Work order processing method and apparatus

Abstract

Embodiments of the present specification provide a work order processing method and device, wherein a work order processing method comprises: in the process of generating and issuing a work order, obtaining problem text input from outside, inputting the obtained problem text into a category matching model to match the category of the problem, obtaining the problem category corresponding to the problem text, based on the problem category, querying the processing personnel set mapped by the problem category in a category and processing personnel mapping table, after obtaining the processing personnel set, generating a work order corresponding to the problem text for a target processing personnel in the processing personnel set, and performing work order issuance processing.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a work order processing method and apparatus. Background Technology

[0002] With the continuous development of Internet technology, application providers have begun to provide merchants with the ability to access their applications. Merchants can access the applications to develop sub-programs for their business operations. The technical obstacles encountered by merchants during the access process require the assistance of application providers. As more and more merchants access the applications, the technical obstacles that application providers need to deal with also increase, which places higher demands on application providers. Summary of the Invention

[0003] This specification provides one or more embodiments of a work order processing method, including: obtaining input problem text. The problem text is generated based on interaction information obtained between customer service and merchants regarding subroutine services of an application. The problem text is input into a category matching model for problem category matching, and the problem category corresponding to the problem text is output. Based on the problem category, a set of handlers mapped to the problem category is queried from a category-handler mapping table. A work order corresponding to the problem text is generated for the target handler in the handler set, and the work order is issued.

[0004] This specification provides one or more embodiments of a work order processing device, including: a problem text receiving module, configured to receive input problem text. The problem text is generated based on interaction information obtained from interactions between customer service and merchants regarding subroutine services of an application. A problem category matching module, configured to input the problem text into a category matching model for problem category matching, and output the problem category corresponding to the problem text. A handler set query module, configured to query a set of handlers mapped to the problem category in a category-handler mapping table based on the problem category. A work order generation module, configured to generate a work order corresponding to the problem text for a target handler in the handler set, and process the issuance of the work order.

[0005] This specification provides one or more embodiments of a work order processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: acquire input problem text. The problem text is generated based on interaction information obtained between customer service and a merchant regarding a subroutine service of an application. The problem text is input into a category matching model for problem category matching, and the problem category corresponding to the problem text is output. Based on the problem category, a set of handlers mapped to the problem category is queried from a category-handler mapping table. A work order corresponding to the problem text is generated for the target handler in the handler set, and the work order is issued.

[0006] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following process: Obtaining input question text. The question text is generated based on interaction information obtained between customer service and merchants regarding subroutine services of an application. The question text is input into a category matching model for question category matching, and the question category corresponding to the question text is output. Based on the question category, a set of handlers mapped to the question category is queried from a category-handler mapping table. A work order corresponding to the question text is generated for the target handler in the handler set, and the work order is issued. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in one or more embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A schematic diagram illustrating the implementation environment of a work order processing method provided in one or more embodiments of this specification;

[0009] Figure 2 A flowchart illustrating a work order processing method provided in one or more embodiments of this specification;

[0010] Figure 3 A schematic diagram illustrating problem categories provided for one or more embodiments of this specification;

[0011] Figure 4 A flowchart illustrating a processing method for a development problem handling scenario, provided by one or more embodiments of this specification;

[0012] Figure 5 A schematic diagram of an embodiment of a work order processing device provided in one or more embodiments of this specification;

[0013] Figure 6 This is a schematic diagram of the structure of a work order processing device provided for one or more embodiments of this specification. Detailed Implementation

[0014] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0015] The work order processing method provided in this embodiment, or one or more embodiments, can be applied to the work order processing implementation environment. (Refer to...) Figure 1 The implementation environment includes at least server 101. Server 101 can be a single server or a server cluster consisting of several servers, or a cloud server of a cloud computing platform. Server 101 is used to obtain problem text, obtain the problem category corresponding to the problem text, query the handling personnel corresponding to the problem category, generate a work order for the handling personnel, and issue it to the handling personnel.

[0016] The implementation environment may also include a customer service system 102, which can be an interactive software platform. The customer service system 102 is used to interact with merchants to obtain interaction information and generate question text based on the interaction information, which is then input into the server 101. The server 101 can obtain the question text from the customer service system 102.

[0017] The implementation environment may also include a database 103. Database 103 stores a mapping table between categories and handlers. Server 101 queries the mapping table of categories and handlers in database 103 for the set of handlers corresponding to the problem category.

[0018] The implementation environment may also include a work order database 104. The work order database 104 is used to store work orders during the processing. After the server 101 issues a work order, it writes the work order into the work order database 104.

[0019] In addition, the implementation environment may also include a work order system 105. The work order system 105 is used to detect the processing time of work orders in the work order database 104, and generate alarm information for the work order and send it to the server 101 after detecting that the processing time of the work order has expired.

[0020] In this implementation environment, during the work order issuance process, server 101 obtains the problem text input by customer service system 102, inputs the problem text into a category matching model for problem category matching, outputs the problem category corresponding to the problem text, queries the category-to-processor mapping table in database 103 to find the set of processors mapped to the problem category, generates a work order corresponding to the problem text for the target processor in the processor set, and issues the work order. The issued work order is written to work order database 104, so that the work order system 105 can detect the processing time of the work orders in work order database 104, so that the target processor can process the work order within a preset processing time according to the problem text contained in the work order.

[0021] One or more embodiments of a work order processing method provided in this specification are as follows:

[0022] Reference Figure 2 The work order processing method provided in this embodiment specifically includes steps S202 to S208.

[0023] Step S202: Obtain the input question text.

[0024] In practical applications, when merchants develop subroutines through the application's subroutine development service, they may encounter some technical problems that hinder the development progress. Merchants can communicate with customer service to provide the technical problems they encounter. If customer service is unable to resolve the technical problem, they can submit the technical problem to the server as a text file, i.e., a problem text file, so that the application provider's staff can handle the technical problem encountered by the merchant.

[0025] The issue text described in this embodiment refers to the information provided by a merchant to customer service when the merchant encounters a technical problem with a sub-service of the application. Customer service then interacts with the merchant to obtain interactive information about the technical problem encountered by the merchant with the sub-service of the application, and obtains the issue text based on this interactive information. The issue text can be a development issue text, a configuration issue text, and / or a runtime issue text. The application can be a payment application, and the corresponding technical problem can be a development issue, a configuration issue, and / or a runtime issue.

[0026] In practice, the question text can be generated based on interaction information obtained between customer service and the merchant regarding the application's subroutines; alternatively, the question text can be generated based on interaction information obtained between customer service and the merchant regarding the application's subroutine services. After the question text is generated, the input question text is retrieved.

[0027] In practical applications, customer service representatives and merchants can interact through text messages to obtain interactive text. Keyword extraction is performed on the interactive text to obtain question text, which is then input to more clearly describe the technical problem. In one optional implementation of this embodiment, the question text is generated and input by the intelligent customer service platform by extracting keywords from the merchant's question about the application's subroutine service and the customer service representative's interactive text.

[0028] Specifically, when merchants and customer service communicate via text, the intelligent customer service platform extracts technical issue keywords from the interaction text between the merchant and customer service regarding technical issues related to the application's sub-program services, generates issue text, and inputs this issue text.

[0029] For example, in response to a merchant's question about configuring the travel sub-program in the payment application, the intelligent customer service platform extracts technical issue keywords from the interaction text between customer service and the merchant to generate the issue text "The travel sub-program cannot configure multiple payment channels" and inputs it.

[0030] In addition, customer service representatives and merchants can also interact via voice messages to obtain interactive voice messages. Speech recognition is performed on the interactive voice messages to obtain recognized text, and keyword extraction is performed on the recognized text to obtain question text. The question text is then input. In another optional implementation provided in this embodiment, the question text is generated and input by the intelligent customer service platform recognizing and extracting keywords from the merchant's questions regarding the subprogram service of the application and the interactive voice messages of the customer service representatives.

[0031] Specifically, when merchants and customer service communicate via voice, the intelligent customer service platform identifies the voice data of the merchants and customer service interacting with each other regarding technical issues of the application's sub-program services, converts it into recognized text, extracts keywords of the technical issues from the recognized text to generate question text, and inputs the question text into the server.

[0032] Step S204: Input the question text into the category matching model to perform question category matching, and output the question category corresponding to the question text.

[0033] The issue category mentioned in this embodiment refers to the classification category of technical issues in the application's subroutine services. The issue category is obtained by matching the issue categories using a trained category matching model. The issue category can be a single-level issue category, and the category matching model can perform issue category matching based on the input issue text. Specifically, the aforementioned issue text is used as input to the trained category matching model for issue category matching processing. After the category matching model completes its processing, it outputs the issue category corresponding to the issue text.

[0034] Furthermore, the problem category can also be a multi-level problem category. The category matching model can perform problem category matching processing based on the input problem text. Based on this, in practical applications, merchants may not be able to provide accurate problem localization for technical problems encountered by subroutine services of an application, making the problem text's description of the problem rather vague, resulting in the problem text not being able to correspond to the appropriate problem category. To address this, multi-level problem categories can be preset, allowing the category matching model to locate the problem category level by level for the problem text, thus improving the accuracy of category matching processing. In one optional implementation of this embodiment, the problem category matching includes:

[0035] Extract the first keyword corresponding to the subroutine type contained in the question text, and match the first keyword with the parent question category to obtain the first parent question category corresponding to the question text;

[0036] Extract the second keyword corresponding to the subroutine configuration contained in the question text, and match the second keyword with the sub-question categories of the first parent question category to obtain the first sub-question category corresponding to the question text.

[0037] Specifically, after the category matching model receives the question text, it extracts the first keyword corresponding to the subroutine type from the question text, performs matching processing on the first keyword with the parent question category to obtain the parent question category corresponding to the first keyword, and uses the parent question category as the parent question category corresponding to the question text. It then extracts the second keyword corresponding to the subroutine configuration from the question text, performs matching processing on the second keyword with the sub-question categories in the parent question category to obtain the sub-question categories in the parent question category corresponding to the question text. Here, the parent question category can be the root question category, the first-level question category, or the second-level question category.

[0038] For example, refer to Figure 3 Given the question text "Configuration method for multiple payment channels in travel subprogram", we extract the first keyword of the subprogram type, "travel subprogram", and perform matching processing on the first keyword to obtain the parent question category "travel subprogram" 301. We extract the second keyword of the subprogram configuration, "payment channel configuration", and perform matching processing on the second keyword to obtain the sub-question category "payment configuration" 302 of the parent question category.

[0039] Furthermore, more keywords can be extracted from the question text for question category matching, making the problem location more accurate and improving the accuracy of the matching. In one optional implementation method provided in this embodiment, it also includes:

[0040] Extract the third keyword corresponding to the subroutine execution contained in the question text, and determine whether the third keyword matches any of the candidate sub-question categories in the first sub-question category;

[0041] If so, select the candidate sub-question category that matches the third keyword from the candidate sub-question categories as the target sub-question category, and obtain the target sub-question category corresponding to the question text;

[0042] If not, no action needs to be taken.

[0043] Specifically, given the above sub-problem categories, the third keyword corresponding to the subroutine execution is extracted from the problem text. It is then determined whether the third keyword matches any candidate sub-problem category under the above sub-problem categories. If they match, the candidate sub-problem category that matches the third keyword is selected as the target sub-problem category, thus obtaining the target sub-problem category corresponding to the above problem text.

[0044] Using the previous example, with the question text being "Configuration method for multiple payment channels in the travel subprogram", we extract the third keyword "configuration method" from the subprogram operation. We determine if the third keyword matches the candidate sub-question category "configuration method class" 303 in the sub-question category. We select this candidate sub-question category as the target sub-question category and obtain the target sub-question category "configuration method class" under the sub-question category "payment configuration class" under the parent question category "travel subprogram" corresponding to the question text.

[0045] In the specific execution process, the process of matching questions for the category matching model can be carried out by inputting the question category into the feature extractor of the category matching model, and inputting the obtained initial features into the encoder of the category matching model to obtain the question category; optionally, the category matching model includes: a feature extractor and an encoder.

[0046] Based on the above category matching model, which includes a feature extractor and an encoder, optionally, the feature extractor is used to extract features from the question text to obtain initial features; the encoder is used to encode the initial features to obtain category features.

[0047] In practice, the training of the aforementioned category matching model can be completed in advance, for example, on a cloud server or offline. During model training, to improve the training efficiency of the category matching model, in one optional implementation method provided in this embodiment, the category matching model is trained in the following way:

[0048] The problem text sample is input into the feature extractor of the category matching model to be trained for feature extraction to obtain the initial features of the sample;

[0049] The initial features of the sample are input into the encoder of the class matching model to be trained for encoding to obtain the sample class features;

[0050] The training loss is calculated based on the sample category features and the category labels of the question text samples;

[0051] The parameters of the feature extractor and encoder of the class matching model to be trained are adjusted based on the training loss.

[0052] Specifically, during the training process of the category matching model, the question text sample is input into the feature extractor of the category matching model to be trained for feature extraction to obtain the initial features of the sample. The initial features of the sample are then input into the encoder of the category matching model to be trained for encoding to obtain the sample category features. The sample category features corresponding to the question text sample output by the category matching model to be trained are compared with the preset category labels of the question text sample. The training loss is calculated based on the comparison result. The parameters of the feature extractor and encoder of the category matching model to be trained are adjusted based on the training loss. The preset category labels can be the question categories corresponding to the question text samples in advance.

[0053] The category matching model is trained according to the above training method until the difference between the sample category features output by the encoder of the category matching model and the preset category label converges. The training of the category matching model is then completed. By calculating the training loss and adjusting the parameters, the category matching model can learn the ability to match question categories and obtain a more accurate question category matching ability.

[0054] Step S206: Based on the problem category, query the set of handlers mapped to the problem category in the category-handler mapping table.

[0055] In this embodiment, the personnel handling the technical problems encountered by the merchants are the personnel who handle the technical problems encountered by the merchants. Each problem category can correspond to at least one personnel, and at least one personnel corresponding to the same problem category can form at least one set, that is: a set of personnel, and the same problem category can correspond to at least one set of personnel.

[0056] A mapping relationship can be pre-defined between problem categories and the set of problem handlers, generating a mapping table. Specifically, this category-to-handler mapping table is used to query the set of handlers based on the problem category. In practice, based on the problem category output by the aforementioned category matching model, the set of handlers mapped to the problem category is queried from the category-to-handler mapping table.

[0057] In practical applications, merchants may encounter complex technical problems that even their staff may not be able to solve. To address this, a problem category mapping table can be pre-defined to specify a set of associated staff with lower technical levels and a set of assisting staff with higher technical levels. By pre-setting the technical levels, associated staff can escalate the problem when encountering difficulties, i.e., send the problem to assisting staff with higher technical levels for processing. In one optional implementation of this embodiment, querying the set of staff mapped to the problem category in the problem-to-staff mapping table includes:

[0058] Query the set of associated handlers and the set of assisting handlers for the problem category in the category-handling personnel mapping table.

[0059] Step S208: Generate a work order corresponding to the problem text for the target handler in the set of handlers, and process the issuance of the work order.

[0060] The work order described in this embodiment is a work document that records the workload of the target processing personnel. The work order contains a problem text. After receiving the work order, the target processing personnel understand the problem through the problem text in order to handle the technical problem of the merchant. The work order may also carry the contact information of the merchant's contact person corresponding to the problem text, so that the target processing personnel can communicate with the merchant's contact person about the technical problem through the contact information. After the target processing personnel completes the processing, they can also mark the work order as completed.

[0061] In practice, for the set of personnel to be processed, a work order corresponding to the problem text is generated for the target personnel in the set of personnel to be processed, and the work order is sent to the target personnel so that the target personnel can handle the technical problem of the merchant after receiving the work order.

[0062] In practical applications, to enable target personnel to quickly understand the technical problems encountered by merchants, service data for subroutine development services corresponding to the problem text can be provided. This allows target personnel to pinpoint the specific problem more quickly and improve problem-solving efficiency. In an optional implementation of this embodiment, generating a work order corresponding to the problem text for target personnel in the set of personnel includes:

[0063] Obtain service data for the subroutine development service corresponding to the problem text, package the service data to obtain development logs, and generate a work order containing the development logs for the target handler in the set of handlers, so that the target handler can load the subroutine development service based on the development logs.

[0064] Specifically, the service data of the subroutine development service corresponding to the problem text is obtained, the service data is packaged to obtain the development log of the subroutine development service, a work order carrying the development log is generated for the target handler in the set of handlers, and the work order is issued to the target handler so that the target handler can load the subroutine development service in the problem state based on the development log to handle the development problem; wherein, the service data may be the program data, error code and / or environment variables of the subroutine development service.

[0065] For example, the program data of the travel subroutine development service corresponding to the problem text is obtained, the program data is packaged to obtain the development log, and a work order containing the development log is generated and issued to the target personnel so that the target personnel can load the travel subroutine development service based on the development log, in order to reproduce the problem and help the target personnel quickly understand the problem.

[0066] Furthermore, to enable target personnel to quickly understand the technical issues encountered by merchants, a problem redirection interface for the subroutine development service corresponding to the problem text can be provided. This redirection interface can be a page redirection interface for the subroutine development service and / or a remote service redirection interface, allowing target personnel to quickly locate the specific problem and improve problem-solving efficiency. In another optional implementation of this embodiment, generating a work order corresponding to the problem text for the target personnel in the set of personnel includes:

[0067] Obtain the problem redirection interface of the subroutine development service corresponding to the problem text, and generate a work order carrying the problem redirection interface for the target handler in the set of handlers, so that the target handler can access the problem page and handle the problem through the problem redirection interface.

[0068] In practical applications, to rationally allocate work orders, the candidate processing personnel in the processing personnel set can be scheduled in shifts, so that processing personnel can arrange their work reasonably according to the schedule. To this end, the priority of the processing personnel on duty can be adjusted according to the schedule, so as to select the target processing personnel based on the priority of each candidate processing personnel in the processing personnel set. In an optional implementation provided in this embodiment, the target processing personnel are determined in the following way:

[0069] Obtain the priority of each candidate processor in the set of processors, and sort the candidate processors in the set of processors according to the priority;

[0070] Based on the ranking results of the candidate processors, the candidate processor corresponding to the target priority is selected as the target processor from the set of processors.

[0071] Specifically, the priority of the pre-set on-duty processing personnel is the target priority. After querying the processing personnel set, the priority of each candidate processing personnel in the processing personnel set is obtained. The candidate processing personnel are sorted according to their priority. After the sorting is completed, the candidate processing personnel corresponding to the target priority are selected from the processing personnel set according to the sorting results of each candidate processing personnel in the processing personnel set, and the candidate processing personnel is selected as the target processing personnel.

[0072] In addition, the priority can be preset based on the technical level of each candidate processor in the set of processors, or based on the service satisfaction of each candidate processor in the set of processors; correspondingly, the target priority can be the priority corresponding to the technical level, the priority corresponding to the service satisfaction, or the priority corresponding to the on-duty status.

[0073] As described above, the associated set of handlers and the set of assisting handlers for the problem category mapping are queried in the category-handling personnel mapping table. Based on this, a work order can be generated and issued first for the associated handlers in the set of associated handlers with lower technical levels. If the associated handlers encounter obstacles during the processing, they can apply for problem escalation, that is, the work order is issued to the assisting handlers in the set of assisting handlers with higher technical levels, so that the assisting handlers can process the work order and solve the more complex technical problems encountered by the merchant. In an optional implementation of this embodiment, the step of generating a work order corresponding to the problem text for the target handler in the set of handlers and issuing the work order includes:

[0074] For the associated processing personnel in the associated processing personnel set, generate a work order corresponding to the problem text, and process the issuance of the work order;

[0075] If a work order transfer request submitted by the associated processing personnel is detected, the work order will be issued to the assisting processing personnel in the set of assisting processing personnel.

[0076] Specifically, a set of personnel with lower technical skills is designated as the associated personnel set, and a set of personnel with higher technical skills is designated as the assisting personnel set. Work orders corresponding to the problem text are generated for the associated personnel in the associated personnel set, and the work orders are issued. If the associated personnel encounter obstacles, they submit a work order escalation request. After detecting the work order escalation request, the work order is issued to the assisting personnel in the assisting personnel set with higher technical skills so that the assisting personnel can handle the work order.

[0077] For example, if the problem category is "system integration", a work order corresponding to the problem text is generated for the relevant personnel in the set of relevant personnel, and the work order is issued to the relevant personnel. After the relevant personnel submit a work order transfer application, the work order is issued to the assisting personnel in the set of assisting personnel, so that the assisting personnel with higher technical skills can process the work order to solve the technical problems encountered by the merchant.

[0078] It should be noted that the associated processing personnel in the associated processing personnel set and the assisting processing personnel in the assisting processing personnel set in the above-mentioned work order flow method can be determined by the method for determining the target processing personnel in the processing personnel set provided above. For example: obtain the priority of each candidate associated processing personnel in the associated processing personnel set, and sort each candidate associated processing personnel in the associated processing personnel set according to the priority; according to the sorting result of each candidate associated processing personnel in the associated processing personnel set, select the candidate associated processing personnel corresponding to the target priority in the associated processing personnel set as the associated processing personnel, and process the work order; wherein, the priority can be determined based on the service satisfaction of each candidate associated processing personnel in the associated processing personnel set.

[0079] In practical applications, the problem category output after matching the above problem categories may be a parent problem category. After receiving the work order, the target handler in the set of handlers corresponding to the parent problem category can locate the problem and mark the work order according to the located sub-problem category before returning the work order. This allows the work order to be issued to the target handler in the set of handlers corresponding to the sub-problem category, improving work order processing efficiency. In an optional implementation of this embodiment, after generating the work order corresponding to the problem text for the target handler in the set of handlers and performing the work order issuance process, the method further includes:

[0080] If a work order return request submitted by the target handler is detected, the first set of handlers mapped to the first issue category is queried in the category-handler mapping table according to the first issue category carried in the work order return request;

[0081] The work order is issued to the first target handler in the first set of handlers.

[0082] Specifically, after the target handler locates the problem in the work order, the system receives the work order return request submitted by the target handler, extracts the first problem category determined by the target handler after locating the problem in the work order return request, queries the first set of handlers that the first problem category is mapped to in the category-handler mapping table, and issues the work order to the first target handler in the first set of handlers so that the first target handler can process the work order to resolve the technical problem encountered by the merchant.

[0083] For example, refer to Figure 3 In the case of the above-mentioned problem category "Payment Configuration" 302, after the target handler in the set of handlers corresponding to "Payment Configuration" locates the problem, the work order return application submitted by the target handler is received, the first problem category "Configuration Method" 303 carried in the work order return application is extracted, the first set of handlers mapped to "Configuration Method" 303 is queried in the category and handler mapping table, and the above-mentioned work order is issued to the first target handler in the first set of handlers.

[0084] Furthermore, in practical applications, staff may forget to process some work orders during the process. To improve work order processing efficiency, the work order system can detect the processing time of work orders and submit an alarm message after the preset processing time is reached to remind staff to process overdue work orders as soon as possible or to process completed work orders in a timely manner. Alternatively, in one optional implementation of this embodiment, it also includes:

[0085] The work order is written into the work order database so that the processing time of the work order can be detected through the work order system;

[0086] If the preset processing time for the work order expires, the alarm information submitted by the work order system for the work order is received and sent to the target processing personnel.

[0087] Specifically, the purpose of writing work orders into the work order database is to monitor the processing time of work orders in the database through the work order system. After the preset processing time of the work order expires, the work order system generates an alarm message for the work order and submits it. The server receives the alarm message submitted by the work order system and sends the alarm message to the target personnel to remind them to process the work order as soon as possible or to process completed work orders in a timely manner.

[0088] Here, taking the above-mentioned work order processing time detection process as an example, the work order system's processing time detection for any work order in the work order database is similar to the above-mentioned work order processing process. The processing time detection process can be carried out by referring to the above-mentioned work order processing process, and will not be described again in this embodiment.

[0089] In this embodiment, the work orders completed by the target personnel can be verified and written into the historical problem database. The historical work orders in the historical problem database are then used as samples for training the category matching model. That is, the historical problem database is used as the sample database for the problem category matching model. In one optional implementation of this embodiment, after generating the work order corresponding to the problem text for the target personnel in the set of personnel and processing the work order issuance, the method further includes:

[0090] Once the work order is detected as completed, the work order is verified, and after the verification is passed, the work order is written into the historical problem database.

[0091] The work order is split to obtain the problem text and the problem category. The problem text is used as a training sample for the category matching model, and the problem category is used as a category label to train the category matching model.

[0092] Optionally, the verification result is generated based on the screening result after the work order manager filters the work orders.

[0093] Specifically, after the aforementioned work order is detected and completed, it undergoes verification. Upon successful verification, the work order is added to the historical issue database. After being added, the work order is then split to obtain the aforementioned issue text and issue category. The issue text is used as a training sample for the category matching model, and the issue category is used as the category label to train the model. The verification result can be generated based on the filtering results from the work order administrator regarding the validity of the work order. For example, a work order with the processing result "The merchant's technical personnel misread the technical document, causing this technical problem" is not valid and fails verification.

[0094] For example, after the above work order is completed, the verified work order is written into the historical issue database and the work order is split to obtain the issue text "Multiple payment channels configured in the travel subroutine cannot be paid" and the issue category "Unable to pay". The issue text is used as a training sample for the category matching model and the issue category is used as the category label to train the category matching model.

[0095] Here, taking the above-mentioned work order processing process as an example, the processing of any historical work order in the historical problem database is similar to the above-mentioned work order processing process. The historical work orders are split, training samples are generated, and category labels are generated in accordance with the above-mentioned work order processing process. This embodiment will not be described in detail here.

[0096] It should be noted that the problem text samples and category labels in the above category matching model process can be the problem texts and problem categories of historical work orders in the historical problem database, so that the problem category matching of the category matching model can be more accurate.

[0097] In summary, the work order processing method provided in this embodiment, after customer service and merchants interact with each other to obtain interaction information and generate interaction question text for the subroutine service of the application, obtains the input question text, inputs the question text into a category matching model for question category matching, obtains the question category corresponding to the output question text, and based on the question category, queries the set of handlers mapped to the question category in the category-handler mapping table, generates a work order corresponding to the question text for the target handler in the handler set, and issues it to the target handler so that the target handler can process the work order to solve the technical problems encountered by the merchant in the development of the application's subroutine service. The work order processing method provided in this embodiment, by querying the set of handlers corresponding to the question category in the category-handler mapping table, enables the quick location of the responding handler for the technical problems encountered by the merchant, improves the efficiency of the work order generation and sending process, and thus improves the response efficiency of the merchant's technical problems.

[0098] Furthermore, an interface for merchants to submit issues can be opened, allowing merchants to directly connect with the application provider's processing personnel. This improves merchants' awareness of the work order processing nodes, thereby increasing the efficiency of work order processing and the efficiency of resolving merchants' technical issues.

[0099] The following description uses the application of a work order processing method provided in this embodiment in a development problem handling scenario as an example to further illustrate the work order processing method provided in this embodiment. (See also...) Figure 4 The work order processing method, which is applied to the development of problem-solving scenarios, includes the following steps.

[0100] Step S402: Obtain the development question text input by the intelligent customer service platform.

[0101] Previously, the intelligent customer service platform extracted keywords from the interaction text between merchants and customer service regarding the development of subroutines for payment applications to generate development question text.

[0102] Step S404: Input the development problem text into the category matching model to perform problem category matching, and output the problem category corresponding to the development problem text.

[0103] The category matching model includes a feature extractor and an encoder; the feature extractor is used to extract features from the development question text to obtain initial features, and the encoder is used to extract features from the development question text to obtain category features.

[0104] Previously, the category matching model was trained by inputting question text samples into the feature extractor of the category matching model to be trained to extract initial features of the samples, inputting the initial features into the encoder of the category matching model to be trained to encode them, obtaining sample category features, calculating the training loss based on the sample category features of the question text samples and the preset classification labels, and adjusting the parameters of the feature extractor and encoder of the category matching model to be trained based on the training loss.

[0105] Step S406: Based on the problem category, query the set of associated handlers and the set of assisting handlers for the problem category mapping in the category-handler mapping table.

[0106] Step S408: Generate a work order corresponding to the development issue text for the associated processing personnel in the associated processing personnel set, and process the work order issuance.

[0107] Step S410: After detecting the work order transfer application submitted by the associated processing personnel, the work order is issued to the assisting processing personnel in the set of assisting processing personnel.

[0108] Step S412: After the work order is detected, the work order is verified and written into the historical problem database after the verification is passed.

[0109] The verification results are generated based on the screening results of the work order managers after they have screened the validity of the work orders.

[0110] Step S414: The work order is split to obtain the development problem text and problem category. The development problem text is used as the training sample for the category matching model and the problem category is used as the category label.

[0111] Subsequently, the historical question database was used as the sample database for training the category matching model.

[0112] The following is an embodiment of a work order processing device provided in this specification:

[0113] In the above embodiments, a work order processing method is provided, and correspondingly, a work order processing device is also provided, which will be described below with reference to the accompanying drawings.

[0114] Reference Figure 5 The diagram shows a schematic representation of an embodiment of a work order processing device provided in this embodiment.

[0115] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0116] This embodiment provides a work order processing device, including:

[0117] The question text acquisition module 502 is configured to acquire the input question text; the question text is generated based on the interaction information obtained by the customer service and the merchant in relation to the subroutine service of the application.

[0118] The question category matching module 504 is configured to input the question text into the category matching model to perform question category matching, and output the question category corresponding to the question text.

[0119] The personnel set query module 506 is configured to query the set of personnel mapped to the problem category in the category-personnel mapping table based on the problem category;

[0120] The work order generation module 508 is configured to generate a work order corresponding to the problem text for the target handler in the set of handlers, and to process the issuance of the work order.

[0121] The following is an example of a work order processing device provided in this manual:

[0122] Corresponding to the work order processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a work order processing device for executing the work order processing method provided above. Figure 6 This is a schematic diagram of the structure of a work order processing device provided for one or more embodiments of this specification.

[0123] This embodiment provides a work order processing device, including:

[0124] like Figure 6As shown, the work order processing device can vary significantly due to differences in configuration or performance. It may include one or more processors 601 and memory 602, and the memory 602 may store one or more application programs or data. The memory 602 may be temporary or persistent storage. The application programs stored in the memory 602 may include one or more modules (not shown), each module may include a series of computer-executable instructions in the work order processing device. Furthermore, the processor 601 may be configured to communicate with the memory 602 and execute the series of computer-executable instructions in the memory 602 on the work order processing device. The work order processing device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input / output interfaces 605, one or more keyboards 606, etc.

[0125] In one specific embodiment, the work order processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the work order processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0126] Obtain the input question text; the question text is generated based on the interaction information obtained between customer service and the merchant regarding the application's subroutine services;

[0127] The question text is input into a category matching model to perform question category matching, and the question category corresponding to the question text is output.

[0128] Based on the problem category, query the set of handlers that are mapped to the problem category in the category-handler mapping table;

[0129] A work order corresponding to the problem text is generated for the target handler in the set of handlers, and the work order is issued.

[0130] This specification provides an example of a storage medium as follows:

[0131] Corresponding to the work order processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a storage medium.

[0132] The storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed by a processor, implement the following process:

[0133] Obtain the input question text; the question text is generated based on the interaction information obtained between customer service and the merchant regarding the application's subroutine services;

[0134] The question text is input into a category matching model to perform question category matching, and the question category corresponding to the question text is output.

[0135] Based on the problem category, query the set of handlers that are mapped to the problem category in the category-handler mapping table;

[0136] A work order corresponding to the problem text is generated for the target handler in the set of handlers, and the work order is issued.

[0137] It should be noted that the embodiments concerning the storage medium and the embodiments concerning the work order processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0138] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, please refer to each other. Each embodiment focuses on describing the differences from other embodiments. For example, the device embodiment, equipment embodiment, and storage medium embodiment are all similar to the method embodiment, so the description is relatively simple. For reading the relevant content of the device embodiment, equipment embodiment, and storage medium embodiment, please refer to the description of the method embodiment.

[0139] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0140] In the 1940s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0141] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F420. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0142] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0143] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0144] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also 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 instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0149] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0150] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0151] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0152] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0153] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A work order processing method, comprising: The system obtains and inputs development question texts based on interaction information obtained by technical personnel from their interactions with customer service regarding development issues related to the subroutine development service of the payment application. The development problem text is input into a category matching model for problem category matching, and the problem category corresponding to the development problem text is output. The feature extractor of the category matching model is used to extract features from the development problem text to obtain initial features, and the encoder of the category matching model is used to encode the initial features to obtain category features. Based on the problem category, query the set of associated handlers and the set of assisting handlers mapped to the problem category in the category-handler mapping table; The service data of the subroutine development service corresponding to the development problem text is obtained. The service data is packaged to obtain development logs. A work order containing the development logs is generated for the associated processing personnel in the associated processing personnel set. The work order is issued so that the associated processing personnel or assisting processing personnel can load the subroutine development service in the problem state based on the development logs and handle the development problem. The service data includes the program data, error codes and / or environment variables of the subroutine development service. If a work order transfer request submitted by the associated processing personnel is detected, the work order will be issued to the assisting processing personnel in the set of assisting processing personnel; the problem categories include single-level problem categories and multi-level problem categories.

2. The work order processing method according to claim 1, wherein the problem category matching includes: Extract the first keyword corresponding to the subroutine type contained in the development problem text, and match the first keyword with the parent problem category to obtain the first parent problem category corresponding to the development problem text; Extract the second keyword corresponding to the subroutine configuration contained in the development problem text, and match the second keyword with the sub-problem category of the first parent problem category to obtain the first sub-problem category corresponding to the development problem text.

3. The work order processing method according to claim 2 further includes: Extract the third keyword corresponding to the subroutine execution contained in the development problem text, and determine whether the third keyword matches any of the candidate sub-problem categories in the first sub-problem category; If so, select the candidate sub-question category that matches the third keyword from the candidate sub-question categories as the target sub-question category, and obtain the target sub-question category corresponding to the development question text.

4. The work order processing method according to claim 1, wherein the associated processing personnel are determined in the following manner: Obtain the priority of each candidate processor in the set of processors, and sort the candidate processors according to the priority; Based on the ranking results of the candidate processors, the candidate processors corresponding to the target priority are selected as the associated processors from the set of processors.

5. The work order processing method according to claim 1, after generating the work order corresponding to the development problem text for the associated processing personnel in the associated processing personnel set and performing the work order issuance processing operation, it further includes: If a work order return request submitted by the associated processing personnel is detected, the first set of processing personnel mapped to the first issue category is queried in the category-processing personnel mapping table according to the first issue category carried in the work order return request; The work order is issued to the first associated processing personnel in the first set of processing personnel.

6. The work order processing method according to claim 1, wherein the category matching model is trained in the following manner: The text sample of the development problem is input into the feature extractor of the category matching model to be trained for feature extraction to obtain the initial features of the sample; The initial features of the sample are input into the encoder of the class matching model to be trained for encoding to obtain the sample class features; The training loss is calculated based on the sample category features and the category labels of the development question text samples; The parameters of the feature extractor and encoder of the class matching model to be trained are adjusted based on the training loss.

7. The work order processing method according to claim 6, after generating a work order containing the development log for the associated processing personnel in the associated processing personnel set and performing the work order issuance processing operation, further includes: Once the work order is detected as completed, the work order is verified, and after the verification is passed, the work order is written into the historical problem database. The work order is split to obtain the development problem text and the problem category. The development problem text is used as the training sample of the category matching model and the problem category is used as the category label to train the category matching model. The verification result is generated based on the screening result of the work order management personnel after screening the work orders.

8. The work order processing method according to claim 1, after generating a work order containing the development log for the associated processing personnel in the associated processing personnel set and performing the work order issuance processing operation, further includes: The work order is written into the work order database so that the processing time of the work order can be detected through the work order system; If the preset processing time of the work order expires, the alarm information submitted by the work order system for the work order is received and sent to the associated processing personnel or assisting personnel.

9. The work order processing method according to claim 1, wherein the development problem text is generated and input by the intelligent customer service platform by extracting keywords from the technical personnel's questions regarding the subroutine development service of the payment application and the interaction text with the customer service; or, The intelligent customer service platform identifies and extracts keywords from the technical staff's questions regarding the subroutine development service of the payment application and the customer service staff's interactive voice, generates and inputs these keywords.

10. A work order processing device, comprising: The issue text acquisition module is configured to acquire and input the development issue text generated by the customer service system based on the interaction information obtained by the technical staff in their interaction with customer service regarding development issues related to the subroutine development service of the payment application. The problem category matching module is configured to input the development problem text into the category matching model for problem category matching, and output the problem category corresponding to the development problem text; the feature extractor of the category matching model is used to extract features from the development problem text to obtain initial features, and the encoder of the category matching model is used to encode the initial features to obtain category features; The personnel set query module is configured to query the associated personnel set and assisting personnel set of the problem category in the category-personnel mapping table based on the problem category; The work order generation module is configured to obtain service data of the subroutine development service corresponding to the development problem text, package the service data to obtain development logs, generate work orders containing the development logs for the associated processing personnel in the associated processing personnel set, and issue the work orders so that the associated processing personnel or assisting processing personnel can load the subroutine development service in the problem state based on the development logs and handle the development problem; the service data includes the program data, error codes, and / or environment variables of the subroutine development service; If a work order transfer request submitted by the associated processing personnel is detected, the work order will be issued to the assisting processing personnel in the set of assisting processing personnel; the problem categories include single-level problem categories and multi-level problem categories.

11. A work order processing device, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: The system obtains and inputs development question texts based on interaction information obtained by technical personnel from their interactions with customer service regarding development issues related to the subroutine development service of the payment application. The development problem text is input into a category matching model for problem category matching, and the problem category corresponding to the development problem text is output. The feature extractor of the category matching model is used to extract features from the development problem text to obtain initial features, and the encoder of the category matching model is used to encode the initial features to obtain category features. Based on the problem category, query the set of associated handlers and the set of assisting handlers mapped to the problem category in the category-handler mapping table; The service data of the subroutine development service corresponding to the development problem text is obtained. The service data is packaged to obtain development logs. A work order containing the development logs is generated for the associated processing personnel in the associated processing personnel set. The work order is issued so that the associated processing personnel or assisting processing personnel can load the subroutine development service in the problem state based on the development logs and handle the development problem. The service data includes the program data, error codes and / or environment variables of the subroutine development service. If a work order transfer request submitted by the associated processing personnel is detected, the work order will be issued to the assisting processing personnel in the set of assisting processing personnel; the problem categories include single-level problem categories and multi-level problem categories.

12. A storage medium for storing computer-executable instructions, which, when executed by a processor, perform the following process: The system obtains and inputs development question texts based on interaction information obtained by technical personnel from their interactions with customer service regarding development issues related to the subroutine development service of the payment application. The development problem text is input into a category matching model for problem category matching, and the problem category corresponding to the development problem text is output. The feature extractor of the category matching model is used to extract features from the development problem text to obtain initial features, and the encoder of the category matching model is used to encode the initial features to obtain category features. Based on the problem category, query the set of associated handlers and the set of assisting handlers mapped to the problem category in the category-handler mapping table; The service data of the subroutine development service corresponding to the development problem text is obtained. The service data is packaged to obtain development logs. A work order containing the development logs is generated for the associated processing personnel in the associated processing personnel set. The work order is issued so that the associated processing personnel or assisting processing personnel can load the subroutine development service in the problem state based on the development logs and handle the development problem. The service data includes the program data, error codes and / or environment variables of the subroutine development service. If a work order transfer request submitted by the associated processing personnel is detected, the work order will be issued to the assisting processing personnel in the set of assisting processing personnel; the problem categories include single-level problem categories and multi-level problem categories.

Images