Method and device for apportionment settlement based on electronic miscellaneous charge invoice service item
By semantic parsing and knowledge graph retrieval of the electronic miscellaneous charges service description field, the service provider type and cost attributes are automatically identified, solving the accuracy and efficiency problems of electronic miscellaneous charges allocation processing in the existing technology, realizing efficient and accurate multi-dimensional settlement, and adapting to the complex aviation revenue settlement needs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ACCOUNTING CENT OF CHINA AVIATION LTD CO
- Filing Date
- 2026-03-17
- Publication Date
- 2026-07-24
Smart Images
Figure CN122453399A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cross-technology of civil aviation information technology and revenue settlement, and in particular to a method and apparatus for apportionment settlement based on electronic miscellaneous fee bill service items. Background Technology
[0002] An Electronic Miscellaneous Document (EMD) is a standardized electronic voucher promoted by the International Air Transport Association (IATA) for collecting ancillary fees beyond the ticket price (such as seat selection fees, baggage fees, in-flight meals, and insurance). In practice, one EMD often corresponds to multiple service items (such as "seat selection + baggage + meals"), and these services may be provided by different airlines (the airline that sold the ticket and the airline that actually operates the flight) or different flight segments.
[0003] In existing aviation revenue settlement systems, the allocation of electronic miscellaneous charges generally relies on preset business type codes or fixed rules, which has the following technical drawbacks: (1) The specific service content carried by the electronic miscellaneous bill cannot be accurately identified, which makes it impossible to confirm who provides the service. This is especially complicated when multiple third parties are involved, requiring multiple communications with the third parties, resulting in high time costs. (2) It is highly dependent on manual intervention. When the electronic miscellaneous expense bill business type is not covered or the rules are missing, manual judgment and manual adjustment of the allocation results are required. This is inefficient, prone to errors, and difficult to meet the audit traceability requirements. (3) The allocation process is inefficient and inaccurate, relying on static rules and manual intervention. It is difficult to dynamically adapt to multi-airline agreements, complex service combinations and real-time flight changes. In high-frequency transaction scenarios, allocation errors, omissions, duplications or delays are likely to occur, leading to difficulties in financial reconciliation, revenue loss or even cross-entity disputes. (4) Lacking flexible configuration and expansion capabilities, it is difficult to adapt to the increasingly diversified and semantic value-added service sales scenarios in the NDC (New Distribution Capability) environment.
[0004] Therefore, there is an urgent need for a method that can parse the service details of electronic miscellaneous charges, dynamically match the allocation rules, and automatically generate multi-dimensional settlement instructions. Summary of the Invention
[0005] This invention provides a method for apportionment settlement based on electronic miscellaneous bill service items, which intelligently parses the service details of electronic miscellaneous bills, improves the accuracy of determining the attribution of service responsibility entities, and enhances the efficiency and accuracy of electronic miscellaneous bill apportionment processing. The method includes: Obtain electronic miscellaneous bill data; the electronic miscellaneous bill data includes the total amount and one or more service item ticket copies, each service item ticket copy including a service description field and an amount; Semantic parsing is performed on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type; By using structured semantic tags to search in a pre-built service catalog knowledge graph, the service provider type and cost attribute of each service item are determined; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; When there are multiple different service provider types, the total amount is allocated to each service item ticket by combining the amounts of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
[0006] This invention also provides a cost-sharing and settlement device based on electronic miscellaneous bill service items, used to intelligently parse the service details of electronic miscellaneous bills, improve the accuracy of determining the attribution of service responsibility entities, and improve the efficiency and accuracy of electronic miscellaneous bill cost-sharing processing. The device includes: The data acquisition module is used to acquire electronic miscellaneous bill data; the electronic miscellaneous bill data includes a total amount and one or more service item ticket slips, each service item ticket slip including a service description field and an amount; The semantic parsing module is used to perform semantic parsing on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type. The graph retrieval module is used to search in a pre-built service catalog knowledge graph using structured semantic tags to determine the service provider type and cost attribute of each service item; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; The apportionment processing module is used to apportion the total amount to each service item ticket when there are multiple different service provider types, by combining the amounts of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
[0007] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described apportionment settlement method based on electronic miscellaneous bill service items.
[0008] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described apportionment settlement method based on electronic miscellaneous fee bill service items.
[0009] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described apportionment settlement method based on electronic miscellaneous fee bill service items.
[0010] In this embodiment of the invention, the service description field in the electronic miscellaneous bill is semantically parsed. Combined with a pre-built service catalog knowledge graph, it can automatically identify the service provider type and cost attributes of each service item. It can intelligently parse the service details of the electronic miscellaneous bill, improve the accuracy of determining the service responsibility subject, and avoid cross-subject settlement mismatch. The entire automatic processing flow, from semantic parsing, determination of the responsible subject and allocation calculation to outputting the final result, reduces the risk of manual operation and labor costs, and significantly improves the efficiency and accuracy of electronic miscellaneous bill allocation processing. Attached Figure Description
[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart illustrating the apportionment and settlement method based on electronic miscellaneous fee bill service items in an embodiment of the present invention; Figure 2 This is a schematic diagram of the service directory knowledge graph in an embodiment of the present invention; Figure 3 This is a schematic diagram of a specific process for cost-sharing settlement in an embodiment of the present invention; Figure 4 This is a schematic diagram of the apportionment settlement device based on electronic miscellaneous fee bill service items in an embodiment of the present invention; Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation
[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.
[0013] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order.
[0014] The acquisition, storage, use, and processing of data in this application all comply with relevant laws and regulations.
[0015] First, the technical terms involved in the embodiments of the present invention will be explained.
[0016] 1. Electronic Miscellaneous Document (EMD): An electronic document developed by the International Air Transport Association (IATA) for processing non-ticketing miscellaneous fees related to air transport, such as excess baggage fees, in-flight catering fees, seat selection fees, or involuntary change / refund fees. The core function of the EMD is to replace the traditional paper Miscellaneous Charges (MCO), enabling the electronic issuance, processing, and settlement of miscellaneous fees. It supports various application scenarios, including the collection of fees for involuntary changes. Its structure is based on the definition in IATA Resolution 725C (2011) and is mainly divided into two types: EMD-A (linked electronic miscellaneous document, directly associated with the flight itinerary) and EMD-S (unlinked electronic miscellaneous document, independent of the specific itinerary). Through electronic processes, the EMD improves the operational efficiency of airlines and distribution channels, reducing the use of paper documents.
[0017] 2. An issue ticket is an electronic ticket that has been successfully issued after payment is completed through standard sales channels (such as airline websites, GDS, travel agencies, etc.), and has not been reissued, cancelled, or refunded, and whose ticket status is "OPEN FORUSE" (can be used).
[0018] 3. A reissue ticket is a new electronic ticket generated when a passenger changes their original ticket (e.g., by altering the flight, date, cabin class, or itinerary) through the airline or authorized agent. The original ticket becomes invalid. A reissue ticket is a derivative ticket relative to a "normal ticket" (the initial ticket sold). Its core purpose is to adjust the itinerary or fare while retaining some of the original ticket's value.
[0019] 4. The Fare Amount refers to the basic price determined by the airline based on its published fare rules for the air transport service purchased by the passenger, excluding any taxes and surcharges. This amount constitutes the airline's main operating revenue and is the core basis for revenue recognition, allocation, auditing, and revenue management.
[0020] 5. Straight Line Proportion (SRP) is a core method for allocating revenue in international air transport settlements. Its basic principle is to allocate the entire fare proportionally to each carrier based on published fares and applicable allocation coefficients. Revenue allocation is based on the allocation coefficients in the published fare manual (such as PMP) corresponding to the original ticketing date, ensuring consistency of rules. The allocation process uses a quotient algorithm, where the allocated amount is divided by the sum of allocation coefficients to obtain a baseline value, with the remainder rounded to five decimal places to accurately calculate each carrier's share. Key elements of allocation include: the allocated amount (the entire fare), the total amount of fixed charges to be deducted, the actual allocated amount (allocated amount minus fixed charges), and the participating flight segments and their respective allocation coefficients; the allocation coefficients are usually determined based on costs or agreements.
[0021] In existing technologies, the allocation of electronic miscellaneous charges (EMD) generally relies on preset business type codes or fixed rules, which has defects such as unclear attribution of service responsibility entities, high dependence on manual intervention, rigid allocation logic, and easy to cause revenue mismatch or financial compliance risks.
[0022] To address the aforementioned technical problems or deficiencies in the existing technology, this invention aims to provide an intelligent cost-sharing and settlement method based on EMD service items, achieving: Accurately identify the responsible parties for each service item in the EMD; The amount is automatically allocated based on the service cost attributes; The entire process is auditable, configurable, and requires zero human intervention.
[0023] Figure 1 This is a flowchart illustrating the apportionment and settlement method based on electronic miscellaneous fee bill service items in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes: Step 101: Obtain electronic miscellaneous bill data; the electronic miscellaneous bill data includes the total amount and one or more service item ticket slips, each service item ticket slip including a service description field and an amount; Step 102: Perform semantic parsing on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type; Step 103: Use structured semantic tags to search in a pre-built service catalog knowledge graph to determine the service provider type and cost attribute of each service item; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; Step 104: When there are multiple different service provider types, the total amount is allocated to each service item ticket based on the total amount of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
[0024] This invention breaks through the traditional apportionment model by introducing intelligent semantic parsing, graph retrieval, rule engine and dynamic configuration mechanism, which significantly improves the accuracy, automation level and compliance of aviation non-transport revenue settlement.
[0025] In step 101, electronic miscellaneous bill data is obtained; the electronic miscellaneous bill data includes the total amount and one or more service item tickets, each service item ticket includes a service description field and an amount, wherein the amount of each service item ticket may be 0.
[0026] In implementation, a processing system is constructed, and the method of this embodiment of the invention is implemented based on this processing system. The system first receives multiple electronic expense bills, each of which contains, but is not limited to, the following six categories of key data: • Total amount (Fare Amount); • Ticket information: including ticket serial number and carrier airline code; • Service description text, such as: “Seat selection fee - Emergency exit row”, “Excess baggage - 23kg”, “Airport VIP lounge - Priority Pass”, etc. (free text fields); • Sales agent number and sales channel type; • The primary ticket number associated with the EMD (if it exists); • Transaction hours and currency information; • Business type code, for example: 0AA; the business type code indicates whether the electronic miscellaneous expense bill data is directly related to the flight itinerary.
[0027] For example, referring to Table 1 below, this EMD contains the following three services: Table 1
[0028] Each ticket coupon independently carries the value of a service. The coupon value is the chargeable amount for that service. Ideally, the sum of the face values of all valid coupons equals the total amount of the EMD. When the EMD is created, the PSS (Passenger Service System) only records the total amount (Fare Amount). When the coupon value is 0, it indicates that service credit is reserved, and the actual charge occurs during subsequent use (such as prepaid cards or credit authorization). Its characteristics are: The total amount issued at the time of issuance is greater than 0 (indicating a spending limit). All ticket amounts = 0 (because no actual consumption has occurred); When a passenger actually uses a service, the system generates a new EMD or updates the status of the original ticket and populates the value.
[0029] For example, an airline issues a "VIP Lounge Prepaid Card" (EMD) with a limit of USD 100: Total EMD amount = 100; Initially, there is one ticket with an amount of 0; After the passenger uses the VIP lounge for the first time, the system updates the ticket amount to 35, and the remaining amount of 65 can continue to be used.
[0030] In step 102, semantic parsing is performed on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type.
[0031] In one embodiment, semantic parsing is performed on the service description field to obtain a structured semantic tag for each service item, including mapping the service description field to the structured semantic tag based on named entity recognition and keyword extraction.
[0032] By employing an AI-based semantic parsing approach, even when faced with uncovered business types, this embodiment of the invention can dynamically add new service description patterns and automatically infer the responsible party through semantic parsing.
[0033] Electronic surcharges are used to collect fees for additional services, whether related to or unrelated to transportation, and are issued by the ticketing airline. These services include, but are not limited to, one or any combination of the following: Excess baggage fee, preferred seat fee, upgrade fee, in-flight meal upgrade, lounge access fee, rescheduling fee, ticket refund fee, travel insurance.
[0034] Structured semantic tags can also include attribute values such as corporate brand.
[0035] For example, extracting structured semantic tags from an electronic expense receipt includes the following: 1) Service type (such as Preferred Seat, Excess Baggage, Lounge Access). 2) Key attribute values (e.g., weight=23kg, brand=Priority Pass); At this point, preliminary semantic labels can be determined: marked as "revenue-generating" (airline-operated service), "cost-generating" (requires payment to a third party), or "collection and payment on behalf" (pure conduit, no net income).
[0036] In step 103, structured semantic tags are used to search the pre-built service catalog knowledge graph to determine the service provider type and cost attributes of each service item.
[0037] The types of service providers include, but are not limited to, one or any combination of carriers, ground service providers, and third-party partners.
[0038] The cost attributes reflect profit and loss; cost attributes include revenue-type, cost-type, and collection and payment-type; revenue-type indicates that the ticketing airline operates its own service, cost-type indicates that the ticketing airline needs to pay a third party, and collection and payment-type indicates that for the ticketing airline, it is just a channel with no net income.
[0039] The nodes of the service catalog knowledge graph include service type, service provider type, etc., and each node has attribute information. The service provider type can be determined by setting rules. (Reference) Figure 2 , Figure 2 This is a schematic diagram of the service catalog knowledge graph in this embodiment of the invention. Service instances are obtained by semantic parsing of EDM service description text, and service types are determined, such as nodes for seat selection service, excess baggage service, and VIP lounge service. Then, the service provider, such as the carrier airline or third-party partner, is determined through association rules.
[0040] For example, based on semantic tags and combined with a pre-built knowledge graph of airline service catalogs, the actual service provider for each service can be queried: 1) If the service type is Preferred Seat and there is no third-party brand → Responsible party = Carrying airline; 2) If the service description includes Priority Pass → Responsible Entity = Third-Party Partner; 3) If it is a tax or fee (such as security check fee) → the responsible party = the person collecting and paying on behalf of the airline, it is not included in the airline's revenue.
[0041] In step 104, when there are multiple different service provider types, the total amount is allocated to each service item ticket by combining the amounts of all service item tickets.
[0042] During implementation, when multiple different responsible parties are identified (such as an EMD that includes both airline seat selection fees and Priority Pass lounge fees), revenue is split, and the total amount of the EMD is broken down into individual ticket slips according to the details of each service item. Each item has a corresponding service provider type, i.e., the responsible party.
[0043] In one embodiment, allocating the total amount across all service item tickets by combining the amounts of all service item tickets may include: The total amount is allocated to each service item ticket based on the combined amount of all service item tickets according to a preset allocation strategy.
[0044] The preset allocation strategy includes one or any combination of direct assignment rule, average allocation rule, and proportional allocation rule. The direct assignment rule means that when the electronic miscellaneous bill data includes only one service item ticket, the total amount is assigned to the amount of that service item ticket; when the electronic miscellaneous bill data includes N service item tickets, the first N-1 service item tickets are directly assigned the amount of their respective service item tickets, and the difference between the total amount and the sum of the amounts of the first N-1 service item tickets is assigned to the last service item ticket; N is a positive integer greater than or equal to 2; The average allocation rule means: the total amount is allocated by dividing the total amount by the number of service item tickets, with the integer part assigned to the first N-1 service item tickets and the remaining part assigned to the last service item ticket; the proportional allocation means that the total amount is allocated according to the number of service item tickets. The proportional allocation rule means that the total amount is allocated to the first N-1 service item tickets according to a preset ratio, and the remaining difference is allocated to the last service item ticket; where the ratio represents the proportion of the amount of a single service item ticket to the sum of the amounts of all service item tickets.
[0045] Existing technologies often employ rigid allocation logic, typically allocating amounts solely based on the number of invoices or a simple ratio, without considering the cost attributes of different service items. This can easily lead to revenue mismatch or financial compliance risks. In this invention, a preset allocation strategy is proposed, which fully considers various situations and dynamically selects appropriate allocation rules to ensure efficient and accurate allocation calculation of electronic miscellaneous fees.
[0046] Furthermore, by combining the amounts of all service item tickets and allocating the total amount to each service item ticket according to a preset allocation strategy, the following may be included: When the business type code indicates that the electronic miscellaneous expense bill data is directly associated with the air ticket itinerary, the allocation processing module is invoked for allocation processing. The allocation processing module is specifically used to: obtain the air ticket allocation data directly associated with the electronic miscellaneous expense bill; the allocation data includes the allocation coefficient of each service item ticket; using the allocation coefficient of each service item ticket, the total amount is allocated to each service item ticket using a proportional allocation rule, wherein the preset ratio is determined based on the allocation coefficient of a single service item ticket and the sum of the allocation coefficients of all service item ticket tickets; When the business type code indicates that the electronic miscellaneous fee bill data is not directly related to the flight itinerary, the total amount is allocated to each service item ticket according to the sum of the amounts of all service item ticket copies and the total amount, as well as whether the amount of each service item ticket copy is 0, based on a preset allocation strategy.
[0047] The system includes a cost-sharing module, whose main function is to split the total amount of the ticket and EMD onto each ticket copy based on bilateral or multilateral cost-sharing agreements maintained by the airline.
[0048] Furthermore, based on the sum of the amounts of all service item tickets and the total amount, as well as whether the amount of each service item ticket is 0, the total amount is allocated to each service item ticket according to a preset allocation strategy, which may include: Verify that the amounts on all service item tickets are 0; When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes only one service item ticket, the direct assignment rule is used for apportionment. When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes N service item tickets, the average allocation rule is used for apportionment. When not all service item ticket amounts are 0 and the sum of all service item ticket amounts equals the total amount, the direct assignment rule is used for allocation; where the amount of each service item ticket is used as the allocated amount. When not all service item ticket amounts are 0, the sum of all service item ticket amounts is not equal to the total amount, and the electronic miscellaneous bill data includes N service item ticket amounts, calculate the sum of the amounts S of the first N-1 service item ticket amounts; If the sum of the amounts S ≥ the total amount, the apportionment is carried out using a proportional apportionment rule, wherein the preset ratio is based on the ratio of the amount of a single service item ticket to the sum of the amounts of all service item tickets; If the sum of the amounts S is less than the total amount, the allocation will be performed using the direct assignment rule.
[0049] Figure 3 This is a schematic diagram of a specific process for cost-sharing settlement in an embodiment of the present invention, as shown below. Figure 3 As shown, the following process can be used as a reference: 1. Beginning: 2. After the electronic miscellaneous expense bill data is imported into the processing system, the system first determines whether the apportionment processing module needs to be called based on the business type code of the electronic miscellaneous expense bill data.
[0050] 3. When it is determined that the apportionment processing module needs to be called, the system first identifies whether the invoice associated with the electronic miscellaneous expense bill is a reissued invoice.
[0051] 4. If the associated ticket is a normal ticket, i.e., not a reissued ticket, then the allocation will be processed according to the proportional allocation rules (the preset ratio is determined based on the allocation coefficient of a single service item ticket and the sum of the allocation coefficients of all service item ticket tickets), and the specific allocation steps are as follows: 4.1) Obtain the total amount F of the EMD for this ticket; 4.2) Obtain the ticket allocation data, including the allocation coefficients W1, W2, ..., Wn of the n ticket copies of the EMD associated with the ticket (where n≥1, and n is an integer); 4.3) Calculate the total allocation coefficient. ; 4.4) For the first N-1 tickets, calculate their allocated amount as follows: a i i = 1, 2, ..., n-1; Rounding is performed according to a preset precision (e.g., retaining two decimal places); 4.5) Set the apportionment amount for the Nth ticket (i.e., the last ticket) as: a n ; To ensure that the sum of the apportioned amounts of all ticket copies is exactly equal to the total EMD amount F, any difference will be borne by the last ticket copy.
[0052] Example 1 (Normal ticket scenario): Total EMD amount: F=300; apportionment coefficients: W1=70, W2=80, W3=80, W4=60; The total allocation coefficient W = 290; The allocation result is as follows: Ticket stub 1: 300 × 70 / 290 = 72.41; Ticket stub 2: 300 × 80 / 290 = 82.76; Ticket stub 3: 300 × 80 / 290 = 82.76; Ticket stub 4: 300 - (72.41 + 82.76 + 82.76) = 62.07.
[0053] 5. If the associated ticket is a reissued ticket, the following verification and allocation process shall be executed: The system checks whether the original ticket (i.e., the old ticket that was replaced) exists in the master data of the processing system; 6. If the original invoice exists, the allocation will be processed using the proportional allocation rule. The total EMD amount F of the current invoice and its allocation coefficients W1, W2, …, Wn will be obtained. The same proportional allocation rule (SRP) as the normal invoice will be used for allocation. Example 2 (Invoice Renewal Scenario): Total EMD amount: F=260; apportionment coefficients: W1=70, W2=80, W3=90; The total allocation coefficient W = 240; The allocation result is as follows: Ticket stub 1: 260 × 70 / 240 = 75.83; Ticket stub 2: 260 × 80 / 240 = 86.67; Ticket stub 3: 260 - (75.83 + 86.67) = 97.5; 7. If the original ticket does not exist, an allocation error log is recorded and an exception handling mechanism is triggered. The system is configured with a scheduled batch processing job (e.g., executed every night) to backtrack and verify the missing original ticket data and automatically retry the allocation after the original ticket is re-entered.
[0054] The allocation mechanism of this allocation processing module distinguishes the processing paths of normal tickets and reissued tickets. In the reissued scenario, it introduces the existence verification of the original ticket to ensure data integrity. It also uniformly adopts the straight proportional allocation rule (SRP) combined with the tail difference collection strategy to ensure that the allocation result not only complies with business rules but also meets the requirements of financial accuracy, effectively supporting the automation and compliance of airline revenue settlement.
[0055] 8. When it is determined that there is no need to call the cost-sharing module, first check whether the amount of all service item tickets is 0.
[0056] 9. When the amount of all service item tickets is 0, determine whether the electronic miscellaneous bill includes only one ticket.
[0057] 10. When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes only one service item ticket, the direct assignment rule shall be used for apportionment. At this point, regardless of whether the ticket is a normal ticket or a reissued ticket, the total amount of the EMD will be directly used as the apportioned amount for that ticket copy.
[0058] 11. When the total amount of all service item tickets is 0, but the number of electronic miscellaneous fees includes multiple tickets, the average allocation rule shall be used for apportionment. At this point, regardless of whether the ticket is a normal ticket or a reissued ticket, the total amount of the EMD is distributed equally according to the number of ticket copies. The integer part of the allocated amount is assigned to the first N-1 ticket copies, and the remaining amount is added to the Nth ticket copy (i.e., the last ticket copy).
[0059] The aforementioned allocation mechanism ensures that, in business scenarios where the value of an EMD ticket is zero, the ticket-related amount can be completely and without omission allocated to each ticket, thereby guaranteeing the accuracy and compliance of air transport revenue settlement.
[0060] 12. If not all service item ticket amounts are 0, further determine whether the sum of all service item ticket amounts equals the total amount F.
[0061] 13. When not all service item ticket amounts are 0 and the sum of all service item ticket amounts equals the total amount, the direct assignment rule is used for allocation; whereby the amount of each service item ticket is used as the allocated amount, that is, the system directly allocates the amount of each EMD ticket to its corresponding ticket allocation value, that is, the allocation amount of the Nth ticket is equal to the EMD Coupon Value of that ticket. Example 3: Assume the total amount of the tickets (whether regular or reissued) is 110; The EMD contains three ticket copies, with the following ticket value: Ticket 1:30; Ticket 2: 60; Ticket 3:20 The sum of the amounts on each ticket is 30 + 60 + 20 = 110, which is equal to the total amount of the tickets, thus satisfying the above conditions.
[0062] At this point, the system assigns the amounts to each ticket copy of the EMD as follows: Ticket 1:30 Ticket 2: 60 Ticket 3:20 This processing logic ensures that, in scenarios where the sum of all ticket amounts in the EMD matches the total EMD amount, the allocation result accurately reflects the actual value of each service item, avoiding rounding errors or allocation distortions introduced by secondary calculations, thereby improving the accuracy and auditability of airline revenue settlement.
[0063] 14. When not all service item ticket amounts are 0, and the sum of all service item ticket amounts is not equal to the total EMD amount, further determine whether the sum of all service item ticket amounts is greater than or equal to the total EMD amount; Suppose that the EMD contains N coupons (N≥2), and the coupon amount of each coupon (i.e., the EMD Coupon Value, denoted as Vi, where i=1,2,…,N) is V1, V2,…, VN, respectively, and their sum is... ; Calculate the sum S of the ticket amounts of the first N-1 ticket slips. ; Compare S and F.
[0064] 15. If S≥F, the apportionment shall be allocated according to the proportional allocation rule, wherein the preset ratio is based on the ratio of the amount of a single service item ticket to the sum of the amounts of all service item tickets: For each ticket i (i=1,2,…,N), calculate its initial apportionment amount: ai ; Assign the apportionment amount of the first N-1 tickets to ai (retaining the preset number of decimal places, such as two); Let the apportionment amount of the Nth ticket (i.e., the last ticket) be an. ; To ensure that the sum of the apportioned amounts on all ticket slips is exactly equal to the total amount F, any discrepancies are borne by the last ticket slip.
[0065] Example 4: Total amount: F=110; The ticket amounts are: V1=30, V2=80, V3=20; The sum of the amounts of the first N-1=2 tickets, S=30+80=110≥F, satisfies the proportional apportionment condition; The total V = 130; The allocation result is as follows: Ticket stub 1: 30 × 110 / 130 = 25.38; Ticket stub 2: 80 × 110 / 130 = 67.69; Ticket 3: 110 - (25.38 + 67.69) = 16.93.
[0066] 16. If the sum of the amounts S < the total amount, the allocation shall be performed using the direct assignment rule: Assign the apportionment amount to the first N-1 ticket coupons respectively, i.e., ai=Vi (i=1,2,…,N-1); Let the apportionment amount for the Nth ticket be: a n ; Example 5: Total amount: F=150; The ticket amounts are: V1=30, V2=80, V3=20; The sum of the values of the first N-1=2 ticket copies, S=30+80=110<150, satisfies the direct assignment condition; The allocation result is as follows: Ticket 1:30; Ticket stub 2: 80; Ticket 3: 150 - (30 + 80) = 40.
[0067] The aforementioned cost-sharing mechanism uses the comparison between the sum of the previous N-1 ticket amounts and the total amount as the basis for strategy switching. Under the premise of ensuring that the total cost-sharing amount is strictly equal to the total EMD amount, it avoids over-allocation in high-value ticket scenarios and ensures the reasonable reflection of the value of each ticket in low-value scenarios, thereby improving the accuracy, consistency and auditability of airline revenue settlement.
[0068] 17. End.
[0069] After the allocation process is completed, accounting data is generated.
[0070] Billing data is generated based on the semantic tags of each service: "Revenue-generating" services → are fully included in the main operating revenue of the carrier airline; "Cost-based" services → trigger accounts payable process and settle accounts with the designated service provider; "Collection and payment on behalf of others" → Only records are posted, no profit or loss is generated.
[0071] This process ensures that the semantic parsing results are consistent with the business rules, avoiding misattribution due to textual ambiguity.
[0072] In one embodiment, after allocating the total amount to each service item ticket by combining the amounts of all service item tickets, the method may further include: generating a responsible entity accounting voucher; the responsible entity accounting voucher includes debit and credit amounts recorded for each service provider entity.
[0073] During implementation, differentiated financial treatment will be applied based on the identified responsible party: If multiple different responsible parties are identified (e.g., an EMD includes both airline seat selection fees and Priority Pass lounge fees), then perform the following operations: Step 1: Revenue Breakdown; Break down the total EMD amount into individual service item invoices, with each item having a corresponding responsible party; Step 2: Generate accounting vouchers for each entity; For example, for the carrier airline portion: generate a debit to "Accounts Receivable - BSP" and a credit to "Main Business Revenue"; For example, for the third-party partner institution portion: generate a debit to "Accounts Payable - Priority Pass" and a credit to "Other Payables"; Step 3: Output audit trail logs; Record the original description text, the ultimate responsible party, and the allocated amount for each service, for subsequent audit retrospective and anomaly investigation, to meet the relevant departments' requirements regarding "variable consideration allocation".
[0074] In summary, the embodiments of the present invention include at least four stages: semantic parsing, liability determination, allocation engine, and audit trail. These stages work closely together to achieve end-to-end automated processing from EMD service text input to revenue attribution and voucher generation, without any manual intervention, ensuring high efficiency, accuracy, and auditability.
[0075] The method of this invention can be seamlessly integrated into the existing BSP / ARC settlement system or airline revenue accounting system, providing a highly scalable and compliant allocation solution for the increasingly complex ancillary service sales scenarios under the NDC (New Distribution Capability) environment, and effectively supporting the construction of financial infrastructure for airlines to transform from "ticket sales" to "service retail".
[0076] This invention also provides a cost-sharing settlement device based on electronic miscellaneous bill service items, as described in the following embodiments. Since the principle by which this device solves the problem is similar to the cost-sharing settlement method based on electronic miscellaneous bill service items, the implementation of this device can refer to the implementation of the cost-sharing settlement method based on electronic miscellaneous bill service items; repeated details will not be elaborated further.
[0077] Figure 4 This is a schematic diagram of a cost-sharing and settlement device based on electronic miscellaneous fee bill service items in an embodiment of the present invention, as shown below. Figure 4 As shown, the device is applied to a method for apportionment settlement based on electronic miscellaneous bill service items. The device 400 includes: Data acquisition module 401 is used to acquire electronic miscellaneous bill data; the electronic miscellaneous bill data includes a total amount and one or more service item ticket slips, each service item ticket slip including a service description field and an amount; The semantic parsing module 402 is used to perform semantic parsing on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type; The graph retrieval module 403 is used to perform retrieval in a pre-built service catalog knowledge graph using structured semantic tags to determine the service provider type and cost attribute of each service item; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; The apportionment processing module 404 is used to apportion the total amount to each service item ticket when there are multiple different service provider types, by combining the amounts of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
[0078] In one embodiment, the semantic parsing module 402 is specifically used for: Based on named entity recognition and keyword extraction, service description fields are mapped to structured semantic tags.
[0079] In one embodiment, the service provider type includes one or any combination of carrier airlines, ground service providers, and third-party partners.
[0080] In one embodiment, the cost attributes include revenue-type, cost-type, and collection-on-delivery-type; revenue-type indicates that the ticketing airline operates its own services, cost-type indicates that the ticketing airline needs to pay a third party, and collection-on-delivery-type indicates that the ticketing airline has no net income.
[0081] In one embodiment, the amortization processing module 404 is specifically used for: Based on the total amount of all service item tickets, the total amount is allocated to each service item ticket according to a preset allocation strategy; the preset allocation strategy includes one or any combination of direct assignment rule, average allocation rule, and proportional allocation rule. The direct assignment rule means that when the electronic miscellaneous bill data includes only one service item ticket, the total amount is assigned to the amount of that service item ticket; when the electronic miscellaneous bill data includes N service item tickets, the first N-1 service item tickets are directly assigned the amount of their respective service item tickets, and the difference between the total amount and the sum of the amounts of the first N-1 service item tickets is assigned to the last service item ticket; N is a positive integer greater than or equal to 2; The average allocation rule means: the total amount is divided by the number of service item tickets, the integer part is assigned to the first N-1 service item tickets, and the remaining part is assigned to the last service item ticket; the proportional allocation means that the total amount is divided by the number of service item tickets. The proportional allocation rule means that the total amount is allocated to the first N-1 service item tickets according to a preset ratio, and the remaining difference is allocated to the last service item ticket.
[0082] In one embodiment, the electronic miscellaneous bill data further includes a service type code; the service type code indicates whether the electronic miscellaneous bill data is directly associated with an air ticket itinerary. The allocation processing module 404 is specifically used for: When the business type code indicates that the electronic miscellaneous expense bill data is directly associated with the air ticket itinerary, the allocation processing module is invoked for allocation processing. The allocation processing module is used to: obtain the air ticket allocation data directly associated with the electronic miscellaneous expense bill; the allocation data includes the allocation coefficient of each service item ticket; using the allocation coefficient of each service item ticket, the total amount is allocated to each service item ticket using a proportional allocation rule, wherein the preset ratio is determined based on the allocation coefficient of a single service item ticket and the sum of the allocation coefficients of all service item ticket tickets. When the business type code indicates that the electronic miscellaneous fee bill data is not directly related to the flight itinerary, the total amount is allocated to each service item ticket according to the sum of the amounts of all service item ticket copies and the total amount, as well as whether the amount of each service item ticket copy is 0, based on a preset allocation strategy.
[0083] In one embodiment, the amortization processing module 404 is specifically used for: Verify that the amounts on all service item tickets are 0; When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes only one service item ticket, the direct assignment rule is used for apportionment. When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes N service item tickets, the average allocation rule is used for apportionment. When not all service item ticket amounts are 0 and the sum of all service item ticket amounts equals the total amount, the direct assignment rule is used for allocation; where the amount of each service item ticket is used as the allocated amount. When not all service item ticket amounts are 0, the sum of all service item ticket amounts is not equal to the total amount, and the electronic miscellaneous bill data includes N service item ticket amounts, calculate the sum of the amounts S of the first N-1 service item ticket amounts; If the sum of the amounts S ≥ the total amount, the apportionment is carried out using a proportional apportionment rule, wherein the preset ratio is based on the ratio of the amount of a single service item ticket to the sum of the amounts of all service item tickets; If the sum of the amounts S is less than the total amount, the allocation will be performed using the direct assignment rule.
[0084] In one embodiment, the device 400 further includes: The accounting voucher processing module is used to generate a responsible entity accounting voucher after the allocation processing module 404 allocates the total amount to each service item voucher in combination with the amounts of all service item vouchers; the responsible entity accounting voucher includes debit and credit amounts recorded for each service provider entity.
[0085] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described apportionment settlement method based on electronic miscellaneous bill service items.
[0086] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention, such as... Figure 5 As shown, this embodiment of the invention also provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the above-mentioned apportionment settlement method based on electronic miscellaneous bill service items.
[0087] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described apportionment settlement method based on electronic miscellaneous fee bill service items.
[0088] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described apportionment settlement method based on electronic miscellaneous fee bill service items.
[0089] This invention provides an intelligent cost-sharing and settlement method based on EMD service item semantic parsing. Through a rule engine and dynamic configuration mechanism, it breaks through the traditional extensive cost-sharing model that relies on fixed coding or manual intervention, achieving refined, automated, and intelligent management of aviation non-transport revenue. Specifically, this invention can: Accurately identify the responsible parties for each service item in the EMD: Based on semantic analysis of the service description text in the EMD ticket (such as “seat selection fee - emergency exit row”, “overweight baggage - 23kg”, “airport VIP lounge - Priority Pass”), combined with the airline service catalog knowledge graph, the actual provider of each service (such as the carrier, ground service provider, third-party partner) is automatically identified, thereby accurately attributing the revenue to the responsible party and avoiding cross-entity settlement mismatch.
[0090] Automatic allocation of costs based on service cost attributes: Based on the semantic tags of service items (such as "cost type", "revenue type", "collection and payment type") and preset cost allocation strategies, strategies such as proportional allocation, direct assignment, average allocation, and tail difference collection are used to scientifically allocate EMD amounts to each ticket or related transportation segment, ensuring that financial accounting complies with accounting standards and IATA revenue accounting specifications.
[0091] The entire process is auditable, configurable, and requires zero human intervention: all allocation logic is driven by a visual rule engine. The system records the semantic parsing results, the basis for determining the responsible party, the allocation calculation process, and the final result throughout the entire process, forming a complete audit trail. From EMD access to settlement and accounting, no manual review or adjustment is required, significantly improving processing efficiency and reducing operational risks and labor costs. The allocated amount for each ticket can be viewed through a visual interface.
[0092] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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.
[0093] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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, generate instructions 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.
[0094] 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.
[0095] 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.
[0096] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for apportionment and settlement of service items based on electronic miscellaneous charges, characterized in that, include: Obtain electronic miscellaneous bill data; the electronic miscellaneous bill data includes the total amount and one or more service item ticket copies, each service item ticket copy including a service description field and an amount; Semantic parsing is performed on the service description field to obtain the structured semantic tags for each service item; Structured semantic tags include service type; By using structured semantic tags to search in a pre-built service catalog knowledge graph, the service provider type and cost attribute of each service item are determined; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; When there are multiple different service provider types, the total amount is allocated to each service item ticket by combining the amounts of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
2. The method as described in claim 1, characterized in that, Semantic parsing is performed on the service description field to obtain the structured semantic tags for each service item, including: Based on named entity recognition and keyword extraction, service description fields are mapped to structured semantic tags.
3. The method as described in claim 1, characterized in that, The service provider types include one or any combination of carrier airlines, ground service providers, and third-party partners.
4. The method as described in claim 1, characterized in that, The cost attributes include revenue-type, cost-type, and collection-on-delivery-type; revenue-type indicates that the ticketing airline operates the service itself, cost-type indicates that the ticketing airline needs to pay a third party, and collection-on-delivery-type indicates that the ticketing airline has no net income.
5. The method as described in claim 1, characterized in that, The total amount is then allocated to each service item ticket by combining the amounts from all service item tickets, including: Based on the total amount of all service item tickets, the total amount is allocated to each service item ticket according to a preset allocation strategy; the preset allocation strategy includes one or any combination of direct assignment rule, average allocation rule, and proportional allocation rule. The direct assignment rule means that when the electronic miscellaneous bill data includes only one service item ticket, the total amount is assigned to the amount of that service item ticket; when the electronic miscellaneous bill data includes N service item tickets, the first N-1 service item tickets are directly assigned the amount of their respective service item tickets, and the difference between the total amount and the sum of the amounts of the first N-1 service item tickets is assigned to the last service item ticket; N is a positive integer greater than or equal to 2; The average allocation rule means: the total amount is allocated by dividing the total amount by the number of service item tickets, with the integer part assigned to the first N-1 service item tickets and the remaining part assigned to the last service item ticket; the proportional allocation means that the total amount is allocated according to the number of service item tickets. The proportional allocation rule means that the total amount is allocated to the first N-1 service item tickets according to a preset ratio, and the remaining difference is allocated to the last service item ticket.
6. The method as described in claim 5, characterized in that, The electronic miscellaneous bill data also includes a business type code; the business type code indicates whether the electronic miscellaneous bill data is directly related to the flight itinerary. Based on the total amount of all service item tickets, the total amount is allocated to each service item ticket according to a preset allocation strategy, including: When the business type code indicates that the electronic miscellaneous expense bill data is directly associated with the air ticket itinerary, the allocation processing module is invoked for allocation processing. The allocation processing module is used to: obtain the air ticket allocation data directly associated with the electronic miscellaneous expense bill; the allocation data includes the allocation coefficient of each service item ticket; using the allocation coefficient of each service item ticket, the total amount is allocated to each service item ticket using a proportional allocation rule, wherein the preset ratio is determined based on the allocation coefficient of a single service item ticket and the sum of the allocation coefficients of all service item ticket tickets. When the business type code indicates that the electronic miscellaneous fee bill data is not directly related to the flight itinerary, the total amount is allocated to each service item ticket according to the sum of the amounts of all service item ticket copies and the total amount, as well as whether the amount of each service item ticket copy is 0, based on a preset allocation strategy.
7. The method as described in claim 6, characterized in that, Based on the sum of all service item ticket amounts and the total amount, and considering whether the amount on each service item ticket is zero, the total amount is allocated to each service item ticket according to a preset allocation strategy, including: Verify that the amounts on all service item tickets are 0; When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes only one service item ticket, the direct assignment rule is used for apportionment. When the total amount of all service item tickets is 0 and the electronic miscellaneous bill data includes N service item tickets, the average allocation rule is used for apportionment. When not all service item ticket amounts are 0 and the sum of all service item ticket amounts equals the total amount, the direct assignment rule is used for allocation; where the amount of each service item ticket is used as the allocated amount. When not all service item ticket amounts are 0, the sum of all service item ticket amounts is not equal to the total amount, and the electronic miscellaneous bill data includes N service item ticket amounts, calculate the sum of the amounts S of the first N-1 service item ticket amounts; If the sum of the amounts S ≥ the total amount, the apportionment is carried out using a proportional apportionment rule, wherein the preset ratio is based on the ratio of the amount of a single service item ticket to the sum of the amounts of all service item tickets; If the sum of the amounts S is less than the total amount, the allocation will be performed using the direct assignment rule.
8. The method as described in claim 3, characterized in that, After allocating the total amount across all service item tickets, the remaining amount also includes: Generate accounting vouchers for the responsible entities; the accounting vouchers for the responsible entities include debit and credit amounts recorded for each service provider entity.
9. A cost-sharing and settlement device based on electronic miscellaneous fee bill service items, characterized in that, include: The data acquisition module is used to acquire electronic miscellaneous bill data; the electronic miscellaneous bill data includes a total amount and one or more service item ticket slips, each service item ticket slip including a service description field and an amount; The semantic parsing module is used to perform semantic parsing on the service description field to obtain the structured semantic tags for each service item; the structured semantic tags include the service type. The graph retrieval module is used to search in a pre-built service catalog knowledge graph using structured semantic tags to determine the service provider type and cost attribute of each service item; the cost attribute reflects profit and loss; the nodes of the service catalog knowledge graph include service type and service provider type; The apportionment processing module is used to apportion the total amount to each service item ticket when there are multiple different service provider types, by combining the amounts of all service item tickets; wherein, the service provider type corresponding to each service item ticket is marked.
10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.
12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.