Charging pile fault diagnosis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a charging pile fault diagnosis method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a plurality of historical orders corresponding to a target charging pile, and determining an abnormal identifier set corresponding to at least one fault cause according to each abnormal identifier, and according to the screening parameter of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, determining a score of a corresponding fault reason, and according to the score of each fault reason, determining a fault diagnosis result of the target charging pile. Therefore, the score corresponding to each fault reason and the fault diagnosis result are determined by analyzing the abnormal identifier in the historical order, and the fault reason of the charging pile can be rapidly determined, so that a maintainer can maintain the charging pile according to the fault diagnosis result, and the fault maintenance efficiency of the charging pile is improved.

Description

Technical Field

[0001] This invention relates to the field of charging equipment technology, and specifically to a method, apparatus, electronic device, and storage medium for diagnosing charging pile faults. Background Technology

[0002] With the widespread use of new energy vehicles, the use of charging piles to charge these vehicles has also become more common. Currently, most charging pile businesses operate on a model where manufacturers produce the charging piles, and merchants entrust them to a platform after purchasing them. The platform will create a work order and notify maintenance personnel to repair the charging pile once an anomaly is detected.

[0003] However, due to the lack of fault diagnosis capabilities in the existing charging pile maintenance process, maintenance personnel need to conduct on-site inspections to determine the actual cause of the charging pile's fault, which takes a long time. This results in low maintenance efficiency and high maintenance costs for charging piles. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method for diagnosing charging pile faults, so as to quickly determine the cause of charging pile faults and thereby improve the efficiency of charging pile fault repair.

[0005] In a first aspect, embodiments of the present invention aim to provide a method for diagnosing charging pile faults, the method comprising:

[0006] Obtain multiple historical orders corresponding to the target charging pile, and at least some of the historical orders include at least one anomaly identifier;

[0007] Based on each of the aforementioned anomaly identifiers, at least one set of anomaly identifiers corresponding to a fault cause is determined, wherein the set of anomaly identifiers includes anomaly identifiers belonging to the corresponding fault cause in each of the aforementioned historical orders;

[0008] Based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, the score of the corresponding fault cause is determined. The filtering parameters are used to characterize the proportion of abnormal identifiers in the abnormal identifier set whose initial weight is less than a first threshold in the abnormal identifier set.

[0009] The fault diagnosis result of the target charging pile is determined based on the score of each fault cause.

[0010] Further, the step of determining the score for the corresponding fault cause based on the filtering parameters of the anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set includes:

[0011] In response to the filtering parameter being less than a preset ratio, the score of the corresponding fault cause is determined according to the initial weight of each anomaly identifier in the anomaly identifier set.

[0012] In response to the filtering parameters being no less than a preset ratio, the score for the corresponding fault cause is determined to be 0.

[0013] Further, the step of determining the score for the corresponding fault cause based on the filtering parameters of the anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set includes:

[0014] The initial score for the corresponding fault cause is determined based on the initial weight of each anomaly identifier in the anomaly identifier set.

[0015] In response to the filtering parameter being less than a preset ratio, the initial score is determined as the score for the corresponding cause of the fault;

[0016] In response to the filtering parameter being no less than a preset ratio, the initial score is modified, and the modified initial score is determined as the score for the corresponding fault cause.

[0017] Furthermore, the step of determining the score for the corresponding fault cause based on the initial weight of each anomaly identifier in the anomaly identifier set includes:

[0018] The initial weights of each anomaly identifier in the set of anomaly identifiers are summed to determine the score of the corresponding fault cause.

[0019] Furthermore, the step of determining the score for the corresponding fault cause based on the initial weight of each anomaly identifier in the anomaly identifier set includes:

[0020] Adjust the initial weights of each anomaly identifier in the anomaly identifier set, and determine the target weights of each anomaly identifier;

[0021] The scores for the corresponding fault causes are determined by summing the weights of each target.

[0022] Further, adjusting the initial weights of each anomaly identifier in the anomaly identifier set and determining the target weights of each anomaly identifier includes:

[0023] The adjustment coefficient of the anomaly identifier is determined based on the time interval between the historical orders corresponding to the anomaly identifier and adjacent historical orders and / or the user identifier;

[0024] The target weight of the anomaly identifier is determined by multiplying the adjustment coefficient of the anomaly identifier by the initial weight.

[0025] Furthermore, determining the fault diagnosis result of the target charging pile based on the scores of each of the fault causes includes:

[0026] The scores of each of the aforementioned fault causes are compared with preset scores to determine at least one alternative result, wherein the alternative result is a fault cause whose score reaches the preset score;

[0027] The fault diagnosis result of the target charging pile is determined based on each of the alternative results.

[0028] Furthermore, determining the fault diagnosis result of the target charging pile based on each of the candidate results includes:

[0029] In response to the number of alternative results being 0, the fault diagnosis result of the target charging pile is determined to be that the target charging pile has no fault;

[0030] In response to the fact that the number of alternative results is 1, the fault cause corresponding to the alternative result is determined as the fault diagnosis result of the target charging pile;

[0031] In response to the number of alternative results being greater than 1, the fault diagnosis result of the target charging pile is determined based on the anomaly identifier corresponding to each alternative result.

[0032] Furthermore, determining the fault diagnosis result of the target charging pile based on the anomaly identifier corresponding to each of the candidate results includes:

[0033] Determine diagnostic parameters for each of the candidate results, wherein the diagnostic parameters are used to characterize the number of anomaly identifiers whose initial weight is greater than a second threshold among the anomaly identifiers corresponding to the candidate results;

[0034] The fault cause corresponding to the candidate result with the largest diagnostic parameter is determined as the fault diagnosis result of the target charging pile.

[0035] Furthermore, determining the fault diagnosis result of the target charging pile based on each of the candidate results includes:

[0036] The candidate results are sorted according to their scores, and the fault cause corresponding to the candidate result with the highest score is determined as the fault diagnosis result of the target charging pile.

[0037] Furthermore, obtaining multiple historical orders corresponding to the target charging pile includes:

[0038] In response to a diagnostic request sent by a user terminal, the detection that the cumulative number of abnormal orders in the charging orders generated by the target charging pile has reached a preset number, or the detection that the target charging pile has not generated any charging orders within a preset time period, the system retrieves multiple historical orders corresponding to the target charging pile.

[0039] Furthermore, the method also includes:

[0040] Obtain anomaly identification information corresponding to different fault causes, wherein the anomaly identification information includes anomaly identification and an initial weight corresponding to the anomaly identification.

[0041] Furthermore, obtaining the anomaly identification information corresponding to different fault causes includes:

[0042] Obtain a dataset, which includes work order data corresponding to at least one historical maintenance work order and order data generated on charging piles corresponding to each historical maintenance work order;

[0043] Cluster analysis is performed on the work order data and order data to determine the anomaly identifiers corresponding to each fault cause and the initial weights corresponding to each anomaly identifier.

[0044] Secondly, embodiments of the present invention aim to provide a charging pile fault diagnosis device, the device comprising:

[0045] An acquisition unit is used to acquire multiple historical orders corresponding to the target charging pile, wherein at least some of the historical orders include at least one anomaly identifier;

[0046] An analysis unit is configured to determine at least one set of abnormal identifiers corresponding to a fault cause, and to determine the score of the corresponding fault cause based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set; wherein, the abnormal identifier set includes abnormal identifiers belonging to the corresponding fault cause in each of the historical orders; the filtering parameters are used to characterize the proportion of abnormal identifiers in the abnormal identifier set whose initial weight is less than a first threshold in the abnormal identifier set;

[0047] A diagnostic unit is used to determine the fault diagnosis result of the target charging pile based on the scores of each of the fault causes.

[0048] Thirdly, embodiments of the present invention aim to provide a computer program product, the computer program product including a computer program / instruction, which, when executed by a processor, implements the method described in any of the preceding claims.

[0049] Fourthly, embodiments of the present invention aim to provide an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any of the preceding claims.

[0050] Fifthly, embodiments of the present invention aim to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0051] The technical solution of this embodiment obtains multiple historical orders corresponding to the target charging pile, determines at least one set of abnormal identifiers corresponding to each fault cause based on each abnormal identifier, determines the score of the corresponding fault cause based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, and determines the fault diagnosis result of the target charging pile based on the score of each fault cause. Therefore, this embodiment, by analyzing the abnormal identifiers in historical orders to determine the score and fault diagnosis result corresponding to each fault cause, can quickly determine the fault cause of the charging pile, thereby enabling maintenance personnel to repair the charging pile based on the fault diagnosis result and improving the fault repair efficiency of the charging pile. Attached Figure Description

[0052] The above and other objects, features and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0053] Figure 1 This is a flowchart of a charging pile fault diagnosis method according to an embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram of abnormal identification information for a fault cause according to an embodiment of the present invention;

[0055] Figure 3 This is a schematic diagram of abnormal identification information for another fault cause according to an embodiment of the present invention;

[0056] Figure 4 This is a flowchart illustrating a scoring method for determining the cause of a fault, according to an embodiment of the present invention.

[0057] Figure 5 This is a flowchart illustrating the determination of target weights according to an embodiment of the present invention;

[0058] Figure 6 This is a schematic diagram illustrating the scoring of determining the cause of a fault according to an embodiment of the present invention;

[0059] Figure 7 This is another flowchart of a score for determining the cause of a fault, according to an embodiment of the present invention;

[0060] Figure 8 This is another flowchart of a scoring method for determining the cause of a fault according to an embodiment of the present invention;

[0061] Figure 9 This is a flowchart illustrating the process of determining fault diagnosis results according to an embodiment of the present invention;

[0062] Figure 10 This is a flowchart illustrating the process of determining candidate results according to an embodiment of the present invention;

[0063] Figure 11 This is a schematic diagram of the fault diagnosis result display page according to an embodiment of the present invention;

[0064] Figure 12 This is a schematic diagram of the fault diagnosis result details display page according to an embodiment of the present invention;

[0065] Figure 13 This is a schematic diagram of a charging pile fault diagnosis device according to an embodiment of the present invention;

[0066] Figure 14 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0067] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the substance of the present application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0068] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0069] Unless the context explicitly requires it, words such as "including" or "contains" throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, meaning "including but not limited to".

[0070] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0071] The solutions described in this specification and embodiments, if involving information acquisition, will collect data under legal and compliant conditions, ensuring the legality of the data source, and will take appropriate technical and management measures to ensure data security. If involving personal information processing, processing will be carried out under legal grounds (e.g., obtaining the consent of the personal information subject, or being necessary for contract performance), and will only be conducted within the prescribed or agreed scope. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0072] Currently, most charging piles on the market are managed through dedicated platforms. When the platform detects an anomaly in a charging pile, it creates a work order and notifies maintenance personnel to come and repair it. During the repair process, maintenance personnel need to go offline to inspect the pile and determine the actual cause of the fault, and then perform targeted repairs based on the cause. This process is time-consuming and inefficient. Therefore, if the platform had fault diagnosis capabilities, allowing it to know the fault diagnosis results of the charging pile before maintenance personnel go offline to inspect it, and to determine whether maintenance personnel need to go offline and whether repairs should be performed based on the fault diagnosis results, maintenance efficiency could be improved. This would also help charging pile merchants have a comprehensive understanding of the damaged equipment, facilitating their subsequent decision-making. Based on this, this embodiment aims to provide a charging pile fault diagnosis method to quickly determine the cause of charging pile faults, thereby improving the efficiency of charging pile fault repair.

[0073] Figure 1 This is a flowchart of a charging pile fault diagnosis method according to an embodiment of the present invention. Figure 1 As shown, the charging pile fault diagnosis method in this embodiment is applied to the charging pile management platform and achieves charging pile fault diagnosis through the following steps.

[0074] In step S110, multiple historical orders corresponding to the target charging pile are obtained, and at least some of the historical orders include at least one abnormal identifier.

[0075] In this embodiment, the fault process of the target charging pile can be triggered in multiple ways. After the fault process of the target charging pile is triggered, multiple historical orders corresponding to the target charging pile are acquired. Among them, the historical orders are charging orders that have occurred on the target charging pile, and if the historical order includes at least one abnormal identifier, the corresponding historical order is determined to be an abnormal order.

[0076] Optionally, in this embodiment, in response to receiving a diagnostic request sent by a user terminal, detecting abnormal orders, detecting that the cumulative number of abnormal orders among the charging orders generated by the target charging pile has reached a preset number, or detecting that the target charging pile has not generated any charging orders within a preset time period, multiple historical orders corresponding to the target charging pile are obtained.

[0077] Furthermore, in this embodiment, when acquiring multiple historical orders corresponding to a target charging pile, the most recent abnormal order on the target charging pile is first identified. Then, a certain number (e.g., 15) of orders preceding this abnormal order are used as the multiple historical orders to be acquired (including the abnormal order). Each historical order has corresponding order data, which includes user identifier, order time, abnormal identifier, charging pile abnormality rate, charging pile attributes (e.g., charging pile brand, model, etc.), vehicle attributes (e.g., vehicle brand, vehicle model, etc.), and / or other data related to the charging order. The abnormal identifier is used to characterize the fault condition detected by the charging pile.

[0078] It should be understood that charging piles typically detect relevant operating parameters during use (such as undervoltage, overcurrent, etc.) using configured sensors or other detection methods, and output anomaly flags based on the detected parameters. These anomaly flags can be represented as pure numbers (0001), pure letters (aabba), a combination of numbers and letters (xxxx01), or other formats. However, determining the cause of a fault based on anomaly flags requires a large algorithm model, which requires a significant amount of data for training and use, resulting in high processing complexity and computational load, leading to low efficiency in charging pile fault diagnosis and repair. Therefore, this embodiment obtains anomaly flags from historical orders of the charging pile through the platform and uses these flags for fault diagnosis to determine the cause of the fault. This approach balances the accuracy and efficiency of charging pile fault diagnosis.

[0079] In step S120, at least one set of abnormal identifiers corresponding to each fault cause is determined based on each abnormal identifier. The set of abnormal identifiers includes abnormal identifiers belonging to the corresponding fault cause in each historical order.

[0080] Optionally, since charging piles typically include various components (such as charging guns, functional modules, etc.), any abnormality in any component will lead to a charging pile malfunction. Furthermore, different component malfunctions correspond to various malfunction scenarios (such as undervoltage, overcurrent, etc.), and each malfunction scenario has a corresponding anomaly identifier. To balance the accuracy and efficiency of charging pile fault diagnosis, this embodiment will diagnose the charging pile fault based on the fault cause corresponding to the component, and determine the fault cause at the component level. That is, one fault cause corresponds to one component malfunction, the same fault cause corresponds to multiple malfunction scenarios, and one malfunction scenario corresponds to one anomaly identifier; thus, one fault cause corresponds to multiple anomaly identifiers.

[0081] Furthermore, to facilitate the determination of fault diagnosis results for charging piles, this embodiment acquires anomaly identification information corresponding to different fault causes before performing fault diagnosis on the target charging pile. The anomaly identification information includes anomaly identifiers and their corresponding initial weights. The anomaly identifiers characterize the fault conditions of the charging pile, while the initial weights characterize the degree of impact of the corresponding fault conditions on the performance of the charging pile.

[0082] Optionally, when obtaining the abnormal identification information corresponding to different fault causes, the different fault causes include all fault causes occurring in various components of the charging pile, and the abnormal identification information corresponding to each fault cause includes various fault conditions of the corresponding component. Further, in this embodiment, the different fault causes of the charging pile and the abnormal identification information corresponding to each fault cause can be determined by querying the charging pile's factory user manual and / or usage information recorded during use.

[0083] Furthermore, in this embodiment, usage information recorded during the use of the charging pile is used to determine the anomaly identification information corresponding to different fault causes, so that the anomaly identification information corresponding to different fault causes is more consistent with the actual usage scenario. Moreover, when obtaining the anomaly identification information corresponding to different fault causes, a dataset is first obtained. The dataset includes work order data corresponding to at least one historical maintenance work order and order data generated on the charging pile corresponding to each historical maintenance work order. Then, by performing cluster analysis on the work order data and order data in the dataset, the anomaly identification information corresponding to each fault cause and the initial weight corresponding to each anomaly identification information are determined.

[0084] Specifically, to improve the efficiency of determining the anomaly identification information corresponding to different fault causes, this embodiment, after acquiring the dataset, will preprocess the work order data and order data in the dataset, and use the preprocessed work order data and order data to determine the anomaly identification information corresponding to different fault causes. Optionally, the preprocessing in this embodiment includes the following operations:

[0085] Keyword Matching: Since historical maintenance work orders may contain invalid samples, this embodiment performs keyword matching on all historical maintenance work orders based on component keywords (e.g., charging gun, charging module, etc.) to filter out invalid samples and obtain valid samples in the dataset. Blacklist Filtering: By verifying the work order data in historical maintenance work orders, work order data that is filled out incorrectly or haphazardly, or work order data from maintenance personnel with high repetition rates or poor reliability, is added to a blacklist. Work order data not on the blacklist is used as data in the dataset. Secondary Verification: The dataset obtained after the above matching and blacklist filtering is manually verified a second time to confirm the accuracy and reliability of the dataset.

[0086] Meanwhile, in actual use of charging piles, the failure scenarios of different components exhibit a certain degree of clustering and distinctness. That is, anomaly indicators for different failure scenarios under the same fault cause typically only appear in the corresponding component failure, while the overlap between anomaly indicators corresponding to different fault causes is low. Therefore, in this embodiment, when performing clustering analysis, anomaly indicators with high clustering and distinctness in work order data and order data are selected as the primary analysis targets. In other words, only anomaly indicators with high clustering and distinctness among all anomaly indicators corresponding to a fault cause are identified as the anomaly indicator information corresponding to that fault cause.

[0087] Furthermore, considering that there are many anomaly markers related to different components, but the correlation between different anomaly markers may vary, this embodiment assigns a value to each anomaly marker, that is, each anomaly marker has a corresponding initial weight. Optionally, the initial weight of each anomaly marker in this embodiment can be determined by data analysis combined with expert experience, so as to characterize the reference value of the anomaly marker in the corresponding fault cause and the degree of impact on the charging pile fault through the initial weight.

[0088] Figure 2-3 This is a schematic diagram illustrating abnormal identification information for different fault causes according to an embodiment of the present invention. For example... Figure 2 As shown, the causes of charging gun malfunctions include various scenarios, such as incorrect gun connection, charging connection failure, and nozzle malfunction. Figure 3 As shown, under the fault cause of module failure, there are various fault scenarios, including three-phase imbalance, module power-on timeout, and charging module failure. Furthermore, each fault scenario has a corresponding anomaly identifier and initial weight. The initial weights for different fault scenarios can be the same or different.

[0089] It should be understood that the fault cause-related anomaly identification information and the initial weight values ​​corresponding to each anomaly identification given in this embodiment are only examples, and can be set according to the actual use scenario.

[0090] Furthermore, after determining all the abnormal identifiers corresponding to each fault cause, this embodiment traverses each historical order and, based on the correspondence between the fault cause and each abnormal identifier, determines the abnormal identifiers belonging to each fault cause in each historical order, thereby determining the set of abnormal identifiers corresponding to each fault cause.

[0091] It should be noted that since the same fault condition may occur multiple times on a charging station, different charging orders on the same charging station may have the same abnormality identifier; and when the abnormality code reporting cycle is short, the same charging order may report multiple abnormality codes frequently. Therefore, in order to ensure the accuracy of fault diagnosis, in this embodiment, the abnormality identifiers corresponding to the same fault condition in different historical orders are counted cumulatively, while the abnormality identifiers corresponding to the same fault condition reported multiple times in the same order are counted once.

[0092] For example, suppose the charging station malfunction has two causes: cause A and cause B. Cause A has all anomaly identifiers A1, A2, A3, and A4, while cause B has all anomaly identifiers B1, B2, and B3. The historical orders used for fault diagnosis include historical order 1 and historical order 2. Historical order 1 has anomaly identifiers A1, A2, and B2, while historical order 2 has anomaly identifiers A1 and B3. Therefore, by iterating through historical order 1 and historical order 2, we can determine that the set of anomaly identifiers for cause A is {A1*2, A2, A3}, and the set of anomaly identifiers for cause B is {B2, B3}.

[0093] In step S130, the score of the corresponding fault cause is determined according to the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set. The filtering parameters are used to characterize the proportion of abnormal identifiers in the abnormal identifier set whose initial weight is less than the first threshold.

[0094] In this embodiment, after determining the set of abnormal identifiers corresponding to each fault cause, the score of the corresponding fault cause can be determined according to the filtering parameters of each set of abnormal identifiers and / or the initial weight of each abnormal identifier in the set of abnormal identifiers.

[0095] In one optional implementation, in this embodiment, the score of the corresponding fault cause is determined based on the initial weight of each anomaly identifier in the anomaly identifier set.

[0096] Optionally, in this embodiment, the score of the corresponding fault cause is determined by summing the initial weights of each fault identifier in the fault identifier set. For example, if the fault identifier set for fault cause A is {A1*2, A2, A3}, and the initial weights corresponding to identifiers A1-A3 are 0.15, 0.35, and 0.4 respectively, the score of fault cause A is determined to be 0.15+0.15+0.35+0.4=1.05.

[0097] Alternatively, in this embodiment, by means of... Figure 4 The method shown determines the score for the cause of the fault, and specifically includes the following steps.

[0098] In step S410, the initial weights of each anomaly identifier in the anomaly identifier set are adjusted, and the target weights of each anomaly identifier are determined.

[0099] In this embodiment, since the set of abnormal identifiers for fault causes includes abnormal identifiers from different historical orders, and the occurrence time of different historical orders is different, the usage status of the charging pile at the corresponding time will be different. Therefore, in this embodiment, the initial weight of each abnormal identifier in the set of abnormal identifiers will be adjusted, and the corresponding fault cause score will be determined based on the target weight determined after adjustment.

[0100] Optionally, in this embodiment, the adjustment strategy for each anomaly identifier can be determined based on at least one of the initial weight of the anomaly identifier, the order time of the historical order corresponding to the anomaly identifier, and the user identifier of the historical order corresponding to the anomaly identifier, so as to adjust each anomaly identifier based on the adjustment strategy and determine the corresponding target weight.

[0101] Furthermore, different adjustment strategies can be applied to different anomaly identifiers within the same historical order. When using different adjustment strategies, the corresponding strategy can be determined based on the initial weight of each anomaly identifier and / or the reporting time. For example, the larger the initial weight of the anomaly identifier, the larger the corresponding adjustment range; the earlier the anomaly identifier is reported, the larger the corresponding adjustment range.

[0102] For the same fault condition corresponding to different historical orders, this embodiment can adopt the same adjustment strategy or different adjustment strategies. When adopting different adjustment strategies, the corresponding adjustment strategy can be determined according to the order time or user ID of the historical order corresponding to each fault ID. For example, the earlier the order time of the historical order, the greater the adjustment range of the corresponding fault ID; the lower the user level corresponding to the user ID, the greater the adjustment range of the corresponding fault ID.

[0103] Specifically, in this embodiment, the same adjustment strategy is adopted for different anomaly identifiers in the same historical order, and through methods such as... Figure 5 The method shown determines the target weight after the anomaly label is adjusted.

[0104] In step S510, the adjustment coefficient of the abnormality identifier is determined based on the time interval between the historical orders corresponding to the abnormality identifier and adjacent historical orders and / or the user identifier.

[0105] In this embodiment, when determining the target weight of each anomaly identifier, in order to improve the adjustment coefficient of the anomaly identifier in each historical order, the historical orders are first arranged according to the chronological order of their order times, and then a historical order and its adjacent historical orders are selected in sequence to determine the adjustment coefficient of the anomaly identifier of that historical order.

[0106] Optionally, in this embodiment, adjacent historical orders are the previous or next historical orders of the current historical order for which the adjustment coefficient is to be determined. For example, suppose there are 3 historical orders, which are ordered in ascending order of time as historical order 1, historical order 2, and historical order 3. When determining the adjustment coefficient, if the previous historical order is used as the adjacent historical order, the adjustment coefficient of the anomaly identifier of historical order 3 is determined based on the time interval between historical order 3 and historical order 2 and / or the user identifier; the adjustment coefficient of the anomaly identifier of historical order 2 is determined based on the time interval between historical order 2 and historical order 1 and / or the user identifier; and for the anomaly identifier of historical order 1 that has no adjacent historical orders, the initial weight corresponding to the anomaly identifier may not be adjusted, that is, the adjustment coefficient of the anomaly identifier of historical order that has no adjacent historical orders is determined to be 1.

[0107] Furthermore, when determining the adjustment coefficient of the anomaly identifier based on the time interval between the historical order and adjacent historical orders and / or the user identifier, this embodiment first determines the time interval between the two historical orders and / or the user identifiers corresponding to the two historical orders based on their order times. If the time interval between the historical order and adjacent historical orders is less than a preset duration, and / or the historical order and adjacent historical orders correspond to the same user, it indicates a high similarity between the two orders. In this case, the initial weight adjustment coefficient of the anomaly identifier of the historical order is determined to be 'a', where 'a' takes a value between 0 and 1, and can be set according to the actual application scenario. Conversely, if the time interval between the historical order and adjacent historical orders is not less than a preset duration, or the historical order and adjacent historical orders correspond to different users, it indicates a low similarity between the two orders. In this case, the initial weight of the anomaly identifier of the historical order does not need to be adjusted, and the corresponding adjustment coefficient is determined to be 1.

[0108] Therefore, the adjustment parameters for historical orders in this embodiment can be expressed by the following formula:

[0109]

[0110] Among them, P i Adjustment parameters for anomaly flags in historical orders; t i For historical orders, the order time; t i-1 The order time is the time of adjacent historical orders; t0 is the preset duration; user i User identifier for historical orders; user i-1 User identifier for adjacent historical orders.

[0111] In step S520, the adjustment coefficient of the anomaly identifier is multiplied by the initial weight to determine the target weight of the anomaly identifier.

[0112] Furthermore, in this embodiment, after determining the adjustment parameters for the anomaly identifiers of each historical order, the anomaly identifiers of each historical order are multiplied by the corresponding adjustment coefficients to determine the target weight of the anomaly identifiers.

[0113] In step S420, the weights of each target are summed to determine the score of the corresponding fault cause.

[0114] In this embodiment, after adjusting the initial weights of each anomaly identifier corresponding to the fault cause and determining the corresponding target weights, the score of the corresponding fault cause is determined by summing the target weights. Specifically, it can be calculated using the following formula:

[0115]

[0116] Where, score represents the score for the cause of the failure; w ij Let P be the initial weight of the j-th anomaly identifier in the i-th order. i is the adjustment coefficient for the initial weight of the anomaly identifier in the i-th historical order; i takes the value from 1 to m, where m is the number of historical orders corresponding to the fault cause; j takes the value from 1 to n, where n is the number of anomaly identifiers in a historical order.

[0117] It should be understood that the parameters i and j in this embodiment are set only for calculation convenience. The values ​​of i and j are determined based on the number of historical orders corresponding to the fault cause for which the score is to be calculated and the number of anomaly identifiers belonging to that fault cause in each historical order. When the number of historical orders corresponding to different fault causes is different, the maximum value of i will also be different. Similarly, when calculating the score for the same fault cause, when the number of anomaly identifiers belonging to that fault cause in different historical orders is different, the maximum value of j will also be different.

[0118] Optionally, to ensure the orderly determination of the fault cause score, this embodiment can first arrange and assign corresponding numbers to each historical order corresponding to the fault cause when calculating the fault cause score. When determining the score of each fault cause, the cumulative score of the abnormal identifier under the current fault cause in each historical order is determined in the order of the numbers. Then, the cumulative scores corresponding to each historical order are summed to determine the score of the current fault cause.

[0119] Figure 6 This is another schematic diagram illustrating the scoring of determining the cause of a fault according to an embodiment of the present invention. For example... Figure 6 As shown, in determining the score of a fault scenario, this embodiment uses the following steps to determine the score of the current fault cause.

[0120] In step S610, obtain the current historical orders.

[0121] In this embodiment, historical orders are identified as current historical orders in ascending order of order time, and are denoted as order E. i The minimum value of order number i is 1. Each time the cumulative score of a historical order is calculated, the value of order number i is incremented by 1, until the last historical order E. m The cumulative score has been calculated.

[0122] In step S620, it is determined whether the current historical order is an abnormal order.

[0123] In this embodiment, in the current historical order E i When an anomaly flag is found, determine the current historical order E. i This is an abnormal order, and proceed to step S630. In the current historical order E... i If no abnormal identifier is found in the current historical order E, then determine the current historical order E. i This is a normal order, and we will continue with step S650-3.

[0124] In step S650-3, the score for the current fault scenario is determined. If the current historical order is a normal order, the score for the current historical order E is set. i The cumulative score is 0, and the current historical order E is set to 0. i The cumulative score is summed with the historical score for the current fault scenario to determine the score *sum* corresponding to the current fault scenario. The historical score for the current fault scenario is represented by the current historical order E. i All previous historical orders E i ~E i-1 The sum of the cumulative scores.

[0125] In step S630, when the current historical order is an abnormal order, it is determined whether there is an abnormal identifier in the current abnormal order that belongs to the cause of the current failure.

[0126] In this embodiment, if an exception identifier belonging to the cause of the current fault exists in the current abnormal order, step S640 is executed. If no exception identifier belonging to the cause of the current fault exists in the current abnormal order, the process returns to step S660.

[0127] In step S640, it is determined whether the time interval between the current historical order and the adjacent historical order is less than a preset duration or whether they are charging orders from the same user.

[0128] In this embodiment, if the time interval between the current historical order and the adjacent historical order is not less than a preset duration or the order is not from the same user, step S650-1 is executed. If the time interval between the current historical order and the adjacent historical order is less than a preset duration or the order is from the same user, step S650-2 is executed.

[0129] In step S650-1, the score of the current fault scenario is determined.

[0130] In this embodiment, by analyzing the current historical order E i The initial weight w of the anomaly identifier belonging to the current fault scenario. ij Perform cumulative summation to determine the current historical order E. i The cumulative score; and the current historical order E i The cumulative score is summed with the historical score of the current fault scenario to determine the score sum corresponding to the current fault scenario.

[0131] In step S650-2, the score of the current fault scenario is determined.

[0132] In this embodiment, the current historical order E is first processed. i The initial weight w of the anomaly identifier belonging to the current fault scenario. ij Adjustments were made to determine the target weight w corresponding to each anomaly identifier. ij P i Then, the target weights of each anomaly identifier are summed to determine the current historical order E. i Cumulative score Finally, the current historical order E i The cumulative score is summed with the historical score of the current fault scenario to determine the score sum corresponding to the current fault scenario.

[0133] In step S660, it is determined whether the current historical order is the last historical order.

[0134] In this embodiment, the current historical order E is determined. i To determine the current historical order E, we need to check if the value of the number i is the maximum historical order number m. i Is this the last historical order E? m When i = m, it indicates the current historical order E. i For the last historical order, the score for the current fault scenario is calculated, and step S670 continues. Conversely, when i ≠ m (i.e., i < m), it indicates that the current historical order E... i If it is not the last historical order and there are other historical orders whose cumulative scores have not yet been calculated, then step S680 is executed, and the next historical order is taken as the new current historical order and the above processing method is executed again until all historical orders have been calculated.

[0135] In step S670, the score for the current fault scenario is output.

[0136] Therefore, in this embodiment, by traversing each historical order and calculating the cumulative score of each historical order based on the above method, the cumulative scores of each historical order are summed to determine and output the score of the current fault scenario.

[0137] In another optional implementation, in this embodiment, the score of the corresponding fault cause is determined based on the filtering parameters of each anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set.

[0138] Optionally, in this embodiment, by means of... Figure 7 The method shown determines the score for the cause of the fault, and specifically includes the following steps.

[0139] In step S710, the filtering parameters for the set of abnormal identifiers that determine the cause of the fault are determined.

[0140] In this embodiment, when determining the filtering parameters corresponding to the set of abnormal identifiers for the cause of the fault, the initial weight of each abnormal identifier in the set of abnormal identifiers corresponding to the cause of the fault is first compared with the first threshold to determine the number of abnormal identifiers in the set of abnormal identifiers whose initial weight is less than the first threshold; then the ratio of the number of abnormal identifiers whose initial weight is less than the first threshold to the total number of abnormal identifiers in the set of abnormal identifiers is calculated to determine the filtering parameters corresponding to the cause of the fault.

[0141] For example, suppose the set of abnormal identifiers for fault cause A is {A1*2, A2, A3}, and the initial weights corresponding to identifiers A1-A3 are 0.15, 0.35 and 0.4 respectively, and the first threshold is 0.2. Then, the number of abnormal identifiers with initial weights less than the first threshold in the set of abnormal identifiers for fault cause A is 2, which accounts for 50% of the total number of abnormal identifiers of 4. That is, the screening parameter for fault cause A is 50%.

[0142] In step S720, it is determined whether the filtering parameter is less than the preset ratio.

[0143] In this embodiment, the relationship between the screening parameters and the preset ratio is determined by comparing each screening parameter with a preset ratio. When the screening parameter is not less than the preset ratio, it indicates that the number of anomaly identifiers with an initial weight greater than the first threshold in the anomaly identifier set corresponding to the fault cause is small, and the reliability of the fault diagnosis result determined based on the anomaly identifier set of the fault cause is low. In this case, step S730 is continued. Conversely, when the screening parameter is less than the preset ratio, it indicates that the number of anomaly identifiers with an initial weight greater than the first threshold in the anomaly identifier set corresponding to the fault cause is large, and the reliability of the fault diagnosis result determined based on the anomaly identifier set of the fault cause is higher. In this case, step S740 is continued.

[0144] In step S730, the score for the corresponding fault cause is determined to be 0.

[0145] In step S740, the score of the corresponding fault cause is determined according to the initial weight of each anomaly identifier in the anomaly identifier set.

[0146] In this embodiment, the method for determining the score of the fault cause in step S740 is the same as that described above. Figure 6 The methods described above will not be elaborated here.

[0147] Therefore, in this embodiment, by first determining the filtering parameters of the abnormal identifier set of fault causes, and setting the corresponding fault cause score to 0 when the filtering parameters are not less than a preset ratio; or by determining the score of the corresponding fault cause according to the initial weight of each abnormal identifier in the abnormal identifier set when the filtering parameters are less than the preset ratio, the abnormal identifiers with initial weights greater than the first threshold can play a greater role in fault diagnosis, thereby improving the reliability of fault cause diagnosis.

[0148] Alternatively, in this embodiment, by means of... Figure 8 The method shown determines the score for the cause of the fault, and specifically includes the following steps.

[0149] In step S810, the initial score of the corresponding fault cause is determined according to the initial weight of each abnormal identifier in the abnormal identifier set.

[0150] In this embodiment, the method for determining the initial score of the fault cause is the same as the method described above for determining the fault cause score based on the initial weight of each anomaly identifier in the anomaly identifier set, and will not be repeated here.

[0151] In step S820, the filtering parameters for the set of anomaly identifiers are determined.

[0152] In this embodiment, the method for determining the screening parameters has been described above and will not be repeated here.

[0153] In step S830, it is determined whether the filtering parameter is less than the preset ratio.

[0154] In this embodiment, if the filtering parameter is not less than the preset ratio, step S840 is executed. If the filtering parameter is less than the preset ratio, step S850 is executed.

[0155] In step S840, in response to the screening parameter being no less than a preset ratio, the initial score is modified, and the modified initial score is determined as the score for the corresponding fault cause.

[0156] In this embodiment, when the filtering parameters are not less than a preset ratio, the initial score is modified based on a preset score to reset the score of the corresponding fault cause to the preset score. The preset score is set to 0 by default, but can be set according to the actual usage scenario.

[0157] In step S850, in response to the screening parameter being less than a preset ratio, the initial score is determined as the score for the corresponding fault cause.

[0158] Therefore, in this embodiment, by using different orders to determine the filtering parameters of the abnormal identifier set of fault causes, and setting the corresponding fault cause score to 0 when the filtering parameters are not less than a preset ratio; or when the filtering parameters are less than a preset ratio, determining the corresponding fault cause score based on the initial weight of each abnormal identifier in the abnormal identifier set, it is possible to make abnormal identifiers with initial weights greater than the first threshold play a greater role in fault diagnosis, improve the reliability of fault cause diagnosis, and make the determination of fault cause scores more convenient.

[0159] In step S140, the fault diagnosis result of the target charging pile is determined based on the score of each fault cause.

[0160] In this embodiment, after determining the score of each fault cause based on the aforementioned method, in an optional implementation, the fault causes are sorted according to the score, and the fault cause with the highest score is determined as the fault diagnosis result of the target charging pile.

[0161] In another alternative implementation, this embodiment uses, as follows: Figure 9 The method shown in the diagram determines the fault diagnosis results, specifically including the following steps.

[0162] In step S910, the scores of each fault cause are compared with preset scores to determine at least one alternative result, which is a fault cause whose score reaches the preset score.

[0163] Figure 10 This is a flowchart illustrating the process of determining candidate results in an embodiment of the present invention. For example... Figure 10 As shown in the figure, in this embodiment, at least one alternative result for the fault diagnosis of the target charging pile is determined through the following steps.

[0164] In step S1010, obtain the score for the current fault cause.

[0165] In step S1020, it is determined whether the score of the current fault cause is greater than the preset score.

[0166] In this embodiment, the relationship between the current fault cause score and the preset score is determined by comparing the score of the current fault cause with the preset score. If the score of the current fault cause is greater than the preset score, step S1030 is executed; if the score of the current fault cause is not greater than the preset score (i.e., the score is less than or equal to the preset score), step S1040 is executed.

[0167] In step S1030, the current cause of the fault is determined as an alternative result.

[0168] In this embodiment, when the score of the current fault cause is greater than the preset score, it indicates that the current fault cause has a high probability of causing the target charging pile to malfunction. At this time, the current fault cause is determined as a candidate result for fault diagnosis.

[0169] In step S1040, it is determined that the current cause of the fault is not a candidate result.

[0170] In this embodiment, when the score of the current fault cause is not greater than the preset score, it indicates that the probability of the current fault cause causing the target charging pile to malfunction is small. In this case, the current fault cause is not determined as a candidate result for fault diagnosis.

[0171] Meanwhile, after determining that the current fault cause is not a candidate result, this embodiment continues to determine whether other fault causes are candidate results using the above method, until all fault causes are judged and all candidate results corresponding to the target charging pile are determined.

[0172] In step S920, the fault diagnosis result of the target charging pile is determined based on each alternative result.

[0173] In this embodiment, after determining all the candidate results corresponding to the target charging pile, each candidate result will be further filtered to determine the fault diagnosis result of the target charging pile.

[0174] Optionally, in this embodiment, the candidate results can be sorted according to their scores, and the fault cause corresponding to the candidate result with the highest score can be determined as the fault diagnosis result of the target charging pile.

[0175] Alternatively, in this embodiment, the fault diagnosis result of the target charging pile can be determined based on the number of alternative results. Specifically, in this embodiment, in response to the number of alternative results being 0, the fault diagnosis result of the target charging pile is determined to be that the target charging pile has no fault; in response to the number of alternative results being 1, the fault cause corresponding to the alternative result is determined as the fault diagnosis result of the target charging pile; in response to the number of alternative results being greater than 1, the fault diagnosis result of the target charging pile is determined based on the anomaly identifier corresponding to each alternative result.

[0176] Furthermore, in determining the fault diagnosis result of the target charging pile based on the anomaly identifiers corresponding to each candidate result, this embodiment first determines the diagnostic parameters of each candidate result, and then determines the fault cause corresponding to the candidate result with the largest diagnostic parameter as the fault diagnosis result of the target charging pile. The diagnostic parameters are used to characterize the number of anomaly identifiers among the anomaly identifiers corresponding to the candidate results whose initial weight is greater than the second threshold.

[0177] For example, suppose that when diagnosing a fault in a target charging station, there are two alternative results: Alternative Result 1 and Alternative Result 2. Both Alternative Result 1 and Alternative Result 2 are fault causes with scores greater than a preset score of 1. The initial weights of the anomaly identifiers corresponding to Alternative Result 1 are 0.4, 0.4, 0.3, and 0.1, respectively, and the initial weights of the anomaly identifiers corresponding to Alternative Result 2 are 0.1, 0.2, 0.4, 0.2, and 0.15, respectively. The second threshold is 0.25. Then, when determining the fault diagnosis result of the target charging station based on Alternative Result 1 and Alternative Result 2, the diagnostic parameter of Alternative Result 1 is first determined to be 3 / 4 = 0.75, and the diagnostic parameter of Alternative Result 2 is determined to be 1 / 5 = 0.2. Since the diagnostic parameter of Alternative Result 1 is greater than that of Alternative Result 2, the fault cause corresponding to Alternative Result 1 with the largest diagnostic parameter is determined as the fault diagnosis result of the target charging station.

[0178] Optionally, in this embodiment, after determining the fault diagnosis result of the target charging pile, the fault diagnosis result and the corresponding operation and maintenance suggestions will also be disclosed to the merchant so that the merchant can understand the fault situation of the target charging pile in a timely manner and handle the fault in a timely manner.

[0179] Figure 11 This is a schematic diagram of the fault diagnosis result display page according to an embodiment of the present invention. Figure 12 This is a schematic diagram of the fault diagnosis result details display page according to an embodiment of the present invention. Figure 11 As shown, after determining the fault diagnosis result of the target charging pile, the platform pushes the fault diagnosis result to the terminal and displays the fault diagnosis result display page P1 on the terminal to display the faults existing in the target charging pile. Optionally, the display interface P1 in this embodiment can display the fault diagnosis result, such as a gun head fault; it can also display the fault situation corresponding to the abnormality identifier used when determining the fault diagnosis result. At the same time, when there are multiple target charging piles, the display interface can also display statistical information of the fault diagnosis results of multiple target charging piles, such as a total of x gun head faults.

[0180] Furthermore, when it is necessary to view the fault diagnosis details, a viewing control C is provided on the fault diagnosis result display page P1 in this embodiment. By triggering the viewing control C, the fault diagnosis result page will jump to... Figure 12 The fault diagnosis result details page P2 shows the diagnostic information corresponding to the fault diagnosis result, as well as maintenance suggestions for eliminating the fault. Therefore, this embodiment, through the above method, can help charging station merchants have a comprehensive understanding of the damaged equipment, facilitating their subsequent decision-making.

[0181] The technical solution of this embodiment obtains multiple historical orders corresponding to the target charging pile, determines at least one set of abnormal identifiers corresponding to each fault cause based on each abnormal identifier, determines the score of the corresponding fault cause based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, and determines the fault diagnosis result of the target charging pile based on the score of each fault cause. Therefore, this embodiment, by analyzing the abnormal identifiers in historical orders to determine the score and fault diagnosis result corresponding to each fault cause, can quickly determine the fault cause of the charging pile, thereby enabling maintenance personnel to repair the charging pile based on the fault diagnosis result and improving the fault repair efficiency of the charging pile.

[0182] Figure 13 This is a schematic diagram of a charging pile fault diagnosis device according to an embodiment of the present invention. Figure 13 As shown, the charging pile fault diagnosis device in this embodiment includes an acquisition unit 1, an analysis unit 2, and a diagnosis unit 3. The acquisition unit 1 acquires multiple historical orders corresponding to the target charging pile, with at least some of the historical orders including at least one anomaly identifier. The analysis unit 2 determines a set of anomaly identifiers corresponding to at least one fault cause, and determines the score of the corresponding fault cause based on the filtering parameters of the anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set; wherein the anomaly identifier set includes anomaly identifiers belonging to the corresponding fault cause in each historical order; the filtering parameters characterize the proportion of anomaly identifiers in the anomaly identifier set whose initial weight is less than a first threshold. The diagnosis unit 3 determines the fault diagnosis result of the target charging pile based on the scores of each fault cause.

[0183] Optionally, the acquisition unit 1 in this embodiment is further configured to acquire multiple historical orders corresponding to the target charging pile in response to a diagnostic request sent by the received user terminal, when the cumulative number of abnormal orders in the charging orders generated by the target charging pile reaches a preset number, or when the target charging pile does not generate charging orders within a preset time period.

[0184] Optionally, in this embodiment, when determining the score of the corresponding fault cause based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, in one optional implementation, the analysis unit 2 is further configured to determine the score of the corresponding fault cause based on the initial weight of each abnormal identifier in the abnormal identifier set in response to the filtering parameters being less than a preset ratio; and to determine the score of the corresponding fault cause as 0 in response to the filtering parameters being not less than a preset ratio.

[0185] Furthermore, when determining the score of the corresponding fault cause based on the initial weights of each anomaly identifier in the anomaly identifier set, optionally, the analysis unit 2 can be used to sum the initial weights of each anomaly identifier in the anomaly identifier set to determine the score of the corresponding fault cause. Alternatively, the analysis unit 2 can also be used to adjust the initial weights of each anomaly identifier in the anomaly identifier set to determine the target weight of each anomaly identifier; and sum the target weights to determine the score of the corresponding fault cause. In addition, the analysis unit 2 is also used to determine the adjustment coefficient of the anomaly identifier based on the time interval between the historical orders corresponding to the anomaly identifier and adjacent historical orders and / or the user identifier; and multiply the adjustment coefficient of the anomaly identifier by the initial weight to determine the target weight of the anomaly identifier.

[0186] Optionally, in this embodiment, when determining the fault diagnosis result of the target charging pile based on the scores of each fault cause, the diagnosis unit 3 is further configured to compare the scores of each fault cause with a preset score to determine at least one alternative result, wherein the alternative result is a fault cause whose score reaches the preset score; and determine the fault diagnosis result of the target charging pile based on each alternative result. Further, in response to the number of alternative results being 0, the diagnosis unit 3 determines the fault diagnosis result of the target charging pile as no fault has occurred; in response to the number of alternative results being 1, the fault cause corresponding to the alternative result is determined as the fault diagnosis result of the target charging pile; in response to the number of alternative results being greater than 1, the fault diagnosis result of the target charging pile is determined based on the anomaly identifier corresponding to each alternative result. Specifically, the diagnosis unit 3 is further configured to determine the diagnostic parameters of each alternative result, wherein the diagnostic parameters characterize the number of anomaly identifiers with an initial weight greater than a second threshold among the anomaly identifiers corresponding to the alternative results; and determine the fault cause corresponding to the alternative result with the largest diagnostic parameter as the fault diagnosis result of the target charging pile. Alternatively, the alternative results are sorted according to their scores, and the fault cause corresponding to the alternative result with the highest score is determined as the fault diagnosis result of the target charging pile.

[0187] In another optional implementation, the analysis unit 2 is further configured to determine the initial score of the corresponding fault cause based on the initial weight of each fault identifier in the fault identifier set; in response to the filtering parameter being less than a preset ratio, the initial score is determined as the score of the corresponding fault cause; in response to the filtering parameter being not less than a preset ratio, the initial score is modified and the modified initial score is determined as the score of the corresponding fault cause.

[0188] Figure 14 This is a schematic diagram of an electronic device according to an embodiment of the present invention. (For example...) Figure 14 As shown, Figure 14The illustrated electronic device is a general-purpose data processing device, comprising a general-purpose computer hardware architecture, including at least a processor 41 and a memory 42. The processor 41 and memory 42 are connected via a bus 43. The memory 42 is adapted to store instructions or programs executable by the processor 41. The processor 41 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 41 executes the instructions stored in the memory 42, thereby performing the method flow of the embodiments of the present invention as described above to process data and control other devices. The bus 43 connects the aforementioned components together, and also connects these components to a display controller 44, a display device, and an input / output (I / O) device 45. The input / output (I / O) device 45 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 45 is connected to the system via an input / output (I / O) controller 46.

[0189] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0190] This application is described with reference to flowchart illustrations of methods, apparatus (devices), and computer program products according to embodiments of this application. It should be understood that each step in the flowchart can be implemented by computer program instructions.

[0191] These computer program instructions may be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction means, the implementation process of which is described in the instruction means. Figure 1 The function specified in one or more processes.

[0192] These computer program instructions may also be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce instructions for implementing processes. Figure 1 A device for a function specified in one or more processes.

[0193] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for use by a computer to execute some or all of the above-described method embodiments.

[0194] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program specifying the relevant hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0195] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for diagnosing faults in charging piles, characterized in that, The method includes: Obtain multiple historical orders corresponding to the target charging pile, and at least some of the historical orders include at least one anomaly identifier; Based on each of the aforementioned anomaly identifiers, at least one set of anomaly identifiers corresponding to a fault cause is determined, wherein the set of anomaly identifiers includes anomaly identifiers belonging to the corresponding fault cause in each of the aforementioned historical orders; Based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set, the score of the corresponding fault cause is determined. The filtering parameters are used to characterize the proportion of abnormal identifiers in the abnormal identifier set whose initial weight is less than a first threshold in the abnormal identifier set. The fault diagnosis result of the target charging pile is determined based on the score of each fault cause.

2. The method according to claim 1, characterized in that, The step of determining the score for the corresponding fault cause based on the filtering parameters of the anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set includes: In response to the filtering parameter being less than a preset ratio, the score of the corresponding fault cause is determined according to the initial weight of each anomaly identifier in the anomaly identifier set. In response to the filtering parameters being no less than a preset ratio, the score for the corresponding fault cause is determined to be 0.

3. The method according to claim 1, characterized in that, The step of determining the score for the corresponding fault cause based on the filtering parameters of the anomaly identifier set and / or the initial weight of each anomaly identifier in the anomaly identifier set includes: The initial score for the corresponding fault cause is determined based on the initial weight of each anomaly identifier in the anomaly identifier set. In response to the filtering parameter being less than a preset ratio, the initial score is determined as the score for the corresponding cause of the fault; In response to the filtering parameter being no less than a preset ratio, the initial score is modified, and the modified initial score is determined as the score for the corresponding fault cause.

4. The method according to claim 2, characterized in that, The score for determining the corresponding fault cause based on the initial weight of each anomaly identifier in the anomaly identifier set includes: The initial weights of each anomaly identifier in the set of anomaly identifiers are summed to determine the score of the corresponding fault cause.

5. The method according to claim 2, characterized in that, The score for determining the corresponding fault cause based on the initial weight of each anomaly identifier in the anomaly identifier set includes: Adjust the initial weights of each anomaly identifier in the anomaly identifier set, and determine the target weights of each anomaly identifier; The scores for the corresponding fault causes are determined by summing the weights of each target.

6. The method according to claim 5, characterized in that, The step of adjusting the initial weights of each anomaly identifier in the anomaly identifier set and determining the target weights of each anomaly identifier includes: The adjustment coefficient of the anomaly identifier is determined based on the time interval between the historical orders corresponding to the anomaly identifier and adjacent historical orders and / or the user identifier; The target weight of the anomaly identifier is determined by multiplying the adjustment coefficient of the anomaly identifier by the initial weight.

7. The method according to claim 1, characterized in that, The process of determining the fault diagnosis result of the target charging pile based on the scores of each fault cause includes: The scores of each of the aforementioned fault causes are compared with preset scores to determine at least one alternative result, wherein the alternative result is a fault cause whose score reaches the preset score; The fault diagnosis result of the target charging pile is determined based on each of the alternative results.

8. The method according to claim 7, characterized in that, The process of determining the fault diagnosis result of the target charging pile based on each of the candidate results includes: In response to the number of alternative results being 0, the fault diagnosis result of the target charging pile is determined to be that the target charging pile has no fault; In response to the fact that the number of alternative results is 1, the fault cause corresponding to the alternative result is determined as the fault diagnosis result of the target charging pile; In response to the number of alternative results being greater than 1, the fault diagnosis result of the target charging pile is determined based on the anomaly identifier corresponding to each alternative result.

9. The method according to claim 8, characterized in that, The step of determining the fault diagnosis result of the target charging pile based on the anomaly identifier corresponding to each of the candidate results includes: Determine diagnostic parameters for each of the candidate results, wherein the diagnostic parameters are used to characterize the number of anomaly identifiers whose initial weight is greater than a second threshold among the anomaly identifiers corresponding to the candidate results; The fault cause corresponding to the candidate result with the largest diagnostic parameter is determined as the fault diagnosis result of the target charging pile.

10. The method according to claim 7, characterized in that, The process of determining the fault diagnosis result of the target charging pile based on each of the candidate results includes: The candidate results are sorted according to their scores, and the fault cause corresponding to the candidate result with the highest score is determined as the fault diagnosis result of the target charging pile.

11. The method according to claim 1, characterized in that, The acquisition of multiple historical orders corresponding to the target charging pile includes: In response to a diagnostic request sent by a user terminal, the detection that the cumulative number of abnormal orders in the charging orders generated by the target charging pile has reached a preset number, or the detection that the target charging pile has not generated any charging orders within a preset time period, the system retrieves multiple historical orders corresponding to the target charging pile.

12. A charging pile fault diagnosis device, characterized in that, The device includes: An acquisition unit is used to acquire multiple historical orders corresponding to the target charging pile, wherein at least some of the historical orders include at least one anomaly identifier; An analysis unit is configured to determine at least one set of abnormal identifiers corresponding to a fault cause, and to determine the score of the corresponding fault cause based on the filtering parameters of the abnormal identifier set and / or the initial weight of each abnormal identifier in the abnormal identifier set; wherein, the abnormal identifier set includes abnormal identifiers belonging to the corresponding fault cause in each of the historical orders; the filtering parameters are used to characterize the proportion of abnormal identifiers in the abnormal identifier set whose initial weight is less than a first threshold in the abnormal identifier set; A diagnostic unit is used to determine the fault diagnosis result of the target charging pile based on the scores of each of the fault causes.

13. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method of any one of claims 1-11.

14. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any one of claims 1-11.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-11.

Images