Work order allocation method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a work order allocation method, electronic equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence, the method comprises the following steps: identifying key entity information in a target work order, and retrieving associated knowledge of the target work order from a preset knowledge base based on the key entity information; inputting the target work order, the associated knowledge and the work order allocation prompt information into a work order allocation model, so that the work order allocation model performs work order allocation based on the associated knowledge and the work order allocation prompt information to obtain a target business system allocated to the target work order; querying personnel configuration information of the target service system to determine a person in charge of the target work order, and obtaining a target person in charge; and pushing the target work order to the workbench of the target person in charge. According to the method, the associated knowledge retrieved based on the key entity information is input into the model, so that the model deeply understands the business logic behind the work order, multiple features and context information of the work order are considered, intelligent matching and reasoning are performed, and the work order distribution accuracy is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of artificial intelligence technology, and in particular to a work order allocation method, electronic device, storage medium and program product. Background Technology

[0002] Financial institutions generate a large number of business event orders every day, covering multiple areas such as account management, transaction processing, and risk control. Given this massive volume of business, the efficient and accurate allocation of these business event orders directly impacts a financial institution's response speed, resource allocation, and customer service quality.

[0003] The current automatic event ticket allocation scheme is based on keyword retrieval technology. This involves extracting keywords from the event ticket description and matching them against a pre-defined application system keyword database to allocate the event ticket. For example, extracting "printer configuration" from the event ticket and matching it against the "business printing management system" category in the database, finally assigning the event ticket to the corresponding application support department. While this method is simple and fast, it suffers from low allocation accuracy. For instance, when keywords in the event ticket description are ambiguous, missing, or have multiple meanings, the accuracy of the matching results drops significantly. Furthermore, when dealing with event tickets involving complex transaction processes, this method cannot deeply understand the underlying business logic, leading to a relatively high probability of allocation errors. Summary of the Invention

[0004] This invention provides a work order allocation method, electronic device, storage medium, and program product, which can improve the accuracy of work order allocation.

[0005] In a first aspect, the work order allocation method provided in the embodiments of the present invention includes:

[0006] Identify key entity information in the target work order, and retrieve related knowledge of the target work order from a pre-set knowledge base based on the key entity information;

[0007] Input the target work order, related knowledge, and work order allocation prompts into the work order allocation model so that the work order allocation model can allocate work orders based on the related knowledge and work order allocation prompts, thereby obtaining the target business system to which the target work order is allocated.

[0008] Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the target person in charge;

[0009] Push the target work order to the workbench of the person responsible for the target.

[0010] Secondly, the work order allocation device provided in the embodiments of the present invention includes:

[0011] The retrieval module is used to identify key entity information in the target work order and retrieve related knowledge of the target work order from a preset knowledge base based on the key entity information.

[0012] The allocation module is used to input the target work order, related knowledge, and work order allocation prompt information into the work order allocation model, so that the work order allocation model can allocate the work order based on the related knowledge and work order allocation prompt information to obtain the target business system to which the target work order is allocated.

[0013] The query module is used to query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the target person responsible.

[0014] The push module is used to push target work orders to the workbench of the person in charge of the target.

[0015] Thirdly, the electronic device provided in the embodiments of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the work order allocation method as described in any embodiment of the present invention.

[0016] Fourthly, the computer-readable storage medium provided in the embodiments of the present invention stores a computer program thereon, which, when executed by a processor, implements the work order allocation method as described in any embodiment of the present invention.

[0017] Fifthly, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the work order allocation method as described in any embodiment of the present invention.

[0018] In this embodiment of the invention, by identifying key entity information in the target work order and retrieving related knowledge from a preset knowledge base, the work order allocation model can deeply understand the business logic behind the work order. For example, for work orders involving complex transaction processes, the business process information in the related knowledge can be combined to accurately determine the business system to which the work order belongs, rather than relying solely on surface matching of keywords, thereby significantly improving the accuracy of work order allocation. The work order allocation model allocates work orders based on related knowledge and work order allocation prompts, comprehensively considering various characteristics and contextual information of the work order for intelligent matching and reasoning. This allows the model to make accurate allocation decisions even when faced with ambiguous, missing, or multi-meaning keywords. After accurately allocating the work order to the target business system, the personnel configuration information of the target business system is further queried to determine the person responsible for the work order. This precise responsibility determination mechanism ensures that the work order can be directly assigned to the most suitable personnel, avoiding the possibility of work orders being repeatedly transferred between departments, thus improving resource utilization efficiency. By clearly defining the person responsible for the work order, financial institutions can better understand the workload and professional skill matching of each position, thereby rationally allocating and optimizing personnel and improving overall work efficiency. In addition, the present invention significantly reduces the need for manual intervention through an intelligent work order allocation process, enabling customers' problems to be responded to and handled by professionals more quickly, thereby improving the quality and efficiency of problem solving. Attached Figure Description

[0019] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the work order allocation method provided in an embodiment of the present invention;

[0021] Figure 2 This is another flowchart illustrating the work order allocation method provided in this embodiment of the invention;

[0022] Figure 3 This is an example diagram of an application scenario of the work order allocation method provided in this embodiment of the invention;

[0023] Figure 4 This is a schematic diagram of a work order allocation device provided in an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Figure 1 This is a flowchart illustrating a work order allocation method provided in an embodiment of the present invention. This method is applicable to scenarios involving the automatic allocation of work orders generated from financial transactions. The work order allocation method can be executed by a work order allocation device provided in this embodiment, which can be implemented using software and / or hardware. In a specific embodiment, this device can be integrated into an electronic device, such as a computer or server. The following embodiment uses the integration of the work order allocation device into an electronic device as an example. See also... Figure 1 The work order allocation method in this embodiment may include the following steps:

[0028] Step 101: Identify key entity information in the target work order, and retrieve related knowledge of the target work order from the preset knowledge base based on the key entity information.

[0029] A work order is a document or record used to document, track, and manage specific tasks or issues. It is widely used in the operation and management of enterprises and organizations, with the core purpose of ensuring that tasks or issues are processed and resolved efficiently and accurately. The main components of a work order may include:

[0030] Work order number: Used to identify a work order, making it easy to quickly find and track it in the system.

[0031] Work order type: Describes the nature of the work order, such as fault report, service request, change request, inquiry, etc.

[0032] Work order description: Provide a detailed description of the work order, including the details of the problem, the requirements of the task, and the customer's needs.

[0033] Priority: Set according to the urgency and importance of the work order, such as high, medium and low, to help the staff arrange the work order reasonably.

[0034] Status: Reflects the progress of work order processing, such as new, assigned, in process, completed, closed, etc.

[0035] Creation Time: Records the time when the work order was generated, used to track processing time.

[0036] A target work order refers to a work order that needs to be processed and assigned at present. In a financial scenario, a target work order might be a transaction exception work order submitted by a customer, such as a customer reporting that their credit card was charged twice in a certain transaction.

[0037] Entity information refers to identifiable objects or concepts with specific meaning in text or data. These entities are typically concrete things, attributes, or actions mentioned in the text, such as names of people, places, dates, times, organization names, product names, and operational actions. Entity information is an important concept in natural language processing, used to help computers understand the semantics of text. Key entity information refers to information about entities in a work order description that plays a crucial role in understanding the work order content and determining its processing direction. This can include the business system name, operational actions, error codes, business terminology, etc. For example, in a work order for duplicate credit card charges, key entity information might include "credit card system," "duplicate charge," "transaction serial number," and "error code 1234."

[0038] Specifically, identifying the key entity information in the target work order can include three stages: text preprocessing, entity recognition, and criticality assessment. In the text preprocessing stage, the work order text can be tokenized to split it into words or phrases; common meaningless words can be removed, such as "de", "shi", "he", etc., to reduce interference; the词性 of each word can be marked, such as noun, verb, adjective, etc., to help identify possible entities. In the entity recognition stage, regular expressions or predefined rules can be used to identify entities in specific formats, such as dates, account numbers, etc.; machine learning or deep learning models can be used to identify named entities, and these models can identify common entity types such as person names, place names, organization names, product names, etc.; domain knowledge bases or domain models can be used to identify domain-specific entities, such as account numbers and transaction codes in the financial domain. In the criticality assessment stage, the importance of an entity in the text can be judged by combining context information; for example, if an entity appears multiple times or is closely related to the business logic, it is a key entity; the key entities can be determined according to the rules of the business scenario; for example, in financial transactions, the transaction amount and account number are usually key entities; machine learning models can also be used to score the importance of the identified entities and screen out the key entities.

[0039] The preset knowledge base is a pre-constructed database containing a large amount of business-related knowledge. In the financial scenario, it may contain information such as financial business processes, system architectures, common problems and solutions, business rules, and the interaction relationships between systems. For example, the knowledge base may record the transaction processing process of the credit card system, the interface information with the third-party payment system, the meanings and handling methods of different error codes, etc. Associated knowledge refers to the knowledge content related to the key entity information of the target work order, and this knowledge can help further understand the background of the work order, the problem area, and possible solutions. For example, for a work order of repeated credit card deductions, the associated knowledge may include the handling rules for repeated deductions in the credit card system, the method for querying the status of the third-party payment system related to this transaction, and the handling cases of historical similar problems.

[0040] Keyword matching can be used to retrieve related knowledge. This involves using extracted key entity information as keywords to match within the knowledge base. For example, searching for business processes and common problems related to "credit card system," searching for handling methods and solutions for "duplicate charges," and searching for the definition and common causes of "error code 1234." Beyond simple keyword matching, semantic retrieval technology can be used to understand the relationships and context between key entities. For instance, if "duplicate charges" and "error code 1234" appear simultaneously, the knowledge base can be searched for related entries, retrieving business rules and processing procedures related to "duplicate charges" in the "credit card system." From the retrieved knowledge, the most relevant parts to the target work order are selected. For example, the specific meaning and handling suggestions of "error code 1234" in the credit card system can be extracted, as well as common causes and solutions for "duplicate charges," and transaction records and historical processing cases related to "transaction serial number 123456789" can be extracted. The selected knowledge is then integrated into the related knowledge for the target work order.

[0041] For example, if the target work order is a duplicate credit card charge, the associated knowledge retrieved for the target work order can be as follows:

[0042] Error code 1234 means that the transaction failed during the settlement process, but the payment was successfully deducted.

[0043] The procedure for handling duplicate charges is as follows: First, confirm the status of transaction number 123456789 and check whether it is due to duplicate submission or system failure.

[0044] The process for handling duplicate charges in a credit card system is as follows: contact the payment system to confirm the transaction status, roll back the duplicate charge, and notify the customer of the processing result.

[0045] Historical case: Similar issues have occurred where duplicate charges were caused by abnormal status returned by the third-party payment system. The solution was to contact the payment system's technical support.

[0046] Step 102: Input the target work order, related knowledge, and work order allocation prompt information into the work order allocation model so that the work order allocation model can allocate work orders based on the related knowledge and work order allocation prompt information, thereby obtaining the target business system to which the target work order is allocated.

[0047] Work order allocation prompts, also known as guidance words, can be understood as text that provides clear instructions and guidance to the model, helping it better understand and process work order allocation tasks. Work order allocation prompts can be templated instructions or dynamically generated by combining templated instructions with specific search content, guiding the model to focus on key information and thus make more accurate allocation decisions.

[0048] Templated instructions are predefined, structured texts used to explicitly tell the model the task it needs to perform. It is typically a general framework that can be tailored to specific situations. For example:

[0049] "Based on the following event description and related knowledge fragments, determine the application system to which it belongs."

[0050] "Based on the error code and transaction serial number, the work order will be assigned to the appropriate processing team."

[0051] "Based on the priority and urgency of the work order, we decide which business system to assign it to."

[0052] These templated instructions provide the model with clear task objectives, enabling it to know what information to focus on and make decisions accordingly.

[0053] The retrieved content refers to specific information related to the target work order extracted from a pre-defined knowledge base. This information provides the model with the background and details for processing the work order, helping the model better understand the context of the work order. For example, if the target work order is a case of duplicate credit card charges, the retrieved content could include:

[0054] Key entity information: such as error code 1234, transaction serial number 123456789, amount 5000 yuan, etc.

[0055] Related knowledge: such as the definition of error code 1234, methods for handling duplicate charges, historical cases, etc.

[0056] Work order description: For example, "A customer reported that his credit card was charged twice on July 1, 2024, for a transaction amount of 5,000 yuan. The transaction number is 123456789 and the error code is 1234."

[0057] Dynamic prompt design combines templated instructions with specific search content to generate a complete prompt message to guide the model's decision-making process. This design can dynamically adjust according to different work order content and scenarios, ensuring that the model can focus on key information and make accurate allocation decisions.

[0058] Combining templated instructions and search content, the generated dynamic prompts can be:

[0059] Based on the following event description and related knowledge fragments, determine the relevant application system: A customer reported that their credit card was charged twice on July 1, 2024, for a transaction of 5,000 yuan. The transaction serial number is 123456789, and the error code is 1234. Error code 1234 indicates that the transaction failed during the clearing process, but the deduction was successful. The solution is to check the status of transaction serial number 123456789 to see if it was due to a duplicate submission or a system malfunction. Historical cases show that similar issues have occurred due to abnormal status returns from third-party payment systems, leading to duplicate deductions. The solution in those cases was to contact the payment system's technical support.

[0060] Dynamic prompts can clarify task objectives, provide key information, and guide the decision-making process. Specifically, they tell the model the task to be completed, such as determining the application system to which the work order belongs. By integrating key information from the work order description and related knowledge, the model can focus its efforts and make accurate allocation decisions through clear instructions and detailed background information.

[0061] A work order assignment model is a system based on machine learning or rule engines that automatically determines which business system or processing team to assign a work order to based on the input work order content, related knowledge, and prompts. It typically combines historical data and business rules for intelligent decision-making. The target business system refers to the business system to which the target work order is ultimately assigned; it is responsible for handling the specific issue of the target work order. In a financial scenario, the target business system might be a credit card system, a payment system, or a clearing system. For example, if the work order involves a credit card transaction issue, the target business system might be the credit card system. If the work order involves a payment system returning an abnormal status, the target business system might be the payment system.

[0062] The work order allocation model can make inference decisions based on input data. The specific steps are as follows:

[0063] Application work order assignment prompts: Parse the prompts to clarify the tasks that need to be completed.

[0064] Understanding work order content: Work order descriptions can be parsed using word segmentation, part-of-speech tagging, and named entity recognition to extract key information, understand the semantics of the work order, and identify the core content of the problem.

[0065] Apply related knowledge: Match the extracted key entity information with related knowledge to find relevant processing methods, error code definitions, etc.

[0066] System and Dependency Identification: Identify the business systems involved in the work order, such as credit card systems and payment systems, analyze the dependencies between systems, and determine the processing order and allocation logic.

[0067] Work order allocation decision: Based on the extracted features and related knowledge, possible processing teams or business systems are scored and ranked. Combined with business rules (such as priority, urgency, etc.), the most suitable processing team or business system is selected to generate work order allocation results. The work order allocation results may include the target business system to which the target work order is assigned, and may also include the basis for work order allocation.

[0068] Step 103: Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the target person responsible.

[0069] Personnel configuration information refers to detailed information about personnel in the target business system, which may include, but is not limited to:

[0070] Personnel list: All personnel in the system who may handle work orders.

[0071] Roles and Responsibilities: The specific roles of each person (such as technical support, customer service, system administrator, etc.) and their scope of responsibilities.

[0072] Skills and expertise: The professional skills of the personnel and the types of problems they are good at handling.

[0073] Workload: The current workload of each employee and the number of work orders being processed.

[0074] Availability: The current status of personnel (e.g., online, offline, busy, etc.).

[0075] For example, in a credit card system, the following personnel configuration information may be available:

[0076] Personnel A: Technical support, skilled in handling transaction issues, currently with a low workload.

[0077] Personnel B: Customer service representative, skilled in communicating with customers, currently handling other customer inquiries.

[0078] Personnel C: System administrator, responsible for system maintenance and troubleshooting, currently online.

[0079] The person ultimately responsible for handling a target work order is the specific individual assigned to do so. This person is required to take appropriate action to resolve the issue based on the content and requirements of the work order. For example, in the aforementioned work order regarding duplicate credit card charges, after querying and analyzing personnel configuration information, it was ultimately decided to assign the work order to person A (technical support) because person A is skilled at handling transaction issues and currently has a low workload. Therefore, person A is the person ultimately responsible for handling the target work order.

[0080] By querying the personnel configuration information of the target business system, and combining this information with the specific content of the work order and the personnel's skills, workload, and availability, the most suitable person to handle the work order can be accurately identified. This process ensures that work orders are processed efficiently and accurately, thereby improving customer satisfaction and overall operational efficiency.

[0081] Step 104: Push the target work order to the workbench of the person in charge of the target.

[0082] A workbench refers to the interface or platform used by the responsible person to process work orders. It is typically an integrated system that provides detailed work order information, processing tools, and historical records to help the responsible person complete tasks efficiently. In a financial context, the workbench might be the internal management interface of a credit card system, through which the responsible person can view work order details, handle issues, record processing progress, and communicate with customers.

[0083] Specifically, the system can obtain the workbench information of the responsible party, including the workbench address, login method, and notification mechanism. Based on this, detailed information about the target work order can be pushed to the responsible party's workbench. The pushed information may include: work order number, work order description, assignment basis, processing suggestions, and relevant attachments or links. The system can use workbench notification mechanisms (such as pop-ups, emails, and SMS) to notify the responsible party of new work orders requiring processing. The responsible party can then view the work order details on their workbench and begin processing the work order. Through this process, the responsible party can view detailed work order information on their workbench and efficiently resolve issues based on the processing suggestions and assignment basis provided by the system.

[0084] In this embodiment, by identifying key entity information in the target work order and retrieving related knowledge from a pre-set knowledge base, the work order allocation model can gain a deeper understanding of the business logic behind the work order. For example, for work orders involving complex transaction processes, the business process information in the related knowledge can be combined to accurately determine the system to which the work order belongs, rather than relying solely on surface-level keyword matching, thereby significantly improving the accuracy of work order allocation. The work order allocation model allocates work orders based on related knowledge and work order allocation prompts, comprehensively considering various characteristics and contextual information of the work order for intelligent matching and reasoning. This allows the system to make accurate allocation decisions even when faced with ambiguous, missing, or multi-meaning keywords. After accurately allocating the work order to the target business system, the personnel configuration information of the target business system is further queried to determine the person responsible for the work order. This precise responsibility determination mechanism ensures that the work order can be directly assigned to the most suitable personnel, avoiding the possibility of work orders being repeatedly transferred between departments, thus improving resource utilization efficiency. By clearly defining the person responsible for the work order, financial institutions can better understand the workload and professional skill matching of each position, thereby rationally allocating and optimizing personnel and improving overall work efficiency. In addition, the present invention significantly reduces the need for manual intervention through an intelligent work order allocation process, enabling customers' problems to be responded to and handled by professionals more quickly, thereby improving the quality and efficiency of problem solving.

[0085] The following is combined Figure 2 and Figure 3 The following example further illustrates the work order allocation method provided in the embodiments of the present invention. Figure 2 This is another flowchart illustrating the work order allocation method provided in this embodiment of the invention. Figure 3 This is an example diagram of an application scenario of the work order allocation method provided in the embodiments of the present invention.

[0086] In practical applications, some work orders need to be split before allocation, while others can be allocated directly without splitting. This example illustrates the work order allocation process using the need for work order splitting as an example. In practice, whether a work order needs to be split depends on various factors, including the number of business systems involved, the temporal dependencies of operations, and the mandatory splitting rules in the knowledge base. Generally, situations requiring work order splitting include:

[0087] (1) Involving multiple systems. If a work order involves multiple business systems, and each system needs to handle different tasks independently, then it needs to be split up.

[0088] For example, regarding a work order for a failed cross-border payment settlement, the work order description is: A customer initiated a cross-border payment, the core system showed the deduction was successful, but the recipient did not receive the funds, and the error code is PAY408. Preliminary analysis indicates the problem involves the following business systems:

[0089] Core system: Responsible for deduction operations and displaying successful deduction.

[0090] Clearing system: responsible for cross-border clearing; error code PAY408 indicates clearing failure.

[0091] Foreign exchange system: responsible for exchange rate calculation, which may involve abnormal exchange rate calculations.

[0092] Because multiple systems are involved, the work order needs to be split into multiple sub-work orders and assigned to different systems respectively.

[0093] (2) There is a time dependency. If the system operations in the work order have a sequential dependency, that is, some tasks can only be performed after other tasks are completed, then they need to be split.

[0094] For the example of a failed cross-border payment clearing order above, the timing dependency might be as follows: first, confirm the deduction status in the core system; then, analyze the error code PAY408 in the clearing system; and finally, check whether the exchange rate calculation in the foreign exchange system is abnormal. Due to the timing dependency, the work order needs to be split into multiple sub-work orders, and it must be ensured that they are processed in the correct order.

[0095] (3) If the knowledge base defines certain mandatory splitting rules for specific situations, then the splitting must be carried out in accordance with these rules.

[0096] For the example of a failed cross-border payment clearing ticket mentioned above, the knowledge base may have defined rules for handling error code PAY408, requiring the processing tasks of the clearing system and the foreign exchange system to be separated.

[0097] If a work order involves only one business system and has no temporal dependencies, then it does not need to be split.

[0098] See Figure 2 This embodiment uses a cross-border payment clearing failure work order as an example to illustrate the need for work order splitting. The work order allocation method in this embodiment may include:

[0099] Step 201: Retrieve multiple original work orders from the work order collection system.

[0100] A work order collection system is a platform for centralized management and storage of work orders. It typically receives, records, and performs initial processing of work orders from various channels. It may be an internal service desk system, a customer relationship management system, or a dedicated work order management system. These systems usually have the following functions:

[0101] Receiving work orders: Receiving work orders from customers, employees, or automated monitoring systems.

[0102] Record work orders: Record detailed information such as the content, source, and timestamp of the work order.

[0103] Preliminary processing: Performing preliminary classification and priority marking operations on work orders.

[0104] In financial settings, a ticket collection system might be a bank's service desk system used to receive questions and requests submitted by customers via telephone, online banking, or mobile applications. For example, if a customer reports an anomaly in their credit card transaction, this request will be recorded in the ticket collection system.

[0105] Original work orders refer to work orders obtained directly from the work order collection system without processing or screening. These work orders contain the original information submitted by the customer or the system.

[0106] Specifically, such as Figure 3 As shown, you can connect to the work order collection system via application programming interface (API), database query, or other data interface. Multiple raw work orders can be retrieved from the system according to preset rules (such as time range, work order status, etc.). The retrieved work orders may include various types of issues and requests, such as customer complaints, system failures, and inquiries. The retrieved raw work orders can be recorded in a local database or processing queue for subsequent processing and analysis. The recorded information may include the work order number, description, submission time, and submitter.

[0107] Step 202: Select the target work order from multiple original work orders based on the multidimensional feature information of each original work order.

[0108] Multidimensional feature information of a work order refers to the various attributes and characteristics used to describe the work order. These characteristics can reflect the nature and importance of the work order from multiple perspectives. For example, multidimensional feature information may include:

[0109] Work order types: such as fault reporting, inquiries, complaints, etc.

[0110] Priority: such as high, medium, low, indicating the urgency of the work order.

[0111] Submission Time: The specific time the work order was submitted, used to determine the timeliness of the work order.

[0112] Work order sources: such as customer submissions, automatic system triggers, employee reports, etc.

[0113] Systems involved: Business systems involved in the work order, such as core systems, clearing systems, foreign exchange systems, etc.

[0114] Error code: The error code mentioned in the work order, such as PAY408.

[0115] Amount: The transaction amount involved, such as 5,000 yuan.

[0116] Customer Information: Information about the customer who submitted the work order, such as customer level and historical transaction records.

[0117] Target work orders are those that have been screened and require further processing. These work orders typically meet specific screening criteria, such as high priority, involvement of critical systems, or specific error codes. Target work orders are the focus of subsequent processing flows.

[0118] Specifically, filtering rules can be defined based on business needs and processing capacity. These rules can be based on multi-dimensional characteristics of the work order, such as priority, work order type, systems involved, and error codes. For example, a filtering rule could be "work orders with high priority and involving core systems".

[0119] It can obtain multi-dimensional feature information for each original work order, such as work order type, priority, submission time, involved systems, and error codes. This multi-dimensional feature information is matched against preset filtering rules to determine if each original work order meets the filtering criteria. Work orders that meet the criteria are then selected as target work orders. There can be one or more target work orders. For example, from 100 original work orders, 10 target work orders that meet the criterion of "high priority and involving core systems" can be selected.

[0120] By defining filtering rules, extracting multi-dimensional feature information, and applying these rules to filter target work orders, it is possible to efficiently identify work orders that require priority attention, thereby improving processing efficiency and quality. This process ensures the targeted and effective processing of work orders.

[0121] Step 203: Identify key entity information in the target work order and retrieve the original knowledge from the preset knowledge base using the key entity information.

[0122] Raw knowledge refers to all knowledge entries related to the target work order retrieved from a pre-defined knowledge base. These knowledge entries may contain a large amount of information, but have not yet been filtered or refined. For example, the raw knowledge retrieved from the knowledge base might include:

[0123] The definition of error code PAY408: It indicates that the transaction failed during the clearing process, but the payment was successfully deducted.

[0124] Solution: Confirm the status of the transaction serial number, contact the payment system to confirm the transaction status, and roll back the duplicate deduction.

[0125] Historical Cases: Records of how similar problems were handled in the past.

[0126] System information: This involves the core system, clearing system, and foreign exchange system.

[0127] Business rules: The priority and urgency that must be followed when handling this issue.

[0128] By identifying key entity information and retrieving original knowledge, detailed background information and processing suggestions can be provided for subsequent work order processing.

[0129] Step 204: Compress the original knowledge to obtain the associated knowledge of the target work order.

[0130] Compression processing refers to the screening and refinement of raw knowledge, removing redundant information and extracting the core content most relevant to the target work order. The purpose of compression processing is to improve the relevance and practicality of knowledge and reduce information overload. For example, the following core content can be extracted from the raw knowledge mentioned above:

[0131] The definition of error code PAY408: It indicates that the transaction failed during the clearing process, but the payment was successfully deducted.

[0132] Solution: Confirm the status of the transaction serial number, contact the payment system to confirm the transaction status, and roll back the duplicate deduction.

[0133] Relevant knowledge refers to the core knowledge that is most relevant to the target work order after compression.

[0134] In one specific implementation, the top few pieces of knowledge with the highest relevance can be selected as associated knowledge based on relevance ranking. For example, natural language processing techniques can be used to calculate the relevance score between key entity information and each piece of knowledge in the knowledge base. The knowledge items are then ranked according to the relevance scores, with the highest-scoring knowledge items at the top. The top three pieces of knowledge with the highest relevance scores are then selected as associated knowledge.

[0135] In another specific embodiment, content can be aggregated into representative topic units by identifying semantic similarity between knowledge fragments, eliminating redundant descriptions. For example, each knowledge fragment can be converted into a high-dimensional vector to capture deep semantics. A density clustering algorithm is then used to automatically group fragments with similar content based on vector similarity, forming topic clusters. Within each topic cluster, the sentence with the highest average similarity to other fragments within the cluster is selected as the representative, forming compressed knowledge.

[0136] In a specific embodiment, key entity types can be predefined based on the decision-making requirements of financial work orders, retaining only the core relationship chains between entities. For example, a domain entity recognition module can be used to extract system names (e.g., clearing system), error codes (e.g., PAY408), business actions (e.g., "clearing"), and numerical indicators (e.g., "1000 transactions") from knowledge. Based on preset rules (e.g., "error codes must be associated with handling actions"), valid relationships between entities are filtered, and descriptive text is discarded. The retained entities are then logically concatenated into concise statements, forming an "entity-relationship-entity" chain.

[0137] Step 205: Input the target work order, related knowledge, and work order allocation prompts into the work order allocation model.

[0138] like Figure 3 As shown, the inputs to the work order allocation model include the target work order, related knowledge, and work order allocation prompts.

[0139] Step 206: Use the work order allocation model to identify the multiple business systems involved in the target work order and the dependencies between the multiple business systems based on association knowledge.

[0140] Multiple business systems refer to the various business processing systems involved in the target work order. These systems are typically responsible for handling specific business processes, such as the core system, clearing system, and foreign exchange system. Dependency refers to the sequential or logical relationship between multiple business systems when processing work orders. Some tasks must be completed before others can be performed; this sequential relationship is called a dependency. For example, when processing a target work order, the deduction status in the core system must be confirmed first, then the error code PAY408 in the clearing system can be analyzed, and finally, the exchange rate calculation in the foreign exchange system must be checked for anomalies. The purpose of this process is to ensure that work orders are correctly allocated to the various business systems and processed in the correct order, thereby improving processing efficiency and quality.

[0141] Specifically, keyword matching technology can be used to identify multiple business systems involved in a target work order. This involves extracting keywords related to the business systems from associated knowledge, such as system names and function descriptions, and then matching these extracted keywords with a pre-defined list of business systems to identify the relevant systems. For example, if the keywords extracted from associated knowledge include "core system," "clearing system," and "foreign exchange system," the model can identify that the target work order involves these systems.

[0142] Natural language processing (NLP) technology can also be used to perform semantic understanding on associated knowledge, extract semantic information related to business systems, and identify the business systems involved based on the semantic information. For example, semantic understanding can identify "core system responsible for deduction operations," "clearing system responsible for transaction clearing," and "foreign exchange system responsible for exchange rate calculation" mentioned in the associated knowledge, thereby determining that these target work orders involve "core system," "clearing system," and "foreign exchange system."

[0143] Based on business processes and historical data, dependency rules between business systems can be preset. The work order allocation model can then match the identified business systems with these preset dependency rules to determine the dependencies. Alternatively, each business system and its operations can be represented as nodes and edges in a graph model. By analyzing the paths between the current business systems using the graph model, the processing order can be determined, thereby obtaining the dependencies.

[0144] Based on the identified business systems and dependencies, the order of work order processing can be generated. The processing order can be represented in the form of a list or diagram, clearly indicating the processing tasks and their order of priority for each system.

[0145] Step 207: Using the work order allocation model, the target work order is split into multiple sub-work orders based on multiple business systems and the dependencies between them.

[0146] A sub-work order refers to a target work order broken down into multiple independent work orders. Each sub-work order corresponds to a business system or a specific processing task. The purpose of sub-work orders is to decompose complex work orders into multiple simple tasks for easier processing. For example, a target work order is broken down into the following sub-work orders:

[0147] Sub-work order 1: The core system confirms the deduction status.

[0148] Sub-work order 2: Clearing system analysis error code PAY408.

[0149] Sub-work order 3: Check if the exchange rate calculation is abnormal in the foreign exchange system.

[0150] Step 208: Use the work order allocation model to allocate each sub-work order based on the work order allocation prompt information and related knowledge to obtain the work order allocation result. The work order allocation result includes the target business system and allocation basis for each sub-work order.

[0151] The work order allocation result refers to the final allocation decision generated by the work order allocation model based on the input prompts and related knowledge. The allocation result typically includes:

[0152] Target business system: The specific business system to which each sub-work order is assigned.

[0153] Allocation Basis: The basis for the model to make allocation decisions, such as the definition of error codes, handling methods, business rules, etc.

[0154] For example, the work order assignment results might include:

[0155] Sub-work order 1 is assigned to the core system based on "confirmed deduction status".

[0156] Sub-work order 2 was assigned to the settlement system based on "analysis error code PAY408".

[0157] Sub-work order 3 was assigned to the foreign exchange system based on the principle of "checking whether the exchange rate calculation is abnormal".

[0158] The output allocation criteria clearly demonstrate how the work order allocation model makes decisions. Processing personnel can clearly see the reasons why each sub-work order is assigned to a specific business system, rather than just seeing the allocation result, significantly improving the transparency, traceability, and quality of work order processing. Furthermore, the output allocation criteria provide reviewers with clear references, enabling them to quickly verify the rationality of allocation decisions. If allocation errors are found, the problem can be quickly located and adjusted. Processing personnel can directly begin processing tasks based on the allocation criteria without needing to reanalyze the work order content, thus saving time and effort.

[0159] Step 209: Send the work order assignment results to the review end for review.

[0160] The review panel refers to the system or team responsible for reviewing the work order assignment results. This panel can consist of experienced managers or a dedicated review team, who are responsible for verifying the accuracy and reasonableness of the assignment results. This process can improve the quality and reliability of work order processing, reducing misassignment and mishandling.

[0161] Step 210: Obtain the review results of the work order allocation from the review end.

[0162] The review result refers to the verification and evaluation result of the work order allocation by the review end. The review result can be either pass or fail. The review personnel or system on the review end receive the allocation result and conduct a detailed review. The review content may include: verifying whether the target business system is correct, checking whether the allocation basis is reasonable, whether it conforms to business rules and processing procedures, and confirming whether the allocation result matches the priority and urgency of the work order. The review result can be obtained through internal networks, message queues, or API calls, etc.

[0163] Step 211: Determine whether the audit result is passed. If it is passed, proceed to step 212; otherwise, proceed to step 216.

[0164] A "pass" result indicates that the allocation meets the requirements; a "fail" result indicates that adjustments are needed.

[0165] Step 212: Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain multiple candidate persons responsible.

[0166] Candidate responsible persons refer to multiple individuals initially selected after querying the personnel configuration information of the target business system who are likely to handle the target work order. These individuals typically possess the skills and permissions required to handle the work order, but further screening is needed to determine the final responsible person.

[0167] Step 213: Select the target responsible person from multiple candidate responsible persons based on the multidimensional feature information of each candidate responsible person.

[0168] Multidimensional characteristic information of responsible persons refers to the various attributes and characteristics used to describe each candidate responsible person. These characteristics can reflect the candidate's capabilities and status from multiple perspectives. For example, multidimensional characteristic information includes:

[0169] Skills and expertise: The types of problems that the candidate is good at handling.

[0170] Workload: The current workload of each employee and the number of work orders being processed.

[0171] Availability: The current status of personnel (e.g., online, offline, busy, etc.).

[0172] Processing history: The success rate and efficiency of personnel in handling similar work orders in the past.

[0173] Roles and Responsibilities: The specific roles of each person (such as technical support, customer service, system administrator, etc.) and their scope of responsibilities.

[0174] The person ultimately responsible for a target work order is the specific individual assigned to handle that work order. This person is required to take appropriate actions to resolve the issue based on the content and requirements of the work order.

[0175] Specifically, the multidimensional characteristics of each candidate responsible can be evaluated based on preset rules or models. The evaluation may include:

[0176] Skills matching: Whether the candidate's skills meet the requirements of the work order.

[0177] Workload: Is the current workload of the candidate responsible low?

[0178] Availability: Whether the candidate responsible is currently online.

[0179] Processing history: The success rate and efficiency of the candidate in handling similar work orders in the past.

[0180] Based on the evaluation results, the most suitable person to handle the target work order is selected from multiple candidate responsible persons.

[0181] By acquiring multidimensional characteristic information of candidate responsible persons, evaluating these characteristics, and screening out the target responsible persons, we can ensure that work orders are assigned to the most suitable personnel, thereby improving processing efficiency and quality.

[0182] Step 214: Generate processing suggestions for the target work order based on the processing records of historical work orders.

[0183] Historical work order processing records refer to detailed records of similar work orders processed in the past, including information such as the work order content, processing steps, solutions, results, and personnel involved. These records are typically stored in the historical database of the work order management system and are an important part of enterprise knowledge management and experience accumulation. Historical work order processing records may include:

[0184] Work order number: 20240630-001.

[0185] Work order details: Customer reports abnormal credit card transaction, error code PAY408.

[0186] Processing steps: Confirm the transaction serial number status, contact the payment system to confirm the transaction status, and roll back duplicate deductions.

[0187] Outcome: Problem resolved, customer satisfied.

[0188] Personnel handling the matter: Personnel A.

[0189] Processing suggestions refer to the processing methods and recommendations generated for the current target work order based on the processing records of historical work orders. These suggestions typically include specific processing steps, solutions, and precautions, aiming to help processing personnel resolve problems quickly and effectively.

[0190] Step 215: Push the target work order and its processing suggestions to the workbench of the person responsible for the target work order.

[0191] The purpose of this process is to ensure that the responsible party receives detailed information about the work order and processing suggestions in a timely manner, so as to resolve the problem quickly and effectively.

[0192] Step 216, manual processing.

[0193] If the review result is "not approved," the work order will be transferred to manual processing. Specifically, in cases where automatic assignment fails or the review is not approved, manual intervention can be used to ensure that the work order is processed correctly.

[0194] In this embodiment, by identifying key entity information in the target work order and retrieving related knowledge from a pre-set knowledge base, the work order allocation model can gain a deeper understanding of the business logic behind the work order. For example, for work orders involving complex transaction processes, the business process information in the related knowledge can be combined to accurately determine the system to which the work order belongs, rather than relying solely on surface-level keyword matching, thereby significantly improving the accuracy of work order allocation. The work order allocation model allocates work orders based on related knowledge and work order allocation prompts, comprehensively considering various characteristics and contextual information of the work order for intelligent matching and reasoning. This allows the system to make accurate allocation decisions even when faced with ambiguous, missing, or multi-meaning keywords. After accurately allocating the work order to the target business system, the personnel configuration information of the target business system is further queried to determine the person responsible for the work order. This precise responsibility determination mechanism ensures that the work order can be directly assigned to the most suitable personnel, avoiding the possibility of work orders being repeatedly transferred between departments, thus improving resource utilization efficiency. By clearly defining the person responsible for the work order, financial institutions can better understand the workload and professional skill matching of each position, thereby rationally allocating and optimizing personnel and improving overall work efficiency. In addition, the present invention significantly reduces the need for manual intervention through an intelligent work order allocation process, enabling customers' problems to be responded to and handled by professionals more quickly, thereby improving the quality and efficiency of problem solving.

[0195] Figure 4 This is a schematic diagram of a work order allocation device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes:

[0196] The retrieval module 401 is used to identify key entity information in the target work order and retrieve related knowledge of the target work order from the preset knowledge base based on the key entity information.

[0197] The allocation module 402 is used to input the target work order, related knowledge and work order allocation prompt information into the work order allocation model, so that the work order allocation model can allocate the work order based on the related knowledge and work order allocation prompt information to obtain the target business system allocated to the target work order.

[0198] Query module 403 is used to query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the target person responsible.

[0199] The push module 404 is used to push target work orders to the workbench of the person in charge of the target.

[0200] In one embodiment, the target work order is obtained by the following method:

[0201] Retrieve multiple original work orders from the work order collection system;

[0202] The target work order is selected from multiple original work orders based on the multidimensional feature information of each original work order.

[0203] In one embodiment, the retrieval module 401 retrieves the associated knowledge of the target work order from a preset knowledge base based on key entity information, including:

[0204] Retrieve original knowledge from a pre-set knowledge base using key entity information;

[0205] The original knowledge is compressed to obtain the associated knowledge of the target work order.

[0206] In one embodiment, the allocation module 402 inputs the target work order, associated knowledge, and work order allocation prompt information into the work order allocation model, so that the work order allocation model allocates work orders based on the associated knowledge and work order allocation prompt information, thereby obtaining the target business system allocated to the target work order, including:

[0207] Input the target work order, related knowledge, and work order allocation prompts into the work order allocation model;

[0208] The work order allocation model is used to identify multiple business systems involved in the target work order and the dependencies between these systems based on association knowledge.

[0209] The work order allocation model is used to split the target work order into multiple sub-work orders based on multiple business systems and the dependencies between them.

[0210] The work order allocation model is used to allocate each sub-work order based on work order allocation prompts and related knowledge, and the work order allocation result is obtained. The work order allocation result includes the target business system and allocation basis for each sub-work order.

[0211] In one embodiment, the device further includes an auditing module, which is used to:

[0212] Send the work order assignment results to the review panel for review;

[0213] Obtain the review results of the work order allocation from the review panel;

[0214] If the review result is approved, the query module 403 is triggered to query the personnel configuration information of the target business system.

[0215] In one embodiment, the query module 403 queries the personnel configuration information of the target business system to determine the person responsible for the target work order, and obtains the target person responsible, including:

[0216] Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain multiple candidate persons responsible.

[0217] The target responsible person is selected from multiple candidates based on the multidimensional characteristic information of each candidate responsible person.

[0218] In one embodiment, the push module 404 is further configured to:

[0219] Processing suggestions for the target work order are generated based on the processing records of historical work orders.

[0220] Push processing suggestions for the target work order to the workbench of the person responsible for the target.

[0221] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0222] The apparatus of this invention, by identifying key entity information in a target work order and retrieving related knowledge from a preset knowledge base, enables the work order allocation model to deeply understand the business logic behind the work order. For example, for work orders involving complex transaction processes, it can accurately determine the system to which the work order belongs by combining business process information in the related knowledge, rather than simply relying on surface matching of keywords, thereby significantly improving the accuracy of work order allocation. The work order allocation model allocates work orders based on related knowledge and work order allocation prompts, comprehensively considering various characteristics and contextual information of the work order, and performing intelligent matching and reasoning. This allows the system to make accurate allocation decisions even when faced with ambiguous, missing, or multiple meanings of keywords. After accurately allocating the work order to the target business system, it further queries the personnel configuration information of the target business system to determine the person responsible for the work order. This precise person-responsibility determination mechanism ensures that the work order can be directly assigned to the most suitable person, avoiding the possibility of work orders being repeatedly transferred between departments, and improving resource utilization efficiency. By clearly defining the person responsible for the work order, financial institutions can better understand the workload and professional skill matching of each position, thereby rationally allocating and optimizing personnel and improving overall work efficiency. In addition, the present invention significantly reduces the need for manual intervention through an intelligent work order allocation process, enabling customers' problems to be responded to and handled by professionals more quickly, thereby improving the quality and efficiency of problem solving.

[0223] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing an electronic device according to embodiments of the present invention. Figure 5The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0224] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computer system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0225] The following components are connected to I / O interface 505: input section 506 including keyboard, mouse, etc.; output section 507 including cathode ray tube, liquid crystal display, etc., and speakers, etc.; storage section 508 including hard disk, etc.; and communication section 509 including network interface card, such as modem, etc. Communication section 509 performs communication processing via a network such as the Internet. Drive 510 is also connected to I / O interface 505 as needed. Removable media 511, such as disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 510 as needed so that computer programs read from them can be installed into storage section 508 as needed.

[0226] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0227] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, etc., or any suitable combination thereof.

[0228] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0229] The modules and / or units described in the embodiments of this invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including a retrieval module, an allocation module, a query module, and a push module. The names of these modules do not necessarily limit the module itself.

[0230] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0231] Identify key entity information in the target work order, and retrieve related knowledge of the target work order from a pre-set knowledge base based on the key entity information; input the target work order, related knowledge, and work order allocation prompts into the work order allocation model so that the work order allocation model can allocate the work order based on the related knowledge and work order allocation prompts to obtain the target business system to which the target work order is allocated; query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the person responsible for the target work order; push the target work order to the work platform of the person responsible for the target work order.

[0232] The technical solution of this invention, by identifying key entity information in the target work order and retrieving related knowledge from a preset knowledge base, enables the work order allocation model to deeply understand the business logic behind the work order. For example, for work orders involving complex transaction processes, the business process information in the related knowledge can be combined to accurately determine the system to which the work order belongs, rather than relying solely on surface matching of keywords, thereby significantly improving the accuracy of work order allocation. The work order allocation model allocates work orders based on related knowledge and work order allocation prompts, comprehensively considering various characteristics and contextual information of the work order for intelligent matching and reasoning. This allows the system to make accurate allocation decisions even when faced with ambiguous, missing, or multi-meaning keywords. After accurately allocating the work order to the target business system, the personnel configuration information of the target business system is further queried to determine the person responsible for the work order. This precise responsibility determination mechanism ensures that the work order can be directly assigned to the most suitable personnel, avoiding the possibility of work orders being repeatedly transferred between departments, thus improving resource utilization efficiency. By clearly defining the person responsible for the work order, financial institutions can better understand the workload and professional skill matching of each position, thereby rationally allocating and optimizing personnel and improving overall work efficiency. In addition, the present invention significantly reduces the need for manual intervention through an intelligent work order allocation process, enabling customers' problems to be responded to and handled by professionals more quickly, thereby improving the quality and efficiency of problem solving.

[0233] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the work order allocation method provided in any embodiment of this invention.

[0234] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0235] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0236] It should be noted that the collection, use, storage, sharing, and transfer of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations, and require notification to the user and obtaining the user's consent or authorization. Where applicable, user personal information has undergone de-identification and / or anonymization and / or encryption technical processing. In addition, a corresponding operation entry is provided for the user to choose to agree to or reject the automated decision result; if the user chooses to reject, the process proceeds to the expert decision-making process.

[0237] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A work order allocation method, characterized in that, include: Identify key entity information in the target work order, and retrieve related knowledge of the target work order from a pre-set knowledge base based on the key entity information; Input the target work order, related knowledge, and work order allocation prompts into the work order allocation model so that the work order allocation model can allocate work orders based on the related knowledge and work order allocation prompts, thereby obtaining the target business system to which the target work order is allocated. Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain the target person in charge; Push the target work order to the workbench of the person responsible for the target.

2. The method according to claim 1, characterized in that, The target work order is obtained through the following method: Retrieve multiple original work orders from the work order collection system; The target work order is selected from multiple original work orders based on the multidimensional feature information of each original work order.

3. The method according to claim 1, characterized in that, Based on key entity information, relevant knowledge about the target work order is retrieved from a pre-defined knowledge base, including: Retrieve original knowledge from a pre-set knowledge base using key entity information; The original knowledge is compressed to obtain the associated knowledge of the target work order.

4. The method according to claim 1, characterized in that, The target work order, associated knowledge, and work order allocation prompts are input into the work order allocation model. This allows the model to allocate work orders based on the associated knowledge and the prompts, resulting in the target business system assigned to the target work order, including: Input the target work order, related knowledge, and work order allocation prompts into the work order allocation model; The work order allocation model is used to identify multiple business systems involved in the target work order and the dependencies between these systems based on association knowledge. The work order allocation model is used to split the target work order into multiple sub-work orders based on multiple business systems and the dependencies between them. The work order allocation model is used to allocate each sub-work order based on work order allocation prompts and related knowledge, and the work order allocation result is obtained. The work order allocation result includes the target business system and allocation basis for each sub-work order.

5. The method according to claim 4, characterized in that, Before querying the personnel configuration information of the target business system, the following is also included: Send the work order assignment results to the review panel for review; Obtain the review results of the work order allocation from the review panel; If the review result is approved, the system will be triggered to query the personnel configuration information of the target business system.

6. The method according to claim 1, characterized in that, Query the personnel configuration information of the target business system to determine the person responsible for the target work order, and obtain the target responsible person, including: Query the personnel configuration information of the target business system to determine the person responsible for the target work order and obtain multiple candidate persons responsible. The target responsible person is selected from multiple candidates based on the multidimensional characteristic information of each candidate responsible person.

7. The method according to claim 1, characterized in that, Also includes: Processing suggestions for the target work order are generated based on the processing records of historical work orders. Push processing suggestions for the target work order to the workbench of the person responsible for the target.

8. 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 program, it implements the work order allocation method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the work order allocation method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the work order allocation method as described in any one of claims 1 to 7.

Images