Fault work order distribution method and device, electronic equipment and storage medium
By generating fault features through a large fault analysis model and matching them with the skill vector library of the handlers, the problems of low accuracy and efficiency in fault work order allocation are solved, and efficient and accurate fault handling is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- LAUNCH TECH CO LTD
- Filing Date
- 2026-01-16
- Publication Date
- 2026-04-28
AI Technical Summary
In existing technologies, the allocation of fault work orders relies on manual experience or fixed rules, resulting in low allocation accuracy and efficiency, which in turn affects the accuracy and efficiency of fault handling.
By acquiring fault data from fault work orders, fault features, including fault vectors, are generated using a large fault analysis model. These features are then matched against a skill vector library to determine the most suitable handler. The assignment of handlers is dynamically adjusted, taking into account factors such as the target fault type, the correlation weights in the skill vector library, and the availability status of the handlers.
This improved the efficiency and accuracy of fault work order allocation, thereby enhancing the efficiency and accuracy of fault handling, ensuring that emergency faults are handled promptly, and reducing the number of fault work orders that cannot be allocated or are missed.
Smart Images
Figure CN121936844A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of computer application technology, and in particular relates to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for allocating fault work orders. Background Technology
[0002] In modern, complex equipment operation and maintenance systems, such as intelligent equipment like vehicle diagnostic devices, the equipment generates massive amounts of real-time, diverse fault information during operation. Efficiently and accurately assigning these fault work orders to the most suitable personnel is crucial for ensuring stable system operation, shortening fault repair time, improving user experience, and maintaining business continuity.
[0003] In related technologies, fault work order allocation mainly relies on manual experience or fixed rules for assignment. When faced with unstructured, semantically complex fault data and the dynamic changes in the skills of various handlers, this approach is increasingly inadequate, resulting in low accuracy and efficiency in fault work order allocation, which in turn leads to low accuracy and efficiency in fault handling. Summary of the Invention
[0004] The purpose of this application is to provide a method, apparatus, electronic device, and computer-readable storage medium for allocating fault work orders, which can solve the problems of low accuracy and efficiency in fault work order allocation caused by relying on manual experience or fixed rules in related technologies, and consequently, low accuracy and efficiency in fault handling.
[0005] In a first aspect, embodiments of this application provide a method for allocating fault work orders, comprising: acquiring fault data corresponding to the fault work order; inputting the fault data into a fault analysis big model to generate fault features corresponding to the fault data, wherein the fault features include fault vectors corresponding to the fault data; and matching the fault vectors in a handler skill vector library to determine a first target handler corresponding to the fault work order, wherein the skill query vector library includes skill vectors of at least one handler.
[0006] In one possible implementation of the first aspect, the aforementioned fault features further include the target fault type corresponding to the fault data, and the aforementioned handler skill vector library further includes at least one fault type and the association weights between each fault type and each skill vector. The aforementioned matching of fault vectors in the handler skill vector library to determine the first target handler corresponding to the fault work order includes: Based on the target fault type and the association weights between each fault type and each skill vector, at least one first candidate handler is determined from among the handlers for the fault work order. The fault vector is matched with the skill vector of each first candidate handler to determine the first target handler from among the first candidate handlers.
[0007] Optionally, in another possible implementation of the first aspect, the above-mentioned matching of the fault vector with the skill vector of each first candidate processor to determine the first target processor from among the first candidate processors includes: The fault vectors are matched with the skill vectors of each first candidate handler to determine the matching confidence of each first candidate handler. Based on the matching confidence of each first candidate processor, at least one second candidate processor is determined from each first candidate processor; Obtain the available status information of each second candidate processor; Based on the available status information of each second candidate processor and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
[0008] Optionally, in another possible implementation of the first aspect, the aforementioned fault characteristics further include the target fault level corresponding to the fault data. The determination of the first target processor from among the second candidate processors based on the available status information of each second candidate processor and the matching confidence level ranking of each second candidate processor includes: Based on the target fault level, the available status information of each second candidate handler, and the matching confidence ranking of each second candidate handler, the first target handler is determined from each second candidate handler.
[0009] Optionally, in another possible implementation of the first aspect, after determining the first target processor from among the second candidate processors based on the target fault level, the available status information of each second candidate processor, and the matching confidence of each second candidate processor, the method further includes: If the first target handler is unable to handle the fault work order, or if the first target handler times out, the second target handler is determined from the second candidate handlers based on the available status information of each second candidate handler and the matching confidence of each second candidate handler. The second target handler is different from the first target handler. The person handling the first target will be replaced by the person handling the second target.
[0010] Optionally, in another possible implementation of the first aspect, the above method further includes: Obtain the processing results corresponding to the fault work order; Based on the processing results, the correlation weights between each fault type and each skill vector are optimized and updated.
[0011] Optionally, in another possible implementation of the first aspect, the above method further includes: Obtain the work order feedback information from the first target handler regarding the fault work order; Based on the feedback information from the work orders, the fault analysis model was optimized and updated.
[0012] Secondly, this application also provides a fault work order allocation device, comprising: an acquisition module for acquiring fault data corresponding to the fault work order; a generation module for inputting the fault data into a fault analysis big model to generate fault features corresponding to the fault data, wherein the fault features include fault vectors corresponding to the fault data; and a determination module for matching the fault vectors in a handler skill vector library to determine the first target handler corresponding to the fault work order, wherein the skill query vector library includes skill vectors of at least one handler.
[0013] In one possible implementation of the second aspect, the aforementioned fault features further include the target fault type corresponding to the fault data, and the aforementioned human skill vector library further includes at least one fault type, and the association weights between each fault type and each skill vector; correspondingly, the aforementioned determining module includes: The first determining unit is used to determine at least one first candidate handler corresponding to the fault work order from among the handlers based on the target fault type and the association weights between each fault type and each skill vector. The second determining unit is used to match the fault vector with the skill vector of each first candidate handler, so as to determine the first target handler from each first candidate handler.
[0014] Optionally, in another possible implementation of the second aspect, the aforementioned second determining unit is specifically used for: The fault vectors are matched with the skill vectors of each first candidate handler to determine the matching confidence of each first candidate handler. Based on the matching confidence of each first candidate processor, at least one second candidate processor is determined from each first candidate processor; Obtain the available status information of each second candidate processor; Based on the available status information of each second candidate processor and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
[0015] Optionally, in another possible implementation of the second aspect, the aforementioned fault characteristics further include the target fault level corresponding to the fault data; correspondingly, the aforementioned second determining unit is further used for: Based on the target fault level, the available status information of each second candidate handler, and the matching confidence ranking of each second candidate handler, the first target handler is determined from each second candidate handler.
[0016] Optionally, in another possible implementation of the second aspect, the aforementioned second determining unit is further used for: If the first target handler is unable to handle the fault work order, or if the first target handler times out, the second target handler is determined from the second candidate handlers based on the available status information of each second candidate handler and the matching confidence of each second candidate handler. The second target handler is different from the first target handler. The person handling the first target will be replaced by the person handling the second target.
[0017] Optionally, in another possible implementation of the second aspect, the above-mentioned apparatus further includes: The first optimization module is used to obtain the processing results corresponding to the fault work orders; The second optimization module is used to optimize and update the correlation weights between each fault type and each skill vector based on the processing results.
[0018] Optionally, in another possible implementation of the second aspect, the above-mentioned apparatus further includes: The third optimization module is used to obtain the work order feedback information of the first target handler on the fault work order; The fourth optimization module is used to optimize and update the fault analysis model based on the feedback information from the work orders.
[0019] Thirdly, this application also provides an electronic device. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement any of the implementations of the first aspect described above.
[0020] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method of any of the implementations of the first aspect described above.
[0021] Fifthly, this application also provides a computer program product that, when run on an electronic device, causes the electronic device to execute any of the implementation methods of the first aspect described above.
[0022] The beneficial effects of this application embodiment compared with the prior art are: by generating a fault vector corresponding to the fault work order through the fault data of the fault work order, and by matching the fault vector in the handler skill vector library, a handler matching the fault work order is generated, thereby improving the efficiency and accuracy of fault work order allocation, and thus improving the efficiency and accuracy of fault handling. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a flowchart illustrating a fault work order allocation method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of the fault work order distribution device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0026] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.
[0027] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0028] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."
[0029] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0030] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0031] The following description, with reference to the accompanying drawings, details the method, apparatus, electronic equipment, storage medium, and computer program for allocating fault work orders provided in this application.
[0032] Figure 1 The diagram shows a flowchart of a fault work order allocation method provided in an embodiment of this application.
[0033] Step 101: Obtain the fault data corresponding to the fault work order.
[0034] It should be noted that the fault work order allocation method of this application embodiment can be executed by the fault work order allocation device of this application embodiment. The fault work order allocation device of this application embodiment can be configured in any electronic device to execute the fault work order allocation method of this application embodiment.
[0035] Among them, a fault work order can be an electronic task document created to record and track a specific fault of a faulty device. The faulty device can be a vehicle fault diagnosis device, etc., but is not limited to this.
[0036] Among them, fault data can refer to various types of data related to faults. For example, it can include error logs collected from faulty devices, device operating status data, environmental configuration data, operation context data, etc.
[0037] For example, error logs can include core textual information such as error codes and error descriptions; device operating status data can include dynamic data such as CPU utilization, memory usage, and communication status; environment configuration data can include static data such as firmware version, software configuration, and hardware model; and operation context data can include the user's operation sequence and environmental state at the time of the fault.
[0038] It should be noted that the fault data listed above are merely exemplary. In actual use, the specific fault data can be determined based on actual usage needs and application scenarios. This application embodiment does not impose any limitations on this.
[0039] As one possible approach, fault data corresponding to the fault work order can be obtained through the specific interface of the faulty device. Furthermore, the fault data can be parsed, cleaned, normalized, and encapsulated in a structured manner to generate structured fault data.
[0040] For example, firstly, error logs in the fault data can be parsed and key fields extracted to generate standardized error logs. Secondly, the device operating status data, environmental configuration data, and operation context data at the time of the fault can be cleaned and correlated. Then, the processed fault data can be integrated into a JSON format data packet, which can then be used as structured fault data.
[0041] Step 102: Input the fault data into the fault analysis model to generate the fault features corresponding to the fault data.
[0042] The fault characteristics may include, but are not limited to, the fault vector corresponding to the fault data, the target fault type, and the target fault level.
[0043] One possible approach is to construct a large-scale fault analysis model using multi-dimensional feature learning and deep neural network techniques. This model can be pre-trained using historical fault data and an ordinal regression loss function, enabling it to analyze diverse information such as semantic features, fault impact, and fault urgency within the fault data. This allows the model to generate fault features from the fault data, thereby improving the accuracy of fault feature generation.
[0044] Next, the large fault analysis model can be deployed locally. Through model pruning, quantization and other techniques, the large fault analysis model can be compressed to a scale suitable for running on faulty devices (such as vehicle diagnostic equipment). Furthermore, knowledge distillation techniques can be used to reduce the computational and storage overhead of the large fault analysis model while ensuring its accuracy, so as to ensure stable operation on resource-constrained edge devices.
[0045] In one possible implementation of this application, fault data can be input into a pre-trained and deployed fault analysis model. The fault analysis model analyzes the semantic features, fault impact, fault urgency, and other multi-dimensional information in the fault data to generate the target fault type and target fault level corresponding to the fault data. Furthermore, the fault data can be vector-encoded to generate the fault vector corresponding to the fault data.
[0046] As an example, semantic features in fault data can be extracted and analyzed using a large fault analysis model to determine the faulty functional module corresponding to the fault data, thereby determining the target fault type. For example, if the faulty functional module is determined to be a Bluetooth communication module through the extraction and analysis of semantic features in the fault data, then the target fault type can be determined to be a Bluetooth communication module fault.
[0047] It should be noted that the methods for determining the target fault type and the possible fault function modules listed above are merely exemplary. In actual use, they can be determined according to actual usage requirements and application scenarios, and this application embodiment does not limit them in this regard. For example, the target fault type can also be determined by extracting fault component information from fault data, and the possible fault function modules can also be vehicle diagnostic modules, power management modules, etc.
[0048] As an example, the fault level can include three levels. The higher the level, the greater the impact and urgency of the fault. Level 1 can be used to represent non-critical faults that only need to be recorded and tracked. Level 2 can represent faults that need to be dealt with but do not affect core functions. Level 3 can represent faults that affect core functions and need to be dealt with immediately.
[0049] It should be noted that the number of fault levels and the fault conditions corresponding to each fault level are merely illustrative examples. In actual use, they can be determined according to actual usage needs and application scenarios. This application embodiment does not limit this.
[0050] Step 103: Match the fault vector in the handler skill vector library to determine the first target handler corresponding to the fault work order.
[0051] The skill query vector library may include the skill vectors of at least one processor.
[0052] In one possible implementation of this application, skill information for each processor can be pre-generated. For example, historical fault handling records and self-evaluations of each processor can be integrated to generate skill information for each processor separately. Next, the skill information of each processor can be vector-encoded to generate skill vectors for each processor, and these skill vectors can be stored in a processor skill vector library.
[0053] As one possible implementation, the fault vector corresponding to the fault data can be matched in the skill vector library of the handler. For example, the matching confidence (such as cosine similarity) between the fault vector and each skill vector in the skill vector library can be calculated, and the handler corresponding to the skill vector with the highest matching confidence with the fault vector can be determined as the first target handler. Then, the fault work order and the corresponding fault data can be sent to the first target handler to notify the first target handler to handle the fault.
[0054] Optionally, the handlers can be initially screened based on the target fault type of the fault work order, and then the fault vector can be matched with the skill vectors of the initially screened handlers. This avoids the problem of low fault work order allocation efficiency caused by matching the fault vector with the skill vectors of all handlers. That is, in one possible implementation of this application, step 103 above may include: Based on the target fault type and the association weights between each fault type and each skill vector, at least one first candidate handler is determined from among the handlers for the fault work order. The fault vector is matched with the skill vector of each first candidate handler to determine the first target handler from among the first candidate handlers.
[0055] In one possible implementation, the handler skill vector library also includes one or more fault types, and association weights between each fault type and each skill vector. These association weights can be numerical values, quantifying the fit between each handler and each fault type. The initial values of the weights can be manually set based on the organizational structure's responsibility allocation. In this way, by quantifying the relationships between handlers and fault types through association weights, these relationships do not need to be re-maintained when the organizational structure changes.
[0056] As an example, the handler skill vector library includes three fault types: Bluetooth communication module fault, vehicle diagnostic module fault, and power management module fault. It also includes five handler skill vectors: handler A's skill vector a, handler B's skill vector b, handler C's skill vector c, handler D's skill vector d, and handler E's skill vector e. It also includes the association weights between the three fault types and the five handler skill vectors. For example, the association weights between the Bluetooth communication module fault and skill vectors a, b, c, d, and e are 0.9, 0.5, 0.6, 0.2, and 0.7, respectively.
[0057] In one possible implementation of this application, the target fault type can be one of the fault types included in the handler skill vector library. The skill vectors with the top K (K can be an integer greater than or equal to 1) association weights with the target fault type can be queried in the handler skill vector library, and the handlers corresponding to these K skill vectors can be determined as the first candidate handlers. Alternatively, the handlers corresponding to the skill vectors in the handler skill vector library whose association weights with the target fault type exceed a preset weight threshold can be determined as the first candidate handlers.
[0058] In one possible implementation of this application, each fault type can be represented by a fault type vector in the processor skill vector library. The target fault type can be encoded to generate a target fault type vector. The target fault type vector is then matched with each fault type vector in the processor skill vector library. The fault type vector with the highest matching degree with the target fault type vector in the processor skill vector library can be determined as a similar fault type vector. Then, the processors corresponding to the top K skill vectors in the processor skill vector library with the highest association weight with the similar fault type vectors can be determined as the first candidate processors. Alternatively, the processors corresponding to the skill vectors in the processor skill vector library with the association weight with the similar fault type vectors exceeding a preset weight threshold can be determined as the first candidate processors.
[0059] As one possible implementation, the fault vector corresponding to the fault data can be matched with the skill vector of the first candidate handler. For example, the matching confidence (such as cosine similarity) between the fault vector and the skill vector of each first candidate handler can be calculated, and the first candidate handler corresponding to the skill vector with the highest matching confidence with the fault vector can be determined as the first target handler.
[0060] In this embodiment, a "fallback mechanism" can also be provided for fault work order allocation. Specifically, if the identified first target handler is "empty," or the matching confidence level corresponding to the first target handler is lower than a preset confidence threshold, the fault work order, its corresponding fault data, target fault type, and target fault level can be sent to a preset fault manager, who can then be notified to allocate the fault work order. This avoids situations where fault work orders are left unassigned, omitted, or shelved, thus improving the reliability and robustness of fault work order allocation.
[0061] Optionally, the first target processor can also be determined based on the available status information of each processor. That is, in one possible implementation of this application, the above-mentioned matching of the fault vector with the skill vectors of each first candidate processor to determine the first target processor from among the first candidate processors may include: The fault vectors are matched with the skill vectors of each first candidate handler to determine the matching confidence of each first candidate handler. Based on the matching confidence of each first candidate processor, at least one second candidate processor is determined from each first candidate processor; Obtain the available status information of each second candidate processor; Based on the available status information of each second candidate processor and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
[0062] The available status information for each second candidate handler may include, but is not limited to, the number of historical fault work orders pending or being processed by that second candidate handler.
[0063] One possible implementation is to match the fault vector with the skill vectors of each first-candidate handler, such as by calculating the cosine similarity between the fault vector and the skill vectors of each first-candidate handler, and then determining the corresponding cosine similarity of each first-candidate handler as the matching confidence score. The matching confidence scores of each first-candidate handler can be sorted, and the top M (M can be an integer greater than or equal to 1) matching confidence scores corresponding to the M first-candidate handlers can be determined as second-candidate handlers.
[0064] Secondly, the availability status information of each second candidate processor can be obtained, for example, by retrieving it from the database through a preset interface. If the number of pending or currently processing historical fault work orders included in the availability status information of the second candidate processor is 0, then this second candidate processor can be determined to be in an available state; otherwise, if the number of pending or currently processing historical fault work orders included in the availability status information of the second candidate processor is not 0, then this second candidate processor can be determined to be in an unavailable state. Next, the judgment can start from the second candidate processor with the highest matching confidence. If the second candidate processor with the highest matching confidence is in an available state, then this second candidate processor is directly determined as the first target processor. If the second candidate processor is in an unavailable state, then the judgment is made on whether the second candidate processor with the second highest matching confidence is in an available state, and so on, until the first target processor is determined or all second candidate processors have been traversed.
[0065] In this embodiment of the application, if the first target processor is still not determined after traversing all the second candidate processors, the above-mentioned "fallback mechanism" can be executed. The specific implementation method can be referred to the description in the above embodiment, and will not be repeated here.
[0066] In this way, based on the availability status information of each second candidate handler, the first target handler is only determined when the second candidate handler is in an available state. This avoids the problem of inaccurate fault work order allocation caused by the first target handler being unable to handle the current fault work order due to the need to handle other historical fault work orders after the fault work order is assigned.
[0067] Optionally, the priority of handling a fault work order can be determined based on its target fault level. That is, in one possible implementation of this application, determining the first target handler from among the second candidate handlers based on their available status information and matching confidence levels can include: Based on the target fault level, the available status information of each second candidate handler, and the matching confidence ranking of each second candidate handler, the first target handler is determined from each second candidate handler.
[0068] The available status information for each second candidate processor may also include the fault level of the historical fault work orders that the second candidate processor is waiting to process or is currently processing, but is not limited to this.
[0069] In one possible implementation of this application, if the target fault level of the current fault work order is higher than the fault level of each historical fault work order in the available status information of the second candidate handler, the current fault work order can be processed first. As an example, the judgment can start from the second candidate handler with the highest matching confidence. If the number of historical fault work orders in the available status information of the second candidate handler with the highest matching confidence is 0, or the fault level of all historical fault work orders is lower than the target fault level, this second candidate handler can be determined as the first target handler. If there are historical fault work orders with a fault level higher than or equal to the target fault level in the available status information of the second candidate handler, this second candidate handler can not be determined as the first target handler, and the judgment can continue to be made on the second candidate handler with the second highest matching confidence, and so on, until the first target handler is determined, or all second candidate handlers have been traversed.
[0070] Optionally, after determining the first target handler, the fault data and target fault level of the fault work order can be sent to the first target handler so that the first target handler can prioritize the processing of the current fault work order based on the fault data and target fault level.
[0071] This allows for priority processing of high-level fault work orders, preventing urgent faults from going unresolved and ensuring business continuity. This improves the reliability of fault work order allocation and reduces the operational risks of faulty equipment.
[0072] Optionally, if the first target handler is unable to process the request or the processing times out, the first target handler can be replaced. That is, in one possible implementation of this application, after determining the first target handler from among the second candidate handlers based on the target fault level, the available status information of each second candidate handler, and the matching confidence level of each second candidate handler, the following may be included: If the first target handler is unable to handle the fault work order, or if the first target handler times out, the second target handler is determined from the second candidate handlers based on the available status information of each second candidate handler and the matching confidence of each second candidate handler. The second target handler is different from the first target handler. The person handling the first target will be replaced by the person handling the second target.
[0073] In one possible implementation of this application, if feedback is received from the first target handler that the current fault work order cannot be processed, a second target handler can be determined from the second candidate handlers other than the first target handler, and the first target handler can be replaced by the second target handler.
[0074] As one possible implementation, a processing time threshold can be preset. If the first target handler fails to complete the processing of the fault work order within the preset processing time threshold, it can be determined that the first target handler has timed out.
[0075] For example, the same processing time threshold can be preset for each fault work order, or different processing time thresholds can be preset for fault work orders of different fault levels. For example, when the fault level is 3, the processing time threshold can be 2 hours, and when the fault level is 2 or 1, the processing time threshold can be 24 hours.
[0076] It should be noted that the processing time thresholds listed above are merely illustrative. In actual use, they can be determined according to actual usage needs and application scenarios. This application embodiment does not limit this.
[0077] In one possible implementation of this application, if the first target processor times out, a second target processor can be determined from the second candidate processors other than the first target processor, and the first target processor can be replaced by the second target processor.
[0078] As one possible implementation, the second target processor can be determined from among the second candidate processors excluding the first target processor, based on the availability status information of each second candidate processor and the matching confidence ranking of each second candidate processor. The specific implementation method can be referred to the relevant description in the above embodiment of "determining the first target processor from among the second candidate processors based on the availability status information of each second candidate processor and the matching confidence ranking of each second candidate processor," which will not be repeated here.
[0079] As one possible implementation, the second target processor can be determined from the second candidate processors excluding the first target processor based on the target fault level, the available status information of each second candidate processor, and the matching confidence ranking of each second candidate processor. The specific implementation method can be referred to the relevant description in the above embodiment of "determining the first target processor from each second candidate processor based on the target fault level, the available status information of each second candidate processor, and the matching confidence ranking of each second candidate processor," which will not be repeated here.
[0080] Optionally, if the first target handler times out, the fault data, target fault level, target fault type, and other data corresponding to the fault work order can be sent to the preset fault manager, and the manager can be notified to allocate the fault work order.
[0081] In this way, when the primary handler is unable to process a faulty work order or the processing timeout occurs, the faulty work order can be reassigned to avoid situations where faulty work orders cannot be processed, thereby improving the reliability of faulty work order allocation and thus improving the accuracy, robustness, and efficiency of fault handling.
[0082] Optionally, the skill vector library for handlers can be optimized based on relevant data from the fault work order processing process. That is, in one possible implementation of this application, the above method may further include: Obtain the processing results corresponding to the fault work order; Based on the processing results, the correlation weights between each fault type and each skill vector are optimized and updated.
[0083] One possible implementation is to obtain the processing result corresponding to the faulty work order. For example, it's possible to monitor the faulty equipment involved in the work order and check if the fault recurs under the same equipment operating status data, environmental configuration data, and operation context data. If it recurs, the processing result of the faulty work order can be determined as processing failure. Otherwise, if it does not recur, the processing result of the faulty work order can be determined as processing success.
[0084] When the processing result is successful, the association weight between the skill vector of the first target handler and the fault type corresponding to the target fault type in the skill vector library of the person in charge can be increased, and the skill vector of the first target handler can be updated based on the fault vector. When the processing result is unsuccessful, the association weight between the skill vector of the first target handler and the fault type corresponding to the target fault type in the skill vector library of the person in charge can be decreased.
[0085] Optionally, the skill vectors and fault type vectors of each processor can be updated and fine-tuned periodically according to the correlation weight between each fault type and each skill vector. This will allow the relative positions and distances between each skill vector and each fault type vector in the vector space to more realistically reflect the strength of the correlation between each vector in actual processing efficiency.
[0086] As one possible implementation, the processing result may also include processing timeout or inability to process. If the first target handler reports that it cannot process the fault work order or if the processing timeout of the first target handler is detected, the association weight between the skill vector of the first target handler and the fault type corresponding to the target fault type can be reduced.
[0087] In this way, the association weights between each fault type and each skill vector in the responsible person's skill vector library can be optimized and updated based on the various processing results of fault work orders. As a result, the responsible person's skill vector library no longer stores static, initial association weights, but rather association weights that can dynamically reflect the actual skills of each responsible person, thereby improving the accuracy and efficiency of fault work order allocation.
[0088] Optionally, the above method may also include: Obtain the work order feedback information from the first target handler regarding the fault work order; Based on the feedback information from the work orders, the fault analysis model was optimized and updated.
[0089] In one possible implementation of this application, work order feedback information from the first target handler regarding the faulty work order can be obtained. This feedback information may include the actual fault level determined by the first target handler after evaluating the faulty work order, the first target handler's assessment of the accuracy of the faulty work order allocation, the faulty work order reassignment path and reason, the "fallback mechanism" scheme, and the processing result of the faulty work order. Based on the work order feedback information, a large-scale fault analysis model can be trained, thereby optimizing and updating the parameters of the large-scale fault analysis model.
[0090] It should be noted that the above-mentioned work order feedback information may include one or more of the following: "the actual fault level determined by the first target handler after evaluating the fault work order, the first target handler's evaluation of the accuracy of the fault work order allocation, the fault work order transfer path and reason, the 'backup mechanism' scheme and the processing result of the fault work order", or it may include other data. In actual use, it can be determined according to the actual use needs and application scenarios. This application embodiment does not limit this.
[0091] In this way, the fault analysis model can be optimized based on the feedback information from the first target handler regarding the fault work order. This allows the fault analysis model to continuously learn, improving the accuracy of its predictions and thus enhancing the accuracy and efficiency of fault work order allocation.
[0092] In one possible implementation of this application, the visualization interface can be controlled to display the processing status of each fault work order, such as the fault level, timeout status, or whether the processing was successful. The visualization interface can also be controlled to display the correlation weights between each fault type and each handler's skill vector, as well as the changing trends of these correlation weights. Furthermore, the visualization interface can be controlled to display the prediction accuracy and optimization trend of the fault analysis model for the target fault level.
[0093] The fault work order allocation method provided in this application generates a fault vector corresponding to the fault work order based on the fault data of the fault work order, and then matches the fault vector with the handler skill vector library to generate a handler that matches the fault work order, thereby improving the efficiency and accuracy of fault work order allocation, and thus improving the efficiency and accuracy of fault handling.
[0094] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0095] Corresponding to the fault work order allocation method described in the above embodiments, Figure 2 The diagram shows a structural block diagram of a fault work order allocation device provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.
[0096] Reference Figure 2 The device 20 includes: Module 21 is used to acquire fault data corresponding to fault work orders; The generation module 22 is used to input fault data into the fault analysis model and generate fault features corresponding to the fault data, wherein the fault features include fault vectors corresponding to the fault data. The determination module 23 is used to match the fault vector in the handler skill vector library to determine the first target handler corresponding to the fault work order, wherein the skill query vector library includes the skill vector of at least one handler.
[0097] In practical use, the fault work order allocation device provided in this application embodiment can be configured in any electronic device to execute the aforementioned fault work order allocation method.
[0098] The fault work order allocation device provided in this application embodiment generates a fault vector corresponding to the fault work order based on the fault data of the fault work order, and matches the fault vector with the handler skill vector library to generate a handler that matches the fault work order, thereby improving the efficiency and accuracy of fault work order allocation, and thus improving the efficiency and accuracy of fault handling.
[0099] In one possible implementation of this application, the aforementioned fault features further include the target fault type corresponding to the fault data, and the aforementioned human skill vector library further includes at least one fault type, and the association weights between each fault type and each skill vector; correspondingly, the aforementioned determining module 23 includes: The first determining unit is used to determine at least one first candidate handler corresponding to the fault work order from among the handlers based on the target fault type and the association weights between each fault type and each skill vector. The second determining unit is used to match the fault vector with the skill vector of each first candidate handler, so as to determine the first target handler from each first candidate handler.
[0100] Optionally, in another possible implementation of this application, the second determining unit is specifically used for: The fault vectors are matched with the skill vectors of each first candidate handler to determine the matching confidence of each first candidate handler. Based on the matching confidence of each first candidate processor, at least one second candidate processor is determined from each first candidate processor; Obtain the available status information of each second candidate processor; Based on the available status information of each second candidate processor and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
[0101] Optionally, in another possible implementation of this application, the aforementioned fault characteristics further include the target fault level corresponding to the fault data; correspondingly, the aforementioned second determining unit is further used for: Based on the target fault level, the available status information of each second candidate handler, and the matching confidence ranking of each second candidate handler, the first target handler is determined from each second candidate handler.
[0102] Optionally, in yet another possible implementation of this application, the second determining unit is further used for: If the first target handler is unable to handle the fault work order, or if the first target handler times out, the second target handler is determined from the second candidate handlers based on the available status information of each second candidate handler and the matching confidence of each second candidate handler. The second target handler is different from the first target handler. The person handling the first target will be replaced by the person handling the second target.
[0103] Optionally, in another possible implementation of this application, the above-mentioned device 20 further includes: The first optimization module is used to obtain the processing results corresponding to the fault work orders; The second optimization module is used to optimize and update the correlation weights between each fault type and each skill vector based on the processing results.
[0104] Optionally, in another possible implementation of this application, the above-mentioned device 20 further includes: The third optimization module is used to obtain the work order feedback information of the first target handler on the fault work order; The fourth optimization module is used to optimize and update the fault analysis model based on the feedback information from the work orders.
[0105] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.
[0106] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0107] To implement the above embodiments, this application also proposes an electronic device.
[0108] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.
[0109] like Figure 3 As shown, the above-mentioned electronic device 200 includes: The system includes a memory 210 and at least one processor 220, and a bus 230 connecting different components (including the memory 210 and the processor 220). The memory 210 stores a computer program, which, when executed by the processor 220, implements the fault work order allocation method described in the embodiments of this application.
[0110] Bus 230 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0111] Electronic device 200 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 200, including volatile and non-volatile media, removable and non-removable media.
[0112] Memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. Electronic device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 260 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 230 via one or more data media interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.
[0113] A program / utility 280 having a set (at least one) of program modules 270 may be stored in, for example, memory 210. Such program modules 270 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 270 typically perform the functions and / or methods described in the embodiments of this application.
[0114] Electronic device 200 can also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), and with one or more devices that enable a user to interact with electronic device 200, and / or with any device that enables electronic device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 292. Furthermore, electronic device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 293. As shown, network adapter 293 communicates with other modules of electronic device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0115] The processor 220 performs various functional applications and data processing by running programs stored in the memory 210.
[0116] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the fault work order allocation method in the embodiments of this application, and will not be repeated here.
[0117] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.
[0118] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.
[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.
[0120] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0122] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0124] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for allocating fault work orders, characterized in that, include: Obtain the fault data corresponding to the fault work order; The fault data is input into the fault analysis model to generate fault features corresponding to the fault data, wherein the fault features include the fault vector corresponding to the fault data. The fault vector is matched in the handler skill vector library to determine the first target handler corresponding to the fault work order, wherein the skill query vector library includes the skill vector of at least one handler.
2. The method as described in claim 1, characterized in that, The fault characteristics also include the target fault type corresponding to the fault data, and the handler skill vector library also includes at least one fault type and the association weights between each fault type and each skill vector. Matching the fault vectors in the handler skill vector library to determine the first target handler corresponding to the fault work order includes: Based on the target fault type and the association weights between each fault type and each skill vector, at least one first candidate handler corresponding to the fault work order is determined from each handler. The fault vector is matched with the skill vector of each of the first candidate processors to determine the first target processor from among the first candidate processors.
3. The method as described in claim 2, characterized in that, The step of matching the fault vector with the skill vector of each of the first candidate processors to determine the first target processor from among the first candidate processors includes: The fault vector is matched with the skill vector of each first candidate processor to determine the matching confidence of each first candidate processor; Based on the matching confidence of each first candidate processor, at least one second candidate processor is determined from each of the first candidate processors; Obtain the available status information of each of the second candidate processors; Based on the available status information of each second candidate processor and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
4. The method as described in claim 3, characterized in that, The fault characteristics also include the target fault level corresponding to the fault data. The step of determining the first target processor from among the second candidate processors based on the available status information of each second candidate processor and the matching confidence level ranking of each second candidate processor includes: Based on the target fault level, the available status information of each second candidate processor, and the matching confidence ranking of each second candidate processor, the first target processor is determined from each second candidate processor.
5. The method as described in claim 3 or 4, characterized in that, After determining the first target processor from among the second candidate processors based on the target fault level, the availability status information of each second candidate processor, and the matching confidence score of each second candidate processor, the process further includes: If the first target handler is unable to process the fault work order, or if the first target handler times out, a second target handler is determined from the second candidate handlers based on the available status information of each second candidate handler and the matching confidence ranking of each second candidate handler, wherein the second target handler is different from the first target handler. Replace the first target handler with the second target handler.
6. The method according to any one of claims 2-4, characterized in that, The method further includes: Obtain the processing result corresponding to the fault work order; Based on the processing results, the association weights between each fault type and each skill vector are optimized and updated.
7. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtain the work order feedback information from the first target handler regarding the fault work order; Based on the work order feedback information, the fault analysis model is optimized and updated.
8. A fault work order distribution device, characterized in that, include: The acquisition module is used to acquire fault data corresponding to fault work orders. The generation module is used to input the fault data into the fault analysis model and generate fault features corresponding to the fault data, wherein the fault features include the fault vector corresponding to the fault data. The determination module is used to match the fault vector in the handler skill vector library to determine the first target handler corresponding to the fault work order, wherein the skill query vector library includes the skill vector of at least one handler.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by an electronic device, it implements the method as described in any one of claims 1 to 7.