AGV auxiliary scheduling method and device based on knowledge graph

By constructing a knowledge graph of AGV, cargo and road network entities, calculating the scheduling weights of production entities, and generating AGV scheduling schemes and scores, the problem of failure to utilize data in the existing technology is solved and the operation efficiency of AGV is improved.

CN118689186BActive Publication Date: 2024-11-08GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411167474.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-08
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

The prior art fails to effectively utilize the large amount of data generated during the production process in AGV scheduling, resulting in inefficient operation of AGV.

Method used

Using a knowledge graph-based method, a knowledge graph containing AGV, cargo and road network entities is constructed by obtaining production data (offline data and real-time data), calculating the scheduling weights of the production entity based on real-time data, generating scheduling schemes and reliable scores, assisting AGV scheduling.

Benefits of technology

Making full use of production data improves the operation efficiency of AGV, providing reliable scheduling plans and scoring, helping managers make better decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118689186B_ABST
    Figure CN118689186B_ABST
Patent Text Reader

Abstract

The present application relates to an AGV assisted scheduling method and device based on a knowledge graph, the method comprising: obtaining production data; wherein the production data includes offline data and real-time data; constructing a knowledge graph based on offline data; in response to the issuance of a distribution task, determining a graph network that uniquely corresponds to the distribution task in the knowledge graph based on the distribution task, and determining the scheduling weight of the production entity contained in the graph network based on the real-time data; determining at least one graph subnetwork in the graph network, and calculating the total scheduling weight of the graph subnetwork based on the scheduling weight of the production entity contained in the graph subnetwork; outputting the graph subnetwork as a scheduling plan, and outputting the total scheduling weight of the graph subnetwork as a reliable score of the scheduling plan. Through the technical solution provided by the present application, with the knowledge graph as the core, the assisted scheduling of AGV is realized from the perspective of big data, thereby improving the operating efficiency of AGV.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of logistics, and in particular to an AGV assisted scheduling method and device based on a knowledge graph. Background Art

[0002] AGV (Automated Guided Vehicle) is a transport vehicle that can drive autonomously, usually used for cargo handling and transportation in factories, warehouses, logistics centers and other places.

[0003] In modern factories, AGVs will output a large amount of operating data when working, and at the same time, the production workshops in the factory will also output a large amount of production data. These data can describe the production process of the factory to a certain extent, and can play an important role in the scheduling of AGVs.

[0004] When scheduling AGVs, existing technologies mostly start from the perspective of algorithms, and do not make good use of the large amount of data generated during the production process. Therefore, we hope to start from the perspective of big data, make full use of the large amount of data generated during the production process, realize auxiliary scheduling of AGVs, and thus improve the operating efficiency of AGVs. Summary of the invention

[0005] The present application provides an AGV assisted scheduling method and device based on a knowledge graph, so as to make full use of the large amount of data generated in the production process, realize AGV assisted scheduling from the perspective of big data, and thus improve the operation efficiency of AGV.

[0006] In a first aspect, the present application provides an AGV assisted scheduling method based on a knowledge graph, the method comprising:

[0007] Acquire production data; wherein the production data includes offline data and real-time data, the offline data is data that remains unchanged during the production process, and the real-time data is data that changes in real time during the production process;

[0008] Constructing a knowledge graph according to the offline data; wherein the knowledge graph includes a plurality of production entities, the production entities are connected by entity relationships, and the production entities include at least an AGV entity, a cargo entity, and a road network entity;

[0009] In response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, and a scheduling weight of the production entity contained in the graph network is determined according to the real-time data;

[0010] Determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities contained in the graph sub-network; wherein the graph sub-network contains only one AGV entity;

[0011] The graph subnetwork is output as a scheduling solution, and the total scheduling weight of the graph subnetwork is output as a reliability score of the scheduling solution.

[0012] In a feasible embodiment of the present application, constructing a knowledge graph according to the offline data includes:

[0013] For the structured data in the offline data, determining the entity relationship between the production entities and the production entities by using a preset entity extraction rule;

[0014] For the unstructured data in the offline data, determining the entity relationship between the production entities and the production entities through a preset entity extraction model;

[0015] The knowledge graph is constructed according to the production entities and the entity relationships between the production entities.

[0016] In a feasible embodiment of the present application, in response to the issuance of a delivery task, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, including:

[0017] Determine the delivery starting point, delivery destination and delivery goods from the delivery task;

[0018] Determine at least one distribution road network according to the distribution starting point and the distribution end point;

[0019] A knowledge graph search formula is constructed based on the distribution road network and the distribution goods, and the graph network is found in the knowledge graph through the knowledge graph search formula; wherein, the graph network includes at least one of the road network entities and at least one of the AGV entities, the road network entity corresponds to the distribution road network, and the AGV entity corresponds to the AGV currently available for the distribution task.

[0020] In a feasible embodiment of the present application, determining the scheduling weight of the production entity included in the graph network according to the real-time data includes:

[0021] Obtain the stable operation time, the remaining time of the current task, and the current target distance of the AGV corresponding to the AGV entity in the graph network; wherein the current target distance is the distance between the AGV and the delivery starting point;

[0022] The scheduling weight of the AGV entity corresponding to the AGV is determined according to the stable operation time of the AGV, the remaining time of the current task and the current target distance; wherein, the stable operation time of the AGV is proportional to the scheduling weight of the AGV entity corresponding to the AGV, the remaining time of the current task of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV, and the current target distance of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV.

[0023] In a feasible embodiment of the present application, determining the scheduling weight of the production entity included in the graph network according to the real-time data further includes:

[0024] Determine the pass rate of the distribution road network corresponding to the road network entity in the graph network; wherein the pass rate of the distribution road network is described by the historical failure rate of the AGV on the distribution road network;

[0025] The dispatching weight of the road network entity corresponding to the distribution road network is determined according to the passing rate of the distribution road network; wherein the passing rate of the distribution road network is proportional to the dispatching weight of the road network entity corresponding to the distribution road network.

[0026] In a feasible embodiment of the present application, determining the scheduling weight of the production entity included in the graph network according to the real-time data further includes:

[0027] Determine the unit hourly output of the goods production line corresponding to the goods entity in the graph network;

[0028] The scheduling weight of the cargo entity corresponding to the cargo production line is determined according to the unit hourly output of the cargo production line; wherein the unit hourly output of the cargo production line is proportional to the scheduling weight of the cargo entity corresponding to the cargo production line.

[0029] In a feasible embodiment of the present application, the graph sub-network is output as a scheduling scheme, including:

[0030] Determine the road network entity corresponding to the graph subnetwork, and determine the shortest delivery route according to the delivery road network corresponding to the road network entity;

[0031] Determine the AGV entity corresponding to the graph subnetwork, and determine the AGV corresponding to the AGV entity;

[0032] The shortest delivery route and the AGV are output as the scheduling plan.

[0033] In a second aspect, the present application provides an AGV auxiliary scheduling device based on a knowledge graph, the device comprising:

[0034] An acquisition module is used to acquire production data; wherein the production data includes offline data and real-time data, wherein the offline data is data that remains unchanged during the production process, and the real-time data is data that changes in real time during the production process;

[0035] A construction module, configured to construct a knowledge graph based on the offline data; wherein the knowledge graph includes a plurality of production entities, the production entities are connected by entity relationships, and the production entities include at least an AGV entity, a cargo entity, and a road network entity;

[0036] A first determination module is used to determine, in response to the delivery task being issued, a graph network uniquely corresponding to the delivery task in the knowledge graph according to the delivery task, and determine a scheduling weight of the production entity contained in the graph network according to the real-time data;

[0037] A second determination module is used to determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities contained in the graph sub-network; wherein the graph sub-network contains only one AGV entity;

[0038] An output module is used to output the graph sub-network as a scheduling plan, and output the total scheduling weight of the graph sub-network as a reliability score of the scheduling plan.

[0039] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute an AGV assisted scheduling method based on a knowledge graph as described in any one of the first aspects of the present application.

[0040] In a fourth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute an AGV assisted scheduling method based on a knowledge graph as described in any one of the first aspects of the present application.

[0041] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0042] The method provided in the embodiment of the present application obtains production data; wherein the production data includes offline data and real-time data, the offline data is the data that remains unchanged during the production process, and the real-time data is the data that changes in real time during the production process; a knowledge graph is constructed based on the offline data; wherein the knowledge graph includes multiple production entities, and the production entities are connected by entity relationships, and the production entities include at least AGV entities, cargo entities, and road network entities; in response to the issuance of a delivery task, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph based on the delivery task, and the scheduling weights of the production entities included in the graph network are determined based on the real-time data; at least one graph sub-network is determined in the graph network, and the total scheduling weight of the graph sub-network is calculated based on the scheduling weights of the production entities included in the graph sub-network; wherein the graph sub-network only contains one AGV entity; the graph sub-network is output as a scheduling plan, and the total scheduling weight of the graph sub-network is output as a reliability score of the scheduling plan.

[0043] Through the technical solution provided in this application, full use is made of the production data in the production process, a knowledge graph is constructed based on the production data, and the complex scenarios involved in the production process of AGV are reproduced through knowledge graph technology. Auxiliary scheduling is achieved with the knowledge graph as the core, and possible scheduling plans and reliable scores corresponding to the scheduling plans are output to managers to assist managers in making scheduling decisions. Auxiliary scheduling of AGVs is achieved from the perspective of big data, thereby improving the operating efficiency of AGVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0047] Figure 1 A schematic diagram of a flow chart of an AGV assisted scheduling method based on a knowledge graph provided in an embodiment of the present application;

[0048] Figure 2A schematic diagram of the construction of a knowledge graph in an AGV assisted scheduling method based on a knowledge graph provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of the structure of an AGV auxiliary scheduling system based on a knowledge graph provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of the structure of an AGV auxiliary scheduling device based on a knowledge graph provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0053] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0054] In order to make full use of the large amount of data generated in the production process and realize the auxiliary scheduling of AGV from the perspective of big data, thereby improving the operating efficiency of AGV, the present application provides an AGV auxiliary scheduling method and device based on knowledge graph, which can realize auxiliary scheduling with knowledge graph as the core, output possible scheduling plans and the corresponding reliable scores of the scheduling plans to managers, and assist managers in making scheduling decisions.

[0055] Figure 1 A flow chart of an AGV assisted scheduling method based on a knowledge graph provided in an embodiment of the present application, referring to Figure 1 , an AGV assisted scheduling method based on knowledge graph provided in this application includes the following steps:

[0056] S1: Obtain production data; the production data includes offline data and real-time data, the offline data is the data that remains unchanged during the production process, and the real-time data is the data that changes in real time during the production process;

[0057] Specifically, the production data in the production workshop is obtained. The production data includes offline data and real-time data. The offline data is the data that remains unchanged in the production workshop during the production process, and the real-time data is the data that changes in real time in the production workshop during the production process.

[0058] In a feasible embodiment of the present application, offline data can be manually entered by the management personnel of the production workshop through input devices. Specifically, the offline data may include the brand of AGVs currently running in the production workshop, the basic attributes of each AGV, the basic information of each staff member in the production workshop, etc.

[0059] In a feasible embodiment of the present application, real-time data can be automatically obtained from the AGV, production line, and workshop warehouse in the production workshop. For example, the real-time position, current task status, working hours, etc. of the AGV can be obtained by obtaining the AGV's operation log. For example, the unit hourly output, operating status, operating time, etc. of the production line can be directly obtained from the production line.

[0060] In a feasible embodiment of the present application, after the production data is acquired, the production data may be stored in a corresponding database, and the production data may be cleaned in the corresponding database.

[0061] S2: Build a knowledge graph based on offline data; the knowledge graph includes multiple production entities, which are connected by entity relationships. The production entities include at least AGV entities, cargo entities, and road network entities.

[0062] Specifically, a knowledge graph is constructed based on offline data in the production data. The knowledge graph includes multiple production entities. There are corresponding entity relationships between the various production entities. The various production entities are connected through the entity relationships to complete the construction of the knowledge graph. In a feasible embodiment of the present application, the production entity includes at least an AGV entity, a cargo entity, and a road network entity. In other feasible embodiments of the present application, the production entity may also include a personnel entity, a task entity, a workshop entity, and the like.

[0063] It is understandable that the constructed knowledge graph can describe the current production situation of the production workshop and reproduce the complex scenarios involved in the production process of AGV.

[0064] In a feasible embodiment of the present application, constructing a knowledge graph based on offline data specifically includes the following steps:

[0065] For structured data in offline data, the entity relationship between production entities is determined through preset entity extraction rules;

[0066] For unstructured data in offline data, the entity relationship between production entities is determined through a preset entity extraction model;

[0067] Construct a knowledge graph based on production entities and entity relationships between production entities.

[0068] Specifically, for structured data, the production entities and entity relationships contained therein are relatively clear, and the production entities can be directly extracted and the entity relationships can be determined through the preset entity extraction rules. It should be noted that the entity extraction rules can be a set of templates pre-defined by the management personnel, and the relationships between entities are matched according to such templates, triples are constructed, and the production entities and entity relationships are determined. For example, the relationship between a task and an AGV is "AGV-completed-task", and the relationship between an AGV and a road network is "AGV-belongs to-road network".

[0069] Unstructured data usually appears in the form of text, and the production entities and entity relationships contained therein are not very clear, and need to be processed by an entity extraction model. In a feasible embodiment of the present application, the entity extraction model can specifically be a deep learning model such as BiLSTM+CRF, which inputs the unstructured data into the entity extraction model, identifies the production entities contained in the unstructured data, and determines the entity relationships between the production entities based on contextual semantics.

[0070] After determining each production entity and the entity relationship between each production entity from the offline data, a knowledge graph is constructed. In a feasible embodiment of the present application, part of the constructed knowledge graph can be constructed as follows: Figure 2 shown.

[0071] S3: In response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, and the scheduling weights of the production entities included in the graph network are determined according to the real-time data;

[0072] Specifically, after the delivery task is issued, in response to the issuance of the delivery task, the delivery task is obtained and identified, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, and the scheduling weights of each production entity are calculated based on the real-time data corresponding to the production nodes contained in the graph network.

[0073] A delivery task at least includes a delivery starting point, a delivery destination, and delivery goods. A delivery task is used to instruct the AGV where to get what goods and where to transport them. Delivery tasks can be automatically planned by the workshop management system or manually issued by the management staff of the production workshop.

[0074] In a feasible embodiment of the present application, in response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, specifically including the following steps:

[0075] Determine the delivery starting point, delivery destination and delivery goods from the delivery task;

[0076] Determine at least one distribution road network according to the distribution starting point and the distribution end point;

[0077] A knowledge graph retrieval formula is constructed based on the distribution road network and the distribution goods, and a graph network is found in the knowledge graph through the knowledge graph retrieval formula; wherein the graph network includes at least one road network entity and at least one AGV entity, the road network entity corresponds to the distribution road network, and the AGV entity corresponds to the AGV currently available for the distribution task.

[0078] Specifically, after determining the delivery starting point, delivery destination, and delivery goods from the delivery task, at least one delivery road network can be determined when the delivery starting point and delivery destination are clear. The delivery road network consists of one or more routes that the AGV may travel from the delivery starting point to the delivery destination. The delivery road network contains multiple road network nodes, and each road network node corresponds to a waypoint in the delivery road network.

[0079] After determining the route network nodes and the delivered goods, a knowledge graph search formula is constructed based on the route network nodes and the delivered goods, and the graph network is found in the knowledge graph through the knowledge graph search formula. Specifically, the technical solution of constructing the knowledge graph search formula and finding the corresponding graph network in the knowledge graph can be implemented through a graph query language, such as Cypher, Gremlin, SPARQL, etc. This part of the technical solution is an existing technology and will not be described in detail here.

[0080] The graph network includes at least one road network entity and at least one AGV entity. The road network entity corresponds to the distribution road network, and the AGV entity corresponds to the AGV currently available for the distribution task. The graph network also includes multiple production entities, and there are entity relationships between these production entities and the road network entity and / or AGV entity.

[0081] According to the real-time data corresponding to the production entities in the graph network, the dispatch weight of each production entity is calculated. In a feasible embodiment of the present application, the graph network includes at least an AGV entity, a cargo entity and a road network entity, and the dispatch weight includes at least the dispatch weight of the AGV entity, the dispatch weight of the cargo entity and the dispatch weight of the road network entity.

[0082] In a feasible embodiment of the present application, the scheduling weight of the AGV entity can be determined in the following manner:

[0083] Obtain the stable running time, remaining time of the current task, and current target distance of the AGV corresponding to the AGV entity in the graph network; the current target distance is the distance between the AGV and the delivery starting point;

[0084] The scheduling weight of the AGV entity corresponding to the AGV is determined according to the stable operation time of the AGV, the remaining time of the current task and the current target distance; wherein, the stable operation time of the AGV is proportional to the scheduling weight of the AGV entity corresponding to the AGV, the remaining time of the current task of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV, and the current target distance of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV.

[0085] In a feasible embodiment of the present application, the dispatch weight of the road network entity can be determined in the following manner:

[0086] Determine the pass rate of the distribution road network corresponding to the road network entity in the graph network; wherein the pass rate of the distribution road network is described by the historical failure rate of AGVs on the distribution road network;

[0087] The dispatch weight of the road network entity corresponding to the distribution road network is determined according to the passing rate of the distribution road network; wherein the passing rate of the distribution road network is proportional to the dispatch weight of the road network entity corresponding to the distribution road network.

[0088] In a feasible embodiment of the present application, the dispatch weight of the cargo entity may be determined in the following manner:

[0089] Determine the hourly output of the goods production line corresponding to the goods entity in the graph network;

[0090] The dispatch weight of the cargo entity corresponding to the cargo production line is determined according to the unit hourly output of the cargo production line; wherein, the unit hourly output of the cargo production line is proportional to the dispatch weight of the cargo entity corresponding to the cargo production line.

[0091] It should be noted that this application does not limit the specific calculation method of the scheduling weight of the above-mentioned AGV entity, the scheduling weight of the cargo entity and the scheduling weight of the road network entity. It only requires that the offline data and the scheduling weight satisfy the corresponding proportional or inverse proportional relationship.

[0092] As an example, the dispatch weight of the AGV entity can be calculated by the following formula:

[0093] The scheduling weight of the AGV entity = stable running time / (current target distance + remaining time of the current task).

[0094] Through the above-mentioned embodiments of calculating the dispatching weight of the AGV entity, the dispatching weight of the cargo entity and the dispatching weight of the road network entity, it can be known that the dispatching weight of the production entity is actually used to describe the reliability of the production entity in the distribution task. The technical solution provided by the above-mentioned embodiments quantifies a variety of offline data, calculates the dispatching weight, and completes the quantitative description of the reliability of the distribution task.

[0095] S4: determining at least one graph sub-network in the graph network, and calculating the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities included in the graph sub-network; wherein the graph sub-network only includes one AGV entity;

[0096] Specifically, the graph network includes at least one AGV entity and at least one road network entity. When the graph network includes multiple AGV entities and multiple road network entities, multiple graph sub-networks are determined based on one AGV entity. The graph sub-network includes an AGV entity and production entities that have an entity relationship with an AGV entity, such as a road network entity, a personnel entity, a cargo entity, etc.

[0097] It can be understood that any graph subnetwork corresponds to a scheduling scheme that can be implemented for the current delivery task. The AGV corresponding to the AGV entity in the graph subnetwork is the AGV selected for the scheduling scheme, and the distribution road network corresponding to the road network entity in the graph subnetwork is the road network that the AGV needs to travel in the scheduling scheme.

[0098] According to the scheduling weights of each production node in the graph sub-network, the total scheduling weight of the graph sub-network is calculated. Specifically, the scheduling weights of each production node in the graph sub-network are accumulated to obtain the total scheduling weight of the graph sub-network.

[0099] S5: Output the graph sub-network as a scheduling solution, and output the total scheduling weight of the graph sub-network as a reliability score of the scheduling solution;

[0100] Specifically, the graph subnetwork is output as a scheduling plan to clarify the delivery route and corresponding AGV of the current delivery task. At the same time, the total scheduling weight of the graph subnetwork is output as the reliability score of the scheduling plan. The reliability score actually describes the reliability of the scheduling plan. The higher the reliability score, the higher the probability of the scheduling plan being successfully completed, and the higher the priority of the scheduling plan.

[0101] In a feasible embodiment of the present application, the graph sub-network is output as a scheduling scheme, which specifically includes the following steps:

[0102] Determine the road network entity corresponding to the graph subnetwork, and determine the shortest delivery route based on the delivery road network corresponding to the road network entity;

[0103] Determine the AGV entity corresponding to the graph subnetwork, and determine the AGV corresponding to the AGV entity;

[0104] The shortest delivery route and AGV are output as a scheduling plan.

[0105] Specifically, the road network entity corresponding to the graph subnetwork is determined, and the shortest delivery route in the distribution road network corresponding to the current road network entity is determined through the preset shortest route planning algorithm. The shortest delivery route starts from the distribution starting point in the distribution road network and reaches the distribution destination through the least road network nodes. At the same time, the AGV corresponding to the AGV entity is determined based on the AGV entity in the graph subnetwork.

[0106] Therefore, the distribution plan actually consists of the following elements: the AGV that executes the distribution plan, the distribution node where the AGV travels, the distribution goods of the AGV, the distribution starting point and the distribution end point.

[0107] Through the technical solution provided in this application, full use is made of the production data in the production process, a knowledge graph is constructed based on the production data, and the complex scenarios involved in the production process of AGV are reproduced through knowledge graph technology. Auxiliary scheduling is achieved with the knowledge graph as the core, and possible scheduling plans and reliable scores corresponding to the scheduling plans are output to managers to assist managers in making scheduling decisions. Auxiliary scheduling of AGVs is achieved from the perspective of big data, thereby improving the operating efficiency of AGVs.

[0108] In a possible practical implementation scenario of the present application, an AGV assisted scheduling system based on a knowledge graph can be deployed in a production workshop, and the method provided by any of the above embodiments of the present application can be executed through the system.

[0109] Reference Figure 3 , an AGV auxiliary scheduling system based on knowledge graph may include a data layer, a graph layer and an application layer, wherein:

[0110] The data layer is used to obtain production data from the production workshop and upload the production data to the atlas layer; production data includes offline data and real-time data. Offline data refers to data that remains unchanged during the production process, and real-time data refers to data that changes in real time during the production process.

[0111] The graph layer is used to construct a knowledge graph based on offline data; the knowledge graph includes multiple production entities, which are connected by entity relationships. The production entities include at least AGV entities, cargo entities, and road network entities.

[0112] The application layer is used to respond to the delivery task, determine the graph network that uniquely corresponds to the delivery task in the knowledge graph according to the delivery task, and determine the scheduling weight of the production entity contained in the graph network according to the real-time data;

[0113] And, the application layer is further used to determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities included in the graph sub-network; wherein the graph sub-network only includes one AGV entity;

[0114] Furthermore, the application layer is used to output the graph subnetwork as a scheduling plan, and output the total scheduling weight of the graph subnetwork as a reliability score of the scheduling plan.

[0115] In the specific implementation scenario, the data layer can be deployed in the production workshop, specifically, it can be deployed on the upper management computer of various production equipment in the production workshop; the graph layer can be deployed in the back-end server, and the back-end server is connected to the upper management computer of various production equipment in the production workshop, and can directly obtain the production data collected by the data layer; the application layer can be deployed on the upper computer for the production workshop management personnel, which can call the knowledge graph in the graph layer and realize the auxiliary scheduling of AGV based on the knowledge graph.

[0116] Continue to refer to Figure 4 In the graph layer, after the knowledge graph is constructed based on production data, the knowledge graph is stored in the Neo4j database as entity-relationship-entity triples. At the same time, when the graph layer extracts knowledge based on production data, the constructed knowledge graph is also updated synchronously in response to the update of real-time data.

[0117] Corresponding to the above method embodiment, the present application also provides an AGV auxiliary scheduling device based on knowledge graph, referring to Figure 4 The device specifically includes an acquisition module 401, a construction module 402, a first determination module 403, a second determination module 404 and an output module 405.

[0118] The acquisition module 401 is used to acquire production data; wherein the production data includes offline data and real-time data, the offline data is the data that remains unchanged during the production process, and the real-time data is the data that changes in real time during the production process;

[0119] A construction module 402 is used to construct a knowledge graph based on offline data; wherein the knowledge graph includes multiple production entities, and the production entities are connected by entity relationships, and the production entities at least include AGV entities, cargo entities, and road network entities;

[0120] The first determination module 403 is used to determine, in response to the delivery task being issued, a graph network uniquely corresponding to the delivery task in the knowledge graph according to the delivery task, and determine the scheduling weight of the production entity included in the graph network according to the real-time data;

[0121] The second determination module 404 is used to determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities included in the graph sub-network; wherein the graph sub-network only includes one AGV entity;

[0122] The output module 405 is used to output the graph sub-network as a scheduling solution, and output the total scheduling weight of the graph sub-network as a reliability score of the scheduling solution.

[0123] In a feasible embodiment of the present application, the construction module 402 includes:

[0124] A first construction unit is used to determine the entity relationship between production entities and production entities through a preset entity extraction rule for structured data in offline data;

[0125] The second construction unit is used to determine the entity relationship between production entities and production entities through a preset entity extraction model for unstructured data in offline data;

[0126] The third construction unit is used to construct a knowledge graph based on production entities and entity relationships between production entities.

[0127] In a feasible embodiment of the present application, the first determining module 403 includes:

[0128] A first determining unit is used to determine a delivery starting point, a delivery destination, and delivery goods from a delivery task;

[0129] A second determining unit is used to determine at least one delivery road network according to the delivery starting point and the delivery end point;

[0130] A search unit is used to construct a knowledge graph search formula based on the distribution road network and the distribution goods, and to find a graph network in the knowledge graph through the knowledge graph search formula; wherein the graph network includes at least one road network entity and at least one AGV entity, the road network entity corresponds to the distribution road network, and the AGV entity corresponds to the AGV currently available for the distribution task.

[0131] In a feasible embodiment of the present application, the first determining module 403 further includes:

[0132] The first acquisition unit is used to acquire the stable operation time, the remaining time of the current task and the current target distance of the AGV corresponding to the AGV entity in the graph network; wherein the current target distance is the distance between the AGV and the delivery starting point;

[0133] The third determination unit is used to determine the scheduling weight of the AGV entity corresponding to the AGV according to the stable operation time of the AGV, the remaining time of the current task and the current target distance; wherein, the stable operation time of the AGV is proportional to the scheduling weight of the AGV entity corresponding to the AGV, the remaining time of the current task of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV, and the current target distance of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV.

[0134] In a feasible embodiment of the present application, the first determining module 403 further includes:

[0135] A fourth determination unit is used to determine the pass rate of the distribution road network corresponding to the road network entity in the graph network; wherein the pass rate of the distribution road network is described by the historical failure rate of the AGV on the distribution road network;

[0136] The fifth determining unit is used to determine the dispatching weight of the road network entity corresponding to the distribution road network according to the passing rate of the distribution road network; wherein the passing rate of the distribution road network is proportional to the dispatching weight of the road network entity corresponding to the distribution road network.

[0137] In a feasible embodiment of the present application, the first determining module 403 further includes:

[0138] A sixth determination unit, used to determine the unit hourly output of the goods production line corresponding to the goods entity in the graph network;

[0139] The seventh determination unit is used to determine the scheduling weight of the cargo entity corresponding to the cargo production line according to the unit hourly output of the cargo production line; wherein the unit hourly output of the cargo production line is proportional to the scheduling weight of the cargo entity corresponding to the cargo production line.

[0140] In a feasible embodiment of the present application, the output module 405 includes:

[0141] An eighth determination unit, used to determine the road network entity corresponding to the graph sub-network, and determine the shortest delivery route according to the delivery road network corresponding to the road network entity;

[0142] A ninth determination unit, used to determine the AGV entity corresponding to the graph subnetwork, and determine the AGV corresponding to the AGV entity;

[0143] The output unit is used to output the shortest delivery route and AGV as a scheduling plan.

[0144] like Figure 5 As shown, an embodiment of the present application provides an electronic device, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504.

[0145] Memory 503, used for storing computer programs;

[0146] In one embodiment of the present application, the processor 501 is used to execute the program stored in the memory 503 to implement an AGV assisted scheduling method based on a knowledge graph provided by any of the aforementioned method embodiments, including:

[0147] Obtain production data; production data includes offline data and real-time data, offline data is data that remains unchanged during the production process, and real-time data is data that changes in real time during the production process;

[0148] Construct a knowledge graph based on offline data; wherein the knowledge graph includes multiple production entities, which are connected by entity relationships, and the production entities include at least AGV entities, cargo entities, and road network entities;

[0149] In response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, and the scheduling weights of the production entities contained in the graph network are determined according to the real-time data;

[0150] Determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities included in the graph sub-network; wherein the graph sub-network only includes one AGV entity;

[0151] The graph sub-network is output as a scheduling plan, and the total scheduling weight of the graph sub-network is output as the reliability score of the scheduling plan.

[0152] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of an AGV assisted scheduling method based on a knowledge graph as provided in any of the aforementioned method embodiments are implemented.

[0153] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0155] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0156] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An AGV assisted scheduling method based on knowledge graph, characterized in that: The method comprises: Acquire production data; wherein the production data includes offline data and real-time data, the offline data is data that remains unchanged during the production process, and the real-time data is data that changes in real time during the production process; Constructing a knowledge graph according to the offline data; wherein the knowledge graph includes a plurality of production entities, the production entities are connected by entity relationships, and the production entities include at least an AGV entity, a cargo entity, and a road network entity; In response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, and a scheduling weight of the production entity contained in the graph network is determined according to the real-time data; Determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities contained in the graph sub-network; wherein the graph sub-network contains only one AGV entity; Outputting the graph subnetwork as a scheduling solution, and outputting the total scheduling weight of the graph subnetwork as a reliability score of the scheduling solution; Wherein, determining the scheduling weight of the production entity contained in the graph network according to the real-time data includes: Determine the unit hourly output of the goods production line corresponding to the goods entity in the graph network; The scheduling weight of the cargo entity corresponding to the cargo production line is determined according to the unit hourly output of the cargo production line; wherein the unit hourly output of the cargo production line is proportional to the scheduling weight of the cargo entity corresponding to the cargo production line.

2. The method according to claim 1, characterized in that Constructing a knowledge graph based on the offline data, including: For the structured data in the offline data, determining the entity relationship between the production entities and the production entities by using a preset entity extraction rule; For the unstructured data in the offline data, determining the entity relationship between the production entities and the production entities through a preset entity extraction model; The knowledge graph is constructed according to the production entities and the entity relationships between the production entities.

3. The method according to claim 1, characterized in that In response to the delivery task being issued, a graph network uniquely corresponding to the delivery task is determined in the knowledge graph according to the delivery task, including: Determine the delivery starting point, delivery destination and delivery goods from the delivery task; Determine at least one distribution road network according to the distribution starting point and the distribution end point; A knowledge graph search formula is constructed based on the distribution road network and the distribution goods, and the graph network is found in the knowledge graph through the knowledge graph search formula; wherein, the graph network includes at least one of the road network entities and at least one of the AGV entities, the road network entity corresponds to the distribution road network, and the AGV entity corresponds to the AGV currently available for the distribution task.

4. The method according to claim 3, characterized in that Determining the scheduling weight of the production entity included in the graph network according to the real-time data includes: Obtain the stable operation time, the remaining time of the current task, and the current target distance of the AGV corresponding to the AGV entity in the graph network; wherein the current target distance is the distance between the AGV and the delivery starting point; The scheduling weight of the AGV entity corresponding to the AGV is determined according to the stable operation time of the AGV, the remaining time of the current task and the current target distance; wherein, the stable operation time of the AGV is proportional to the scheduling weight of the AGV entity corresponding to the AGV, the remaining time of the current task of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV, and the current target distance of the AGV is inversely proportional to the scheduling weight of the AGV entity corresponding to the AGV.

5. The method according to claim 4, characterized in that Determining the scheduling weight of the production entity included in the graph network according to the real-time data, further comprising: Determine the pass rate of the distribution road network corresponding to the road network entity in the graph network; wherein the pass rate of the distribution road network is described by the historical failure rate of the AGV on the distribution road network; The dispatching weight of the road network entity corresponding to the distribution road network is determined according to the passing rate of the distribution road network; wherein the passing rate of the distribution road network is proportional to the dispatching weight of the road network entity corresponding to the distribution road network.

6. The method according to claim 5, characterized in that Outputting the graph subnetwork as a scheduling solution includes: Determine the road network entity corresponding to the graph subnetwork, and determine the shortest delivery route according to the delivery road network corresponding to the road network entity; Determine the AGV entity corresponding to the graph subnetwork, and determine the AGV corresponding to the AGV entity; The shortest delivery route and the AGV are output as the scheduling plan.

7. An AGV auxiliary scheduling device based on knowledge graph, characterized in that: The device comprises: An acquisition module is used to acquire production data; wherein the production data includes offline data and real-time data, wherein the offline data is data that remains unchanged during the production process, and the real-time data is data that changes in real time during the production process; A construction module, configured to construct a knowledge graph based on the offline data; wherein the knowledge graph includes a plurality of production entities, the production entities are connected by entity relationships, and the production entities include at least an AGV entity, a cargo entity, and a road network entity; A first determination module is used to determine, in response to the issuance of a delivery task, a graph network uniquely corresponding to the delivery task in the knowledge graph according to the delivery task, and determine a scheduling weight of the production entity contained in the graph network according to the real-time data; A second determination module is used to determine at least one graph sub-network in the graph network, and calculate the total scheduling weight of the graph sub-network according to the scheduling weights of the production entities contained in the graph sub-network; wherein the graph sub-network contains only one AGV entity; An output module, used to output the graph sub-network as a scheduling solution, and output the total scheduling weight of the graph sub-network as a reliability score of the scheduling solution; Wherein, the first determining module includes: A sixth determination unit, used to determine the unit hourly output of the goods production line corresponding to the goods entity in the graph network; The seventh determination unit is used to determine the scheduling weight of the cargo entity corresponding to the cargo production line according to the unit hourly output of the cargo production line; wherein the unit hourly output of the cargo production line is proportional to the scheduling weight of the cargo entity corresponding to the cargo production line.

8. An electronic device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to implement the method according to any one of claims 1-6.

9. A computer storage medium, characterized in that Computer executable instructions are stored, and the computer executable instructions are used to execute the method according to any one of claims 1-6.