Material flow determination method, device and medium based on industrial neural network

Abstract

The embodiment of the present invention discloses a material flow determination method, device and medium based on industrial neural network. The method includes: creating a target flow structure diagram of the material according to the initial business data in the target flow and a preset flow chart model; the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship; according to the original data of the bottom-level nodes and the preset industrial neural network algorithm, determining the flow data of the root node in the target flow structure diagram. By establishing the target flow structure diagram, determining the relationship between the nodes in the flow, and determining the data of the root node according to the original data of the bottom-level nodes, it is convenient to quickly check the relevant information of the flow, save manpower and time, and improve the determination efficiency of processes such as material procurement and distribution.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and more particularly to a material flow determination method, device and medium based on an industrial neural network. Background Art

[0002] As the scale of the enterprise increases, the production or sales processes become more and more complicated. For example, the workload of purchasing and distributing materials gradually increases, and the efficiency of communication and collaboration between relevant departments continues to decrease.

[0003] Under existing technical conditions, enterprises usually use manual methods, paper documents and data lists to store information elements of processes such as procurement and distribution. Various types of information are stored in different locations, which lacks flexibility and is not conducive to quickly checking historical orders, the sequence of elements, and the relationship between elements. The efficiency of process determination is low, wasting a lot of manpower and time. Summary of the invention

[0004] The embodiments of the present invention provide a material flow determination method, device and medium based on an industrial neural network to improve the efficiency of determining the material flow.

[0005] In a first aspect, an embodiment of the present invention provides a material flow determination method based on an industrial neural network, the method comprising:

[0006] According to the initial business data in the target process and the preset flowchart model, a target process structure diagram of the material is created; wherein the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship;

[0007] According to the original data of the bottom-level nodes and a preset industrial neural network algorithm, the process data of the root node in the target process structure diagram is determined.

[0008] In a second aspect, an embodiment of the present invention further provides a material flow determination device based on an industrial neural network, the device comprising:

[0009] A flow chart creation module is used to create a target flow chart of a material according to the initial business data in the target flow and a preset flow chart model; wherein the initial business data includes the original data of the bottom nodes, and the bottom nodes are connected to the root node through at least one layer of edge connection relationship;

[0010] The process data determination module is used to determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm.

[0011] In a third aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the material flow determination method based on industrial neural network as described in any embodiment of the present invention.

[0012] The embodiment of the present invention obtains the initial business data of the target process, creates a target process structure diagram according to a preset flowchart model, and calculates the process data of the root node in the target process based on a preset industrial neural network algorithm. The problem of manually calculating process data and viewing the process through a data list in the prior art is solved, and the automation and intelligence of the process determination such as material procurement and distribution is realized. The situation of the target process can be quickly checked through the target process structure diagram, which saves manpower and time and improves the efficiency of the determination of each process such as material procurement and distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flow chart of a material flow determination method based on industrial neural network in Embodiment 1 of the present invention;

[0014] Figure 2 It is a schematic diagram of the material procurement business process structure diagram in the first embodiment of the present invention;

[0015] Figure 3 It is a flow chart of a material flow determination method based on industrial neural network in Embodiment 2 of the present invention;

[0016] Figure 4 It is a flow chart of a material flow determination method based on industrial neural network in Embodiment 3 of the present invention;

[0017] Figure 5 It is a structural block diagram of a material flow determination device based on industrial neural network in embodiment 4 of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0019] Embodiment 1

[0020] Figure 1 The present invention provides a schematic flow chart of a material flow determination method based on an industrial neural network. This embodiment is applicable to the case of determining a process link. The method can be executed by a material flow determination device based on an industrial neural network. Figure 1As shown, the method specifically comprises the following steps:

[0021] S110. Create a target process structure diagram of the material according to the initial business data in the target process and a preset flow chart model; wherein the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship.

[0022] Among them, the material flow is the process involving materials in the production process of the product. The initial business data refers to the original data pre-set in the target process, which can include the original data of the underlying nodes. The original data of the underlying nodes refers to the basic attribute data of each link in the target process, and the basic attribute data nodes are used as the underlying nodes. For example, the target process of materials can be processes such as material procurement and distribution. The links in this process can include the contract signing link. The attribute data of the contract signing link can be the name, work number and position of the person signing the contract. The underlying nodes are the name node, work number node and position node of the person signing the contract. The attribute data can come from files, pictures or other relational databases.

[0023] The flowchart model is pre-set. The target process can be applied to the preset flowchart model to obtain the target process structure diagram of material procurement and distribution. The nodes in the flowchart model can be connected by edges. For example, the child node and the parent node are connected by edges, and the child node is the subordinate node of the parent node. The bottom node is the child node, and the root node is the parent node. The bottom node and the root node are connected by at least one layer of edge connection relationship, that is, there can be other levels of nodes between the bottom node and the root node. For example, there is a level of intermediate node between the bottom node and the root node, then the intermediate node is the parent node of the bottom node, and the root node is the parent node of the intermediate node.

[0024] In this embodiment, optionally, the initial business data also includes the process relationship between each node in the target process, wherein each node includes a bottom node and a root node; accordingly, based on the initial business data in the target process and the preset flowchart model, a target process structure diagram of the material is created, including: according to the process relationship between each node in the target process and the preset flowchart model, each node in the target process is connected by edges to complete the creation of the target process structure diagram of the material.

[0025] Specifically, the initial business data may include the original data of the bottom node, and may also include the process relationship between each node. The process relationship refers to the edge connection relationship between each node, and each node may include a bottom node, a root node, and an intermediate node. According to the process relationship between each node and the preset process model diagram, each node of the target process is applied to the process model diagram, and each node is edge-connected to obtain a target process structure diagram, and the original data of the bottom node is stored in the bottom node. The process model diagram is pre-set, and can be obtained by obtaining the relevant personnel information, equipment information, material information, process determination rule information and each process environment information in each material process, and associated according to the association relationship between them to form a process model diagram. The material is the material required in the production field, and the material information can be the composition, proportion and hardness of the material. The beneficial effect of such a setting is that the operation steps of the user to create the target process structure diagram are reduced, and the correctness of the target process structure diagram is improved by obtaining the process relationship, and the situation of the target process is quickly checked through the target process structure diagram, saving manpower and time, and improving the efficiency of process determination.

[0026] Figure 2 It is a schematic diagram of the material procurement business process structure diagram. The root node 201 includes the issuance of procurement tasks, contract signing, supplier delivery, arrival handover, inspection and warehousing, and payment settlement. The root node 201 represents each link of the material procurement business process. The intermediate node 202 is a child node of the root node 201, and has an edge connection relationship with the root node 201. For example, the intermediate nodes that have an edge connection relationship with the issuance of procurement tasks include process processing and personnel. The bottom node 203 is a child node of the intermediate node 202, and has an edge connection relationship with the intermediate node 202. It can represent the attribute data of the intermediate node 202. For example, the attribute data of the personnel includes name, work number, and position.

[0027] S120. Determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm.

[0028] Among them, the industrial neural network is a form of industrial network that can be used for industrial design, production and manufacturing based on the combination of graph database technology and algorithms. The preset industrial neural network algorithm is used to traverse the target process structure diagram and calculate the process data of the root node in the target process structure diagram. For example, the time when the process ends or the amount spent at the end of the process can be calculated. After the user issues a calculation instruction for the process data, the preset industrial neural network algorithm obtains the original data in the underlying node, calculates step by step according to the original data, and obtains the process data in the root node.

[0029] In this embodiment, optionally, the process data of the root node in the target process structure diagram is determined according to the original data of the underlying nodes and a preset industrial neural network algorithm, including: determining the edge connection relationship between the underlying nodes and the root node according to the target process structure diagram; determining the process data of the root node based on the preset industrial neural network algorithm according to the original data of the underlying nodes and the edge connection relationship between the underlying nodes and the root node.

[0030] Specifically, by obtaining the target process structure diagram, determining the edge connection relationship between the nodes in the diagram, and obtaining the path from the bottom node to the root node according to the edge connection relationship between the bottom node and the root node. The preset industrial neural network algorithm obtains the original data in the bottom node, and according to the obtained path, starts from the bottom node and calculates to the root node to obtain the process data of the root node. For example, the time period for completing each root node in the preset process is 1 day, there are three root nodes, and the original data of the bottom node is the time when the first root node starts, which is July 1st, then the estimated end time of the process can be obtained as July 4th. The beneficial effect of such a setting is that the process data of the root node can be quickly obtained through the target process structure diagram of the material and the industrial neural network algorithm, which solves the problem of manually calculating or viewing the process data table to obtain the process data in the prior art, improves the calculation efficiency of the process data, and is conducive to checking the processes such as the procurement and distribution of materials.

[0031] In this embodiment, optionally, according to the original data of the underlying nodes and the edge connection relationship between the underlying nodes and the root node, the process data of the root node is determined based on a preset industrial neural network algorithm, including: using the preset industrial neural network algorithm to traverse the edge connection relationship between the underlying nodes and the root node in the target process structure diagram; based on the traversal results, determining the shortest path from the underlying node to the root node; based on the shortest path and the preset industrial neural network algorithm, passing the original data of the underlying node to the root node to determine the process data of the root node.

[0032] Specifically, a preset industrial neural network algorithm is used to traverse the target process structure diagram, traverse the edge connection relationship between all nodes in the diagram, and obtain the path from the bottom node to the root node. Compare the path lengths from all bottom nodes to the root node, and determine the shortest path from the bottom node to the root node, so as to calculate the process data according to the shortest path. For example, there are two root nodes, namely node one and node two, and the shortest paths from the bottom node to node one and node two can be obtained, that is, two shortest paths are obtained. The process data of node one and node two are obtained according to the shortest path. The process data is the end time of node one and node two. The interval time between the two links of node one and node two is preset. According to the preset interval time and the end time of node one and node two, the completion time of the entire process is obtained.

[0033] According to the preset industrial neural network algorithm, the original data of the bottom node in the shortest path is obtained, the original data is processed and calculated, and the data in the calculation process is passed from bottom to top layer by layer to the top node of the target process, that is, the root node. Users can calculate the process data at any time, or set constraints for automatic calculation. The constraints of each node can be stored in an external function, and the external function is called to execute the relevant functions by executing the industrial neural network algorithm. When the constraint is met, the calculation of the next node is automatically performed. For example, the target process is a procurement business process, and the constraint is that if the original data of the bottom node is received, the preset industrial neural network algorithm is run. The calculation starts from the first root node "procurement task issuance". When it comes to "supplier delivery", since the supplier has not yet delivered, there is no original data of the root node, and the calculation is suspended. When the supplier's delivery data is received, the constraint is met and the calculation continues. The beneficial effect of this setting is that by traversing the target process structure diagram, the shortest path from the bottom node to the root node is found, and the calculation is performed according to the shortest path, saving calculation time. By passing data layer by layer, the omission of nodes is avoided, and the calculation accuracy and efficiency of process data are improved.

[0034] The technical solution of this embodiment obtains the initial business data of the target process, creates a target process structure diagram based on a preset flowchart model, and calculates the process data of the root node in the target process based on a preset industrial neural network algorithm. It solves the problem of manually calculating process data and viewing processes through data lists in the prior art, gets rid of the constraints of traditional relational databases, greatly improves performance for large-scale deep traversal, and can achieve rapid analysis based on massive relational data. It realizes the rapid review of the target process through the target process structure diagram, saves manpower and time, and improves the efficiency of material flow determination.

[0035] Embodiment 2

[0036] Figure 3 The following is a flow chart of a material flow determination method based on an industrial neural network provided in the second embodiment of the present invention. This embodiment is further optimized based on the above embodiment. The method can be executed by a material flow determination device based on an industrial neural network. Figure 3 As shown, the method specifically comprises the following steps:

[0037] S310. Create a target process structure diagram for the material based on the initial business data in the target process and a preset flow chart model; wherein the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship.

[0038] S320. Determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm.

[0039] S330. In response to the user's node data update instruction, update the data of the target bottom-level node in the target process structure diagram.

[0040] Among them, according to the node data update instruction issued by the user, the target node to update the node data is determined, the latest node data input by the user is obtained, and the latest node data is stored in the target node. For example, there is a root node for signing a contract in the target process structure diagram. After the contract is signed, the data such as the time and personnel of the contract are stored in the relevant bottom nodes.

[0041] In this embodiment, optionally, in response to the user's node data update instruction, the data of the target underlying node in the target process structure diagram is updated, including: obtaining the latest data of the target underlying node in the target process structure diagram; in response to the node data update instruction, replacing the original data of the target underlying node with the latest data.

[0042] Specifically, in response to the node data update instruction issued by the user, the target node is determined, wherein the target node is the bottom node, and the data of the bottom node is changed, and other nodes that have edge connection relationships with the bottom node will also be updated accordingly. The latest data input by the user is obtained, and the original data in the target bottom node is replaced with the latest data. The interface corresponding to the node in the target process structure diagram of the industrial neural network can be connected to the database to obtain the data of the node through the database. For example, in the process determination process, it may be necessary to update the data of the node in real time, so the interface corresponding to the node can be connected to the database to obtain the node data from the database in time. The process data assembly rules can be constructed and stored in the database to facilitate node calls. The beneficial effect of such a setting is that the user only needs to update the data of the bottom node, avoiding the problem that the data of the bottom node is still the original data after the user changes the data of the intermediate node or the root node, and cannot be updated in real time, thereby improving the accuracy of the data in the target process structure diagram.

[0043] S340. Determine the latest process data of the root node in the target process structure diagram according to the latest data of the target underlying node and the preset industrial neural network algorithm.

[0044] After determining the target underlying node to update data, a preset industrial neural network algorithm is used to traverse the target process structure diagram to determine the nodes that have edge connections with the target underlying node, which may be intermediate nodes and root nodes. According to the industrial neural network algorithm, data is transmitted from the underlying node to the upper layer, and the data of the nodes that have edge connections with the underlying node is updated until the process data in the root node is updated to obtain the latest process data of the root node.

[0045] The embodiment of the present invention obtains the initial business data of the target process, creates a target process structure diagram of the material according to a preset flowchart model, and calculates the process data of the root node in the target process based on a preset industrial neural network algorithm. When updating the process data, only the data of the underlying node needs to be changed to automatically calculate the process data of the root node. The problem of manually calculating process data and viewing the process through a data list in the prior art is solved, and the situation of the target process can be quickly checked through the target process structure diagram, saving manpower and time, improving the efficiency of process determination, avoiding untimely updates of the data of each node in the target process, and improving the efficiency and accuracy of data updates.

[0046] Embodiment 3

[0047] Figure 4 The following is a flow chart of a material flow determination method based on an industrial neural network provided in the third embodiment of the present invention. This embodiment is further optimized based on the above embodiment. The method can be executed by a material flow determination device based on an industrial neural network. Figure 4 As shown, the method specifically comprises the following steps:

[0048] S410. Create a target process structure diagram of the material according to the initial business data in the target process and a preset flow chart model; wherein the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship.

[0049] S420. Determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm.

[0050] S430 . In response to the process data query instruction of the user, determine the target query node.

[0051] The user issues a process data query instruction, and determines a target query node according to the process data query instruction. The target query node may be a bottom node, an intermediate node, or a root node. For example, the user may select a target query node on a visualization interface of a target process structure diagram and click a query instruction.

[0052] S440: Determine, according to the target process structure diagram, adjacent nodes that have an edge connection relationship with the target query node.

[0053] After the target query node is determined, all nodes in the target process structure diagram are traversed according to a preset query algorithm to determine adjacent nodes that have an edge connection relationship with the target query node.

[0054] S450: Store the process data of the target query node and the adjacent nodes in a data list for display.

[0055] Among them, the process data in the target query node and the adjacent nodes are obtained, and the obtained process data is displayed and saved in the form of a data list. For example, if the target query node is a supplier shipment node, the adjacent node is a device node, and the device node is a child node of the supplier shipment node, then the process data in the supplier shipment node and the process data in the device node are listed in the table, and the fields can be node name and process data. If the node name is supplier shipment, the corresponding process data can be the shipment time; if the node name is device, the corresponding process data can be the device model, etc.

[0056] The embodiment of the present invention obtains the initial business data of the target process, creates a target process structure diagram according to a preset flowchart model, and calculates the process data of the root node in the target process based on a preset industrial neural network algorithm. By determining the target query node, the process data of the target query node and the adjacent nodes can be obtained. The problem of manually calculating process data and viewing process data through a data list in the prior art is solved, and the situation of the target process can be quickly checked through the target process structure diagram, avoiding the omission of data or process nodes, saving manpower and time, and improving the efficiency of material flow determination and data query efficiency.

[0057] Embodiment 4

[0058] Figure 5 This is a structural block diagram of a material flow determination device based on an industrial neural network provided in the fourth embodiment of the present invention, which can execute the material flow determination method based on an industrial neural network provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 5 As shown, the device specifically includes:

[0059] The flowchart creation module 501 is used to create a target process structure diagram of a material according to the initial business data in the target process and a preset flowchart model; wherein the initial business data includes the original data of the bottom node, and the bottom node is connected to the root node through at least one layer of edge connection relationship;

[0060] The process data determination module 502 is used to determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm.

[0061] Optionally, the initial business data also includes a process relationship between nodes in the target process, wherein each node includes a bottom node and a root node;

[0062] Accordingly, the flowchart creation module 501 is specifically used for:

[0063] According to the process relationship between each node in the target process and the preset flowchart model, the nodes in the target process are connected by edges to complete the creation of the target process structure diagram of the material.

[0064] Optionally, the process data determination module 502 includes:

[0065] A relationship determination unit, used to determine the edge connection relationship between the bottom node and the root node according to the target process structure diagram;

[0066] The data determination unit is used to determine the process data of the root node based on a preset industrial neural network algorithm according to the original data of the bottom node and the edge connection relationship between the bottom node and the root node.

[0067] Optionally, the relationship determination unit is specifically used to:

[0068] Using the preset industrial neural network algorithm, the edge connection relationship between the bottom nodes and the root nodes in the target process structure diagram is traversed;

[0069] Based on the traversal results, determine the shortest path from the bottom node to the root node;

[0070] According to the shortest path and the preset industrial neural network algorithm, the original data of the bottom node is passed to the root node to determine the process data of the root node.

[0071] Optionally, the device further comprises:

[0072] A target node update module is used to update the data of the target underlying node in the target process structure diagram in response to a user's node data update instruction after determining the process data of the root node in the target process structure diagram according to the original data of the underlying node and a preset industrial neural network algorithm;

[0073] The root node update module is used to determine the latest process data of the root node in the target process structure diagram based on the latest data of the target underlying node and the preset industrial neural network algorithm.

[0074] Optionally, the target node update module is used to:

[0075] Get the latest data of the target bottom node in the target process structure diagram;

[0076] In response to the node data update instruction, the original data of the target underlying node is replaced with the latest data.

[0077] Optionally, the device further comprises:

[0078] A target node determination module, used to determine a target query node in response to a process data query instruction of a user;

[0079] A neighboring node determination module is used to determine neighboring nodes that have an edge connection relationship with the target query node according to the target process structure diagram;

[0080] The data display module is used to store the process data of the target query node and the adjacent nodes in the data list for display.

[0081] The embodiment of the present invention obtains the initial business data of the target process, creates a target process structure diagram according to a preset flowchart model, and calculates the process data of the root node in the target process based on a preset industrial neural network algorithm. This solves the problem of manually calculating process data and viewing the process through a data list in the prior art, and realizes the rapid review of the target process through the target process structure diagram, saving manpower and time, and improving the efficiency of process determination.

[0082] Embodiment 5

[0083] Embodiment 5 of the present invention further provides a storage medium containing computer executable instructions, on which a computer program is stored. When the program is executed by a processor, the process determination method based on an industrial neural network provided in the embodiment of the present invention is implemented, including:

[0084] According to the initial business data in the target process and the preset flowchart model, a target process structure diagram of the material is created; wherein the initial business data includes the original data of the bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship;

[0085] According to the original data of the bottom nodes and the preset industrial neural network algorithm, the process data of the root node in the target process structure diagram is determined.

[0086] The computer 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, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with 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, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0087] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0088] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0089] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or computer device. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A material flow determination method based on industrial neural network, characterized in that: include: Create a target process structure diagram for materials based on the initial business data in the target process and the preset process flow model; The initial business data includes original data of bottom-level nodes, and the bottom-level nodes are connected to the root node through at least one layer of edge connection relationship; Determining the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm, including: determining the edge connection relationship between the bottom node and the root node according to the target process structure diagram; determining the process data of the root node based on the preset industrial neural network algorithm according to the original data of the bottom node and the edge connection relationship between the bottom node and the root node; The initial business data also includes the process relationship between nodes in the target process, wherein each node includes a bottom node and a root node; Accordingly, based on the initial business data in the target process and the preset flowchart model, a target process structure diagram of the material is created, including: according to the process relationship between each node in the target process and the preset flowchart model, each node in the target process is connected by edges to complete the creation of the target process structure diagram of the material.

2. The method according to claim 1, characterized in that According to the original data of the bottom-level node and the edge connection relationship between the bottom-level node and the root node, the process data of the root node is determined based on a preset industrial neural network algorithm, including: Using a preset industrial neural network algorithm, traverse the edge connection relationship between the bottom node and the root node in the target process structure diagram; Determine the shortest path from the bottom node to the root node according to the traversal result; According to the shortest path and a preset industrial neural network algorithm, the original data of the bottom node is transferred to the root node to determine the process data of the root node.

3. The method according to claim 1, characterized in that After determining the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm, it also includes: In response to a node data update instruction from a user, updating data of a target bottom-level node in the target process structure diagram; According to the latest data of the target underlying node and a preset industrial neural network algorithm, the latest process data of the root node in the target process structure diagram is determined.

4. The method according to claim 3, characterized in that In response to a node data update instruction from a user, updating the data of a target bottom-level node in the target process structure diagram includes: Obtain the latest data of the target bottom-level node in the target process structure diagram; In response to the node data update instruction, the original data of the target underlying node is replaced with the latest data.

5. The method according to claim 1, characterized in that After determining the process data of the root node in the target process structure diagram according to the updated node data and the preset industrial neural network algorithm, the method further includes: In response to a process data query instruction from a user, determining a target query node; According to the target process structure diagram, determining adjacent nodes that have an edge connection relationship with the target query node; The process data of the target query node and the adjacent nodes are stored in a data list for display.

6. A material flow determination device based on industrial neural network, characterized in that: include: A flow chart creation module is used to create a target flow chart of a material according to the initial business data in the target flow and a preset flow chart model; wherein the initial business data includes the original data of the bottom nodes, and the bottom nodes are connected to the root node through at least one layer of edge connection relationship; A process data determination module, used to determine the process data of the root node in the target process structure diagram according to the original data of the bottom node and the preset industrial neural network algorithm, including: determining the edge connection relationship between the bottom node and the root node according to the target process structure diagram; determining the process data of the root node based on the preset industrial neural network algorithm according to the original data of the bottom node and the edge connection relationship between the bottom node and the root node; The initial business data also includes the process relationship between nodes in the target process, wherein each node includes a bottom node and a root node; Accordingly, based on the initial business data in the target process and the preset flowchart model, a target process structure diagram of the material is created, including: according to the process relationship between each node in the target process and the preset flowchart model, each node in the target process is connected by edges to complete the creation of the target process structure diagram of the material.

7. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the material flow determination method based on industrial neural network as described in any one of claims 1 to 5 when executed by a computer processor.

Images