Spare part prediction method and device of bank machine

Abstract

The invention discloses a bank machine spare part prediction method and device, and is used for the financial field and the big data technology field, and the method comprises the steps: receiving a first 5G message which is transmitted by a preset 5G message sensor and carries the target accessory operation data of a target bank machine, and inputting the first 5G message into a bank machine accessory life prediction model, obtaining predicted service life data of each accessory of the target bank machine; according to the accessory life cycle network of the target bank machine, determining whether the accessory of the bank machine has a corresponding associated replacement accessory; and according to the predicted service life data of each accessory of the target bank machine, the market influence factor of each accessory and the spare part inventory information of each accessory, spare part to-be-stored quantity information and spare part storage priority information of each accessory of the target bank machine are generated. The accuracy of predicting the spare part reserve quantity of the bank machine accessories is improved, the reserve cost is reduced, and the reserve efficiency is improved.

Description

Technical Field

[0001] The spare part prediction method and device for bank equipment of the present invention can be used in the financial field and the big data technology field, and can also be used in any field other than the financial field. The application field of the spare part prediction method and device for bank equipment of the present invention is not limited. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention described in the claims. The description herein is not admitted to be prior art merely because it is included in this section.

[0003] Spare parts refer to the equipment, components, materials and accessories that must be reserved in advance to ensure safe production when the production equipment is operating normally. At present, in order to provide better services, major banks usually need to manage the spare parts of products so that the quantity of spare parts of products can meet reasonable consumption.

[0004] However, in the existing methods, the traditional manual analysis and processing method is not only difficult, but also the results are inaccurate. Therefore, in view of the situation that there are a large number of factors affecting spare part requirements and they are complex and changeable, proposing a more accurate, effective and high-precision spare part requirement prediction scheme is of great significance for facilitating decision-makers to make more reasonable plans and improving the overall competitiveness of enterprises. Summary of the Invention

[0005] The embodiments of the present invention provide a spare part prediction method for bank equipment, which is used to improve the accuracy of predicting the spare part reserve quantity of bank equipment accessories, reduce the reserve cost, and improve the reserve efficiency. The method includes:

[0006] Receiving a first 5G message carrying the target accessory operation data of the target bank equipment sent by a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data and operation duration data of the bank equipment;

[0007] Inputting the target accessory operation data of the target bank equipment into a bank equipment accessory life prediction model to obtain the predicted service life data of each accessory of the target bank equipment; the bank equipment accessory life prediction model is trained by using the bank equipment accessory life historical data as a training set for a pre-set neural network model; the bank equipment accessory life historical data includes the historical accessory operation data of different bank equipment and the actual service life data of each accessory in the corresponding bank equipment;

[0008] For each accessory of a target banking machine, determine whether there is a corresponding associated replacement accessory for the accessory of the target banking machine according to the accessory life cycle network of the target banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network.

[0009] Generate the spare part quantity information to be reserved and the spare part reserve priority information for each accessory of the target banking machine according to the predicted service life data of each accessory of the target banking machine, whether there is a corresponding associated replacement accessory for each accessory of the target banking machine, the market influencing factors of each accessory, and the spare part inventory information of each accessory; the spare part inventory information of each accessory is obtained from the second 5G message carrying the spare part inventory information sent by the 5G intelligent label pre-set in the spare part warehouse.

[0010] An embodiment of the present invention further provides a spare part prediction device for a banking machine, which is used to improve the accuracy of predicting the spare part reserve quantity of banking machine accessories, reduce the reserve cost, and improve the reserve efficiency. The device includes:

[0011] A first 5G message receiving module, configured to receive a first 5G message carrying the target accessory operation data of the target banking machine sent by a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine.

[0012] A predicted service life data determination module, configured to input the target accessory operation data of the target banking machine into a banking machine accessory life prediction model to obtain the predicted service life data of each accessory of the target banking machine; the banking machine accessory life prediction model is trained by using the banking machine accessory life historical data as a training set for a pre-set neural network model; the banking machine accessory life historical data includes the historical accessory operation data of different banking machines and the actual service life data of each accessory in the corresponding banking machine.

[0013] An associated replacement accessory determination module, configured to, for each accessory of a target banking machine, determine whether there is a corresponding associated replacement accessory for the accessory of the target banking machine according to the accessory life cycle network of the target banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network.

[0014] A spare part information generation module, which is used to generate the spare part quantity information to be reserved and the spare part reserve priority information for each spare part of the target bank machine according to the predicted service life data of each spare part of the target bank machine, whether there is a corresponding associated replacement part for each spare part of the target bank machine, the market influencing factors of each spare part, and the spare part inventory information of each spare part; the spare part inventory information of each spare part is obtained from a second 5G message carrying the spare part inventory information sent by a 5G smart tag preset in the spare part warehouse.

[0015] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the spare part prediction method of the above bank machine is implemented.

[0016] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the spare part prediction method of the above bank machine is implemented.

[0017] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the spare part prediction method of the above bank machine is implemented.

[0018] In an embodiment of the present invention, a first 5G message carrying the operation data of a target component of a target banking machine is received from a pre-set 5G message sensor; the component operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine; the operation data of the target component of the target banking machine is input into a banking machine component life prediction model to obtain the predicted service life data of each component of the target banking machine; the banking machine component life prediction model is obtained by training a pre-set neural network model with the historical data of the banking machine component life as the training set; the historical data of the banking machine component life includes the historical component operation data of different banking machines and the actual service life data of each component in the corresponding banking machine; for each component of the target banking machine, according to the component life cycle network of the target banking machine, it is determined whether there is a corresponding associated replacement component for the component; the component life cycle network uses the replacement time data of each component as the nodes of the life cycle network; the associated replacement component has a replacement frequency exceeding a preset value within a preset time period after the replacement of the component in the component life cycle network; according to the predicted service life data of each component of the target banking machine, whether there is a corresponding associated replacement component for each component of the target banking machine, the market impact factor of each component, and the spare part inventory information of each component, the spare part quantity to be reserved information and spare part reserve priority information of each component of the target banking machine are generated; the spare part inventory information of each component is obtained from a second 5G message carrying the spare part inventory information sent by a 5G intelligent tag pre-set in the spare part warehouse. Compared with the prior art in which the spare part quantity of banking machine components is predicted manually, the predicted life of each component of the banking machine can be accurately and quickly predicted through the banking machine component life prediction model, which helps to accurately estimate the update of banking machine components; by determining the associated replacement components of each component through the component life cycle network, the spare part reserve strategy can be optimized according to the associated replacement situation of the components, the reserve cost can be reduced, and the utilization rate of spare parts can be improved. Further, by combining the market impact factor and the spare part inventory information, the spare part quantity to be reserved information and spare part reserve priority information of each component are generated, which improves the accuracy of the spare part reserve of banking machine components, reduces the reserve cost, improves the reserve efficiency, accurately predicts the spare part demand of intelligent banking machines, thereby optimizing the spare part inventory management, reducing the risk of operation interruption caused by insufficient spare parts, and avoiding the problems of inventory backlog and spare part shortage. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0020] Figure 1 It is a schematic flow chart of a spare part prediction method for a bank instrument in an embodiment of the present invention;

[0021] Figure 2 It is a specific example diagram of a spare part prediction method for a bank instrument in an embodiment of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a spare part prediction device for a bank instrument in an embodiment of the present invention;

[0023] Figure 4 It is a specific example diagram of a spare part prediction device for a bank instrument in an embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of a computer device for spare part prediction of a bank instrument in an embodiment of the present invention. Specific embodiments

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer and more understandable, the following will further elaborate on the embodiments of the present invention in conjunction with the drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

[0026] The term "and / or" in this article only describes an association relationship, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0027] In the description of this specification, terms such as "include", "comprise", "have", "contain", etc. are all open-ended terms, meaning including but not limited to. The description with reference to terms such as "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. means that the specific features, structures or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0028] In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations. The information collected in this application is information and data authorized by users or fully authorized by all parties. And the processing of relevant data such as collection, storage, use, processing, transmission, provision, disclosure and application all comply with the relevant laws, regulations and standards of relevant countries and regions, adopt necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. In addition, this application provides corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making. If the user chooses to refuse, the expert decision-making process can be entered.

[0029] Spare parts refer to the equipment, components, materials and fittings that must be reserved in advance to ensure safe production when production equipment is operating normally. At present, in order to provide better services, major banks usually need to manage the spare parts of products so that the quantity of spare parts of products can meet reasonable consumption.

[0030] However, in the existing methods, the traditional manual analysis and processing method is not only difficult but also inaccurate in results. Therefore, in view of the situation that there are a large number of factors affecting spare parts demand and they are complex and changeable, proposing a more accurate, effective and high-precision spare parts demand prediction scheme is of great significance for facilitating decision-makers to make more reasonable plans and improving the overall competitiveness of enterprises.

[0031] To solve the above problems, the embodiments of the present invention provide a method for predicting spare parts of banking machines and tools, which is used to improve the accuracy of predicting the spare parts reserve quantity of banking machine accessories, reduce the reserve cost, and improve the reserve efficiency. See Figure 1 , and the method may include:

[0032] Step 101: Receive a first 5G message sent by a pre-set 5G message sensor, which carries the target accessory operation data of the target banking machine; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine.

[0033] Step 102: Input the target accessory operation data of the target banking machine into the banking machine accessory life prediction model to obtain the predicted service life data of each accessory of the target banking machine; the banking machine accessory life prediction model is obtained by training a pre-set neural network model with the banking machine accessory life historical data as the training set; the banking machine accessory life historical data includes the historical accessory operation data of different banking machines and the actual service life data of each accessory in the corresponding banking machine.

[0034] Step 103: For each accessory of the target banking machine, determine whether there is a corresponding associated replacement accessory according to the accessory life cycle network of the target banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has the number of replacements exceeding the preset value within a preset time period after the replacement of the accessory in the accessory life cycle network.

[0035] Step 104: Generate the spare part quantity information to be reserved and the spare part reserve priority information for each accessory of the target banking machine according to the predicted service life data of each accessory of the target banking machine, whether there is a corresponding associated replacement accessory for each accessory of the target banking machine, the market influencing factors of each accessory, and the spare part inventory information of each accessory; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G smart tag pre-set in the spare part warehouse.

[0036] In step 101, the 5G message sensor can be an intelligent sensor with data acquisition, transmission, and reception functions, capable of real-time monitoring of the operation status of banking machine accessories. These sensors are preset on various key components of the banking machine to ensure comprehensive and accurate monitoring.

[0037] In step 102, the banking machine accessory life prediction model is a neural network-based prediction model. Through learning the banking machine accessory life historical data, this model can accurately predict the remaining life of banking machine accessories. This model has strong data processing and analysis capabilities, can process a large amount of complex operation data, and thus improve the accuracy of prediction.

[0038] In step 103, the accessory life cycle network is a network with the data of accessory replacement moments as nodes, which can reflect the usage of accessories in banking machines. By analyzing the accessory life cycle network, it can be found which accessories have associated replacement phenomena, that is, within a certain period of time, the same type of accessories need to be replaced multiple times.

[0039] In step 104, the information on the quantity of spare parts to be stocked and the priority of spare part stocking is generated based on various factors. These factors include predicted service life, associated replacement accessories, market influencing factors, and spare part inventory information. This method can comprehensively consider various factors, thereby improving the rationality and effectiveness of spare part stocking.

[0040] Through the above method, the present invention can effectively predict the stocking demand of banking machine accessories, reduce the stocking cost, improve the stocking efficiency, and thus provide a strong guarantee for the operation of banking machines.

[0041] In an embodiment of the present invention, a first 5G message carrying the operation data of the target accessories of the target bank machine is received from a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the bank machine; the operation data of the target accessories of the target bank machine is input into a bank machine accessory life prediction model to obtain the predicted service life data of each accessory of the target bank machine; the bank machine accessory life prediction model is obtained by training a pre-set neural network model with the bank machine accessory life historical data; the bank machine accessory life historical data includes the historical accessory operation data of different bank machines and the actual service life data of each accessory in the corresponding bank machine; for each accessory of the target bank machine, according to the accessory life cycle network of the target bank machine, it is determined whether there is a corresponding associated replacement accessory for the accessory of the bank machine; the accessory life cycle network uses the replacement time data of each accessory as the node of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network; according to the predicted service life data of each accessory of the target bank machine, whether there is a corresponding associated replacement accessory for each accessory of the target bank machine, the market influence factor of each accessory, and the spare part inventory information of each accessory, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory of the target bank machine are generated; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G intelligent tag pre-set in the spare part warehouse. Compared with the prior art in which the spare part quantity of bank machine accessories is predicted manually, the predicted life of each accessory of the bank machine can be accurately and quickly predicted through the bank machine accessory life prediction model, which helps to accurately estimate the update of bank machine accessories; by determining the associated replacement accessories of each accessory through the accessory life cycle network, the spare part reserve strategy can be optimized according to the associated replacement situation of the accessories, the reserve cost can be reduced, and the utilization rate of spare parts can be improved. Further, by combining the market influence factor and the spare part inventory information, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory are generated, which improves the accuracy of bank machine accessory reserve, reduces the reserve cost, improves the reserve efficiency, accurately predicts the spare part demand of bank intelligent machines, thereby optimizing the spare part inventory management, reducing the operation interruption risk caused by insufficient spare parts, and avoiding the problems of inventory backlog and spare part shortage.

[0042] Specifically, in implementation, first, a first 5G message carrying the operation data of the target accessories of the target bank machine is received from a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the bank machine.

[0043] In the embodiment, the received first 5G message is parsed to extract the operation data of the target banking machine. These data include the operation temperature, operation humidity, operation vibration frequency, and operation duration, etc. In the embodiment, these data will be used for subsequent analysis and processing.

[0044] Once the operation data of the target banking machine is obtained, real-time monitoring and analysis are carried out. Through the pre-set algorithms and models, the relevant system can evaluate the operation status of the banking machine and determine whether there are any abnormalities. If an abnormal situation is found, the system will immediately issue an alarm to remind the relevant personnel to handle it in a timely manner.

[0045] In addition, the lifespan of the banking machine can be predicted based on the operation duration data. When it is predicted that a certain banking machine is about to reach the end of its lifespan, the system will issue a replacement notice in advance so that the bank can arrange equipment updates in a timely manner.

[0046] In the above process, the 5G message sensor plays a key role. By sending the operation data of the banking machine in real time, the sensor provides accurate and timely data support for the system. The high speed and low latency of the 5G network ensure the smooth transmission of data and avoid data loss caused by network problems.

[0047] In summary, by implementing the present invention, real-time monitoring and management of banking machines can be achieved, effectively improving the operation stability and security of banking machines. At the same time, the present invention can also save a large amount of labor and material costs for the bank and improve the operation efficiency. In addition, the present invention can also be applied to other fields, such as intelligent manufacturing, smart city, etc., and has a wide range of application prospects.

[0048] In practical applications, the system can be further optimized according to needs. For example, more types of sensors can be added to collect more dimensional data of the banking machine to improve the accuracy of monitoring. At the same time, the algorithms and models can be continuously optimized to make the system have stronger intelligent analysis and processing capabilities.

[0049] In one embodiment, it further includes:

[0050] Based on feature engineering technology, extract the feature data of the accessory operation data in the first 5G message;

[0051] Input the target accessory operation data of the target banking machine into the banking machine accessory lifespan prediction model to obtain the predicted service life data of each accessory of the target banking machine, including:

[0052] Input the feature data of the target accessory operation data of the target banking machine into the banking machine accessory lifespan prediction model to obtain the predicted service life data of each accessory of the target banking machine.

[0053] In an embodiment, after receiving the first 5G message, in-depth analysis is performed on the accessory operation data in the message. This process mainly includes feature extraction of data such as operating temperature, operating humidity, operating vibration frequency, and operating duration. These feature data include, but are not limited to: the mean value, standard deviation, trend change, etc. of the data. Through these feature data, the operating state of the banking machine can be described and analyzed more precisely.

[0054] Next, the extracted feature data is input into the life prediction model of the banking machine accessories. This model calculates the predicted service life of each accessory of the banking machine based on the input feature data, combined with a pre-set algorithm and model. This predicted service life includes the remaining life of the accessory and the countdown to the end of its life.

[0055] After obtaining the predicted service life data, the system monitors and gives early warnings in real time according to these data. When the predicted service life of a certain accessory of a certain banking machine is approaching the end, the system immediately issues a replacement notice to ensure that the bank can arrange equipment updates in time and prevent business interruptions caused by equipment failures.

[0056] In the above embodiment, the predicted service life data also includes the prediction accuracy and prediction reliability indicators. These two indicators can help the operation and maintenance personnel of the banking machine better understand and evaluate the prediction results, so as to formulate corresponding maintenance and management strategies.

[0057] Next, according to the predicted service life data, targeted maintenance and upkeep can be carried out on each accessory of the target banking machine. For example, for accessories with too high operating temperature or too high operating vibration frequency, replacement or repair can be carried out in advance to avoid potential failure risks. At the same time, according to the operating duration data of the accessories, the inspection frequency and maintenance plan of the operation and maintenance personnel can be reasonably arranged, so as to improve the operating efficiency and stability of the banking machine.

[0058] By implementing the above method, accurate prediction of the service life of banking machine accessories can be achieved, effectively improving the operating efficiency and stability of banking machines, and reducing operation and maintenance costs. At the same time, it can also provide strong support for the operation and maintenance management of banking machines, enhancing the reliability and competitiveness of banking services.

[0059] Combined with a specific application scenario, give an example:

[0060] Suppose that during the business hours of a bank, the operation data of an automated teller machine (ATM) is sent to the system in real time through a pre-set 5G message sensor. The data carried by the sensor includes the operating temperature, operating humidity, operating vibration frequency, and operating duration, etc. After receiving this data, the system first parses and extracts it to obtain the operating status of the ATM.

[0061] Next, the system monitors and analyzes the operating status of the ATM in real time according to the pre-set algorithms and models. By comparing the normal operating range with the actual operating data, it determines whether the ATM is abnormal. For example, if the operating temperature is too high, the operating vibration frequency is too high, etc., the system will immediately issue an alarm to remind the relevant personnel to handle it in time.

[0062] At the same time, the system can also predict the life of the ATM based on the operating duration data. For example, when it is predicted that a certain ATM is about to reach the end of its life, the system will issue a replacement notice in advance so that the bank can arrange equipment updates in time.

[0063] In this process, the 5G message sensor plays a key role. It sends the operating data of the ATM in real time, providing accurate and timely data support for the system. The high speed and low latency of the 5G network ensure the smooth data transmission and avoid data loss caused by network problems.

[0064] In addition, the system can optimize the algorithms and models according to needs. For example, adding more types of sensors to collect more dimensional data of the ATM to improve the accuracy of monitoring. At the same time, continuously optimizing the algorithms and models to make the system have stronger intelligent analysis and processing capabilities.

[0065] By implementing the present invention, real-time monitoring and management of bank equipment can be achieved, effectively improving the operating stability and security of bank equipment. At the same time, the present invention can also save a large amount of human and material costs for the bank and improve the operation efficiency.

[0066] In specific implementation, after receiving a first 5G message carrying the target accessory operation data of the target bank equipment sent by a pre-set 5G message sensor, input the target accessory operation data of the target bank equipment into a bank equipment accessory life prediction model to obtain the predicted service life data of each accessory of the target bank equipment; the bank equipment accessory life prediction model is trained by using the bank equipment accessory life historical data as a training set for a pre-set neural network model; the bank equipment accessory life historical data includes the historical accessory operation data of different bank equipment and the actual service life data of each accessory in the corresponding bank equipment.

[0067] In the embodiment, the first 5G message may further include a preset fault warning signal. When the operation data of the target component of the target bank device is abnormal, the bank device component life prediction model will automatically send out a fault warning signal so that the operation and maintenance personnel of the bank device can perform maintenance and repair in a timely manner.

[0068] Next, according to the predicted service life data of each component of the target bank device, the bank device component life prediction model will generate maintenance suggestions for each component, including replacement time, replacement frequency, etc. These maintenance suggestions will be sent to the operation and maintenance personnel of the bank device so that they can formulate corresponding maintenance plans according to the actual situation.

[0069] In addition, the bank device component life prediction model will also regularly update the predicted service life data to adapt to the changes in the actual operation status of the bank device. This can be achieved by receiving new operation data of the target component and updating the bank device component life historical data.

[0070] In the embodiment, the bank device component life prediction model can also adjust and optimize the preset neural network model according to the actual operation data to improve the prediction accuracy. This helps to ensure that the bank device can maintain efficient and stable operation throughout its life cycle.

[0071] In summary, by using the bank device component life prediction model, real-time monitoring and prediction of bank device components can be realized, providing a scientific and effective decision-making basis for its operation and maintenance personnel. At the same time, this method can also improve the operation efficiency of the bank device, reduce the operation and maintenance costs, and extend the service life of the bank device.

[0072] Take an example of the "bank device component life prediction model":

[0073] In a certain embodiment, the bank device component life prediction model is applied to the automatic teller machine (ATM) system of a large bank. The bank has thousands of ATMs distributed in various places, which brings great challenges to the maintenance and management of these devices. To achieve efficient operation and maintenance, the bank decides to use the bank device component life prediction model to predict the service life of ATM components and formulate corresponding maintenance plans.

[0074] First, the bank collected the operation data of ATMs in the past few years, including hardware failures, maintenance records, etc., and used them as the bank device component life historical data. These data were used to train the neural network model to construct the bank device component life prediction model.

[0075] After the model training is completed, the ATM starts to send operation data to the bank equipment parts life prediction model in real time. After receiving the data, the model predicts the life of each part of the ATM. When it is predicted that the service life of a certain part is about to expire, the model will send a fault warning signal to remind the operation and maintenance personnel to perform maintenance in time.

[0076] At the same time, the model will also generate maintenance suggestions for each part according to the operation status of the ATM, including replacement time, replacement frequency, etc. The operation and maintenance personnel can formulate a maintenance plan based on these suggestions to ensure the stable operation of the ATM.

[0077] In one embodiment, it further includes:

[0078] Using the bank equipment parts life historical data as a validation set, validate the bank equipment parts life prediction model to obtain the bank equipment parts life prediction model after passing the validation;

[0079] Input the operation data of the target parts of the target bank equipment into the bank equipment parts life prediction model to obtain the predicted service life data of each part of the target bank equipment, including:

[0080] Input the operation data of the target parts of the target bank equipment into the bank equipment parts life prediction model after passing the validation to obtain the predicted service life data of each part of the target bank equipment.

[0081] In the specific implementation process, it is necessary to use the bank equipment parts life historical data as a validation set to validate the bank equipment parts life prediction model. The purpose of this step is to ensure that the model has good prediction performance and generalization ability, so as to provide accurate prediction results for the subsequent prediction of the parts life of the target bank equipment.

[0082] During the validation process, the bank equipment parts life historical data is divided into a training set and a validation set. The training set is used to train the preset neural network model, while the validation set is used to evaluate the performance of the model. This process can be carried out by the method of cross-validation to ensure that the model can show good prediction effects on different data distributions.

[0083] In the validation stage, input the operation data of the bank equipment parts to be validated into the trained bank equipment parts life prediction model to obtain the predicted service life of each part. Then, compare the prediction results with the actual service life, and calculate evaluation indicators such as prediction error and accuracy. If the prediction error is within an acceptable range and the accuracy reaches the preset standard, the validation passes, indicating that the bank equipment parts life prediction model has good prediction performance.

[0084] After passing the verification, the model can be applied to the actual scenario to predict the service life of each component of the target bank equipment. The specific operations are as follows:

[0085] 1. Collect the operation data of the components of the target bank equipment in real time, which can be obtained from 5G message sensors.

[0086] 2. Input the operation data of the target components of the collected target bank equipment into the bank equipment component life prediction model that has passed the verification.

[0087] 3. The model will output the predicted service life data of each component of the target bank equipment. These data can help the operation and maintenance personnel of the bank equipment to timely understand the operation status of the components, and make advance maintenance and replacement plans according to the prediction results, so as to reduce the operation and maintenance costs and improve the stability and reliability of the bank equipment.

[0088] Through the above implementation steps, a method for predicting the service life of bank equipment components based on 5G message sensors and neural network models is realized. This method has high accuracy and practicability, and provides strong support for the operation and maintenance management of bank equipment.

[0089] In one embodiment, it further includes: generating a component replacement plan for the target bank equipment according to the predicted service life data of each component of the target bank equipment; and replacing the components of the target bank equipment according to the generated component replacement plan.

[0090] When operating specifically, first input the operation data of the target components of the target bank equipment into the bank equipment component life prediction model that has passed the verification to obtain the predicted service life data of each component of the target bank equipment. Then, according to these prediction data, evaluate the remaining service life of each component, and formulate a component replacement plan based on the evaluation results. In the replacement plan, factors such as the predicted service life of the component, the actual usage situation, and the operation requirements of the bank equipment can be considered to reasonably arrange the replacement time, replacement order, etc.

[0091] In addition, in one embodiment, the bank equipment component life prediction model can be updated and optimized regularly to improve the prediction accuracy. This can be achieved by collecting new operation data of bank equipment components, continuously expanding and updating the historical data of bank equipment component life. At the same time, the neural network model parameters can also be adjusted according to the actual operation situation to adapt to the changing application environment.

[0092] In the above embodiment, the bank equipment component life prediction model also includes data mining technology and machine learning algorithms. Data mining technology is used to extract useful information from historical data, such as the operation mode and usage frequency of bank equipment components, while machine learning algorithms are used to learn from this information and establish a prediction model.

[0093] In the embodiment, the life prediction model of bank machine accessories further includes the following steps:

[0094] 1. Preprocess the historical data of the life of bank machine accessories, including data cleaning, data normalization, etc., to ensure the quality and consistency of the data.

[0095] 2. Use data mining techniques to analyze the preprocessed data and extract the features that affect the life of bank machine accessories.

[0096] 3. Use machine learning algorithms, such as neural networks, decision trees, support vector machines, etc., to establish a life prediction model of bank machine accessories based on the extracted features.

[0097] 4. Use the validation set to validate the prediction model, and evaluate the prediction performance of the model through methods such as cross-validation, such as accuracy, recall rate, etc.

[0098] 5. According to the validation results, optimize and adjust the prediction model to improve the prediction accuracy.

[0099] 6. When receiving the operation data of the target accessories of the target bank machine sent by the 5G message sensor, use the established prediction model, input the data and obtain the predicted service life of each accessory.

[0100] Specifically, when inputting the operation data of the target accessories of the target bank machine into the life prediction model of bank machine accessories and obtaining the predicted service life data of each accessory of the target bank machine, for each accessory of the target bank machine, determine whether there is a corresponding associated replacement accessory according to the accessory life cycle network of the target bank machine; the accessory life cycle network uses the replacement time data of each accessory as the node of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network.

[0101] In the embodiment, the predicted service life data of each accessory of the target bank machine can be further used to formulate targeted maintenance strategies and replacement plans. Specifically, according to the predicted service life of each accessory, the maintenance time and replacement time can be reasonably arranged to ensure the normal operation of the bank machine, reduce the failure rate, and increase the service life.

[0102] After determining the associated replacement parts, dynamic monitoring and early warning can be carried out through the parts life cycle network. When the life of a certain part is about to end, the system can automatically send out an early warning signal to prompt relevant personnel to replace it in time. This can not only avoid the downtime of banking equipment caused by part failures, but also save maintenance costs and improve the operating efficiency of banking equipment.

[0103] In addition, according to the number of replacements in the parts life cycle network, the replacement cycle of parts can be optimized. For parts with more replacement times and shorter lives, the replacement cycle can be considered shortened to reduce the failure rate and maintenance costs. For parts with fewer replacement times and longer lives, the replacement cycle can be appropriately extended to reduce the replacement costs.

[0104] In an embodiment, the following method can be used to optimize the replacement strategy of parts: First, based on the operation data of banking equipment, a parts life prediction model is established to obtain the predicted service life of each part; then, according to the parts life cycle network, the associated replacement parts are determined; next, according to the number of replacements of the associated replacement parts and a preset value, a replacement plan is formulated; finally, according to the predicted service life of the parts and the actual operation situation, the replacement strategy is dynamically adjusted.

[0105] In one embodiment, as Figure 2 shown, it includes:

[0106] Step 201: For each banking equipment, based on the sliced binary tree technology, data slicing processing is performed on the collected replacement time data of different parts of the banking equipment to obtain the continuous time series data of the replacement time data of different parts; the time points in the continuous time series data represent the corresponding part replacement events;

[0107] Step 202: For each part, determine whether the number of replacements of other parts exceeds a preset value within a preset time period after the replacement of this part; if so, regard this other part as the associated replacement part of this part;

[0108] Step 203: Take the replacement time data in the continuous time series data of each part as the nodes of the life cycle network, and establish an edge between the nodes of the life cycle network between each part and the associated replacement part corresponding to this part to obtain the life cycle network.

[0109] In the embodiment, for each banking equipment, based on the sliced binary tree technology, data slicing processing is performed on the collected replacement time data of different parts of the banking equipment to obtain the continuous time series data of the replacement time data of different parts, including:

[0110] For each banking device, window data segmentation is performed on the replacement time data of the accessories corresponding to the banking device within the preset time window of the accessories to obtain multiple replacement times of the accessories;

[0111] For each accessory, the initial replacement time of the accessory is used as the root node of the binary tree of the accessory, and different replacement times of the accessory are used as the child nodes of the binary tree of the accessory; the time window data with continuous time sequence is linked through the nodes to form the binary tree of the accessory;

[0112] Read the continuous time series data of the replacement time data of the accessory from the binary tree of the accessory.

[0113] In the embodiment, the root node of the binary tree is created, representing the earliest time window and containing all relevant data within the window. The time series data is segmented according to the defined time window, and the data of each time window will correspond to a node in the binary tree. The time window data with continuous time sequence is linked through the nodes to form the basic structure of the binary tree.

[0114] For the binary tree, the following processing can also be performed:

[0115] Evaluate the data characteristics within each time window, such as the data volume, the distribution of replacement events, etc.

[0116] Determine the splitting criterion according to the data characteristics and business logic. For example, if the number of replacement events within a certain time window increases abnormally, then this node needs to be split.

[0117] For the node that needs to be split, generate two child nodes according to the splitting criterion, respectively representing different data characteristics within the time window.

[0118] Based on the above embodiment, the process of forming the binary tree of the accessory can be further refined into the following steps:

[0119] First, for each accessory, create a root node according to the initial replacement time, and this root node represents the earliest replacement record of the accessory. Subsequently, for each subsequently collected replacement time data, add it as a new child node to the binary tree. When adding a child node, determine the position of the node according to the time sequence to ensure that the time window data with continuous time sequence is linked through the nodes. And for each accessory, a unique identifier can be created for it to quickly locate the corresponding node in the binary tree. This identifier can be the number, name of the accessory or other attributes that can uniquely identify the accessory.

[0120] Specifically, each new replacement time is compared with the nodes in the current binary tree. If the new replacement time is earlier than all the nodes in the current binary tree, then it will become the new root node; if the new replacement time is later than all the nodes in the current binary tree, then it will be added as a new leaf node to the rightmost side of the binary tree; if the new replacement time is between two nodes in the current binary tree, then it will be inserted between these two nodes to form a new child node.

[0121] In this way, it can be ensured that each replacement time finds a suitable position in the binary tree, and the time window data with continuous time order is linked by nodes to form a complete binary tree structure.

[0122] Finally, by traversing the binary tree of the accessory, the continuous time series data of the replacement time data of the accessory can be read. These data can be further used to analyze key indicators such as the replacement cycle and replacement frequency of the accessory.

[0123] The following is an example of a "life cycle network":

[0124] In the specific implementation process, for each accessory of each target bank machine, according to the accessory life cycle network, it is determined whether there is a corresponding associated replacement accessory for this accessory of the bank machine. The accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network. The number of replacements of the associated replacement accessory within a preset time period after the replacement of this accessory in the accessory life cycle network needs to exceed a preset value.

[0125] In one embodiment, first for each bank machine, based on the sliced binary tree technology, the replacement time data of different accessories of the bank machine collected is subjected to data slicing processing to obtain the continuous time series data of the replacement time data of different accessories. The time points in these continuous time series data represent the corresponding accessory replacement events.

[0126] Next, for each accessory, it is determined whether the number of replacements of other accessories exceeds the preset value within a preset time period after the replacement of this accessory. If so, then this other accessory is used as the associated replacement accessory of this accessory. The replacement time data in the continuous time series data of each accessory is used as the nodes of the life cycle network, and an edge is established between the nodes of the life cycle network between each accessory and the associated replacement accessory corresponding to this accessory to obtain the life cycle network.

[0127] Taking an example of a "life cycle network", assume there is a bank machine, which includes four main components: a processor, a memory, a hard disk, and a display. During the actual operation, the replacement time data of each component is collected and processed based on the sliced binary tree technology. After processing, the continuous time series data of each component is obtained.

[0128] According to the construction principle of the life cycle network, first determine the replacement time data of each component as the nodes of the life cycle network. Then, analyze the correlation between the replacement events of each component to find the associated replacement components. For example, within a preset time period after the processor is replaced, if the number of memory replacements exceeds a preset value, then the memory is regarded as the associated replacement component of the processor.

[0129] Next, establish edges between the nodes in the life cycle network. In this example, an edge is established between the processor node and the memory node, indicating that after the processor is replaced, the memory is its associated replacement component. Similarly, corresponding edges are established between other components. Finally, a life cycle network diagram is formed, intuitively showing the correlation between each component.

[0130] Through the construction of the above life cycle network, the service life of each component of the bank machine can be better predicted, and it provides strong support for realizing intelligent maintenance and management. The operating state of the bank machine will be effectively monitored, thereby improving the stability and reliability of the bank machine, reducing the failure rate, and enhancing the user experience. At the same time, according to the correlation between each component in the life cycle network, the banking institution can reasonably arrange the maintenance plan, save the maintenance cost, and improve the equipment utilization rate.

[0131] In one embodiment, for the said life cycle network, the following operations can be further carried out:

[0132] 1. Conduct a stability analysis of the life cycle network to identify the potentially unstable nodes, that is, those components whose replacement times exceed a preset value within a preset time period. These unstable nodes may be potential fault points, and their operating conditions need to be closely monitored to discover and solve problems in a timely manner.

[0133] 2. Optimize the replacement strategy of the components according to the topological structure of the life cycle network. For example, for components with an associated replacement relationship, the replacement order can be reasonably arranged to extend the overall service life of the machine. At the same time, a reasonable maintenance plan can be formulated based on the life prediction data of the components to ensure the normal operation of the bank machine.

[0134] 3. Use the life cycle network to conduct a performance evaluation of the bank machine. By analyzing the attributes of each node in the life cycle network, the overall performance of the bank machine can be evaluated, providing a reference for the purchase, use, and maintenance of the bank machine.

[0135] 4. Dynamically update the lifecycle network to adapt to the changing usage environment of banking equipment. As the banking equipment is used, the lifespan of its components will continuously change. Therefore, it is necessary to update the lifecycle network regularly to ensure the accuracy of the prediction results.

[0136] In specific implementation, for each component of the target banking equipment, after determining whether there is a corresponding associated replacement component according to the component lifecycle network of the target banking equipment, based on the predicted service life data of each component of the target banking equipment, whether there is a corresponding associated replacement component for each component of the target banking equipment, the market impact factors of each component, and the spare part inventory information of each component, generate the spare part quantity information to be reserved and the spare part reserve priority information for each component of the target banking equipment; the spare part inventory information of each component is obtained from the second 5G message carrying the spare part inventory information sent by the 5G smart tag preset in the spare part warehouse.

[0137] In one embodiment, the market impact factors include: one or any combination of the spare part market supply quantity, the number of repairs, the monthly consumption quantity of spare parts, the number of repairs, the degree of repair, the purchase quantity, the working time of the spare part equipment, the number of spare part suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance times.

[0138] In the embodiment, first, according to the predicted service life data of each component of the target banking equipment, the remaining service life of each component can be calculated. This step can be achieved by collecting historical data and using machine learning algorithms for prediction. The prediction result will serve as the basis for subsequent spare part reserve decisions.

[0139] Next, it is necessary to determine whether there is a corresponding associated replacement component for each component of the target banking equipment. This information can be obtained through in-depth analysis of the component lifecycle network of the banking equipment. The determination of the associated replacement component is crucial for formulating subsequent spare part reserve strategies because it can help predict the replacement demand of components more accurately.

[0140] Then, it is necessary to consider the market impact factors of each component. These factors may include the spare part market supply quantity, the number of repairs, the monthly consumption quantity of spare parts, the number of repairs, the degree of repair, the purchase quantity, the working time of the spare part equipment, the number of spare part suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance times, etc. By analyzing these market impact factors, a more accurate spare part reserve strategy that conforms to the actual situation can be formulated.

[0141] Next, based on the spare part inventory information of each component, the current inventory status can be understood in order to formulate a reasonable inventory management strategy. This information can be obtained through the second 5G message carrying the spare part inventory information sent by the 5G smart tag preset in the spare part warehouse.

[0142] After completing the above information collection and analysis, a specific spare part reserve strategy can be formulated according to the spare part quantity to be reserved information and spare part reserve priority information of each component of the target bank machine. For example, for components with a relatively short predicted service life and significant market impact factors, an appropriate quantity of spare parts can be reserved preferentially to ensure the normal operation of the bank machine.

[0143] Finally, the spare part reserve strategy needs to be updated and adjusted regularly. This can be achieved by real-time monitoring of the operating status of the bank machine, updating information such as the predicted service life of components, and market impact factors. In this way, it can be ensured that the bank machine always has sufficient spare parts to meet the operating requirements.

[0144] In summary, by applying the spare part reserve strategy proposed in this article, bank machines can manage spare part inventory more effectively, reduce operating costs, and improve service quality. At the same time, this strategy can also provide reference for other industries and help enterprises achieve intelligent and refined inventory management.

[0145] In the above embodiment, based on the predicted service life data of each component of the target bank machine, whether there is a corresponding associated replacement component for each component of the target bank machine, the market impact factors of each component, and the spare part inventory information of each component, the spare part quantity to be reserved information and spare part reserve priority information of each component of the target bank machine are further generated. This process can be achieved through big data analysis and artificial intelligence algorithms to improve the accuracy and efficiency of spare part reserve.

[0146] Regarding the spare part reserve priority, it can be determined based on the following aspects: First, the importance of the component, such as key components having a high priority; second, the damage frequency of the component, components with a high damage frequency having a high priority; third, market impact factors, such as components with tight supply having a high priority. By comprehensively analyzing these factors, a scientific basis can be provided for the spare part reserve of bank machines.

[0147] In actual operation, the spare part inventory information can be obtained in real time through 5G smart tags to ensure the timeliness and accuracy of spare part reserve. The 5G smart tags can be attached to the spare parts to update the inventory status of the spare parts at any time, including but not limited to information such as inventory quantity and reserve location. In this way, problems such as insufficient or excessive spare part reserve caused by inaccurate inventory information can be effectively avoided.

[0148] In addition, the spare part reserve strategy can be adjusted according to market influencing factors, such as the supply volume in the spare part market, the number of repairs, the monthly consumption of spare parts, the number of repairs, the degree of repair, the purchase quantity, the working hours of spare part equipment, the number of spare part suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance times. For example, when the market supply of a certain part is tight, the reserve quantity of this part can be appropriately increased to ensure timely replacement when needed.

[0149] During specific implementation, it also includes:

[0150] Display the spare part quantity information to be reserved and the spare part reserve priority information of the parts of each banking machine to the user through a visualization interface; wherein, the visualization interface is used to display data in ways including but not limited to charts, graphs, color coding, or data dashboards.

[0151] In the embodiment, the visualization interface can further include an intelligent early warning function. The intelligent early warning function can analyze possible failures and demands in real time according to the spare part reserve situation of the banking machine, and send out early warning signals in advance so that the user can take timely measures. In addition, the visualization interface can also generate reports regularly to help the user understand the operation status of the banking machine and the spare part reserve situation, and provide a decision-making basis for the user.

[0152] In summary, by analyzing the life cycle network of the parts of the target banking machine, predicting the service life data, market influencing factors, and spare part inventory information, accurate spare part quantity information to be reserved and spare part reserve priority information can be generated. Combining with 5G intelligent label technology, real-time monitoring of spare part inventory is realized, and the spare part reserve strategy is further optimized. This solution can not only improve the operation efficiency of banking machines, but also reduce maintenance costs and enhance the customer experience.

[0153] In actual operation, the spare part reserve strategy can also be adjusted according to specific situations. For example, in different regions and seasons, the reserve strategy can be adjusted according to the damage rate and usage frequency of spare parts; for specific banking machines, the spare part reserve strategy can be adjusted according to their business volume and usage environment. By continuously optimizing the spare part reserve strategy, strong guarantee is provided for the stable operation of banking machines.

[0154] Taking an ATM machine as an example, it mainly includes the following main parts: cash box, cash dispensing module, deposit module, controller, display screen, etc. Specific calculation examples will be demonstrated for these parts below.

[0155] 1. Predict service life data: Through historical data and machine learning algorithms, the remaining service life of each part can be predicted. For example, the remaining service life of the cash box is 2 years, the cash dispensing module is 1.5 years, the deposit module is 3 years, the controller is 4 years, and the display screen is 2 years.

[0156] 2. Associated replacement parts: By analyzing the life cycle network of bank machine parts, it can be found that there are associated replacement phenomena in the cash dispensing module and the deposit module. For example, when the cash dispensing module is damaged, the entire cash dispensing system may need to be replaced; when the deposit module is damaged, the entire deposit system may need to be replaced.

[0157] 3. Market influencing factors: Based on market surveys and data analysis, the following market influencing factors are obtained: The market supply of cash box spare parts is 1000 pieces per month, the number of repairs is 5 times per month, and the monthly consumption of spare parts is 20 pieces; the market supply of cash dispensing module spare parts is 800 pieces per month, the number of repairs is 8 times per month, and the monthly consumption of spare parts is 30 pieces; the market supply of deposit module spare parts is 600 pieces per month, the number of repairs is 6 times per month, and the monthly consumption of spare parts is 25 pieces; the market supply of controller spare parts is 500 pieces per month, the number of repairs is 4 times per month, and the monthly consumption of spare parts is 15 pieces; the market supply of display screen spare parts is 400 pieces per month, the number of repairs is 5 times per month, and the monthly consumption of spare parts is 10 pieces.

[0158] 4. Spare parts inventory information: Obtain the current spare parts inventory situation through the second 5G message sent by the 5G smart label. The inventory of cash box spare parts is 50 pieces, the inventory of cash dispensing module spare parts is 30 pieces, the inventory of deposit module spare parts is 80 pieces, the inventory of controller spare parts is 60 pieces, and the inventory of display screen spare parts is 40 pieces.

[0159] 5. Generate information on the quantity of spare parts to be stocked and the priority of spare parts stocking:

[0160] Cash box: The predicted remaining service life is 2 years, the market influencing factors are large, the current inventory is 50 pieces, the quantity of spare parts to be stocked is 200 pieces, and the priority of spare parts stocking is high.

[0161] Cash dispensing module: The predicted remaining service life is one and a half years, there is an associated replacement phenomenon, the market influencing factors are large, the current inventory is 30 pieces, the quantity of spare parts to be stocked is 150 pieces, and the priority of spare parts stocking is high.

[0162] Deposit module: The predicted remaining service life is 3 years, there is an associated replacement phenomenon, the market influencing factors are average, the current inventory is 80 pieces, the quantity of spare parts to be stocked is 200 pieces, and the priority of spare parts stocking is average.

[0163] Controller: The predicted remaining service life is 4 years, the market influencing factors are small, the current inventory is 60 pieces, the quantity of spare parts to be stocked is 100 pieces, and the priority of spare parts stocking is low.

[0164] Display screen: The predicted remaining service life is 2 years, the market influencing factors are average, the current inventory is 40 pieces, the quantity of spare parts to be stocked is 80 pieces, and the priority of spare parts stocking is low.

[0165] Based on the above calculation examples, specific spare part reserve strategies can be formulated for different accessories. For example, for the cash box and the note dispensing module with relatively short predicted service life and significant market influencing factors, an appropriate quantity of spare parts can be preferentially reserved to ensure the normal operation of bank equipment. At the same time, regularly update and adjust the spare part reserve strategy to ensure that bank equipment always has sufficient spare parts to meet the operation requirements.

[0166] Another example of "setting 5G smart tags in the spare part warehouse":

[0167] By setting 5G smart tags in the spare part warehouse, real-time monitoring and management of spare part inventory can be achieved. When the spare part inventory is lower than the preset threshold, the 5G smart tag will automatically send an inventory warning message to the system, prompting the administrator to replenish the inventory in a timely manner. In addition, the 5G smart tag can also update the location information of the spare parts in real time, facilitating the administrator to quickly search for and allocate spare parts.

[0168] Based on the inventory warning message sent by the 5G smart tag, the system can automatically generate a warning report, including the name of the spare parts with inventory lower than the preset threshold, the inventory quantity, the warning level, etc. The administrator can take timely measures to replenish the inventory according to the warning report to ensure the sufficient supply of spare parts.

[0169] The present invention optimizes spare part inventory through predictive maintenance and data analysis, reduces downtime, and improves maintenance efficiency. A specific embodiment will be used below to illustrate the specific application of the method of the present invention.

[0170] I. Data collection and preprocessing

[0171] 1. 5G sensor data collection: Deploy 5G sensors on the ATM to monitor the operating status of the ATM in real time and collect data including temperature, humidity, vibration frequency, and operating time, etc.

[0172] 2. Spare part inventory information acquisition: Use 5G smart tags to obtain inventory information from the spare part warehouse, such as the inventory quantity of the cash sorter and the note conveyor belt.

[0173] 3. Market influencing factor collection: Collect information such as the market price, supply quantity, and number of suppliers of spare parts.

[0174] 4. Data preprocessing: Clean the collected data, remove outliers and missing values, and then standardize the data to make it suitable for model training.

[0175] II. Feature engineering techniques

[0176] 1. Feature selection: Select features closely related to the spare part life, such as the temperature peak value, humidity fluctuation, and maximum vibration frequency, etc.

[0177] 2. Feature Construction: Create new features such as daily average temperature and average running time to enhance the model's predictive ability.

[0178] III. Life Prediction Model Training and Validation

[0179] 1. Model Selection: Select a suitable neural network architecture, such as Long Short-Term Memory (LSTM), as the prediction model.

[0180] 2. Model Training: Use historical data to train the model and adjust hyperparameters to optimize performance.

[0181] 3. Model Validation: Adopt the holdout method or cross-validation method to evaluate the accuracy and generalization ability of the model.

[0182] IV. Life Prediction and Associated Spare Part Analysis

[0183] 1. Life Prediction: Input the preprocessed feature data into the model to predict the remaining service life of each spare part.

[0184] 2. Associated Spare Part Identification: Use time series analysis and association rule mining to identify associated replacement spare parts.

[0185] 3. Life Cycle Network Construction: Build a life cycle network among spare parts to analyze the mutual influence of spare part replacements.

[0186] V. Market Influence Factor Analysis and Inventory Decision

[0187] 1. Market Analysis: Study the influence of factors such as supply quantity, purchase unit price, and number of suppliers on spare part inventory.

[0188] 2. Inventory Optimization: Combine the prediction data and market factors, and use linear programming or dynamic programming algorithms to optimize spare part inventory.

[0189] 3. Risk Assessment: Evaluate the spare part supply risk and formulate countermeasures.

[0190] VI. Spare Part Reserve Decision and Maintenance Plan

[0191] 1. Reserve Quantity Calculation: Calculate the quantity of spare parts to be reserved based on the predicted life, associated spare parts, and inventory information.

[0192] 2. Priority Allocation: Allocate priorities for spare part reserves according to the importance and replacement urgency of spare parts.

[0193] 3. Maintenance Plan Formulation: Formulate a detailed maintenance plan, including the schedule and sequence of spare part replacements.

[0194] 4. Report Generation: Generate a comprehensive report containing prediction results, inventory suggestions, and maintenance plans.

[0195] Through the present invention, the intelligent maintenance management system of bank ATMs can achieve optimized management of spare parts inventory, effectively reduce downtime, improve maintenance efficiency, and provide better services to users. Meanwhile, the present invention can also be applied to equipment maintenance management in other fields and has broad application prospects.

[0196] In actual operation, the application of predictive analysis technology in bank ATM spare parts management is of great significance. The following is a specific case analysis demonstrating how to use predictive analysis technology to accurately predict and maintain ATM spare parts, improve service quality and operation efficiency, and reduce maintenance costs at the same time.

[0197] I. Scenario setting:

[0198] A certain bank has a large number of ATMs across the country, providing convenient financial services to users. However, as the usage time of ATMs increases, the wear degree of their internal components is also intensifying. In particular, the cash sorter is approaching the predicted value of its service life.

[0199] II. Data collection:

[0200] To accurately predict the remaining service life of the cash sorter, the relevant department of the bank collected the operation data and inventory information of ATMs. These data include the operation time, failure times, inventory quantity, etc. of the cash sorter to ensure the accuracy of predictive analysis.

[0201] III. Prediction and analysis:

[0202] By applying predictive analysis technology, the remaining service life of the cash sorter is predicted to be 250 hours. Meanwhile, the life cycle network analysis shows that the probability of replacing the banknote conveyor belt increases after the cash sorter is replaced.

[0203] IV. Market and inventory considerations:

[0204] As the market supply decreases, the purchase unit price of the cash sorter shows an upward trend. The bank evaluates the inventory of the cash sorter and finds that the inventory is low and immediate procurement is needed to meet potential demand.

[0205] V. Decision output:

[0206] Based on the results of predictive analysis, the bank recommends purchasing 10 spare parts of the cash sorter to meet future replacement needs. Meanwhile, considering the increased probability of replacing the banknote conveyor belt, the bank recommends monitoring the inventory of the banknote conveyor belt to ensure stable operation.

[0207] VI. Implementation effect:

[0208] By promptly purchasing spare parts for the cash sorter, the bank successfully avoided ATM downtime caused by cash sorter failures. Additionally, the associated replacement risks of the banknote conveyor belt were effectively managed, optimizing the spare parts inventory structure.

[0209] VII. Continuous Monitoring and Optimization:

[0210] To ensure the stable operation of ATMs, the bank will continuously monitor the operating status of ATMs and the spare parts inventory. Based on new data, the bank will update the prediction model and maintenance plan to ensure the accuracy and timeliness of spare parts management.

[0211] Through this actual case, the bank made full use of predictive analytics technology to conduct refined management of ATM spare parts, achieving improvements in service quality and operational efficiency while reducing maintenance costs. With the continuous development and improvement of predictive analytics technology, the bank will continue to explore its application in ATM spare parts management in the future to provide better services to users.

[0212] Of course, it can be understood that there may be other variations to the above detailed process, and all relevant variations should fall within the protection scope of the present invention.

[0213] In an embodiment of the present invention, a first 5G message carrying the target accessory operation data of the target banking machine is received from a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine; the target accessory operation data of the target banking machine is input into a banking machine accessory life prediction model to obtain the predicted service life data of each accessory of the target banking machine; the banking machine accessory life prediction model is obtained by training a pre-set neural network model with the banking machine accessory life historical data as a training set; the banking machine accessory life historical data includes the historical accessory operation data of different banking machines and the actual service life data of each accessory in the corresponding banking machine; for each accessory of the target banking machine, according to the accessory life cycle network of the target banking machine, it is determined whether there is a corresponding associated replacement accessory for the accessory of the banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network; according to the predicted service life data of each accessory of the target banking machine, whether there is a corresponding associated replacement accessory for each accessory of the target banking machine, the market impact factor of each accessory, and the spare part inventory information of each accessory, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory of the target banking machine are generated; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G intelligent tag pre-set in the spare part warehouse. Compared with the prior art in which the spare part quantity of banking machine accessories is predicted manually, the predicted life of each accessory of the banking machine can be accurately and quickly predicted through the banking machine accessory life prediction model, which helps to achieve an accurate estimate of the update of banking machine accessories; by determining the associated replacement accessories of each accessory through the accessory life cycle network, the spare part reserve strategy can be optimized according to the associated replacement situation of the accessories, the reserve cost can be reduced, and the utilization rate of spare parts can be improved. Further, by combining the market impact factor and the spare part inventory information, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory are generated, which improves the accuracy of banking machine accessory reserve, reduces the reserve cost, improves the reserve efficiency, accurately predicts the spare part demand of banking intelligent machines, thereby optimizing the spare part inventory management, reducing the operation interruption risk caused by insufficient spare parts, and avoiding the problems of inventory backlog and spare part shortage.

[0214] In an embodiment of the present invention, a spare part prediction device for a banking machine is also provided, as described in the following embodiment. Since the principle of the device for solving problems is similar to that of the spare part prediction method for a banking machine, the implementation of the device can refer to the implementation of the spare part prediction method for a banking machine, and the repeated parts will not be described again.

[0215] An embodiment of the present invention further provides a spare part prediction device for a banking machine, which is used to improve the accuracy of predicting the spare part reserve quantity of the accessories of the banking machine, reduce the reserve cost, and improve the reserve efficiency. As Figure 3 shown, the device includes:

[0216] The first 5G message receiving module 301 is configured to receive a first 5G message carrying the target accessory operation data of the target banking machine sent by a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine;

[0217] The predicted service life data determination module 302 is configured to input the target accessory operation data of the target banking machine into a banking machine accessory life prediction model to obtain the predicted service life data of each accessory of the target banking machine; the banking machine accessory life prediction model is trained by using the banking machine accessory life historical data as a training set for a pre-set neural network model; the banking machine accessory life historical data includes the historical accessory operation data of different banking machines and the actual service life data of each accessory in the corresponding banking machine;

[0218] The associated replacement part determination module 303 is configured to, for each accessory of the target banking machine, determine whether there is a corresponding associated replacement part for the accessory of the banking machine according to the accessory life cycle network of the target banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement part has the number of replacements exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network;

[0219] The spare part information generation module 304 is configured to generate the spare part quantity to be reserved information and the spare part reserve priority information of each accessory of the target banking machine according to the predicted service life data of each accessory of the target banking machine, whether there is a corresponding associated replacement part for each accessory of the target banking machine, the market influencing factors of each accessory, and the spare part inventory information of each accessory; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G smart tag pre-set in the spare part warehouse.

[0220] In one embodiment, as Figure 4 shown, it further includes:

[0221] The life cycle network establishment module 401 is configured to:

[0222] For each banking machine, based on the sliced binary tree technology, perform data slicing on the replacement time data of different components of the collected banking machine to obtain continuous time series data of the replacement time data of different components; the time points in the continuous time series data represent the corresponding component replacement events.

[0223] For each component, determine whether the number of replacements of other components exceeds a preset value within a preset time period after the replacement of this component; if so, regard the other component as the associated replacement component of this component.

[0224] Use the replacement time data in the continuous time series data of each component as the nodes of the life cycle network, and establish edges between the nodes of the life cycle network between each component and the associated replacement component corresponding to this component to obtain the life cycle network.

[0225] In one embodiment, it further includes:

[0226] Based on feature engineering technology, extract the feature data of the component operation data in the first 5G message.

[0227] Input the target component operation data of the target banking machine into the banking machine component life prediction model to obtain the predicted service life data of each component of the target banking machine, including:

[0228] Input the feature data of the target component operation data of the target banking machine into the banking machine component life prediction model to obtain the predicted service life data of each component of the target banking machine.

[0229] In one embodiment, it further includes:

[0230] Use the historical data of the banking machine component life as the validation set to validate the banking machine component life prediction model to obtain the validated banking machine component life prediction model.

[0231] Input the target component operation data of the target banking machine into the banking machine component life prediction model to obtain the predicted service life data of each component of the target banking machine, including:

[0232] Input the target component operation data of the target banking machine into the validated banking machine component life prediction model to obtain the predicted service life data of each component of the target banking machine.

[0233] In one embodiment, the market influencing factors include: one or any combination of the spare parts market supply, the number of repairs, the monthly consumption of spare parts, the number of repairs, the degree of repair, the purchase quantity, the working time of spare parts equipment, the number of spare parts suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance times.

[0234] In one embodiment, the spare part quantity information to be reserved and the spare part reserve priority information of the accessories of each banking machine are displayed to the user through a visualization interface; wherein, the visualization interface is used to display data in a manner including but not limited to charts, graphs, color coding, or data dashboards.

[0235] An embodiment of the present invention provides an embodiment of a computer device for implementing all or part of the above-mentioned spare part prediction method for banking machines. The computer device specifically includes the following:

[0236] A processor, a memory, a communications interface, and a bus; wherein, the processor, the memory, and the communications interface complete mutual communication through the bus; the communications interface is used to implement information transmission between related devices; this computer device can be a desktop computer, a tablet computer, a mobile terminal, etc., and this embodiment is not limited thereto. In this embodiment, this computer device can be implemented with reference to the embodiments for implementing the spare part prediction method for banking machines and the embodiments for implementing the spare part prediction device for banking machines, and the content thereof is incorporated herein, and the repeated parts will not be described again.

[0237] Figure 5 It is a schematic block diagram of the system composition of the computer device 1000 according to an embodiment of the present application. As Figure 5 shown, the computer device 1000 may include a central processing unit 1001 and a memory 1002; the memory 1002 is coupled to the central processing unit 1001. It should be noted that this Figure 5 is exemplary; other types of structures can also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0238] In one embodiment, the spare part prediction function of the banking machine can be integrated into the central processing unit 1001. Among them, the central processing unit 1001 can be configured to perform the following controls:

[0239] Receive a first 5G message carrying the target accessory operation data of the target banking machine sent by a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine;

[0240] Input the target accessory operation data of the target banking machine into a banking machine accessory life prediction model to obtain the predicted service life data of each accessory of the target banking machine; the banking machine accessory life prediction model is obtained by training a pre-set neural network model with the historical data of banking machine accessory life as the training set; the historical data of banking machine accessory life includes the historical accessory operation data of different banking machines and the actual service life data of each accessory in the corresponding banking machine.

[0241] For each accessory of the target banking machine, determine whether there is a corresponding associated replacement accessory for the accessory according to the accessory life cycle network of the target banking machine; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has the number of replacements exceeding a preset value within a preset time period after the accessory is replaced in the accessory life cycle network.

[0242] Generate the spare part quantity information to be reserved and the spare part reserve priority information of each accessory of the target banking machine according to the predicted service life data of each accessory of the target banking machine, whether there is a corresponding associated replacement accessory for each accessory of the target banking machine, the market influencing factors of each accessory, and the spare part inventory information of each accessory; the spare part inventory information of each accessory is obtained from the second 5G message carrying the spare part inventory information sent by the 5G intelligent tag pre-set in the spare part warehouse.

[0243] In another implementation, the spare part prediction device of the banking machine can be separately configured from the central processing unit 1001. For example, the spare part prediction device of the banking machine can be configured as a chip connected to the central processing unit 1001, and the spare part prediction function of the banking machine is realized through the control of the central processing unit.

[0244] As Figure 5 shown, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It should be noted that the computer device 1000 does not necessarily have to include all the components shown in Figure 5 ; in addition, the computer device 1000 may further include components not shown in Figure 5 , and reference can be made to the prior art.

[0245] As Figure 5 shown, the central processing unit 1001 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The central processing unit 1001 receives inputs and controls the operations of the various components of the computer device 1000.

[0246] Among them, the memory 1002 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. It can store the above device-related information, and can also store programs for executing relevant information. And the central processing unit 1001 can execute the program stored in the memory 1002 to achieve information storage or processing, etc.

[0247] The input unit 1004 provides input to the central processing unit 1001. The input unit 1004 is, for example, a key or a touch input device. The power supply 1007 is used to supply power to the computer device 1000. The display 1006 is used to display display objects such as images and texts. The display can be, for example, an LCD display, but is not limited thereto.

[0248] The memory 1002 can be a solid-state memory. For example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that stores information even when powered off, can be selectively erased and has more data. Examples of such a memory are sometimes referred to as EPROM, etc. The memory 1002 can also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 can include an application / function storage unit 1022, which is used to store application programs and function programs or the processes for operating the computer device 1000 through the central processing unit 1001.

[0249] The memory 1002 can also include a data storage unit 1023, which is used to store data, such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. The driver storage unit 1024 of the memory 1002 can include various drivers of the computer device for communication functions and / or for executing other functions of the computer device (such as a messaging application, an address book application, etc.).

[0250] The communication module 1003 is a transmitter / receiver 1003 that transmits and receives signals via the antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processing unit 1001 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0251] Based on different communication technologies, in the same computer device, multiple communication modules 1003 can be provided, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide an audio output via the speaker 1009 and receive an audio input from the microphone 1010, so as to implement normal telecommunication functions. The audio processor 1005 may include any suitable buffers, decoders, amplifiers, etc. Additionally, the audio processor 1005 is also coupled to a central processor 1001, enabling recording on the local machine through the microphone 1010 and playing the sounds stored on the local machine through the speaker 1009.

[0252] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the spare part prediction method of the above-mentioned banking machine is implemented.

[0253] An embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the spare part prediction method of the above-mentioned banking machine is implemented.

[0254] In an embodiment of the present invention, a first 5G message carrying the target accessory operation data of the target bank device sent by a pre-set 5G message sensor is received; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the bank device; the target accessory operation data of the target bank device is input into a bank device accessory life prediction model to obtain the predicted service life data of each accessory of the target bank device; the bank device accessory life prediction model is obtained by training a pre-set neural network model with the bank device accessory life historical data as the training set; the bank device accessory life historical data includes the historical accessory operation data of different bank devices and the actual service life data of each accessory in the corresponding bank device; for each accessory of the target bank device, according to the accessory life cycle network of the target bank device, it is determined whether there is a corresponding associated replacement accessory for the accessory of the bank device; the accessory life cycle network uses the replacement time data of each accessory as the node of the life cycle network; the associated replacement accessory has a replacement frequency exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network; according to the predicted service life data of each accessory of the target bank device, whether there is a corresponding associated replacement accessory for each accessory of the target bank device, the market influencing factors of each accessory, and the spare part inventory information of each accessory, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory of the target bank device are generated; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G intelligent tag pre-set in the spare part warehouse. Compared with the prior art in which the spare part quantity of bank device accessories is predicted manually, the predicted life of each accessory of the bank device can be accurately and quickly predicted through the bank device accessory life prediction model, which helps to accurately estimate the update of bank device accessories; by determining the associated replacement accessories of each accessory through the accessory life cycle network, the spare part reserve strategy can be optimized according to the associated replacement situation of the accessories, the reserve cost can be reduced, and the utilization rate of spare parts can be improved. Further, by combining the market influencing factors and the spare part inventory information, the spare part quantity to be reserved information and the spare part reserve priority information of each accessory are generated, which improves the accuracy of bank device accessory reserves, reduces the reserve cost, improves the reserve efficiency, accurately predicts the spare part demand of bank intelligent devices, thereby optimizing the spare part inventory management, reducing the operation interruption risk caused by insufficient spare parts, and avoiding the problems of inventory backlog and spare part shortage.

[0255] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0256] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0257] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0258] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0259] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting spare parts of a banking machine, characterized in that, Including: Receiving a first 5G message carrying the target accessory operation data of the target bank machine tool sent by a pre-set 5G message sensor; the accessory operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the bank machine tool; Inputting the target accessory operation data of the target bank machine tool into a bank machine tool accessory life prediction model to obtain the predicted service life data of each accessory of the target bank machine tool; the bank machine tool accessory life prediction model is trained by using the bank machine tool accessory life historical data as a training set for a pre-set neural network model; the bank machine tool accessory life historical data includes the historical accessory operation data of different bank machine tools and the actual service life data of each accessory in the corresponding bank machine tool; For each accessory of the target bank machine tool, determining whether there is a corresponding associated replacement accessory according to the accessory life cycle network of the target bank machine tool; the accessory life cycle network uses the replacement time data of each accessory as the nodes of the life cycle network; the associated replacement accessory has the number of replacements exceeding a preset value within a preset time period after the replacement of the accessory in the accessory life cycle network; Generating the spare part quantity information to be reserved and the spare part reserve priority information for each accessory of the target bank machine tool according to the predicted service life data of each accessory of the target bank machine tool, whether there is a corresponding associated replacement accessory for each accessory of the target bank machine tool, the market influence factors of each accessory, and the spare part inventory information of each accessory; the spare part inventory information of each accessory is obtained from a second 5G message carrying the spare part inventory information sent by a 5G smart tag pre-set in the spare part warehouse.

2. The method according to claim 1, characterized in that, Also including: Extracting the feature data of the accessory operation data in the first 5G message based on feature engineering technology; Inputting the target accessory operation data of the target bank machine tool into a bank machine tool accessory life prediction model to obtain the predicted service life data of each accessory of the target bank machine tool, including: Inputting the feature data of the target accessory operation data of the target bank machine tool into a bank machine tool accessory life prediction model to obtain the predicted service life data of each accessory of the target bank machine tool.

3. The method according to claim 1, wherein Also including: For each bank machine tool, based on the sliced binary tree technology, performing data slicing processing on the replacement time data of different accessories of the collected bank machine tool to obtain the continuous time series data of the replacement time data of different accessories; The time points in the continuous time series data represent the corresponding accessory replacement events; For each accessory, determining whether there is another accessory with the number of replacements exceeding a preset value within a preset time period after the replacement of the accessory; if so, regarding the other accessory as the associated replacement accessory of the accessory; Taking the replacement time data in the continuous time series data of each accessory as the nodes of the life cycle network and establishing an edge between the nodes of the life cycle network between each accessory and the associated replacement accessory corresponding to the accessory to obtain the life cycle network.

4. The method according to claim 3, characterized in that, For each banking machine, based on the sliced binary tree technology, perform data slicing on the replacement time data of different components of the banking machine collected, to obtain continuous time series data of the replacement time data of different components, including: For each banking machine, perform window data segmentation on the replacement time data of the component collected with a preset time window corresponding to the component of the banking machine, to obtain multiple replacement times of the component; For each component, use the initial replacement time of the component as the root node of the binary tree of the component, and use different replacement times of the component as the child nodes of the binary tree of the component; link the time window data in chronological order through nodes to form the binary tree of the component; Read the continuous time series data of the replacement time data of the component from the binary tree of the component.

5. The method according to claim 1, wherein It also includes: Use the historical data of the life of banking machine components as the validation set to validate the life prediction model of banking machine components, to obtain the life prediction model of banking machine components after passing the validation; Input the target component operation data of the target banking machine into the life prediction model of banking machine components, to obtain the predicted service life data of each component of the target banking machine, including: Input the target component operation data of the target banking machine into the life prediction model of banking machine components that has passed the validation, to obtain the predicted service life data of each component of the target banking machine.

6. The method according to claim 1, wherein The market influencing factors include one or any combination of the spare parts market supply quantity, the number of repairs, the monthly consumption quantity of spare parts, the number of repairs, the degree of repair, the purchase quantity, the working time of spare parts equipment, the number of spare parts suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance times.

7. The method according to claim 1, wherein It also includes: Display the spare parts to-be-reserved quantity information and spare parts reserve priority information of the components of each banking machine to the user through a visualization interface; wherein, the visualization interface is used to display data in a manner including but not limited to charts, graphs, color coding, or data dashboards.

8. A spare part prediction device for a banking machine, characterized in that, It includes: A first 5G message receiving module, configured to receive a first 5G message carrying the target component operation data of the target banking machine sent by a preset 5G message sensor; the component operation data includes the operation temperature data, operation humidity data, operation vibration frequency data, and operation duration data of the banking machine; A predicted service life data determination module, configured to input the target component operation data of the target banking machine into the life prediction model of banking machine components, to obtain the predicted service life data of each component of the target banking machine; the life prediction model of banking machine components is obtained by training a preset neural network model with the historical data of the life of banking machine components as the training set; the historical data of the life of banking machine components includes the historical component operation data of different banking machines and the actual service life data of each component in the corresponding banking machine; The associated replacement part determination module is used to determine whether there is a corresponding associated replacement part for each part of each target banking machine according to the part life cycle network of the target banking machine; the part life cycle network uses the replacement time data of each part as the nodes of the life cycle network; the associated replacement part has the number of replacements of the associated replacement part exceeding a preset value within a preset time period after the replacement of the part in the part life cycle network. The spare part information generation module is used to generate the spare part quantity information to be reserved and the spare part reserve priority information for each part of the target banking machine according to the predicted service life data of each part of the target banking machine, whether there is a corresponding associated replacement part for each part of the target banking machine, the market influencing factors of each part, and the spare part inventory information of each part; the spare part inventory information of each part is obtained from the second 5G message carrying the spare part inventory information sent by the 5G smart tag preset in the spare part warehouse.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the method according to any one of claims 1 to 7.

Images