Multi-dimensional data-based shared bicycle fault vehicle marking method and system

Abstract

The invention provides a shared bicycle fault vehicle marking method and system based on multi-dimensional data, and relates to the technical field of data processing, a server decomposes the multi-dimensional data of a bicycle end, an equipment end and a server end corresponding to a target bicycle to obtain decomposition information, and classifies the decomposition information to obtain first classification information and second classification information; the management end generates a judgment specification tree of classification information based on the standard specification tree and image interaction; if the independent first classification information or the combined second classification information reaches a judgment condition of the judgment specification tree, adding a fault tag to the corresponding bicycle end and extracting a first moment; the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state is acquired, and the fault label and / or the standard specification tree are / is updated, so that the fault bicycle can be timely and accurately identified and marked.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for marking faulty shared bicycles based on multi-dimensional data. Background Art

[0002] With the widespread use of shared bicycles in urban transportation systems, their frequency of use and coverage continue to expand. Whether in commuting sections during rush hours in the morning and evening, or in densely populated areas such as scenic spots and business districts, shared bicycles have become an important means of transportation for citizens to travel short distances. However, long-term and high-frequency use has caused shared bicycles to face various faults, such as lock failure, brake failure, chain jamming, etc. These faults not only affect the user's riding experience, but may also bring safety hazards and even lead to idle waste of bicycle resources.

[0003] At present, the existing shared bicycle fault detection methods have many limitations. Some methods only rely on users to actively report fault information. This method is greatly affected by the user's subjective will and cognitive level, and there are problems such as missed reports and false reports, and it is impossible to detect potential fault hazards in time. In addition, traditional fault judgment rules often adopt fixed standards and cannot adapt to the differences in different vehicle models, usage environments and operating areas, resulting in insufficient accuracy and adaptability of fault judgment. For example, different cities and seasons have different tolerances for bicycle faults. A unified fault judgment standard may lead to excessive maintenance of vehicles in some areas or failure to deal with faulty vehicles in a timely manner.

[0004] Therefore, how to timely and accurately identify faulty vehicles and mark them has become an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for marking faulty shared bicycles based on multi-dimensional data, which can timely and accurately identify faulty vehicles and perform marking processing.

[0006] A first aspect of an embodiment of the present invention provides a method for marking a faulty shared bicycle based on multidimensional data, comprising: The server decomposes the multi-dimensional data of the bicycle end, the device end and the server end corresponding to the target bicycle to obtain decomposition information, and classifies the decomposition information to obtain first classification information and second classification information; The management end generates a judgment specification tree for classification information based on the standard specification tree and image interaction; If the independent first classification information or the combined second classification information meets the judgment condition of the judgment specification tree, a fault label is added to the corresponding single vehicle end and the first moment is extracted; Acquire multi-dimensional data of the target bicycle from a first moment to a second moment in a normal state, and update the fault label and / or standard specification tree.

[0007] Optionally, in a possible implementation manner of the first aspect, the server decomposes multi-dimensional data of a bicycle end, a device end, and a server end corresponding to the target bicycle to obtain decomposition information, including: Extracting all data of the target bicycle within a first preset time period; All data is decomposed to obtain the automatic fault reporting information of the bicycle side, the active fault reporting information of the equipment side, and the analysis and reporting information of the server side; Automatic fault reporting information, proactive fault reporting information, and analyzed fault reporting information are classified according to dimensions to obtain decomposed information.

[0008] Optionally, in a possible implementation manner of the first aspect, the automatic fault reporting information is generated by the following steps, including: If it is determined that the target bicycle has not been turned on after scanning a preset number of times within the second preset time, an automatic fault reporting message is generated.

[0009] Optionally, in a possible implementation of the first aspect, the analysis and fault reporting information is generated by the following steps, including: If it is determined that the number of times that the riding distance within the second preset time is less than the first preset distance is greater than the first preset number, generating analysis and fault reporting information; If it is determined that the number of times that the riding time within the third preset time is less than the fourth preset time is greater than the second preset number, analysis and fault reporting information is generated.

[0010] Optionally, in a possible implementation manner of the first aspect, the management end generates a judgment specification tree of classification information based on the standard specification tree and the image interaction, including: The standard specification tree includes a first node of a first level, a first child node and a second child node of a second level, and a plurality of grandchild nodes of a third level, wherein the first child node and the second child node correspond to a first threshold value and a second threshold value respectively, and each grandchild node corresponds to at least one module of a shared bicycle; The standard specification tree is adjusted based on the properties of the target bicycle to obtain a target specification tree, and slots are extracted and created on the target specification tree to obtain an interactive image; The management end adjusts the slots based on the interactive images to generate a judgment specification tree for classification information; The first sub-node corresponds to first classification information, and the second sub-node corresponds to second classification information.

[0011] Optionally, in a possible implementation manner of the first aspect, adjusting the standard specification tree based on the attributes of the target bicycle to obtain the target specification tree, and extracting and creating slots on the target specification tree to obtain the interactive image includes: Eliminate the modules that do not correspond to the target attributes in the standard specification tree. Each bicycle of each target attribute has a preset module; Extract the slot positions corresponding to the first child node, the second child node, and the grandchild node, which are in a selectable state, and establish corresponding configuration slots at the slot positions corresponding to the first child node, the second child node, and the grandchild node; Statistically analyze the area formed by the grandchild nodes connected to the first child node to obtain a first interaction slot, and statistically analyze the area formed by the grandchild nodes connected to the second child node to obtain a second interaction slot, and then obtain an interaction image.

[0012] Optionally, in a possible implementation manner of the first aspect, the management end generates a judgment specification tree for classification information based on the interaction image, including: If it is determined that the user selects a grandchild node and moves it to the first interaction slot or the second interaction slot, then connect the corresponding grandchild node to the new first interaction slot or the second interaction slot; Configure a new failure base value for the moved grandchild node; If it is determined that the user adjusts the failure base value and / or the failure weight value of the newly created slot, then adjust the corresponding slot to obtain a judgment specification tree.

[0013] Optionally, in a possible implementation manner of the first aspect, if the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree, then add a failure label to the corresponding bicycle end and extract the first moment, including: If the grandchild node connected to the first child node triggers a failure message, and the failure base value of the corresponding grandchild node is greater than the first threshold of the first child node, then a failure label is added when the judgment condition is met; If the grandchild node connected to the second child node triggers a failure message, then extract the failure base value and the failure weight value of the grandchild node in the judgment specification tree and calculate the failure combination value comprehensively. If the failure combination value is greater than the second threshold, then a failure label is added when the judgment condition is met.

[0014] Optionally, in a possible implementation manner of the first aspect, the acquisition of multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state, and the update of the failure label and / or the standard specification tree, including: The multi-dimensional data at least includes maintenance information, and determine the grandchild nodes corresponding to the maintenance information to obtain a first set; Select and extract the grandchild nodes that trigger failure messages in the judgment specification tree to obtain an updated tree, and statistically analyze the grandchild nodes in the updated tree to obtain a second set; Update the failure label and / or the standard specification tree based on the first set and the second set.

[0015] Optionally, in a possible implementation manner of the first aspect, the update of the failure label and / or the standard specification tree based on the first set and the second set includes: If the first set is empty, update the fault label and / or the standard specification tree based on the second set; If the first set is not empty, determine the intersection point between the first set and the second set. There is a first difference point in the first set that does not exist in the second set, and there is a second difference point in the second set that does not exist in the first set; Update the fault label and / or the standard specification tree based on the intersection point, the first difference point, and the second difference point; The update of the fault label and / or the standard specification tree based on the second set includes: Extract the fault base value of the grandchild nodes within the second set, subtract a preset value from the fault base value to obtain an updated fault base value, and add a reported fault label.

[0016] Optionally, in a possible implementation manner of the first aspect, the update of the fault label and / or the standard specification tree based on the intersection point, the first difference point, and the second difference point includes: Calculate the sum of the quantities of the intersection point, the first difference point, and the second difference point, calculate the ratio of the first difference point to the sum of the quantities to obtain a first ratio, and calculate the ratio of the second difference point to the sum of the quantities to obtain a second ratio; Extract the fault weight value of the intersection point, multiply the first preset value by the sum of the quantities to obtain a positive adjustment coefficient, multiply the first adjustment value by the positive adjustment coefficient to obtain a first positive adjustment value, and add the fault weight value to the first positive adjustment value to obtain an updated fault weight value; Extract the fault weight value of the first difference point, multiply the second adjustment value by the first ratio to obtain a second positive adjustment value, and add the fault weight value to the second positive adjustment value to obtain an updated fault weight value; Extract the fault weight value of the second difference point, multiply the third adjustment value by the second ratio to obtain a third negative adjustment value, and subtract the third negative adjustment value from the fault weight value to obtain an updated fault weight value.

[0017] In the second aspect of the embodiments of the present invention, a shared bicycle fault vehicle marking system based on multi-dimensional data is provided, including: A decomposition module, configured to enable the server to decompose the multi-dimensional data of the target bicycle corresponding to the bicycle end, the device end, and the service end to obtain decomposition information, and classify the decomposition information to obtain first classification information and second classification information; A classification module, configured to enable the management end to generate a judgment specification tree for the classification information based on the standard specification tree and image interaction; A judgment module, configured to add a fault label to the corresponding bicycle end and extract the first moment if the independent first classification information or the combined second classification information reaches the judgment condition of the judgment specification tree; An update module, configured to obtain multi-dimensional data of a target bicycle from a first moment to a second moment in a normal state, and update a fault label and / or a standard specification tree.

[0018] In a second aspect of the present invention, a storage medium is provided. A computer program is stored in the storage medium, and when the computer program is executed by a processor, it is used to implement the method of the first aspect of the present invention and various possible designs of the first aspect.

[0019] The beneficial effects of the present invention are as follows: 1. The present invention can fuse multi-dimensional data, improve the comprehensiveness of fault detection, so as to identify faulty vehicles in a timely and accurate manner and perform marking processing. By integrating multi-dimensional data from the bicycle end, the device end, and the service end, the present invention significantly improves the accuracy and comprehensiveness of fault detection. The server first extracts all the data of the target bicycle within a preset time period and decomposes it into automatic fault reporting information, active fault reporting information, and analysis fault reporting information. These data from different sources complement each other, avoiding judgment deviations caused by single data. At the same time, the fault reporting information is classified by dimension to form first classification information and second classification information, providing comprehensive data support for accurately judging the type and degree of faults subsequently, and effectively solving the problems of incomplete data and high missed detection rate in traditional methods.

[0020] 2. The present invention can improve the flexibility and judgment accuracy of fault identification through the judgment and adjustment of the specification tree. Among them, the present invention can generate a judgment specification tree based on the standard specification tree and image interaction, enabling the fault judgment rules to flexibly adapt to the characteristics and operation requirements of different bicycles. The management end removes the modules in the standard specification tree that do not correspond to the attributes of the target bicycle, extracts and creates slots to form a visual interactive image, and on this basis, adjusts the slots to generate a personalized judgment specification tree. And according to different regions, vehicle models or usage scenarios, the management personnel can adjust the fault base values and weight values of each module, such as increasing the fault judgment sensitivity for new vehicles and appropriately relaxing the standards for old vehicles; in addition, users can also optimize the fault judgment rules in real time by operating on the sub-nodes, adjusting slot parameters, etc. The dynamic rule generation mechanism breaks the limitations of traditional fixed standards, significantly improves the adaptability and accuracy of fault judgment, and ensures that faulty vehicles under different conditions can be marked in a timely and accurate manner.

[0021] 3. The present invention can provide information feedback on fault repairs, optimize fault management, and improve the accuracy of fault marking. Specifically, the present invention can extract multi-dimensional data between fault marking and normal operation, compare the actual repair information with the fault judgment result, form a first set and a second set, and through analyzing the intersection points and difference set points, specifically update the fault label and the standard specification tree. For the modules that are actually repaired but not recognized, i.e., the first difference set points, increase their fault weight values; for the misjudged modules, i.e., the descendant nodes in the second difference set points, reduce the weight values. This optimization mechanism based on actual data feedback not only corrects the deviation of fault judgment, but also continuously improves the fault judgment rules, reduces misjudgment and missed judgment situations. With the accumulation of data and the iteration of rules, the marking of faulty vehicles by the system will be more accurate, effectively improving the overall operation quality and service level of shared bicycles. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flowchart of a method for marking faulty shared bicycles based on multi-dimensional data provided by the present invention; Figure 2 is a schematic diagram of an interactive image provided by the present invention; Figure 3 is a schematic structural diagram of a system for marking faulty shared bicycles based on multi-dimensional data provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The technical solutions of the present invention will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0024] As Figure 1 shown, the present invention provides a method for marking faulty shared bicycles based on multi-dimensional data, including: S1. The server decomposes the multi-dimensional data of the bicycle terminal, device terminal, and service terminal corresponding to the target bicycle to obtain decomposition information, and classifies the decomposition information to obtain first classification information and second classification information.

[0025] It should be noted that due to the long-term use of bicycles, some faults may occur in shared bicycles, which will have a certain impact on users' use. Therefore, data can be collected through various devices, and the collected multi-dimensional data can be analyzed to determine the fault situation of the bicycles, so as to mark the shared bicycles with faults, so that the subsequent suppliers can repair the faulty bicycles in time.

[0026] It can be understood that the target bicycle is the bicycle used by the current user to unlock. The bicycle terminal is the information terminal on the bicycle, which can be a device module for receiving and sending data information. The device terminal is the information terminal corresponding to the user, such as a mobile phone. The server terminal is the server, that is, the service device corresponding to the back end of the bicycle, which is used to analyze and process relevant data information so as to mark the faulty bicycles subsequently.

[0027] Among them, the multi-dimensional data is the combined data from different device sources collected by the server terminal. The decomposed information is multiple single information obtained by the server splitting the multi-dimensional data. The first classified information is the first type of information after classifying the decomposed information, and the second classified information is the second type of information after classifying the decomposed information.

[0028] It is not difficult to understand that the server undertakes the task of processing the multi-dimensional data related to the target bicycle. A large amount of data related to the running state and usage of the bicycle will be generated by the bicycle terminal, the device terminal and the server terminal. These data are extensive in source and diverse in form, belonging to multi-dimensional data. The server first performs a decomposition operation on these multi-dimensional data. This process is like splitting a complex jigsaw puzzle into small pieces, aiming to transform the original and complex data into decomposed information that is easier to analyze and process. Then, the server will classify the decomposed information to obtain the first classified information and the second classified information. The purpose of classification is to make the data more organized and facilitate subsequent judgment and analysis. The first classified information and the second classified information can be regarded as two different "data baskets". The server puts the decomposed information into these two "baskets" according to certain rules, which can be classified according to factors such as the nature of the data, the source, or the degree of influence on fault judgment. In this way, the preliminary processing of the multi-dimensional data is completed, providing a clear data basis for subsequent fault judgment.

[0029] In some embodiments, the specific implementation manner of step S1 (wherein the server decomposes the multi-dimensional data of the bicycle terminal, the device terminal and the server terminal corresponding to the target bicycle to obtain decomposed information) includes: S11, extract all the data of the target bicycle within the first preset time period.

[0030] It can be understood that by extracting all the data corresponding to the devices of the target bicycle within the first preset time period, it is convenient to conduct a comprehensive analysis based on the extracted data subsequently, and improve the accuracy of judging whether the target bicycle has faults.

[0031] Among them, the first preset time period is a preset time period, such as all the data information related to the target bicycle of all devices within the past week.

[0032] S12. Decompose all data to obtain the automatic fault reporting information of the bicycle end, the proactive fault reporting information of the device end, and the analysis fault reporting information of the server end.

[0033] It can be understood that when the bicycle cannot connect to the network, still cannot be normally unlocked after multiple attempts, or there are abnormal jams, abnormal noises, etc. during the riding process, the bicycle end will automatically record and generate automatic fault reporting information. When the user cannot use the bicycle or view the abnormal faults of the bicycle, the corresponding faults can be reported and fed back through the device end. Finally, the server end can automatically analyze the collected data to obtain the analysis fault reporting information.

[0034] Among them, the automatic fault reporting information is the fault alarm information automatically generated by the bicycle end, the proactive fault reporting information is the fault information actively declared by the user through the device end, and the analysis guarantee information is the fault alarm information generated by the server end through analyzing and processing the data. That is, when the server finds that some indicators of the bicycle deviate from the normal range, or there are some potential problem trends, it will generate the analysis fault reporting information.

[0035] Through the above decomposition method, the fault reporting information from different sources and types is clearly separated, facilitating subsequent classification and analysis.

[0036] The automatic fault reporting information is generated through the following steps, including: A1. If it is determined that the target bicycle has not been unlocked after scanning a preset number of times within the second preset time, generate the automatic fault reporting information.

[0037] It can be understood that in the usage scenario of shared bicycles, users usually unlock the bicycles by scanning QR codes, etc. In order to timely detect possible faults of the bicycles, the server sets certain rules to determine whether to generate the automatic fault reporting information.

[0038] Among them, the second preset time is a preset time range, for example, it may be 5 minutes, and the preset number of times is also preset in advance, such as 3 times. When the user scans the target bicycle a preset number of times within the second preset time, but the bicycle still cannot be normally unlocked, this is likely to mean that there is a fault with the bicycle, such as a fault in the unlocking system, damage to the electronic lock, etc.

[0039] It is not difficult to understand that the server corresponding to the bicycle end will monitor and count the time and number of scanning operations in real time. Once the condition of "not being unlocked after scanning a preset number of times within the second preset time" is met, the bicycle end will immediately generate the automatic fault reporting information. The automatic fault reporting information will include relevant identifiers of the bicycle, such as the vehicle number, etc., and may also record specific information such as the scanning time and number of times. This information will be sent to the server end so that the staff can timely understand the fault situation of the bicycle and arrange corresponding maintenance and handling work.

[0040] In this way, it is possible to quickly locate and handle shared bicycles that cannot be normally unlocked, improving the user experience and the operational efficiency of the bicycles.

[0041] The analysis and fault reporting information is generated through the following steps, including: B1, if it is determined that the number of times the riding distance within the second preset time is less than the first preset distance is greater than the first preset number of times, then the analysis and fault reporting information is generated.

[0042] It can be understood that in the operation and management of shared bicycles, the riding distance is an important indicator reflecting the usage status of the bicycle and possible faults. The second preset time is a pre-specified time period, which can be set to one week for example. The first preset distance is a pre-specified riding distance value, such as 2 kilometers. The first preset number of times is a pre-set number of times, such as 5 times.

[0043] Among them, the riding distance is the moving distance during the use of the target bicycle. The server continuously monitors the riding distance of the target bicycle within the second preset time. When it is found that within this time period, the number of times the riding distance of the target bicycle is less than the first preset distance exceeds the first preset number of times, this indicates that the usage situation of the bicycle has become abnormal. Normally, when a shared bicycle is used reasonably, a certain proportion of the riding distance should reach or exceed the first preset distance. Repeatedly short riding distances may imply faults such as insufficient power or too tight brakes, affecting the normal riding of users and resulting in limited riding distance. Once the condition "the number of times the riding distance within the second preset time is less than the first preset distance is greater than the first preset number of times" is met, the server will generate the analysis and fault reporting information.

[0044] It is not difficult to understand that the analysis and fault reporting information will detail relevant information of the bicycle, abnormal riding distance data, and the time period when the abnormality occurred, providing a basis for subsequent fault troubleshooting and repair.

[0045] B2, if it is determined that the number of times the riding time within the third preset time is less than the fourth preset time is greater than the second preset number of times, then the analysis and fault reporting information is generated.

[0046] It can be understood that the riding time is also an important dimension for judging whether there are faults in shared bicycles. The third preset time and the fourth preset time are two different time periods set respectively. For example, the third preset time can be one month, the fourth preset time is set to 30 minutes, and the second preset number of times is assumed to be 8 times.

[0047] Among them, the riding time is the single use duration of the target bicycle used by the user. The server will count and analyze the riding time of each use of the target bicycle within the third preset time. If it is found that the number of times the riding time of the target bicycle is less than the fourth preset time within this time period is greater than the second preset number, it indicates that the riding time of this bicycle is generally short and does not conform to the normal use situation. The short riding time may be due to faults of the bicycle itself, such as vehicle jamming, component damage, etc., resulting in the user being unable to complete a long ride smoothly. When the condition of "the number of times the riding time is less than the fourth preset time within the third preset time is greater than the second preset number" is met, the server will generate an analysis and troubleshooting information.

[0048] It is not difficult to understand that this information will include the specific identification of the bicycle, abnormal riding time data, and relevant time statistical information, etc., which helps the staff quickly locate the bicycles that may have faults and take corresponding maintenance measures to ensure the normal operation of the shared bicycles and the good use experience of users.

[0049] S13, classify the automatic troubleshooting information, active troubleshooting information, and analysis troubleshooting information according to dimensions to obtain decomposed information.

[0050] It can be understood that after obtaining the automatic troubleshooting information, active troubleshooting information, and analysis troubleshooting information, these troubleshooting information can be classified according to different dimensions to obtain decomposed information. The dimensions can be various different classification criteria, such as the nature of the data, the importance degree of fault judgment, etc.

[0051] For example: from the dimension of the nature of the data, the troubleshooting information related to vehicle hardware faults can be classified into one category, such as problems with components like tires and brakes, and the troubleshooting information related to the vehicle software system can be classified into another category, such as unlocking system faults and inaccurate positioning. From the dimension of the importance degree of fault judgment, the serious fault troubleshooting information that directly causes the bicycle to be unable to be used normally can be classified into one category, and the minor fault troubleshooting information that may affect the riding experience but does not affect the basic use can be classified into another category.

[0052] By classifying according to dimensions, the server can further refine and organize the troubleshooting information, making the decomposed information more organized and providing clearer data support for accurately judging bicycle faults in the future.

[0053] S2, the management end generates a judgment specification tree for classification information based on the standard specification tree and image interaction.

[0054] It can be understood that the standard specification tree is a pre-set tree structure that contains information about various modules, components of the shared bicycle, as well as thresholds related to fault judgment, etc. It is the basic framework for the entire judgment. Image interaction provides an intuitive and flexible way for the management end to adjust and generate the judgment specification tree.

[0055] Among them, the management end is the terminal of the information processing personnel who manage the fault judgment of the bicycle. Based on the standard specification tree and combined with the operations of image interaction, the management end will adjust and optimize the standard specification tree. Image interaction can be through a visual interface, enabling the management personnel to intuitively see the structure of the specification tree and modify it according to the actual situation.

[0056] For example, the management personnel can directly operate on the interface to add, delete, or modify information such as nodes and thresholds in the specification tree. Finally, the judgment specification tree generated in this way is like a "fault judgment map", which clarifies under what circumstances each classified information can determine that the bicycle has a fault, providing detailed rules and bases for subsequent fault judgment.

[0057] In some embodiments, the specific implementation manner in step S2 (where the management end generates a judgment specification tree for classified information based on the standard specification tree and image interaction) includes: S21, the standard specification tree includes a first node at the first level, a first sub-node and a second sub-node at the second level, and multiple grandchild nodes at the third level. The first sub-node and the second sub-node respectively correspond to a first threshold and a second threshold, and each grandchild node corresponds to at least one module of the shared bicycle.

[0058] It can be understood that the standard specification tree is the basic framework for the management end to generate the judgment specification tree. It has a clear hierarchical structure. The first node at the first level is the root node of the entire specification tree. For example, it can be the target bicycle. The second level includes a first sub-node and a second sub-node connected to the first node at the first level. These two sub-nodes respectively correspond to different judgment criteria, that is, the first threshold and the second threshold. These thresholds are important reference values for judging whether the bicycle has a fault. The first threshold is the first value pre-set for judging whether the target bicycle has a fault, which can be 0. The second threshold is the second value pre-set for judging whether the target bicycle has a fault, which can be 1.

[0059] Among them, the multiple grandchild nodes at the third level are associated with the specific modules of the shared bicycle. Each grandchild node corresponds to at least one module. For example, there may be a grandchild node corresponding to the brake module and another corresponding to the lock Bluetooth module, etc. This hierarchical structure enables the standard specification tree to comprehensively and meticulously cover all aspects of the shared bicycle, providing a clear framework for subsequent fault judgment.

[0060] It is not difficult to understand that when the third level is connected to the child nodes of the second level, it is determined according to the degree of damage of the module. For example, when there is a hard device damage to the bicycle, such as a broken chain or no signal for the unlocking Bluetooth, the target bicycle cannot be used, so it can be connected to the first child node. When the basket is skewed or the bell is stuck, that is, the corresponding module does not affect the user's use of the bicycle, the corresponding module's grandchild nodes can be connected to the corresponding second child nodes, so that the fault situation of the target bicycle can be quickly determined according to the modules connected to the corresponding thresholds of the child nodes in the future.

[0061] By corresponding different thresholds and modules to the corresponding nodes, it is possible to accurately analyze and make decisions according to different situations in the subsequent judgment process.

[0062] The first child node corresponds to the first classification information.

[0063] It can be understood that the first classification information is the data information that the direct damage of the modules in the bicycles corresponding to the first child node causes the target bicycle to be unable to ride.

[0064] The second child node corresponds to the second classification information.

[0065] It can be understood that the second classification information is the data information that the damaged modules connected to the second child node do not affect the bicycle riding.

[0066] S22, adjust the standard specification tree based on the attributes of the target bicycle to obtain the target specification tree, and perform slot extraction and slot creation on the target specification tree to obtain the interactive image.

[0067] It can be understood that after obtaining the standard specification tree, since shared bicycles from different manufacturers may have different attributes, such as models, configurations, etc. For example, some bicycles do not have a basket, while some bicycles have a basket. When there is no basket, the corresponding node can be deleted, so that the corresponding and more intuitive interactive image of the target bicycle can be obtained in the future. Therefore, it is necessary to adjust the standard specification tree to adapt to the specific bicycle situation, that is, modify or screen the nodes and associated information in the standard specification tree according to the attributes of the target bicycle, so as to obtain the target specification tree.

[0068] For example, if there is no basket, the corresponding node can be deleted, and then slot extraction and slot creation operations are performed on the target specification tree to obtain the interactive image. Slot extraction is to determine the positions with specific meanings and functions from the target specification tree, and these positions can be used to place information related to fault judgment. Slot creation is to create new slots in the target specification tree according to actual needs to meet different judgment requirements. Through these two operations, the target specification tree is transformed into a visual interactive image, which is convenient for the management-side operators to perform intuitive operations and adjustments.

[0069] Among them, the target specification tree is a specification structure tree adapted to the target bicycle, and the interaction image is a display image that constructs new slots for the target specification tree for information interaction.

[0070] It is not difficult to understand that each node has corresponding information, and this information has slots for display. Therefore, the slots can be extracted, and new slots can be constructed next to each node to facilitate subsequent filling of the corresponding decomposed information data, which is convenient for determining the fault condition of the target bicycle.

[0071] In some embodiments, the specific implementation manner in step S22 (adjusting the standard specification tree based on the attributes of the target bicycle to obtain the target specification tree, and performing slot extraction and new slot creation on the target specification tree to obtain the interaction image) includes: S221, removing the modules in the standard specification tree that do not correspond to the target attributes. Each type of target attribute bicycle has a preset module.

[0072] It can be understood that bicycles with different attributes have different configured modules. For example, high-end models may be equipped with intelligent anti-theft modules, electronic assistance modules, etc., while basic models may not have these modules. The standard specification tree is a general framework that includes various possible bicycle modules. In order to make the specification tree more in line with the actual situation of the target bicycle, targeted adjustments are required.

[0073] Among them, the target attribute is the module function attribute of the target bicycle. The server will clarify the preset modules of the bicycles with this attribute according to the attributes of the target bicycle. Then, the modules in the standard specification tree that do not correspond to the target bicycle attributes are removed, so that the adjusted target specification tree only contains the modules that the target bicycle actually has, avoiding the interference of irrelevant information and making the subsequent fault judgment more accurate and efficient.

[0074] S222, extracting the slot positions corresponding to the first sub-node, the second sub-node, and the grandchild node and setting them to be in a selectable state, and establishing corresponding configuration slots at the slot positions corresponding to the first sub-node, the second sub-node, and the grandchild node.

[0075] It can be understood that after obtaining the target specification tree, in order to facilitate subsequent interaction operations, it is necessary to process the slots corresponding to relevant nodes. As Figure 2 shown, that is, the corresponding nodes can be selected to construct new configuration slots for them, so that subsequent corresponding values or fault judgment data, etc. can be configured for each node in the configuration slots, so as to more flexibly adjust and manage the judgment conditions of each node and improve the accuracy and flexibility of fault judgment.

[0076] Among them, the selectable state is to set the slot corresponding to the triggered node to the selected state, so as to construct a new configuration slot beside the node in the selectable state. The configuration slot can be used to store detailed configuration information related to the node, such as fault thresholds, fault weights, etc.

[0077] S223, obtain the first interaction slot by statistically analyzing the area formed by the grandchild nodes connected to the first child node, and obtain the second interaction slot by statistically analyzing the area formed by the grandchild nodes connected to the second child node, and then obtain the interaction image.

[0078] It can be understood that, as Figure 2 shown, the first child node and the second child node are respectively connected to multiple grandchild nodes, and these grandchild nodes correspond to different modules of the shared bicycle. In order to more intuitively display and manage the relationship between these nodes, the server will perform area statistics.

[0079] Among them, the server will statistically analyze the area formed by the grandchild nodes connected to the first child node, and define this area as the first interaction slot. Similarly, statistically analyze the area formed by the grandchild nodes connected to the second child node to obtain the second interaction slot. These two interaction slots integrate nodes at different levels according to their association relationships, forming two areas with specific meanings.

[0080] Through such statistics and division, the target specification tree is transformed into an image with clear interaction areas, that is, the interaction image. In this interaction image, managers can intuitively see the relationship between nodes at different levels, as well as the interaction areas corresponding to each module, so as to more conveniently adjust the slots and set the fault judgment rules.

[0081] S23, the management end generates a judgment specification tree for the classification information based on the interaction image.

[0082] It can be understood that the management end operator performs slot adjustment based on the obtained interaction image. In the interaction image, the operator can intuitively see each slot and the relationship between them. The operator can modify, move, or delete the information in the slot according to the actual situation.

[0083] For example, if it is found that the weight of the grandchild node corresponding to a certain module is unreasonable during the judgment process, the relevant parameters of the slot where the node is located can be adjusted to change its judgment influence.

[0084] By continuously adjusting the slots, a judgment specification tree for classification information is finally generated. The judgment specification tree is customized according to the specific attributes of the target bicycle and the actual management requirements, and can more accurately judge the first classification information and the second classification information, so as to determine whether the bicycle has a fault. It combines the basic framework of the standard specification tree and the personalized characteristics of the target bicycle, which is convenient for improving the accuracy of fault marking of shared bicycles in the future.

[0085] In some embodiments, the specific implementation manner in step S23 (wherein the management end generates a judgment specification tree for classification information based on the interactive image) includes: S231, if it is determined that the user selects a grandchild node and moves it to the first interactive slot or the second interactive slot, then connect the corresponding grandchild node to the new first interactive slot or the second interactive slot.

[0086] It can be understood that when the user selects a grandchild node (representing a specific module of the shared bicycle) and moves it to the first interactive slot or the second interactive slot, the server will respond to this operation. The grandchild node originally has a fixed connection relationship in the target specification tree, and when it is moved to a new interactive slot, the server will re - establish the connection between the grandchild node and the new first interactive slot or the second interactive slot, changing the position and association relationship of the module in the fault judgment system.

[0087] For example, originally a grandchild node corresponds to a module related to the bicycle bell, and it is in a specific position in the standard specification tree, such as in the second interactive slot. When the user moves it to the first interactive slot, it means that in the new fault judgment rule, the bell module has a closer connection with the judgment criterion represented by the first child node, so that when judging faults, it will be analyzed and evaluated according to the new connection relationship.

[0088] S232, configure a new fault base value for the moved grandchild node.

[0089] It can be understood that the fault judgment weights of different grandchild nodes in the first interactive slot and the second interactive slot are different. When the position of the grandchild node is moved, the corresponding fault base value will be adjusted so that the adjusted fault judgment rule better meets the user's needs. That is, when the bicycle bell shows an abnormality, the fault coefficient can be increased, so that when the bell is abnormal, the target bicycle is marked as a faulty bicycle and thus not used.

[0090] Among them, the fault base value is the value for judging faults when it is determined that a bicycle module is damaged, and it is preset.

[0091] In some other embodiments, the specific implementation of the step (the management terminal generates a judgment specification tree for slot adjustment based on the interaction image) further includes: If it is determined that the user adjusts the fault base value and / or the fault weight value of the newly created slot, then the corresponding slot is adjusted to obtain a judgment specification tree.

[0092] It can be understood that since the fault base values set in different regions are different, the corresponding values will also be different. For example, the bicycles in area A are newly configured bicycles, so the fault base value and / or the fault weight value can be increased. When any damage occurs to the target bicycle, it can be determined as a fault, so that it can be repaired in time to maintain the functional integrity of the bicycle. When the bicycles in area B are old bicycles, the corresponding fault base value and / or the fault weight value can be set to a smaller value, that is, when a minor fault occurs, they can continue to be used.

[0093] It is not difficult to understand that when the user's numerical adjustment of the fault base value and / or the fault weight value is received, the corresponding slot is adjusted to obtain a judgment specification tree.

[0094] S3. If the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree, then a fault label is added to the corresponding bicycle terminal and the first moment is extracted.

[0095] It can be understood that according to the generated judgment specification tree, the classification information of the shared bicycle is judged to determine whether to add a fault label to the bicycle. In the above implementation steps, the server decomposes and classifies the multi-dimensional data to obtain the first classification information and the second classification information, and the management terminal also generates a judgment specification tree. Furthermore, when the independent first classification information or the combined second classification information meets the judgment conditions set in the judgment specification tree, it means that the bicycle may have a fault. At this time, a fault label needs to be added to the corresponding bicycle terminal for subsequent management and maintenance. At the same time, the first moment is extracted. This moment records the time point when the bicycle is determined to be faulty, so as to improve the accuracy of subsequent analysis of the fault occurrence law.

[0096] Among them, the fault label is an information label marking the bicycle as faulty, and the first moment is the time point when the bicycle is determined to be faulty.

[0097] In some embodiments, the specific implementation of step S3 (if the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree, then a fault label is added to the corresponding bicycle terminal and the first moment is extracted) includes: S31. If the grandson node connected to the first child node triggers fault information and the fault base value of the corresponding grandson node is greater than the first threshold of the first child node, then the judgment condition is met and a fault label is added.

[0098] It is understandable that in the judgment specification tree, the first child node is connected to multiple grandchild nodes, and each grandchild node corresponds to one or more modules of the shared bicycle. When a fault message is triggered by the grandchild nodes connected to the first child node, it indicates that the module corresponding to the grandchild node may have a fault. At the same time, it is also necessary to meet the condition that the fault base value of the corresponding grandchild node is greater than the first threshold of the first child node. When both of these conditions are met, the judgment condition is reached, and at this time, a fault label will be added to the corresponding bicycle end to identify that the bicycle has a fault.

[0099] Among them, the fault message is the damage information of the module when a fault occurs. The fault base value is set when configuring the grandchild node before, and it reflects the basic influence degree of the module fault on the overall fault judgment. The first threshold is a preset standard value used to measure whether the severity of the grandchild node fault reaches the standard for adding a fault label.

[0100] S32. If a fault message is triggered by the grandchild nodes connected to the second child node, then extract the fault base value and fault weight value of the grandchild node in the judgment specification tree and calculate the combined fault value. If the combined fault value is greater than the second threshold, the judgment condition is reached and a fault label is added.

[0101] It is understandable that for the grandchild nodes connected to the second child node, the judgment method is different. When a fault message is triggered by the grandchild nodes connected to the second child node, it indicates that there is a problem with the module corresponding to the grandchild node. At this time, it is necessary to extract the fault base value and fault weight value of the grandchild node in the judgment specification tree.

[0102] Among them, the fault weight value reflects the importance degree of the grandchild node in the overall fault judgment. It is comprehensively calculated in combination with the fault base value. For example, multiply the fault base value and the fault weight value to obtain the combined fault value. The combined fault value comprehensively considers the basic influence degree of the module fault and its weight in the overall judgment, and then compares the combined fault value with the second threshold. The second threshold is also a preset standard value. When the combined fault value is greater than the second threshold, the judgment condition is reached, and at this time, a fault label will be added to the corresponding bicycle end.

[0103] S4. Obtain the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state, and update the fault label and / or the standard specification tree.

[0104] It can be understood that after the bicycle is determined to be faulty and a fault label is added, in order to make the fault label and the standard specification tree more accurately reflect the actual situation of the bicycle, it is necessary to obtain the multi-dimensional data of the target bicycle during the period from the fault determination moment (the first moment) to the moment when the bicycle returns to the normal state (the second moment). These multi-dimensional data contain various information during the fault handling and recovery process of the bicycle. By analyzing these data, the fault label and the standard specification tree can be updated, thereby improving the accuracy and adaptability of subsequent fault judgments.

[0105] In some embodiments, the specific implementation manner of step S4 (obtaining the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state and updating the fault label and / or the standard specification tree) includes: S41, the multi-dimensional data at least includes maintenance information, and determine the descendant nodes corresponding to the maintenance information to obtain a first set.

[0106] It can be understood that the maintenance information contained in the multi-dimensional data records the specific situation of the bicycle during maintenance during the fault period. The server will determine the corresponding descendant nodes according to the maintenance information. Since in the judgment specification tree, each descendant node corresponds to one or more modules of the shared bicycle, the maintenance information is often related to specific module failures. By finding the descendant nodes corresponding to the maintenance information and collecting these descendant nodes to form a first set, the descendant nodes in the first set represent the modules repaired during the fault handling process, providing an important basis for subsequent update operations.

[0107] For example, if the maintenance information shows that the braking system of the bicycle has been repaired, then the server will find the descendant node corresponding to the braking system in the judgment specification tree and include it in the first set.

[0108] Among them, the maintenance information is the information for repairing the component with the fault label, and the first set is the set of descendant nodes corresponding to the actually repaired modules.

[0109] S42, select and extract the descendant nodes in the judgment specification tree that trigger the fault information to obtain an updated tree, and count the descendant nodes in the updated tree to obtain a second set.

[0110] It can be understood that the server will perform selection and extraction operations on the descendant nodes in the judgment specification tree that trigger the fault information. These descendant nodes that trigger the fault information were considered as possible causes for the bicycle to malfunction during the previous fault judgment process. After extracting these descendant nodes, an updated tree is formed, and then the descendant nodes in the updated tree are counted to obtain a second set. The descendant nodes in this set represent the modules considered to have faults during the fault judgment.

[0111] For example, in the previous judgment, it is found that the child nodes corresponding to modules such as the motor and the lock of the bicycle have triggered fault information, then these child nodes will be extracted into the update tree to form a second set.

[0112] Among them, the update tree is the structure tree corresponding to the child nodes that trigger fault information, and the second set is the set of child nodes of the repair module, that is, the set of nodes corresponding to the modules considered to have faults during fault judgment.

[0113] S43. Update the fault label and / or the standard specification tree based on the first set and the second set.

[0114] It can be understood that based on the first set and the second set, the server will update the fault label and / or the standard specification tree. The first set reflects the actually repaired modules, and the second set reflects the modules considered to have problems during fault judgment. By comparing these two sets, the differences between the fault judgment and the actual repair situation can be found.

[0115] If there are differences between the first set and the second set, it means that there may be inaccuracies in the previous fault judgment, and the fault label needs to be corrected. At the same time, it may also be necessary to adjust the judgment conditions and parameters in the standard specification tree to improve the accuracy of subsequent fault judgment. If the two sets are basically the same, the standard specification tree can also be further optimized according to the actual repair situation. For example, adjust the fault base value, fault weight value, etc. of some modules. Through such update operations, the fault label and the standard specification tree can better adapt to the actual situation of the bicycle and improve the effectiveness and reliability of fault judgment.

[0116] In some embodiments, the specific implementation manner in step S43 (the update of the fault label and / or the standard specification tree based on the first set and the second set) includes: S431. If the first set is empty, update the fault label and / or the standard specification tree based on the second set.

[0117] It can be understood that when the first set is empty, it means that there are no corresponding child nodes in the maintenance information obtained from the first moment to the second moment, that is, there is no information about the actually repaired modules, indicating that the current target bicycle has no faults, that is, there may be errors in the fault warranty. Therefore, the update can be based on the second set, and the system can be adjusted according to the previous fault judgment situation to improve the accuracy of subsequent fault judgment.

[0118] In some embodiments, the specific implementation manner in step S431 (the update of the fault label and / or the standard specification tree based on the second set) includes: S4311, Extract the fault base values of the descendant nodes in the second set, subtract a preset value from the fault base values to obtain updated fault base values, and add fault labels for reporting errors.

[0119] It can be understood that the fault base value is a basic value that measures the degree of influence of the module represented by the descendant node on the overall fault judgment when a fault occurs. In order to make the system more reasonably judge faults and avoid excessive misjudgments, the extracted fault base value will be subtracted by a preset value.

[0120] Among them, the preset value is a fixed value set in advance, which is used to adjust the fault base value. What is obtained after subtracting the preset value is the updated fault base value. At the same time, in order to clarify that these modules have had faults, fault labels for reporting errors will be added to these descendant nodes. Doing so helps to track and analyze the fault history later, and can also enable the management personnel to more clearly understand the fault situation of the bicycle, so as to take corresponding measures, such as strengthening the inspection and maintenance of these modules.

[0121] S432, If the first set is not empty, determine the intersection points in the first set and the second set, there are first difference points in the first set that do not exist in the second set, and there are second difference points in the second set that do not exist in the first set.

[0122] It can be understood that if the first set is not empty, it means that there are actual maintenance information corresponding to some descendant nodes. At this time, the server will compare and analyze the first set and the second set. The intersection points refer to the descendant nodes that are both in the first set and in the second set. These nodes represent the modules that are considered problematic in the fault judgment and have actually been repaired.

[0123] Among them, the first difference points refer to the descendant nodes that exist in the first set but do not exist in the second set, which means that these modules have actually been repaired but were not recognized in the previous fault judgment, which may mean that there are omissions in the fault judgment. The second difference points refer to the descendant nodes that exist in the second set but do not exist in the first set, which means that these modules were considered problematic in the previous fault judgment but have not actually been repaired, which may mean that there are misjudgments in the fault judgment.

[0124] By determining these intersection points, first difference points and second difference points, the differences between the fault judgment and the actual maintenance situation can be clearly understood, so as to improve the accuracy of marking fault labels later.

[0125] S433, Update the fault labels and / or the standard specification tree based on the intersection points, first difference points, and second difference points.

[0126] It can be understood that for the modules corresponding to the first difference set points, it indicates that there are deficiencies in the previous fault judgment. It is necessary to increase the fault judgment sensitivity for these modules in the standard specification tree. For example, adjust the relevant judgment thresholds, increase the fault base values or fault weight values, etc.

[0127] For the modules corresponding to the second difference set points, it shows that there are misjudgments in the previous fault judgment. It is necessary to reduce the fault judgment sensitivity for these modules, such as reducing the fault base values or fault weight values, etc. At the same time, it is also necessary to make corresponding corrections to the fault labels to ensure that they accurately reflect the actual faults of the bicycle. Through such update operations, the fault labels and the standard specification tree can be made more in line with the actual situation of the bicycle, improving the reliability and effectiveness of the entire fault vehicle marking method.

[0128] In some embodiments, the specific implementation manner in step S433 (updating the fault labels and / or the standard specification tree based on the intersection points, the first difference set points, and the second difference set points) includes: S4331, calculate the sum of the numbers of the intersection points, the first difference set points, and the second difference set points, calculate the ratio of the first difference set points to the sum to obtain the first ratio, and calculate the ratio of the second difference set points to the sum to obtain the second ratio.

[0129] It can be understood that first calculate the sum of the numbers of the intersection points, the first difference set points, and the second difference set points. The total number is the number of all key sub-nodes involved in the comparison and analysis of fault judgment and actual maintenance. Then, calculate the ratio of the number of the first difference set points to the sum respectively to obtain the first ratio. The first ratio is the relative quantity situation of the first difference set points among all key sub-nodes. Similarly, calculate the ratio of the number of the second difference set points to the sum to obtain the second ratio. The second ratio is the relative proportion of the second difference set points among all key sub-nodes.

[0130] Through the above implementation manner, the present invention obtains the first ratio and the second ratio for subsequent use in determining the adjustment range of the fault weight values for different types of nodes.

[0131] S4332, extract the fault weight values of the intersection points, multiply the sum by the first preset value to obtain the positive adjustment coefficient, multiply the first adjustment value by the positive adjustment coefficient to obtain the first positive adjustment value, and add the fault weight values and the first positive adjustment value to obtain the updated fault weight values.

[0132] It can be understood that the server multiplies the first preset value (a preset fixed value used as a reference parameter for adjustment) by the sum of the previously calculated quantities to obtain a positive adjustment coefficient. The positive adjustment coefficient comprehensively considers the quantities of all key child nodes and the preset adjustment reference, reflecting the overall amplitude trend of the adjustment of the intersection point fault weight value. Then, the server multiplies the first adjustment value by the positive adjustment coefficient to obtain a first positive adjustment value, which is a value specifically used to increase the intersection point fault weight value. Finally, the server adds the extracted fault weight value to the first positive adjustment value to obtain an updated fault weight value. Since the module corresponding to the intersection point is identified as problematic in the fault judgment and has actually been repaired, increasing its fault weight value can make the server pay more attention to the fault conditions of these modules in subsequent fault judgments, thereby improving the accuracy of fault judgment.

[0133] Among them, the first adjustment value is a preset value used for further refined adjustment.

[0134] S4333. Extract the fault weight value of the first difference set point, multiply the second adjustment value by the first ratio to obtain a second positive adjustment value, and add the fault weight value to the second positive adjustment value to obtain an updated fault weight value.

[0135] It can be understood that for the first difference set point, the server extracts its fault weight value. Since the modules represented by the first difference set point are those that have actually been repaired but were not previously identified by the fault judgment, it is necessary to appropriately increase their fault weight values to improve the sensitivity to the faults of these modules. The server multiplies the second adjustment value by the previously calculated first ratio to obtain a second positive adjustment value, which is calculated based on the relative quantity of the first difference set point among all key child nodes and the preset adjustment value and is used to specifically increase the fault weight value of the first difference set point.

[0136] Among them, the second adjustment value is a preset value used for adjusting the fault weight value of the first difference set point.

[0137] Finally, the server adds the extracted fault weight value to the second positive adjustment value to obtain an updated fault weight value. Through such adjustment, in subsequent fault judgments, the server can pay more attention to the fault conditions of these previously overlooked modules, reduce omissions in fault judgment, and improve the comprehensiveness of fault judgment.

[0138] S4334. Extract the fault weight value of the second difference set point, multiply the third adjustment value by the second ratio to obtain a third negative adjustment value, and subtract the second positive adjustment value from the fault weight value to obtain an updated fault weight value.

[0139] It can be understood that since the modules corresponding to the second difference set points are those that were considered problematic in previous fault judgments but were not actually repaired, it indicates that there may have been misjudgments in the previous fault judgments of these modules. Therefore, it is necessary to reduce their fault weight values. The server multiplies the third adjustment value by the previously calculated second ratio to obtain a third reverse adjustment value. The third reverse adjustment value is calculated based on the relative quantity of the second difference set points among all key sub-nodes and a preset adjustment value, and is used to specifically reduce the fault weight value of the second difference set points.

[0140] Among them, the third adjustment value is a preset value used to adjust the fault weight value of the second difference set points.

[0141] Finally, subtract the third reverse adjustment value from the extracted fault weight value to obtain the updated fault weight value. Through such adjustment, it is possible to reduce the system's fault sensitivity to these modules that may have been misjudged, reduce the situation of misjudgment, and improve the accuracy and reliability of fault judgment.

[0142] As Figure 3 shown, the present invention provides a schematic diagram of the result of a shared bicycle fault vehicle marking system based on multi-dimensional data. The shared bicycle fault vehicle marking system based on multi-dimensional data includes: A decomposition module for enabling the server to decompose the multi-dimensional data of the bicycle end, device end, and service end corresponding to the target bicycle to obtain decomposition information, and classifying the decomposition information to obtain first classification information and second classification information.

[0143] A classification module for enabling the management end to generate a judgment specification tree for classification information based on a standard specification tree and image interaction.

[0144] A judgment module for adding a fault label to the corresponding bicycle end and extracting the first moment if the independent first classification information or the combined second classification information reaches the judgment condition of the judgment specification tree.

[0145] An update module for enabling the acquisition of the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state, and updating the fault label and / or the standard specification tree.

[0146] The present invention also provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the above various embodiments.

[0147] Among them, the storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, the storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). In addition, the ASIC can be located in the user equipment. Of course, the processor and the storage medium can also exist as discrete components in the communication device. The storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0148] The present invention also provides a program product, which includes execution instructions stored in a storage medium. At least one processor of the device can read the execution instructions from the storage medium, and the execution of the execution instructions by at least one processor enables the device to implement the methods provided by the above various embodiments.

[0149] In the above embodiments of the terminal or the server, it should be understood that the processor can be a central processing unit (CPU for short), and can also be other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the present invention can be directly embodied as being executed and completed by a hardware processor, or can be executed and completed by a combination of hardware and software modules in the processor.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for marking malfunctioning shared bicycles based on multi-dimensional data, characterized in that Including: The server decomposes the multi-dimensional data of the bicycle end, device end, and server corresponding to the target bicycle to obtain decomposition information, and classifies the decomposition information to obtain first classification information and second classification information; The management end generates a judgment specification tree for classification information based on the standard specification tree and image interaction; If the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree, a fault label is added to the corresponding bicycle end and the first moment is extracted; Obtain the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state, and update the fault label and / or the standard specification tree.

2. The method according to claim 1, characterized in that The server decomposes the multi-dimensional data of the bicycle end, device end, and server corresponding to the target bicycle to obtain decomposition information, including: Extract all the data of the target bicycle within the first preset time period; Decompose all the data to obtain the automatic fault reporting information of the bicycle end, the active fault reporting information of the device end, and the analysis fault reporting information of the server end; Classify the automatic fault reporting information, active fault reporting information, and analysis fault reporting information according to dimensions to obtain decomposition information.

3. The method according to claim 2, characterized in that Generate automatic fault reporting information through the following steps, including: If it is judged that the target bicycle has not been started after scanning a preset number of times within the second preset time, generate automatic fault reporting information.

4. The method according to claim 2, characterized in that Generate analysis fault reporting information through the following steps, including: If it is judged that the number of times the riding distance is less than the first preset distance within the second preset time is greater than the first preset number of times, generate analysis fault reporting information; If it is judged that the number of times the riding time is less than the fourth preset time within the third preset time is greater than the second preset number of times, generate analysis fault reporting information.

5. The method according to claim 1, characterized in that The management end generates a judgment specification tree for classification information based on the standard specification tree and image interaction, including: The standard specification tree includes a first node at the first level, a first sub-node and a second sub-node at the second level, and a plurality of grandchild nodes at the third level. The first sub-node and the second sub-node correspond to a first threshold and a second threshold respectively, and each grandchild node corresponds to at least one module of the shared bicycle; Adjust the standard specification tree based on the attributes of the target bicycle to obtain a target specification tree, and perform slot extraction and slot creation on the target specification tree to obtain an interactive image; The management end generates a judgment specification tree for classification information based on the interactive image through slot adjustment; Among them, the first sub-node corresponds to the first classification information, and the second sub-node corresponds to the second classification information.

6. The method according to claim 5, characterized in that The adjusting the standard specification tree based on the attributes of the target bicycle to obtain a target specification tree, and performing slot extraction and slot creation on the target specification tree to obtain an interactive image, including: Eliminate the modules in the standard specification tree that do not correspond to the target attributes. Each type of bicycle with target attributes has preset modules; Extract the slot positions corresponding to the first sub-node, the second sub-node, and the grandchild nodes and set them to be in a selectable state, and establish corresponding configuration slots at the slot positions corresponding to the first sub-node, the second sub-node, and the grandchild nodes; The first interaction slot is obtained by counting the area formed by the grandchild nodes connected to the first child node, and the second interaction slot is obtained by counting the area formed by the grandchild nodes connected to the second child node, and then an interaction image is obtained.

7. The method according to claim 6, wherein: The management terminal generates a judgment specification tree of classification information based on the interaction image, including: If it is determined that the user selects a grandchild node and moves it to the first interaction slot or the second interaction slot, then connect the corresponding grandchild node to the new first interaction slot or the second interaction slot; Configure a new failure base value for the moved grandchild node; If it is determined that the user adjusts the failure base value and / or the failure weight value of the newly created slot, then adjust the corresponding slot to obtain a judgment specification tree.

8. The method according to claim 6, wherein: If the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree, then add a failure label to the corresponding bicycle terminal and extract the first moment, including: If the grandchild node connected to the first child node triggers a failure message, and the failure base value of the corresponding grandchild node is greater than the first threshold value of the first child node, then the judgment condition is met and a failure label is added; If the grandchild node connected to the second child node triggers a failure message, then extract the failure base value and the failure weight value of the grandchild node in the judgment specification tree and comprehensively calculate the failure combination value. If the failure combination value is greater than the second threshold value, then the judgment condition is met and a failure label is added.

9. The method according to claim 8, wherein: The multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state is obtained, and the failure label and / or the standard specification tree are updated, including: The multi-dimensional data at least includes maintenance information, and the grandchild node corresponding to the maintenance information is determined to obtain a first set; Select and extract the grandchild nodes that trigger failure messages in the judgment specification tree to obtain an updated tree, and count the grandchild nodes in the updated tree to obtain a second set; Update the failure label and / or the standard specification tree based on the first set and the second set.

10. The method according to claim 9, wherein: The updating of the failure label and / or the standard specification tree based on the first set and the second set includes: If the first set is empty, then update the failure label and / or the standard specification tree based on the second set; If the first set is not empty, then determine the intersection point in the first set and the second set, there is a first difference point in the first set that does not exist in the second set, and there is a second difference point in the second set that does not exist in the first set; Update the failure label and / or the standard specification tree based on the intersection point, the first difference point, and the second difference point; The updating of the failure label and / or the standard specification tree based on the second set includes: Extract the failure base value of the grandchild node in the second set, subtract the preset value from the failure base value to obtain the updated failure base value, and add a reported failure label.

11. The method according to claim 10, wherein: The updating of the failure label and / or the standard specification tree based on the intersection point, the first difference point, and the second difference point includes: Calculate the sum of the numbers of the intersection points, the first difference set points, and the second difference set points, calculate the ratio of the first difference set points to the sum of the numbers to obtain the first ratio, and calculate the ratio of the second difference set points to the sum of the numbers to obtain the second ratio; Extract the fault weight value of the intersection points, multiply the sum of the numbers by the first preset value to obtain the positive adjustment coefficient, multiply the first adjustment value by the positive adjustment coefficient to obtain the first positive adjustment value, and add the fault weight value to the first positive adjustment value to obtain the updated fault weight value; Extract the fault weight value of the first difference set points, multiply the second adjustment value by the first ratio to obtain the second positive adjustment value, and add the fault weight value to the second positive adjustment value to obtain the updated fault weight value; Extract the fault weight value of the second difference set points, multiply the third adjustment value by the second ratio to obtain the third negative adjustment value, and subtract the fault weight value from the second positive adjustment value to obtain the updated fault weight value.

12. A shared bicycle fault vehicle marking system based on multi-dimensional data, characterized in that, Include: A decomposition module for causing the server to decompose the multi-dimensional data of the bicycle end, the device end, and the service end corresponding to the target bicycle to obtain decomposition information, and classify the decomposition information to obtain the first classification information and the second classification information; A classification module for causing the management end to generate a judgment specification tree of the classification information based on the standard specification tree and the image interaction; A judgment module for adding a fault label to the corresponding bicycle end and extracting the first moment if the independent first classification information or the combined second classification information meets the judgment conditions of the judgment specification tree; An update module for causing the multi-dimensional data of the target bicycle from the first moment to the second moment in the normal state to be obtained, and updating the fault label and / or the standard specification tree.

Images