Big data platform management system and method oriented to full life cycle of equipment materials

Abstract

The invention relates to the technical field of data processing, and provides an equipment material full life cycle-oriented big data platform management system and method, and the system comprises a multi-source data collection module which is used for collecting material data of equipment materials in each stage of the full life cycle to form a material data set; the data fusion module is used for carrying out data fusion on different material data in the material data set based on different application scenes so as to form a fused data group corresponding to the application scenes; and the decision module is used for generating at least one decision of an inventory optimization decision and a fault alarm decision based on the fused data set. According to the invention, the problems of information lagging and data islanding in the material management method in the prior art are effectively solved, the inventory optimization decision and the fault alarm decision are generated through the fusion data set, and the function of effective decision making according to the corresponding fusion data set in different application scenarios is realized. The beneficial effects of optimizing inventory or finding faults and giving an alarm are achieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a big data platform management system and method for the entire life cycle of equipment and materials. Background Technology

[0002] Traditional material data management methods mostly rely on manual registration combined with hierarchical reporting, which suffers from shortcomings such as information lag, data silos, and inefficient decision-making. For example, the status of material storage cannot be synchronized in real time, leading to inventory backlog or shortages; transportation route planning lacks dynamic optimization, increasing logistics costs; and material maintenance relies on experience-based judgment, easily resulting in over-maintenance or missed fault detection. In existing technologies, although some management systems have introduced IoT and data analysis technologies, they have not formed a closed-loop management system covering the entire lifecycle (factory delivery, transportation, warehousing, allocation, use, and recycling stages, etc.), and lack deep integration of multimodal data and intelligent decision-making capabilities. Summary of the Invention

[0003] This invention provides a big data platform management system and method for the entire life cycle of equipment and materials, in order to solve the technical problems in the prior art that the material data does not form a closed-loop management covering the entire life cycle and lacks the ability to deeply integrate multimodal data and make intelligent decisions.

[0004] This invention provides a big data platform management system for the entire lifecycle of equipment and materials, comprising the following modules: The multi-source data acquisition module is used to collect material data of equipment and materials at all stages of the entire life cycle in order to form a material dataset. The data fusion module is used to fuse different material data in the material dataset based on different application scenarios to form a fused data group corresponding to the application scenario. The decision module is used to generate at least one of an inventory optimization decision and a fault alarm decision based on the fused data set.

[0005] According to the present invention, a big data platform management system for the entire lifecycle of equipment and materials includes a data fusion module comprising: The data preprocessing submodule is used to preprocess the material data in the material dataset. The preprocessing includes: removing outliers, removing duplicates, and standardization. The fusion and association submodule is used to obtain preset application scenarios, including: transportation scenario, warehousing scenario, material usage scenario, and traceability scenario. For the transportation scenario, the pre-processed first temperature and humidity data, vibration data, transportation trajectory data, and first material image data during transportation are fused into a first fused data group. For the warehousing scenario, the pre-processed second temperature and humidity data, material entry records, material exit records, and second material image data are fused into a second fused data group. For the material usage scenario, the pre-processed material maintenance records and third material image data are fused into a third fused data group. For the traceability scenario, the pre-processed material attribute data, transportation trajectory data, first material image data, second material image data, and third material image data are fused into a fourth fused data group.

[0006] According to the big data platform management system for the entire lifecycle of equipment and materials provided by the present invention, the decision-making module includes: The fault prediction submodule is used to predict whether a material transportation fault will occur based on the first temperature and humidity, vibration data and the first material image data in the first fused data group. When a material transportation fault is predicted, an alarm is issued and the transportation trajectory data is output. The transportation trajectory data is generated by the positioning data collected by the positioning sensor installed on the transportation vehicle. The vibration data is queried to find the positioning data corresponding to the vibration amplitude being greater than the amplitude threshold or the temperature being higher than the preset temperature, so as to determine the transportation segment corresponding to the positioning data. The fault prediction submodule is also used to determine the storage time of materials based on the material inbound record and the material outbound record, and to predict the fault type and the usage time before the fault occurs based on the second temperature and humidity, the storage time of the materials, the material maintenance record and the third material image data.

[0007] According to the big data platform management system for the entire lifecycle of equipment and materials provided by the present invention, the decision-making module further includes: The inventory optimization submodule is used to calculate the current inventory level based on the material inbound and outbound records in the second fused data group, and to generate the current material demand based on the current inventory level, the historical inventory level of the same period, and the historical demand level of the same period, so as to optimize the inventory. Alternatively, it can be used to calculate the current material inventory based on the material inbound and outbound records in the second fused data group, and generate the current material demand based on the current material inventory, the historical material inventory of the same period, the historical material demand of the same period, the material failure type, and the usage time before the failure, so as to optimize the inventory.

[0008] According to the big data platform management system for the entire lifecycle of equipment and materials provided by the present invention, the decision-making module further includes: The route planning submodule is used to plan the transportation route of materials from the factory to the warehouse, and to plan the transportation route of materials from the warehouse to the place of use.

[0009] The big data platform management system for the entire life cycle of equipment and materials provided by the present invention further includes: an emergency response module, used to monitor material data collected by sensors in real time, and to send corresponding alarm information to the monitoring terminal when multiple consecutive material data collected by sensors exceed the corresponding material data threshold. The emergency response module is also used to send a warehouse inventory warning to the monitoring terminal when the inventory of materials is lower than the minimum inventory threshold of the warehouse.

[0010] The big data platform management system for the entire lifecycle of equipment and materials provided by the present invention further includes: a dynamic reconfiguration module, used for: The material procurement plan is dynamically adjusted based on the quality inspection reports of materials leaving the factory, historical delivery data, and material maintenance records. The system acquires vibration data collected by vibration sensors and positioning data collected by positioning sensors on each vehicle during transportation. It then acquires the target time period corresponding to the vibration data where the amplitude is continuously greater than the vibration amplitude that the materials can withstand. If the target time period is greater than a time period threshold, the system replans the transportation route of the materials to avoid the road segment corresponding to the positioning data within the target time period. The frequency of material entry and exit is calculated based on the material entry and exit records. If the frequency of material entry and exit exceeds the entry and exit frequency threshold, the minimum inventory threshold of the warehouse is increased.

[0011] The big data platform management system for the entire life cycle of equipment materials provided by the present invention further includes: a blockchain evidence storage module, used to store key data of the material data on the blockchain, the key data including: quality inspection reports of materials leaving the factory, material warehousing records and material outgoing records.

[0012] This invention also provides a big data platform management method for the entire lifecycle of equipment and materials, comprising the following steps: Collect material data of equipment and supplies at each stage of the entire life cycle to form a material dataset; Based on different application scenarios, the different material data in the material dataset are fused to form a fused data group corresponding to the application scenario. Based on the fused data set, at least one of an inventory optimization decision and a fault alarm decision is generated.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the program, it implements the big data platform management method for the entire life cycle of equipment and materials as described above.

[0014] The big data platform management system and method for the entire lifecycle of equipment and materials provided by this invention forms a closed-loop management of material data covering the entire lifecycle by collecting material data at each stage of the entire lifecycle. Furthermore, it integrates material data throughout the entire lifecycle in different application scenarios, effectively solving the problems of information lag and data silos in existing material management methods. At the same time, by generating at least one of inventory optimization decision and fault alarm decision through the fused data group, it realizes the function of making effective decisions based on the corresponding fused data group in different application scenarios, achieving the beneficial effects of optimizing inventory or detecting and alarming faults. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the structure of the big data platform management system for the entire life cycle of equipment and materials provided by the present invention.

[0017] Figure 2 This is a flowchart illustrating the big data platform management method for the entire lifecycle of equipment and materials provided by this invention.

[0018] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] The big data platform management system for the entire lifecycle of equipment and materials according to embodiments of the present invention, such as... Figure 1 As shown, it includes the following modules: The multi-source data acquisition module 110 is used to collect material data of equipment and materials at each stage of the entire life cycle in order to form a material dataset.

[0021] Specifically, the multi-source data acquisition module 110 collects material data of equipment and materials at each stage of the entire life cycle, namely, different material data at each stage such as factory delivery, transportation, warehousing, allocation, use and recycling.

[0022] At the factory exit stage, material data includes: material attribute data (material name, batch number, ID number, material usage instructions, etc., which can be obtained by scanning the QR code or barcode on the material) and quality inspection report.

[0023] During the transportation phase, the material data includes: first temperature and humidity, vibration data, transportation trajectory data, and first material image data. The first temperature and humidity are collected by temperature and humidity sensors installed on the transportation vehicle, the vibration data are collected by vibration sensors installed on the transportation vehicle, the transportation trajectory data is generated from positioning data collected by positioning sensors installed on the transportation vehicle, and the first material image data is material images collected during transportation.

[0024] During the warehousing stage, the material data includes: secondary temperature and humidity, material inbound records, material outbound records, and secondary material image data. The secondary temperature and humidity are collected by temperature and humidity sensors installed in the warehouse. The material inbound and material outbound records can be obtained by scanning the QR code or barcode on the material when it is inbound or outbound. The secondary material image data can be composed of material images collected at preset intervals during material inbound, material outbound, and during the warehousing process.

[0025] During the usage phase, the material data includes: material maintenance records and third-party material image data. The material maintenance records are the maintenance and upkeep records of the materials during use. The third-party material image data can be composed of material images collected before and after use, especially for materials that can reflect wear and tear or missing parts during use.

[0026] For the allocation and recovery stages, allocation involves transferring materials from one warehouse to another or to the place of use, while recovery involves returning materials from the place of use to the warehouse. The corresponding material data can be referenced from the transportation stage.

[0027] The equipment and supplies managed by the system vary depending on the application area. For example, in the medical field, the supplies include medical devices, first aid kits, and emergency medicines.

[0028] The data fusion module 120 is used to fuse different material data in the material dataset based on different application scenarios to form a fused data group corresponding to the application scenario. Through data fusion, a complete status profile of the materials throughout their entire lifecycle is constructed, eliminating data silos and providing a data foundation that conforms to the application scenario for subsequent decision-making.

[0029] The decision module 130 is used to generate at least one of an inventory optimization decision and a fault alarm decision based on the fused data set. Specifically, it obtains at least one of the inventory optimization decision and fault alarm decision by analyzing the material data in the fused data set. For example, it determines the demand for each material based on the consumption of each material during the warehousing stage, thereby obtaining the inventory optimization decision.

[0030] This embodiment of the big data platform management system for the entire lifecycle of equipment and materials forms a closed-loop management system covering the entire lifecycle of material data by collecting material data at each stage of the entire lifecycle. Furthermore, it integrates material data throughout the entire lifecycle in different application scenarios, effectively solving the problems of information lag and data silos in existing material management methods. At the same time, it generates at least one of the following decisions by integrating data groups: inventory optimization decision and fault alarm decision. This enables effective decision-making based on the corresponding integrated data groups in different application scenarios, achieving the beneficial effects of optimizing inventory or detecting and alarming faults.

[0031] In some embodiments, the data fusion module 120 specifically includes: The data preprocessing submodule 121 is used to preprocess the material data in the material dataset. The preprocessing includes: removing outliers, removing duplicate values, and standardization. Specifically, for data collected by each sensor at each stage, outliers are removed. Since sensors collect data frequently, there are many duplicate values; only one of the duplicates needs to be retained. To facilitate data processing, the sensor data (e.g., vibration sensor data) is converted to a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0032] The fusion and association submodule 122 is used to acquire preset application scenarios, including: transportation scenario, warehousing scenario, material usage scenario, and traceability scenario. For the transportation scenario, the pre-processed first temperature and humidity data, vibration data, transportation trajectory data, and first material image data during transportation are fused into a first fused data group. For the warehousing scenario, the pre-processed second temperature and humidity data, material entry records, material exit records, and second material image data are fused into a second fused data group. For the material usage scenario, the pre-processed material maintenance records and third material image data are fused into a third fused data group. For the traceability scenario, the pre-processed material attribute data, transportation trajectory data, first material image data, second material image data, and third material image data are fused into a fourth fused data group.

[0033] It is understandable that, in a given scenario, material data collected within the same time period constitutes a single data record. All data records then form a fused data set. For example, during the transportation phase, the first temperature and humidity data, vibration data, transportation trajectory data, and the first material image data collected at the same acquisition time point (within acceptable error range) constitute a single data record.

[0034] In this embodiment, by preprocessing the material data and then merging the preprocessed data into different fused data groups according to transportation, warehousing, usage, and traceability scenarios, data silos are eliminated, providing a data foundation that conforms to the application scenario for subsequent decision-making. Furthermore, for the traceability scenario, material attribute data, transportation trajectory data, first material image data, second material image data, and third material image data are merged to achieve traceability of the entire lifecycle of equipment and materials. For example, by using the batch number in the material attribute data of the equipment and materials, combined with the data from various positioning sensors during transportation, the flow path of a certain batch of equipment and materials can be determined, tracing potentially problematic links.

[0035] In some embodiments, the decision module 130 includes a fault prediction submodule 131.

[0036] The fault prediction submodule 131 is used to predict whether a material transportation fault will occur based on the first temperature and humidity, vibration data and the first material image data in the first fused data group. When a material transportation fault is predicted, an alarm is issued and the transportation trajectory data is output.

[0037] In most cases of material transportation failures, vibration during transport causes damage to the materials. For example, vibration data and initial material image data can be input into a pre-trained transportation failure model. The model predicts and outputs whether a transportation failure has occurred. This model is trained based on historical vibration data, historical initial material image data, and historical transportation failure labels marked after each transport. Historical transportation failure labels can be determined as follows: after each historical transport, the failure rate (vibration damage) of a truckload of materials is manually calculated. A failure rate greater than 5% is marked as a transportation failure (represented by 1), otherwise it is marked as no transportation failure (represented by 0). This transportation failure model can be constructed using a Long Short-Term Memory (LSTM) network from deep learning.

[0038] For certain medical supplies, in addition to vibration, prolonged exposure to high temperatures can also cause transport failures that render the medication ineffective. For example, by analyzing the temperature and humidity data in the first fused data set, if the duration of the temperature exceeding a preset temperature exceeds a first preset duration threshold, the result of the transport failure can be directly obtained.

[0039] When a material transportation failure is predicted, an alarm is issued and the transportation trajectory data is output. The transportation trajectory data consists of various positioning data collected by each positioning sensor during transportation. Therefore, the positioning data corresponding to vibration amplitude greater than the amplitude threshold or temperature higher than the preset temperature can be queried in the vibration data to determine the transportation segment corresponding to the positioning data, thereby reminding subsequent transportation vehicles to avoid the transportation segment.

[0040] The fault prediction submodule 131 is also used to determine the material storage time based on material inbound and outbound records, and to predict the type of material fault and the usage time before the fault occurs based on the second temperature and humidity, the material storage time, material maintenance records, and third material image data. The second temperature and humidity and the material storage time in the warehouse will affect the type of fault that occurs. For example, excessively high temperatures and / or excessively long storage times can lead to the loss of efficacy of medical supplies. During the use of materials, the material maintenance records and the third material image data during use will reflect the wear and tear and missing parts of the materials. Wear and tear and missing parts will ultimately lead to different types of faults, and the usage time before the fault can be predicted based on the degree of wear and tear and the degree of missing parts.

[0041] For example, the second temperature and humidity, the storage duration of the materials, the material maintenance records, and the third material image data are input into a pre-trained fault type prediction model. The fault type prediction model predicts the fault type of the materials and the usage duration before the fault occurs. The fault type prediction model is trained based on historical second temperature and humidity, historical material storage duration, historical material maintenance records, and historical third material image data as samples, along with their historical fault types and historical usage durations before the fault as labels. This fault type prediction model can be constructed using a Support Vector Machine (SVM) in deep learning.

[0042] It should be noted that different materials correspond to their own transportation failure models and failure type prediction models.

[0043] In some embodiments, the decision module 130 further includes an inventory optimization submodule 132.

[0044] The inventory optimization submodule 132 is used to calculate the current material inventory based on the material inbound and material outbound records in the second fusion data group, and to generate the current material demand based on the current material inventory, the historical material inventory of the same period, and the historical material demand of the same period, so as to optimize the inventory.

[0045] For example, regarding medical supplies, since many illnesses are seasonal, the current demand for supplies can be determined by referring to historical inventory levels and demand levels for the same period in previous years. Specifically, current demand = historical inventory level - current inventory level + historical demand level.

[0046] Alternatively, the inventory optimization submodule 132 is used to calculate the current material inventory based on the material inbound and material outbound records in the second fused data group, and generate the current material demand based on the current material inventory, the historical material inventory of the same period, the historical material demand of the same period, the material fault type and the usage time before the fault occurred, so as to optimize the inventory.

[0047] Because the types of material failures and the duration of use before failure are predicted, some materials in the warehouse will soon fail. Therefore, the current material demand generated by combining the material failure types and the duration of use before failure fills the gaps in materials that cannot be used due to failure, thus achieving better optimization of inventory.

[0048] Specifically, the current material demand = historical material inventory for the same period - current material inventory + historical material demand for the same period + the number of materials in the current inventory whose usage time before the failure was less than the second preset time threshold.

[0049] In some embodiments, the decision module 130 further includes a route planning submodule 133, used to plan the transportation route of materials from the factory to the warehouse, and to plan the transportation route of materials from the warehouse to the place of use.

[0050] Specifically, route planning can be carried out using Dijkstra's algorithm. As long as the origin, destination and all transit points are known, the shortest path from the origin to the destination can be planned according to Dijkstra's algorithm, thereby saving transportation costs.

[0051] The place of origin can be the place of manufacture and the place of destination can be the place of storage, or the place of origin can be the place of storage and the place of use can be the place of use.

[0052] Furthermore, dynamic optimization of transportation routes is achieved by combining Dijkstra's algorithm and fuzzy inference technology. For route selection in fuzzy environments, a fuzzy shortest route labeling algorithm based on OERI integral is adopted, with the following formula: .

[0053] in, λ For decision-makers' preference coefficient, u and v Representing nodes, connecting nodes u and v The path is called an edge. d ( u , v To determine the ideal distance for a path (edge), μ ( u , v () represents the fuzzy distance. d λ ( u , v ) is a node u and v The actual distance.

[0054] In some embodiments, the big data platform management system for the entire lifecycle of equipment and materials further includes an emergency response module 140. The emergency response module 140 is used to monitor material data collected by sensors in real time, and to send corresponding alarm information to the monitoring terminal when multiple consecutive material data collected by the sensors exceed the corresponding material data threshold.

[0055] In this embodiment, multiple consecutive material data collected by the sensor exceed the corresponding material data threshold, ruling out sensor malfunction. This indicates that the material data collected by the sensor is indeed abnormal. For example, if the temperature in the temperature and humidity data collected by the sensor suddenly increases and continues to increase, it indicates that the ambient temperature during transportation or storage is rising, and emergency cooling measures need to be taken.

[0056] The emergency response module 140 is also used to send a warehouse inventory warning to the monitoring terminal when the inventory of materials is lower than the minimum inventory threshold of the warehouse.

[0057] In this embodiment, the emergency response module 140 can promptly detect abnormal material data and low material inventory, enabling staff to handle emergencies in a timely manner.

[0058] In some embodiments, the big data platform management system for the entire lifecycle of equipment and materials further includes a dynamic reconstruction module 150.

[0059] The dynamic reconfiguration module 150 is used to dynamically adjust the material procurement plan based on the material's quality inspection report, historical delivery data, and material maintenance records. Specifically, if the quality level in the quality inspection report does not meet the specified level, the historical delivery data does not meet the specified delivery requirements, or the maintenance frequency in the material maintenance records exceeds a predetermined frequency threshold, a prompt to dynamically adjust the procurement plan will be output to remind the user to change the material manufacturer to ensure material quality.

[0060] The dynamic reconstruction module 150 is also used to acquire vibration data collected by vibration sensors on each vehicle and positioning data collected by positioning sensors during transportation. It identifies the target time period corresponding to vibration data where the amplitude continuously exceeds the vibration amplitude that the materials can withstand. If the target time period exceeds a time period threshold (e.g., 5-10 minutes), the module replans the subsequent transportation route of the materials, ensuring the replanned route avoids the road segments corresponding to the positioning data within the target time period, thus preventing transportation failures during subsequent transport. Specifically, the route planning submodule 133 can set the road length of the road segments corresponding to the positioning data within the target time period to infinity, allowing the route planning submodule 133 to replan the transportation route.

[0061] The dynamic reconfiguration module 150 is also used to count the frequency of material entry and exit based on material entry and exit records. If the frequency of material entry and exit exceeds a threshold, the minimum warehouse inventory threshold is increased. A frequency greater than the threshold indicates a high demand for materials; therefore, the minimum warehouse inventory threshold is increased to ensure a continuous supply of materials.

[0062] In some embodiments, the big data platform management system for the entire lifecycle of equipment materials further includes: a blockchain evidence storage module 160, used to store key data of the material data on the blockchain, the key data including: quality inspection reports of materials leaving the factory, material warehousing records and material outgoing records.

[0063] Specifically, the data is hashed and encrypted before being stored on the blockchain to ensure its immutability and traceability. In the event of a dispute over the quality of supplies, the blockchain ledger can quickly verify the entire lifecycle of the supplies' flow and operational records, protecting the rights of all parties.

[0064] This invention also provides a big data platform management method for the entire lifecycle of equipment and materials, the specific process of which is as follows: Figure 1 As shown, it includes the following steps S210 to S230.

[0065] Step S210: Collect material datasets for equipment and supplies at each stage of the entire life cycle. The material dataset for each stage includes material data collected by at least one sensor.

[0066] Step S220: Based on different application scenarios, merge the different material data in the material dataset to form a fused data group corresponding to the application scenario.

[0067] Step S230: Generate at least one of an inventory optimization decision and a fault alarm decision based on the fused data set.

[0068] This embodiment of the big data platform management method for the entire lifecycle of equipment and materials forms a closed-loop management system that covers the entire lifecycle of material data by collecting material data at each stage of the entire lifecycle. Furthermore, it integrates material data throughout the entire lifecycle in different application scenarios, effectively solving the problems of information lag and data silos in existing material management methods. At the same time, by generating at least one of inventory optimization decisions and fault alarm decisions through the fused data groups, it realizes the function of making effective decisions based on the corresponding fused data groups in different application scenarios, achieving the beneficial effects of optimizing inventory or detecting and alarming faults.

[0069] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. The processor 310, communications interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions from the memory 330 to execute a big data platform management method for the entire lifecycle of equipment and materials. This method includes: Collect material datasets for equipment and supplies at each stage of their entire lifecycle. Each stage's material dataset includes material data collected by at least one sensor.

[0070] Based on different application scenarios, the different material data in the material dataset are fused to form a fused data group corresponding to the application scenario.

[0071] Based on the fused data set, at least one of an inventory optimization decision and a fault alarm decision is generated.

[0072] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the big data platform management method for the entire life cycle of equipment and materials provided by the above methods. This method includes: Collect material datasets for equipment and supplies at each stage of their entire lifecycle. Each stage's material dataset includes material data collected by at least one sensor.

[0074] Based on different application scenarios, the different material data in the material dataset are fused to form a fused data group corresponding to the application scenario.

[0075] Based on the fused data set, at least one of an inventory optimization decision and a fault alarm decision is generated.

[0076] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the big data platform management method for the entire lifecycle of equipment and materials provided by the methods described above, the method comprising: Collect material datasets for equipment and supplies at each stage of their entire lifecycle. Each stage's material dataset includes material data collected by at least one sensor.

[0077] Based on different application scenarios, the different material data in the material dataset are fused to form a fused data group corresponding to the application scenario.

[0078] Based on the fused data set, at least one of an inventory optimization decision and a fault alarm decision is generated.

[0079] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A big data platform management system for the entire lifecycle of equipment and materials, characterized in that, include: The multi-source data acquisition module is used to collect material data of equipment and materials at all stages of the entire life cycle in order to form a material dataset. The data fusion module is used to fuse different material data in the material dataset based on different application scenarios to form a fused data group corresponding to the application scenario. The decision module is used to generate at least one of an inventory optimization decision and a fault alarm decision based on the fused data set.

2. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 1, characterized in that, The data fusion module includes: The data preprocessing submodule is used to preprocess the material data in the material dataset. The preprocessing includes: removing outliers, removing duplicates, and standardization. The fusion and association submodule is used to obtain preset application scenarios, including: transportation scenario, warehousing scenario, material usage scenario, and traceability scenario. For the transportation scenario, the pre-processed first temperature and humidity data, vibration data, transportation trajectory data, and first material image data during transportation are fused into a first fused data group. For the warehousing scenario, the pre-processed second temperature and humidity data, material entry records, material exit records, and second material image data are fused into a second fused data group. For the material usage scenario, the pre-processed material maintenance records and third material image data are fused into a third fused data group. For the traceability scenario, the pre-processed material attribute data, transportation trajectory data, first material image data, second material image data, and third material image data are fused into a fourth fused data group.

3. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 2, characterized in that, The decision-making module includes: The fault prediction submodule is used to predict whether a material transportation fault will occur based on the first temperature and humidity, vibration data and the first material image data in the first fused data group. When a material transportation fault is predicted, an alarm is issued and the transportation trajectory data is output. The transportation trajectory data is generated by the positioning data collected by the positioning sensor installed on the transportation vehicle. The vibration data is queried to find the positioning data corresponding to the vibration amplitude being greater than the amplitude threshold or the temperature being higher than the preset temperature, so as to determine the transportation segment corresponding to the positioning data. The fault prediction submodule is also used to determine the storage time of materials based on the material inbound record and the material outbound record, and to predict the fault type and the usage time before the fault occurs based on the second temperature and humidity, the storage time of the materials, the material maintenance record and the third material image data.

4. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 3, characterized in that, The decision-making module also includes: The inventory optimization submodule is used to calculate the current inventory level based on the material inbound and outbound records in the second fused data group, and to generate the current material demand based on the current inventory level, the historical inventory level of the same period, and the historical demand level of the same period, so as to optimize the inventory. Alternatively, it can be used to calculate the current material inventory based on the material inbound and outbound records in the second fused data group, and generate the current material demand based on the current material inventory, the historical material inventory of the same period, the historical material demand of the same period, the material failure type, and the usage time before the failure, so as to optimize the inventory.

5. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 3 or 4, characterized in that, The decision-making module also includes: The route planning submodule is used to plan the transportation route of materials from the factory to the warehouse, and to plan the transportation route of materials from the warehouse to the place of use.

6. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 1, characterized in that, Also includes: The emergency response module is used to monitor the material data collected by the sensors in real time. When multiple consecutive material data collected by the sensors exceed the corresponding material data threshold, the module will send the corresponding alarm information to the monitoring terminal. The emergency response module is also used to send a warehouse inventory warning to the monitoring terminal when the inventory of materials is lower than the minimum inventory threshold of the warehouse.

7. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 1, characterized in that, Also includes: The dynamic refactoring module is used for: The material procurement plan is dynamically adjusted based on the quality inspection reports of materials leaving the factory, historical delivery data, and material maintenance records. The system acquires vibration data collected by vibration sensors and positioning data collected by positioning sensors on each vehicle during transportation. It then acquires the target time period corresponding to the vibration data where the amplitude is continuously greater than the vibration amplitude that the materials can withstand. If the target time period is greater than a time period threshold, the system replans the transportation route of the materials to avoid the road segment corresponding to the positioning data within the target time period. The frequency of material entry and exit is calculated based on the material entry and exit records. If the frequency of material entry and exit exceeds the entry and exit frequency threshold, the minimum inventory threshold of the warehouse is increased.

8. The big data platform management system for the entire lifecycle of equipment and materials as described in claim 1, characterized in that, Also includes: The blockchain evidence storage module is used to store key data from the material dataset on the blockchain. The key data includes: quality inspection reports of materials leaving the factory, material warehousing records, and material outbound records.

9. A big data platform management method for the entire lifecycle of equipment and materials, characterized in that, include: Collect material data of equipment and supplies at each stage of the entire life cycle to form a material dataset; Based on different application scenarios, the different material data in the material dataset are fused to form a fused data group corresponding to the application scenario. Based on the fused data set, at least one of an inventory optimization decision and a fault alarm decision is generated.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the big data platform management method for the entire life cycle of equipment and materials as described in claim 9.

Images