A method and device for constructing industrial chain manufacturing resources

Abstract

The present invention discloses a method and device for constructing manufacturing resources in an industrial chain, wherein the construction method includes: constructing a knowledge graph model of manufacturing resources and historical data; performing similarity matching on existing data according to manufacturing tasks, and using the knowledge graph model to screen out qualified manufacturing resources; determining individual evaluation rules for manufacturing resources; performing individual analysis and evaluation on the screened manufacturing resources according to the individual evaluation rules to obtain the best matching object; the construction method constructs a knowledge graph model for manufacturing resources and historical manufacturing task information, and as the amount of data increases, the scale of the model continues to expand, and the reliability of the results of matching manufacturing resources continues to increase, forming a matching system with a virtuous cycle; in addition, similarity matching is performed on manufacturing tasks according to existing data to obtain matching results that are closer to the actual production environment.

Description

Technical Field

[0001] The present invention relates to the field of rapid reconstruction of manufacturing resources, and in particular to a method for optimizing the adjustment of discrete manufacturing resources, and specifically to a method and device for constructing manufacturing resources in an industrial chain. Background Art

[0002] With the rapid development of traditional manufacturing, the demand of manufacturing market continues to show a trend of personalization and diversification, which brings huge challenges to the traditional mass production mode of assembly line. In order to quickly respond to market changes and meet personalized and diversified manufacturing needs, improving the production flexibility of manufacturing equipment and production lines has become a common goal of the entire manufacturing industry. One of the keys is to effectively and quickly reconstruct existing manufacturing resources, and the rapid and accurate matching of manufacturing tasks with manufacturing resources is the focus of the rapid reconstruction of manufacturing resources.

[0003] To achieve rapid reconstruction of manufacturing resources, it is necessary to collect and organize the existing manufacturing resource information, and match the existing manufacturing tasks based on a large amount of historical manufacturing data. Therefore, it is necessary to build an ontology library and knowledge base for manufacturing resources to complete the integration of manufacturing resources, so as to achieve the purpose of matching manufacturing tasks quickly and accurately.

[0004] The Chinese invention patent application with publication number CN111582561A and publication date 2020.08.25 discloses a scheduling optimization method for a reconfigurable production line with small batches and multiple varieties. This method constructs the ontology and reasoning mechanism of manufacturing resources, realizes the knowledge expression of manufacturing resources, and optimizes the resource allocation of a single batch production process from the decision-making level. The shortcomings of this method are: there is no systematic integration of manufacturing resources, and customized scheduling is only based on optimization algorithms during the resource allocation process, which makes it difficult to ensure the rationality and feasibility of the results. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method and device for constructing industrial chain manufacturing resources by performing similarity matching on existing manufacturing tasks based on historical manufacturing data, thereby allocating manufacturing resources and obtaining matching results that are more in line with the actual manufacturing process.

[0006] In order to achieve the above-mentioned object, the present invention provides a method for constructing industrial chain manufacturing resources, comprising:

[0007] Build a knowledge graph model of manufacturing resources and historical data;

[0008] Perform similarity matching on existing data according to manufacturing tasks, and use the knowledge graph model to filter out qualified manufacturing resources;

[0009] Determine individual evaluation rules for manufacturing resources;

[0010] The selected manufacturing resources are individually analyzed and evaluated according to the individual evaluation rules to obtain the best matching object.

[0011] As a preferred technical solution, the construction of a knowledge graph model of manufacturing resources and historical data further includes:

[0012] Constructing an ontology model of manufacturing resources and manufacturing tasks; the ontology model includes a knowledge graph entity type and a knowledge graph attribute type;

[0013] Build a knowledge base of manufacturing resources and manufacturing tasks;

[0014] Update the knowledge base based on the real-time status of manufacturing resources.

[0015] Furthermore, the knowledge graph entity types include: equipment type, tool type, processing material, and manufacturing accuracy; the knowledge graph attribute types include: equipment number, equipment location, operating status, processing type, processing characteristics, and manufacturing cycle.

[0016] As a preferred technical solution, the construction of a knowledge base of manufacturing resources and manufacturing tasks further includes: using NLP technology to collect manufacturing resources and historical manufacturing task information to obtain structured data, corresponding to the constructed entities and attributes, and storing them in a graph database.

[0017] Preferably, the similarity matching of existing data according to the manufacturing task further includes:

[0018] Determine the similarity matching rules for manufacturing tasks;

[0019] Match existing manufacturing tasks with historical manufacturing tasks for similarity;

[0020] The manufacturing resources corresponding to the matching results are added to the candidate set.

[0021] As a preferred technical solution, the determination of the manufacturing task similarity matching rule further includes:

[0022] Determine a similarity algorithm based on various entities and attributes of the manufacturing task;

[0023] Compare the similarity percentage p of the entities or attributes corresponding to the two manufacturing tasks according to the similarity algorithm i , and set weights q for each entity and attribute i .

[0024] Furthermore, the similarity matching of the existing manufacturing tasks with the historical manufacturing tasks further includes:

[0025] Calculate the weighted sum of all n entity and attribute similarities, that is, Consider historical manufacturing tasks with results greater than a set threshold as similar tasks

[0026] Preferably, the evaluation rules are determined according to the operating status, load rate and manufacturing cost of manufacturing resources.

[0027] On the other hand, the present invention also provides a device for constructing industrial chain manufacturing resources, comprising:

[0028] Construction module, used to build a knowledge graph model of manufacturing resources and historical data;

[0029] A screening module is used to perform similarity matching on existing data according to manufacturing tasks, and to screen out qualified manufacturing resources using the knowledge graph model;

[0030] A determination module, used to determine individual evaluation rules for manufacturing resources;

[0031] The individual analysis and evaluation module is used to perform individual analysis and evaluation on the screened manufacturing resources according to the individual evaluation rules to obtain the best matching object.

[0032] The beneficial effects of the present invention compared with the prior art are: by constructing a knowledge graph model for manufacturing resources and historical manufacturing task information, as the amount of data increases, the scale of the model continues to expand, the reliability of the results of manufacturing resource matching continues to increase, and a matching system with a virtuous cycle is formed;

[0033] In addition, similarity matching of manufacturing tasks is performed based on existing data to obtain matching results that are closer to the actual production environment;

[0034] In addition, individual analysis and evaluation of manufacturing resources are conducted to maximize equipment utilization, balance loads, and minimize costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of a method for constructing industrial chain manufacturing resources provided by the present invention;

[0036] Figure 2 is a diagram of a manufacturing resource and manufacturing task ontology model in one embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of a knowledge graph of manufacturing resources and manufacturing tasks in one embodiment of the present invention;

[0038] Figure 4 It is a structural diagram of a device for constructing industrial chain manufacturing resources provided by the invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0040] Reference Figure 1 This embodiment provides a method for constructing industrial chain manufacturing resources, which specifically includes the following steps:

[0041] S10: Build a knowledge graph model of manufacturing resources and historical data;

[0042] Specifically, it is necessary to first construct an ontology model of manufacturing resources and manufacturing tasks. In this embodiment, refer to Figure 2 , construct 4 knowledge graph entity types and 6 knowledge graph attribute types to complete the design of manufacturing resource and manufacturing task knowledge graph entity relationships. The knowledge graph entity types include: equipment type, tool type, processing material, and manufacturing accuracy. The knowledge graph attribute types include: equipment number, equipment location, operating status, processing type, processing characteristics, and manufacturing cycle. Among them, equipment type, tool type, equipment number, equipment location, and operating status are used to construct the manufacturing resource ontology, and processing materials, manufacturing accuracy, processing type, processing characteristics, and manufacturing cycle are used to construct the manufacturing task ontology.

[0043] Next, a knowledge base of manufacturing resources and manufacturing tasks is constructed. Specifically, NLP technology is used to collect manufacturing resources and historical manufacturing task information to obtain structured data, which corresponds to the constructed entities and attributes and is stored in a graph database. In this embodiment, the attribute information of existing manufacturing resources and manufacturing tasks is collected, and structured data is obtained using NLP technology. The data is stored in a Neo4j graph database, and the following is obtained: Figure 3 The data structure shown.

[0044] Finally, the knowledge base is updated according to the real-time status of manufacturing resources. Specifically, the status of existing manufacturing resources is monitored in real time. When the operating status changes, the updated data is uploaded to the graph database to ensure that the data in the database is consistent with the actual situation.

[0045] S20: performing similarity matching on existing data according to the manufacturing tasks, and screening out qualified manufacturing resources using the knowledge graph model;

[0046] Specifically, first, it is necessary to formulate a similarity matching rule for manufacturing tasks; in this embodiment, a specific similarity algorithm is formulated for the attributes of the current manufacturing tasks that need to be matched, and a similarity weight q is set for each attribute. i, and set the threshold for determining similar tasks. Specifically, for a manufacturing task, a larger weight is given to its key attributes, such as processing accuracy, processing type, etc., while the similarity weight can be reduced for secondary attributes such as manufacturing cycle and processing materials. Different similarity algorithms should be formulated for different attributes. For example, for processing accuracy, different accuracy intervals can be set in advance, and a similarity value can be assigned to each interval. The closer the interval is to the original accuracy, the greater the similarity value. The size of the judgment threshold can be determined by the universality of the manufacturing task. For conventional manufacturing tasks with a large number of matches, the judgment threshold can be increased, and vice versa, the threshold can be lowered.

[0047] Next, the current manufacturing task is matched with the historical manufacturing task for similarity; specifically, the similarity p of each attribute between the current manufacturing task and the historical manufacturing tasks T1, T2, T3, and T4 in the database is calculated respectively. i And weighted sum, that is, calculate Historical manufacturing tasks whose results are greater than a set threshold are considered similar tasks.

[0048] Finally, the manufacturing resources corresponding to the matching results are added to the candidate set; specifically, the corresponding manufacturing resources are searched for the screened similar tasks as available resources that meet the processing conditions, which are used for the next step of evaluating and screening individual resources.

[0049] S30: Determine individual evaluation rules for manufacturing resources;

[0050] Specifically, the operating status, load rate, manufacturing cost and other factors of the manufacturing resources are taken into consideration, and the attributes of each manufacturing resource are quantitatively evaluated. For the evaluation of a manufacturing resource, the evaluation rules are designed with the purpose of maximizing equipment utilization, balancing load and minimizing cost.

[0051] S40: Perform individual analysis and evaluation on the selected manufacturing resources according to the individual evaluation rules to obtain the best matching object; specifically, different weights can be assigned to attributes of different manufacturing tasks. If it is a cost-priority task, a greater weight can be assigned to the manufacturing cost, and if it is an efficiency-priority task, a greater weight can be assigned to the load rate.

[0052] Compared with traditional manufacturing resource scheduling optimization methods, this construction method uses knowledge graph technology to integrate manufacturing resources and build a huge knowledge system. It can perform similarity matching on existing manufacturing tasks based on historical manufacturing data, thereby allocating manufacturing resources and obtaining matching results that are more in line with the actual manufacturing process.

[0053] In another embodiment, the present invention also provides a device for constructing industrial chain manufacturing resources, referring to Figure 4 , the construction device specifically includes:

[0054] Construction module 100 is used to construct a knowledge graph model of manufacturing resources and historical data. It should be noted that since the specific construction method and process have been explained in detail in step S10 of the above-mentioned method for constructing manufacturing resources in the industrial chain, they will not be repeated here.

[0055] The screening module 200 is used to perform similarity matching on the existing data according to the manufacturing tasks, and use the knowledge graph model to screen out qualified manufacturing resources; it should be noted here that since the specific screening method and process have been explained in detail in step S20 of the above-mentioned method for constructing manufacturing resources in the industrial chain, it will not be repeated here.

[0056] The determination module 300 is used to determine the individual evaluation rules of manufacturing resources. It should be noted that since the specific determination method and process have been explained in detail in step S30 of the above-mentioned method for constructing manufacturing resources in the industrial chain, they will not be repeated here.

[0057] The individual analysis and evaluation module 400 is used to perform individual analysis and evaluation on the screened manufacturing resources according to the individual evaluation rules to obtain the optimal matching object; it should be noted here that since the specific individual analysis and evaluation method and process have been explained in detail in step S40 of the above-mentioned industrial chain manufacturing resource construction method, it will not be repeated here.

[0058] In addition, an embodiment of the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium may store a program, which, when executed, includes part or all of the steps of any method for constructing industrial chain manufacturing resources recorded in the above method embodiment.

[0059] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0060] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0061] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0062] An exemplary flow chart of a method for implementing a service chain according to an embodiment of the present invention is described above with reference to the accompanying drawings. It should be noted that the large amount of details included in the above description are only exemplary illustrations of the present invention, rather than limitations of the present invention. In other embodiments of the present invention, the method may have more, fewer or different steps, and the order, inclusion, function, etc. of the steps may be different from those described and illustrated.

Claims

1. A method for constructing industrial chain manufacturing resources, characterized in that: include: Build a knowledge graph model of manufacturing resources and historical data; Perform similarity matching on existing data according to manufacturing tasks, and use the knowledge graph model to filter out qualified manufacturing resources; Determine individual evaluation rules for manufacturing resources; Performing individual analysis and evaluation on the selected manufacturing resources according to the individual evaluation rules to obtain the best matching object; Among them, similarity matching of existing data is performed according to manufacturing tasks, including: Determine the similarity matching rules of the manufacturing tasks, including determining a similarity algorithm based on the entities and attributes of the manufacturing tasks; and comparing the similarity percentages of the entities or attributes corresponding to the two manufacturing tasks based on the similarity algorithm. , and set weights for each entity and attribute ; Similarity matching between existing manufacturing tasks and historical manufacturing tasks, including calculating all The weighted sum of the similarity between the entity and the attribute, that is, , historical manufacturing tasks whose results are greater than a set threshold are considered similar tasks; The manufacturing resources corresponding to the matching results are added to the candidate set.

2. The construction method according to claim 1, characterized in that: The construction of the knowledge graph model of manufacturing resources and historical data further includes: Constructing an ontology model of manufacturing resources and manufacturing tasks; the ontology model includes a knowledge graph entity type and a knowledge graph attribute type; Build a knowledge base of manufacturing resources and manufacturing tasks; Update the knowledge base based on the real-time status of manufacturing resources.

3. The construction method according to claim 2, characterized in that: The knowledge graph entity types include: equipment type, tool type, processing material, and manufacturing accuracy; the knowledge graph attribute types include: equipment number, equipment location, operating status, processing type, processing characteristics, and manufacturing cycle.

4. The construction method according to claim 2, characterized in that: The construction of the knowledge base of manufacturing resources and manufacturing tasks further includes: using NLP technology to collect manufacturing resources and historical manufacturing task information to obtain structured data, corresponding to the constructed entities and attributes, and storing them in a graph database.

5. The construction method according to claim 1, characterized in that: The evaluation rules are determined according to the operating status, load rate and manufacturing cost of the manufacturing resources.

6. A device for constructing industrial chain manufacturing resources, characterized in that: include: Construction module, used to build a knowledge graph model of manufacturing resources and historical data; A screening module is used to perform similarity matching on existing data according to manufacturing tasks, and use the knowledge graph model to screen out qualified manufacturing resources; wherein, performing similarity matching on existing data according to manufacturing tasks includes: Determine the similarity matching rules of the manufacturing tasks, including determining a similarity algorithm based on the entities and attributes of the manufacturing tasks; and comparing the similarity percentages of the entities or attributes corresponding to the two manufacturing tasks based on the similarity algorithm. , and set weights for each entity and attribute ; Similarity matching between existing manufacturing tasks and historical manufacturing tasks, including calculating all The weighted sum of the similarity between the entity and the attribute, that is, , historical manufacturing tasks whose results are greater than a set threshold are considered similar tasks; A determination module, used to determine individual evaluation rules for manufacturing resources; The individual analysis and evaluation module is used to perform individual analysis and evaluation on the screened manufacturing resources according to the individual evaluation rules to obtain the best matching object.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for constructing industrial chain manufacturing resources as described in any one of claims 1 to 5 are implemented.

Images