A method, system and device for shared equipment operation and maintenance management based on big data

Abstract

The present application relates to the technical field of shared device management, and discloses a shared device operation and maintenance management method, system and device based on big data. The method includes: dividing shared devices into mobile devices and non-mobile devices, and the shared devices collect their own device data and send them to a central server; the central server integrates the device data of mobile devices in a first time period into a first data set, and the device data of non-mobile devices into a second data set; the first data set is analyzed based on a first prediction model, and the second data set is analyzed based on a second prediction model to determine the health, and the shared devices are divided into healthy devices, critical devices and faulty devices based on the health; the central server shortens the analysis interval of the critical device data, and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty device. The present invention tracks the health status of shared devices at a relatively low cost, so that potential faults can be discovered and repaired in a timely manner.

Description

Technical Field

[0001] The present application relates to the technical field of shared equipment, and in particular to a method, system and equipment for shared equipment operation and maintenance management based on big data. Background Art

[0002] In recent years, the sharing model has developed rapidly driven by the Internet of Things and mobile Internet technologies. Shared equipment has been widely used in transportation, energy, public facilities and other fields. However, since shared equipment needs to be circulated among multiple users, in order to ensure the most efficient use of the equipment, it is necessary to schedule and maintain it in a timely manner according to the use of the equipment.

[0003] To this end, in the prior art, for example, a Chinese patent document with publication number CN119180475A discloses a scheduling method and server for shared vehicles. This method allows the operation and maintenance personnel to select scheduling information with a relatively close distance and a relatively appropriate number in the electronic map according to their location after opening the mobile terminal application and establish a scheduling task. Then, according to the location and number of the pulling points displayed on the electronic map, the operation and maintenance personnel go to the appropriate pulling points to pull the vehicles and deliver them to the delivery points, thereby quickly and effectively guiding the operation and maintenance personnel to dispatch shared vehicles. For example, a Chinese patent document with publication number CN118982179A discloses a shared device scheduling method, device and electronic device. This method can guide the user to obtain the device from the geographical location that meets the device acquisition condition or the device return condition when the user obtains or returns the device by displaying the geographical location where the number of surrounding devices meets the device acquisition condition or the device return condition, thereby reducing the device scheduling cost and improving the device scheduling efficiency.

[0004] In addition to scheduling, the health status of shared devices also needs to be tracked. Currently, the operation and maintenance of shared devices rely on manual inspections or users' proactive repair reports, and potential equipment failures cannot be predicted, resulting in increased downtime and rising maintenance costs, affecting user experience. Summary of the invention

[0005] In order to solve the problems raised in the above background technology, the present application provides a shared equipment operation and maintenance management method, system and equipment based on big data.

[0006] In order to achieve the above-mentioned invention object, the present invention proposes a shared equipment operation and maintenance management method based on big data, comprising: Classifying shared devices into mobile devices and non-mobile devices, wherein the shared devices collect their own device data and send them to a central server; Establishing a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device respectively; The central server distinguishes the device type of the shared device according to the device identifier received in the device data, and integrates the device data of the mobile device in the first time period into a first data set and integrates the device data of the non-mobile device into a second data set; Analyze the first data set based on a first prediction model and analyze the second data set based on a second prediction model to determine the health of the shared device, and classify the shared device into healthy devices, critical devices, and faulty devices based on the health; The central server shortens the analysis interval of the device data of the critical device and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty device.

[0007] Furthermore, the mobile device sending the device data comprises the following steps: A first transmission mode and a second transmission mode are set in the mobile device, the device data includes location information of the mobile device, and the mobile device sends the device information to the central server based on the first transmission mode in a default state; After collecting the device data within the second time period, the central server analyzes the location information included therein to determine high-frequency locations used by the mobile device, and deploys relay nodes at the high-frequency locations. The central server combines the location information and the deployment location of the relay nodes, and when it is determined that the mobile device has entered the coverage range of the relay node, commands the mobile device to use the second transmission method to send the device data to the relay node. The relay node adaptively compresses the device data and sends it to the central server.

[0008] Furthermore, adaptively compressing the device data comprises the following steps: A micro-model is deployed in the relay node, where the micro-model is a simplified model of the first prediction model. The mobile device is divided into the healthy device and the faulty device based on the micro-model and the device data. The device data received from the healthy device in a third time period is aggregated and compressed into a whole block of data and then sent to the central server. The device data of the faulty device is inserted into a fault mark and then sent to the central server.

[0009] Furthermore, establishing the first prediction model comprises the following steps: The historical data includes the location of the mobile device, the corresponding occurrence time and the fault type. The movement characteristics of each user in the process of using the mobile device are calculated based on the historical data. The movement characteristics include average moving speed, maximum moving speed, minimum moving speed, number of brakes, and usage time. The first prediction model is established based on a fully connected neural network. The movement characteristics are used as input features of the first prediction model, and the fault type and occurrence probability are used as output features. The first prediction model is established in combination with the historical data training.

[0010] Furthermore, establishing the second prediction model comprises the following steps: The historical data includes the usage characteristics of the non-mobile device and the fault type, a plurality of the usage characteristics that appear before each fault occurs are integrated into a fault conduction chain for the fault in the order of occurrence time, the fault type is marked in the fault conduction chain, and adjacent and identical usage characteristics in the fault conduction chain are merged to optimize the fault conduction chain into a streamlined conduction chain; Starting with the first usage feature in the streamlined conduction chain, each streamlined conduction chain is recursively split into multiple sub-conduction chains based on time sequence, and the association probability of various fault types caused by the appearance of the sub-conduction chain is statistically calculated based on the historical data, and the sub-conduction chain with the association probability greater than a first threshold is screened as the first sensitive conduction chain. After screening the first sensitive conduction chain, a second sensitive conduction chain is obtained, and the second sensitive conduction chain, the corresponding fault type and the association probability are used as a training set, and the second prediction model based on the time series neural network is established based on the training set.

[0011] Furthermore, screening the first sensitive conductive chain includes the following steps: The first sensitive conduction chain derived from the same streamlined conduction chain is defined as a homologous conduction chain. The homologous conduction chains are sorted from large to small based on length characteristics, and the difference in the association probabilities of the homologous conduction chains at adjacent positions after sorting is calculated. If the difference is greater than a first threshold, the homologous conduction chain with a longer length is retained. If the difference is less than a second threshold, the homologous conduction chain with a shorter length is retained. The retained homologous conduction chain continues to be compared with the homologous conduction chain at a subsequent position. This step is repeated until all the first sensitive conduction chains are traversed and the retained one is defined as the second sensitive conduction chain.

[0012] Further, calculating the health of the non-mobile device includes the following steps: The device data of each user ID in the first data set is integrated into an actual feature chain, each actual feature chain is input into the first prediction model, the fault type with the highest probability of association with the actual feature chain is obtained, the association probabilities of all the fault types are weighted and averaged, the health degree is calculated based on the association probability with the largest average value, and the health degree is output jointly with the corresponding fault type.

[0013] Further, determining the high-frequency location comprises the following steps: The preset area is divided into a fixed number of grid areas, and the mobile devices are clustered in time and space density based on the locations of the mobile devices and the corresponding appearance times. Based on the clustering results, dense areas are screened out from the grid areas, and the grid areas where the dense areas are located are used as the high-frequency locations.

[0014] A shared equipment operation and maintenance management system based on big data, used to implement the above-mentioned shared equipment operation and maintenance management method based on big data, characterized in that: The terminal module includes a shared device, which divides the shared device into a mobile device and a non-mobile device, and the shared device collects its own device data and sends it to the central server; A front-end module is provided in the central server, wherein the front-end module establishes a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device, respectively, distinguishes the device type of the shared device according to the device identifier received in the device data, and integrates the device data of the mobile device within a first time period into a first data set and integrates the device data of the non-mobile device into a second data set; a classification module, arranged in the central server, wherein the classification module analyzes the first data set based on a first prediction model and analyzes the second data set based on a second prediction model to determine the health of the shared device, and classifies the shared device into healthy devices, critical devices, and faulty devices based on the health; A strategy module is provided in the central server, wherein the strategy module shortens the analysis interval of the device data of the critical device and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty device.

[0015] The present application also provides a shared equipment operation and maintenance management device based on big data, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-described method when executing the computer program.

[0016] Beneficial effects; The present invention subdivides shared devices into mobile devices and non-mobile devices, and establishes prediction models based on their characteristics and historical data. This classification process helps to more accurately predict the status of the device and improve the efficiency of operation and maintenance. Shared devices are divided into healthy devices, critical devices and faulty devices according to their health. For critical devices, by shortening the analysis interval of the device data analysis frequency, problems can be discovered more promptly, thereby speeding up the response speed and avoiding further development of equipment failures. For faulty equipment, the ant colony algorithm is used to generate personnel inspection paths, which can ensure that maintenance personnel can handle faulty equipment efficiently and orderly. This intelligent path planning method helps to reduce the time spent by maintenance personnel on the road and improve maintenance efficiency. Therefore, the present invention tracks the health status of shared devices at a lower cost, so that potential faults can be discovered and repaired in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of the steps of a shared equipment operation and maintenance management method based on big data is provided for this application; Figure 2 Schematic diagram of the principle of optimizing the fault transmission chain for this application; Figure 3 Schematic diagram of the principle of splitting and streamlining the conduction chain for this application; Figure 4 The present invention provides a structural diagram of a shared equipment operation and maintenance management system based on big data. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0020] like Figure 1 As shown, a shared equipment operation and maintenance management method based on big data includes: S1: Shared devices are divided into mobile devices and non-mobile devices. Shared devices collect their own device data and send them to the central server.

[0021] The shared devices in this embodiment include shared bicycles, shared electric vehicles, shared power banks, shared massage chairs, etc. Mobile vehicles such as shared bicycles and shared electric vehicles are classified as mobile devices in advance, and the rest are classified as non-mobile devices. All shared devices collect their own device data and send it to the central server. The device data includes device location, start time, end time, etc.

[0022] S2: Establishing a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device respectively.

[0023] S3: The central server distinguishes the device type of the shared device according to the device identifier in the received device data, and integrates the device data of the mobile device in the first time period into a first data set and the device data of the non-mobile device into a second data set.

[0024] S4: Analyze the first data set based on the first prediction model and analyze the second data set based on the second prediction model to determine the health of the shared devices, and divide the shared devices into healthy devices, critical devices, and faulty devices based on the health.

[0025] The first prediction model identifies whether a mobile device has a device failure based on user behavior records, and the second prediction model is used to identify whether a non-mobile device has a device failure. The specific prediction rules will be introduced later. After the central server receives the device data, it determines the device type of the shared device based on the device identifier received together. The device types include shared bicycles, shared electric vehicles, shared power banks, etc. The first time period is 00:00-23:00 every day. For example, after the central server receives the device data sent by the shared bicycle between 00:00-23:00, it organizes it into a first data set. Similarly, the device data of non-mobile devices is organized into a second data set. The first data set is then input into the first prediction model, and the second data set is input into the second prediction model, so that the first prediction model outputs the health of the corresponding mobile device, and the second prediction model outputs the health of the corresponding non-mobile device.

[0026] This embodiment divides the device into three ranges, the first range is 0-40%, the second range is 40-70%, and the third range is 70-100%. When the health of the shared device is within the first range, it is classified as a faulty device. When it is within the second range, it is classified as a critical device, indicating that the device may be about to fail. When it is within the third range, it is classified as a healthy device.

[0027] S5: The central server shortens the analysis interval of the critical equipment data and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty equipment.

[0028] For critical equipment, the monitoring frequency can be increased by shortening the analysis interval. For example, when a shared device is in a healthy state, the analysis frequency is once a day. When it is in a critical state, the analysis frequency is adjusted to once every 8 hours, that is, the device is analyzed once every 8 hours of data collection. This method can detect critical equipment failures more promptly.

[0029] For mobile devices, when the number of mobile devices judged to be faulty in an area exceeds a certain number, these mobile devices are uniformly tested. If a fault is confirmed after the test, it is repaired, otherwise the fault report is eliminated in the system. For non-mobile devices, the ant colony algorithm is used to generate a personnel inspection path, which is the optimal path, so that the maintenance personnel responsible for the area can efficiently test and repair the faulty equipment at each location in turn.

[0030] The present invention subdivides shared devices into mobile devices and non-mobile devices, and establishes prediction models based on their characteristics and historical data. This classification process helps to more accurately predict the status of the device and improve the efficiency of operation and maintenance. Shared devices are divided into healthy devices, critical devices and faulty devices according to their health. For critical devices, by shortening the analysis interval of the device data analysis frequency, problems can be discovered more promptly, thereby speeding up the response speed and avoiding further development of equipment failures. For faulty equipment, the ant colony algorithm is used to generate personnel inspection paths, which can ensure that maintenance personnel can handle faulty equipment efficiently and orderly. This intelligent path planning method helps to reduce the time spent by maintenance personnel on the journey and improve maintenance efficiency.

[0031] It is particularly noteworthy that the present invention can track the health status of shared equipment at a relatively low cost, so that potential faults can be discovered and repaired in a timely manner.

[0032] In this embodiment, the mobile device sending usage information includes the following steps: A first transmission mode and a second transmission mode are set in a mobile device, the device data includes location information of the mobile device, and the mobile device sends the device information to a central server based on the first transmission mode in a default state.

[0033] After collecting the device data within the second time period, the central server analyzes the location information included therein to determine high-frequency locations where the mobile device is used, and deploys relay nodes at the high-frequency locations. The central server combines the location information and the deployment location of the relay nodes, and when it is determined that the mobile device has entered the coverage range of the relay node, it commands the mobile device to use the second transmission method to send the device data to the relay node. The relay node adaptively compresses the device data and sends it to the central server.

[0034] In this embodiment, the first transmission mode is cellular network communication, and the second transmission mode is Bluetooth communication. In other embodiments, the second transmission mode may also be local area network communication.

[0035] In the default state, the mobile device directly sends its own device data to the central server in the first transmission mode. The second time period is one month. For example, after the central server collects the device data of each mobile device in a certain area within one month, it starts to analyze and determine the high-frequency use locations of mobile devices. More mobile devices need to be deployed in high-frequency use locations to ensure that the user's usage needs are met. Since the presence of more mobile devices in the same location will increase the transmission load of the area, in order to achieve faster data transmission, this embodiment sets a relay node at a high-frequency location, and the relay node is an edge server.

[0036] After the relay node is set up, when the central server detects that a mobile device enters the coverage range of a relay node, such as the coverage range is 100m, a conversion instruction is sent to the mobile device, so that the mobile device uses the second transmission method to transmit the device data to the relay node. After the relay node aggregates the device data of multiple mobile devices, it compresses and packages them and sends them to the central server, thereby reducing the amount of data transmission and reducing the receiving frequency of the central server, thereby speeding up the data transmission speed.

[0037] In this embodiment, adaptively compressing device data includes the following steps: A micro-model is deployed in the relay node. The micro-model is a simplified model of the first prediction model. The mobile devices are divided into healthy devices and faulty devices based on the micro-model and device data. The device data of the healthy devices received in the third time period are aggregated and compressed into a whole block of data and then sent to the central server. The device data of the faulty devices are inserted into the fault mark and then sent to the central server.

[0038] Specifically, the micro-model is a simplified version of the first prediction model. In this embodiment, the first prediction model is a 3-layer BP neural network, and the corresponding micro-model is a neural network with reduced input features. By simplifying the structure of the neural network, the relay node as an edge computing node can also quickly evaluate the status of the mobile device, thereby realizing the pre-screening of the status of the mobile device. In particular, the reference range of the relay node for dividing the mobile device is consistent with that before. After identification by the relay node, for healthy devices, they are aggregated and compressed into a whole block of data and then sent to the central server. The central server can obtain complete data after decompression. For the data of the faulty device, the fault mark is inserted before sending. After receiving, the central server can use it directly without decompression. This method can not only obtain the health status of the mobile device more quickly, but also reduce the number of communications between the mobile device and the central server, thereby reducing the communication load of the central server.

[0039] In this embodiment, establishing the first prediction model includes the following steps: The historical data includes the location of the mobile device, the corresponding occurrence time and the fault type. The movement characteristics of each user in the process of using the mobile device are calculated based on the historical data. The movement characteristics include the average moving speed, the maximum moving speed, the minimum moving speed, the number of brakes, and the usage time. The first prediction model is established based on a fully connected neural network. The movement characteristics are used as the input features of the first prediction model, and the fault type and occurrence probability are used as the output features. The first prediction model is established in combination with the historical data training.

[0040] The historical data is a large amount of historical fault data collected in advance, including the fault type of the data, the location of the mobile device every 3 seconds, the time of occurrence of the location, and the location is recorded in the form of longitude and latitude. After the user returns the mobile device, the average moving speed is calculated based on the usage time and the moving path of the mobile device, and the interval speed between two adjacent locations is calculated based on the distance and time difference between each adjacent location, and the highest and lowest moving speeds are screened out. If the speed of two adjacent intervals drops from a larger value to a smaller value, and the difference between the two is greater than the preset value, it is considered that the user has braked. The first prediction model is a 3-layer BP neural network. The input features are the above-mentioned mobile features, and the various fault types and corresponding occurrence probabilities of the output features are normalized to between 0 and 1 by using the Softmax function to obtain the occurrence probability.

[0041] In this embodiment, establishing the second prediction model includes the following steps: Historical data includes usage characteristics and fault types of non-mobile equipment. Multiple usage characteristics that appear before each fault are integrated into a fault conduction chain for this fault in chronological order. The fault type is marked in the fault conduction chain, and adjacent and identical usage characteristics in the fault conduction chain are merged to optimize the fault conduction chain into a streamlined conduction chain.

[0042] Historical data refers to a large amount of historical fault data collected in advance. For example, if a non-mobile device has a fault type 1, multiple usage features before the occurrence of fault type 1 are integrated into a fault conduction chain of fault type 1 according to time. Fault type 1 is, for example, a massage chair that cannot be heated. Its previous usage features include turning on the heating, increasing the temperature by 1°C, increasing the temperature by 1°C, turning off the heating, etc. The above usage features are sorted according to time into a fault conduction chain of fault type 1. Similarly, the above processing is performed on the historical data of all non-mobile devices to obtain multiple different fault conduction chains for the same fault type. Refer to Figure 2 In the schematic diagram shown, in order to simplify the length of the conduction chain, the consecutive appearances are merged using features. For example, if the temperature increases by 1°C twice in a row, they are merged into one and the number of mergers is marked, which is 2 times here.

[0043] Starting with the first usage feature in the streamlined conduction chain, each streamlined conduction chain is recursively split into multiple sub-conduction chains based on time sequence. The association probability of various fault types caused by the appearance of the sub-conduction chain is statistically analyzed based on historical data. The sub-conduction chain with an association probability greater than a first threshold is screened as the first sensitive conduction chain. After screening the first sensitive conduction chain, the second sensitive conduction chain is obtained. The second sensitive conduction chain, the corresponding fault type and the association probability are used as a training set. Based on the training set, a second prediction model based on a time series neural network is established.

[0044] Refer to Figure 3 As shown in the schematic diagram, for example, the streamlined conduction chain is turning on heating - raising the temperature by 1°C (5 times) - turning off heating, then it is recursively split into three sub-conduction chains: turning on heating, turning on heating - raising the temperature by 1°C (5 times), turning on heating - raising the temperature by 1°C (5 times) - turning off heating. For example, there is also a streamlined conduction chain turning on heating - raising the temperature by 5°C (5 times) - turning off heating, then it is recursively split into turning on heating, turning on heating - raising the temperature by 5°C (5 times), turning on heating - raising the temperature by 5°C (5 times) - turning off heating. Repeat this step to split each streamlined conduction chain.

[0045] Then the probability of association between each sub-conduction chain and the fault type is calculated based on the first formula, which is: ,in, is the probability of association between the ith subconduction chain and the jth fault type, is the number of occurrences of the i-th subconduction chain under the j-th fault type, is the number of all sub-conduction chains included in the jth fault type. For example, through calculation, it is determined that the association probability between fault type 1 and sub-conduction chain A is 40%, and the set first threshold is 35%. Then, sub-conduction chain A is used as the first sensitive conduction chain. The higher the association probability, the more likely it is that the device has a fault type 1 after the use characteristics of sub-conduction chain A appear in sequence. Then, the first sensitive conduction chain is simplified to obtain the second sensitive conduction chain. The specific calculation method is introduced later.

[0046] Finally, the second sensitive conduction chain, the corresponding fault type and the associated probability are used as the training set to establish the LSTM time series neural network model as the first prediction model.

[0047] In this embodiment, screening the first sensitive conductive chain includes the following steps: The first sensitive conduction chain originating from the same streamlined conduction chain is defined as a homologous conduction chain. The homologous conduction chains are sorted from large to small based on the length characteristics, and the difference in the association probability of homologous conduction chains at adjacent positions after sorting is calculated. If the difference is greater than the first threshold, the homologous conduction chain with a longer length is retained. If the difference is less than the second threshold, the homologous conduction chain with a shorter length is retained, and the retained homologous conduction chain is continued to be compared with the homologous conduction chain at the subsequent position. This step is repeated until all first sensitive conduction chains are traversed and the retained one is defined as the second sensitive conduction chain.

[0048] For ease of description, the simplified conduction chain is defined as ABCD, and the homologous conduction chains derived from the simplified conduction chain include ABCD, BCD and CD, and the association probabilities with fault type 1 are 54%, 40% and 36% respectively. The above homologous conduction chains have been sorted from large to small according to their length characteristics. The difference in the association probabilities between the homologous conduction chains ABCD and BCD is 14%. If the first threshold is 10%, the homologous conduction chain ABCD is retained and the homologous conduction chain BCD is deleted, indicating that the longer homologous conduction chain is more closely related to fault type 1. For another example, the association probabilities of the above three homologous conduction chains with fault type 1 are 36%, 59% and 60% respectively, and the difference in the association probabilities between the homologous conduction chains ABCD and BCD is -13%. If the second threshold is -10%, the homologous conduction chain BCD is retained and the homologous conduction chain ABCD is deleted. In particular, if the difference is between the first threshold and the second threshold, the homologous conduction chain with a shorter length is retained. For example, in the above examples of 36%, 59%, and 60%, if the difference between BCD and CD is between the first threshold and the second threshold, the homologous conduction chain CD is retained.

[0049] In this embodiment, calculating the health of a non-mobile device includes the following steps: The device data of each user ID in the first data set is integrated into an actual feature chain, and each actual feature chain is input into the first prediction model to obtain the fault type with the highest probability of being associated with the actual feature chain. The weighted average of the associated probabilities of all fault types is taken, and the health degree is calculated based on the associated probability with the largest average value, and is output jointly with the corresponding fault type.

[0050] For example, there are three users using the system in sequence in the first time period. Three corresponding actual feature chains are generated according to the user IDs of the three users, and the actual feature chains are simplified. Then the actual feature chains are input into the first prediction model, and the following results are obtained: the probability of actual feature chain 1 being associated with fault type 1 is the largest, which is 16%, the probability of actual feature chain 2 being associated with fault type 2 is the largest, which is 30%, and the probability of actual feature chain 3 being associated with fault type 1 is the largest, which is 40%. Then, the fault types of the actual feature chains are weighted and averaged according to their time. The closer to the current time, the greater the weight. For example, the weights of the three actual feature chains are 0.3, 0.5, and 0.7, respectively. The average value of fault type 1 is (16%*0.3+40%*0.7) / 2=16.4%, and the average value of fault type 2 is 30%*0.5=15%. Then the health level is 1-16.4%=83.6%.

[0051] Regarding the health of mobile devices, the first prediction model will also output the probability of occurrence of the corresponding fault type based on the mobile characteristics of each user, screen the fault type with the highest probability of occurrence, and then perform weighted summation of the probability of occurrence of the same type of fault types according to the above method. The specific calculation process is the same as above and will not be repeated here.

[0052] In this embodiment, determining the high-frequency location includes the following steps: The preset area is divided into a fixed number of grid areas. The mobile devices are clustered in spatiotemporal density based on their locations and corresponding appearance times. The dense areas are screened out from the grid areas based on the clustering results, and the grid areas where the dense areas are located are regarded as high-frequency locations.

[0053] Specifically, the high-frequency locations are determined through the following steps: first, the preset area is divided into 50m×50m grid units, and ST-DBSCAN is used to perform spatiotemporal density clustering of the locations of mobile devices from the two dimensions of location and time of the mobile devices to determine the hotspot grid where the devices appear. For example, if after clustering, the location information of 100 mobile devices appears at a certain location within 30 minutes, the grid area where the location is located is regarded as a high-frequency location.

[0054] like Figure 4As shown, a shared equipment operation and maintenance management system based on big data is used to implement the above-mentioned shared equipment operation and maintenance management method based on big data, which is characterized by: The terminal module includes shared devices, which divide the shared devices into mobile devices and non-mobile devices. The shared devices collect their own device data and send them to the central server.

[0055] The front-end module is arranged in the central server. The front-end module establishes a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device respectively, distinguishes the device type of the shared device according to the device identifier in the received device data, and integrates the device data of the mobile device in the first time period into a first data set and the device data of the non-mobile device into a second data set.

[0056] A classification module is provided in the central server. The classification module analyzes the first data set based on the first prediction model and analyzes the second data set based on the second prediction model to determine the health of the shared devices, and divides the shared devices into healthy devices, critical devices and faulty devices based on the health.

[0057] The strategy module is set in the central server. The strategy module shortens the analysis interval of the critical equipment data and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty equipment.

[0058] The present application also provides a shared equipment operation and maintenance management device based on big data, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the above method is implemented when the processor executes the computer program.

[0059] It should be understood that the various technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0060] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A shared equipment operation and maintenance management method based on big data, characterized in that: Classifying shared devices into mobile devices and non-mobile devices, wherein the shared devices collect their own device data and send them to a central server; Establishing a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device respectively; The central server distinguishes the device type of the shared device according to the device identifier received in the device data, and integrates the device data of the mobile device in the first time period into a first data set and integrates the device data of the non-mobile device into a second data set; Analyze the first data set based on a first prediction model and analyze the second data set based on a second prediction model to determine the health of the shared device, and classify the shared device into healthy devices, critical devices, and faulty devices based on the health; The central server shortens the analysis interval of the device data of the critical device and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty device.

2. The method according to claim 1, characterized in that: The mobile device sending the device data comprises the following steps: A first transmission mode and a second transmission mode are set in the mobile device, the device data includes location information of the mobile device, and the mobile device sends the device information to the central server based on the first transmission mode in a default state; After collecting the device data within the second time period, the central server analyzes the location information included therein to determine high-frequency locations used by the mobile device, and deploys relay nodes at the high-frequency locations. The central server combines the location information and the deployment location of the relay nodes, and when it is determined that the mobile device has entered the coverage range of the relay node, commands the mobile device to use the second transmission method to send the device data to the relay node. The relay node adaptively compresses the device data and sends it to the central server.

3. The method according to claim 2, characterized in that Adaptively compressing the device data comprises the following steps: A micro-model is deployed in the relay node, where the micro-model is a simplified model of the first prediction model. The mobile device is divided into the healthy device and the faulty device based on the micro-model and the device data. The device data received from the healthy device in a third time period is aggregated and compressed into a whole block of data and then sent to the central server. The device data of the faulty device is inserted into a fault mark and then sent to the central server.

4. The method according to claim 1, characterized in that: Establishing the first prediction model comprises the following steps: The historical data includes the location of the mobile device, the corresponding occurrence time and the fault type. The movement characteristics of each user in the process of using the mobile device are calculated based on the historical data. The movement characteristics include average moving speed, maximum moving speed, minimum moving speed, number of brakes, and usage time. The first prediction model is established based on a fully connected neural network. The movement characteristics are used as input features of the first prediction model, and the fault type and occurrence probability are used as output features. The first prediction model is established in combination with the historical data training.

5. The method according to claim 4, characterized in that Establishing the second prediction model comprises the following steps: The historical data includes the usage characteristics of the non-mobile device and the fault type, a plurality of the usage characteristics that appear before each fault occurs are integrated into a fault conduction chain for the fault in the order of occurrence time, the fault type is marked in the fault conduction chain, and adjacent and identical usage characteristics in the fault conduction chain are merged to optimize the fault conduction chain into a streamlined conduction chain; Starting with the first usage feature in the streamlined conduction chain, each streamlined conduction chain is recursively split into multiple sub-conduction chains based on time sequence, and the association probability of various fault types caused by the appearance of the sub-conduction chain is statistically calculated based on the historical data, and the sub-conduction chain with the association probability greater than a first threshold is screened as the first sensitive conduction chain. After screening the first sensitive conduction chain, a second sensitive conduction chain is obtained, and the second sensitive conduction chain, the corresponding fault type and the association probability are used as a training set, and the second prediction model based on the time series neural network is established based on the training set.

6. The method according to claim 5, characterized in that Screening the first sensitive conductive chain includes the following steps: The first sensitive conduction chain derived from the same streamlined conduction chain is defined as a homologous conduction chain. The homologous conduction chains are sorted from large to small based on length characteristics, and the difference in the association probabilities of the homologous conduction chains at adjacent positions after sorting is calculated. If the difference is greater than a first threshold, the homologous conduction chain with a longer length is retained. If the difference is less than a second threshold, the homologous conduction chain with a shorter length is retained. The retained homologous conduction chain continues to be compared with the homologous conduction chain at a subsequent position. This step is repeated until all the first sensitive conduction chains are traversed and the retained one is defined as the second sensitive conduction chain.

7. The method according to claim 6, characterized in that Calculating the health of the non-mobile device comprises the following steps: The device data of each user ID in the first data set is integrated into an actual feature chain, each actual feature chain is input into the first prediction model, the fault type with the highest probability of association with the actual feature chain is obtained, the association probabilities of all the fault types are weighted and averaged, the health degree is calculated based on the association probability with the largest average value, and the health degree is output jointly with the corresponding fault type.

8. The method according to claim 2, characterized in that: Determining the high frequency location comprises the following steps: The preset area is divided into a fixed number of grid areas, and the mobile devices are clustered in time and space density based on the locations of the mobile devices and the corresponding appearance times. Based on the clustering results, dense areas are screened out from the grid areas, and the grid areas where the dense areas are located are used as the high-frequency locations.

9. A shared equipment operation and maintenance management system based on big data, used to implement a shared equipment operation and maintenance management method based on big data as described in any one of claims 1 to 8, characterized in that: The terminal module includes a shared device, which divides the shared device into a mobile device and a non-mobile device, and the shared device collects its own device data and sends it to the central server; A front-end module is provided in the central server, wherein the front-end module establishes a first prediction model and a second prediction model based on the historical data of the mobile device and the non-mobile device, respectively, distinguishes the device type of the shared device according to the device identifier received in the device data, and integrates the device data of the mobile device within a first time period into a first data set and integrates the device data of the non-mobile device into a second data set; a classification module, arranged in the central server, wherein the classification module analyzes the first data set based on a first prediction model and analyzes the second data set based on a second prediction model to determine the health of the shared device, and classifies the shared device into healthy devices, critical devices, and faulty devices based on the health; A strategy module is provided in the central server, wherein the strategy module shortens the analysis interval of the device data of the critical device and generates a personnel inspection path based on the ant colony algorithm and the location information of the faulty device.

10. A shared equipment operation and maintenance management device based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images