiment, the comparison data items corresponding to the three-party data comparison rules include at least one of project number, document number, document type, material name, specification model, material receipt quantity, purchase unit price, confirmed unit price, tax, total price including tax, paid material fee amount, unpaid material fee amount, application reconciliation amount and actual bill amount.

[0060] It can be seen that through the above optional implementation examples, the comparison data items of the three-party data comparison rules are clarified, which can improve the precision and accuracy of the comparison, thereby helping to greatly improve the efficiency and effectiveness of engineering procurement, reduce procurement book errors, and provide assistance for the smooth development of engineering procurement.

[0061] As an optional embodiment, the classification neural network model is a CNN network model developed and tested under the Pytorch deep learning framework; and / or, the classification neural network model is trained according to the following steps: Determine a training data set and a training classification model including a plurality of training document attachment images labeled with validity types; optionally, the training classification model includes a classification neural network model and a loss function calculation layer; the loss function of the loss function calculation layer is a cross entropy cost function; The training document attachment images and validity type annotations in the training data set are input into the training classification model in the form of paired labels for training. During the training process, the stochastic gradient descent method is used to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain a trained classification neural network model.

[0062] It can be seen that through the above optional embodiments, the type of neural network is clarified and specific training steps are provided to achieve training to obtain a better effectiveness judgment neural network, which can help significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement account errors, and provide assistance for the smooth development of engineering procurement.

[0063] As an optional embodiment, during the training process, a stochastic gradient descent method is used to continuously reduce the loss function value calculated by the loss function calculation layer, and the training network model is optimized until convergence to obtain a trained classification neural network model, including: The SGD stochastic gradient descent algorithm is used to optimize the model parameters of the training network model. A total of 200 rounds of iterations are performed, the initial learning rate is 0.001, the momentum is set to 0.5, and the learning rate is reduced every 50 rounds so that the loss function value calculated by the loss function calculation layer continues to decrease so that the training network model reaches the optimal value.

[0064] It can be seen that through the above optional embodiments, the training optimization details in the training steps of the neural network are clarified to achieve training to obtain a better effectiveness judgment neural network, which can help to significantly improve the efficiency and effectiveness of engineering procurement, reduce procurement account errors, and provide assistance for the smooth development of engineering procurement.

[0065] Embodiment 3 See also Figure 3 , Figure 3 This is another data processing system for engineering procurement management disclosed in an embodiment of the present invention. Figure 3 The data processing system for engineering procurement management described is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the data processing system for engineering procurement management may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the data processing method for engineering procurement management described in the first embodiment.

[0066] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the data processing method for engineering procurement management described in the first embodiment.

[0067] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the data processing method for engineering procurement management described in the first embodiment.

[0068] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] Finally, it should be noted that the data processing method and device for engineering procurement management disclosed in the embodiment of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A data processing method for engineering procurement management, characterized in that: The method comprises: Obtain purchase-related application data sent by the user; Sending the procurement-related application data to the corresponding approval user end to generate approval data, and sending the approval data to the corresponding execution user end to obtain corresponding execution result data; Obtain the reconciliation request for the target procurement project from the reconciliation user end; Reconciliation result data is generated based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item.

2. The data processing method for engineering procurement management according to claim 1, characterized in that: The procurement-related application data includes at least one of material application data, planned procurement application data, actual procurement application data, transfer application data, leasing application data, warehousing application data, material collection application data, return application data and material return and lease return application data.

3. The data processing method for engineering procurement management according to claim 1, characterized in that: The execution result data includes at least one of procurement result data, transfer result data, leasing result data, material picking result data and inventory result data.

4. The data processing method for engineering procurement management according to claim 1, characterized in that: The step of sending the procurement-related application data to the corresponding approval user terminal to generate approval data, and sending the approval data to the corresponding execution user terminal to obtain corresponding execution result data includes: Obtain the inventory approval instructions for the target procurement items input by the approval user; Generate inventory approval data according to the procurement-related application data corresponding to the target procurement item and preset inventory approval rules; Obtaining an inventory execution instruction for the target procurement item input by an execution user terminal; Acquire the actual inventory data and inventory attachments input by the executing user terminal; the inventory attachments include at least one of inventory text, inventory image, and inventory video; The inventory result data is generated according to the inventory approval data, the actual inventory data and the inventory attachments, and the preset inventory execution rules.

5. The data processing method for engineering procurement management according to claim 1, characterized in that: The generating of reconciliation result data based on the input bill data and the document attachment image for the target procurement item sent by the reconciliation user terminal and the execution result data corresponding to the target procurement item and based on a preset reconciliation algorithm combination model includes: Acquire the input bill data for the target procurement item sent by the reconciliation user terminal; Acquire the document attachment image for the target procurement item sent by the reconciliation user terminal, and generate document attachment image data according to a preset data processing rule; Input the document attachment image data into a trained classification neural network model to obtain a validity judgment result; the validity judgment result is valid or invalid; if the validity judgment result is valid, the document attachment image is processed according to a preset OCR image recognition rule to generate document supporting data; Generate system bill data according to the execution result data corresponding to the target procurement project and the preset association rules; Reconciliation result data is generated based on the input bill data, the document supporting data and the system bill data corresponding to the target procurement project, as well as preset three-party data comparison rules.

6. The data processing method for engineering procurement management according to claim 5, characterized in that: The comparison data items corresponding to the three-party data comparison rules include at least one of project number, document number, document type, material name, specification model, material receipt quantity, purchase unit price, confirmed unit price, tax, total price including tax, paid material fee amount, unpaid material fee amount, application reconciliation amount and actual bill amount.

7. The data processing method for engineering procurement management according to claim 5, characterized in that: The classification neural network model is a CNN network model developed and tested under the Pytorch deep learning framework; and / or, the classification neural network model is trained according to the following steps: Determine a training data set and a training classification model including a plurality of training document attachment images annotated with the validity type; the training classification model includes the classification neural network model and a loss function calculation layer; the loss function of the loss function calculation layer is a cross entropy cost function; The training document attachment images and the validity type annotations in the training data set are input into the training classification model in the form of paired labels for training, and the stochastic gradient descent method is used during the training process to continuously reduce the loss function value calculated by the loss function calculation layer, and the training network model is optimized until convergence to obtain the trained classification neural network model.

8. The data processing method for engineering procurement management according to claim 7, characterized in that: The stochastic gradient descent method is used in the training process to make the loss function value calculated by the loss function calculation layer continuously decrease, and the training network model is optimized until convergence to obtain the trained classification neural network model, including: The SGD stochastic gradient descent algorithm is used to optimize the model parameters of the training network model, with a total of 200 iterations, an initial learning rate of 0.001, a momentum of 0.5, and a decrease in the learning rate every 50 rounds so that the loss function value calculated by the loss function calculation layer continues to decrease so that the training network model reaches the optimal value.

9. A data processing device for engineering procurement management, characterized in that: The system comprises: The acquisition module is used to obtain the purchase-related application data sent by the user; An execution module, used for sending the procurement-related application data to a corresponding approval user terminal to generate approval data, and sending the approval data to a corresponding execution user terminal to obtain corresponding execution result data; The application module is used to obtain the reconciliation request of the reconciliation user for the target procurement project; The reconciliation module is used to generate reconciliation result data based on a preset reconciliation algorithm combination model according to the input bill data and document attachment image for the target procurement project sent by the reconciliation user terminal and the execution result data corresponding to the target procurement project.

10. A data processing device for engineering procurement management, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the data processing method for engineering procurement management as described in any one of claims 1-8.

Images