Ticket union freight rate amount association method and device based on freight rate calculation bar

Abstract

The invention discloses a ticket union freight rate amount association method and device based on a freight rate calculation column. The method comprises the following steps: identifying a corresponding character string from the freight rate calculation column of a civil aviation system; splitting the corresponding character string to obtain a plurality of first-level character strings; traversing the first-level character string to screen out a candidate first-level character string containing adhesion combination of the navigation station point sub-character string and the carrier sub-character string; splitting the candidate first-level character string to generate a second-level character string; analyzing in sequence to obtain a second-level character string so as to form an analysis leg; associating the parsed freight rate amount with the parsed route segment to generate a corresponding freight rate unit; matching the carrier information and the leg of the freight rate unit with the carrier information and the leg of the ticket copy information to be tested; and after matching succeeds, the freight rate amount information in the freight rate unit is associated to the ticket copy information to be tested. According to the invention, the united transportation price amount of civil aviation tickets can be accurately obtained, and the automation efficiency and accuracy of civil aviation ticket settlement are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of civil aviation transportation technology, and in particular to a method and device for associating a ticket coupon fare amount based on a fare calculation column. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] In the field of civil aviation passenger transportation, the fare calculation column serves as the core carrier of air ticket settlement, carrying complex information such as the flight's departure station, carrier, arrival station, and fare amount. Its horizontal string is usually composed of multiple fare units, mileage points deductions, and fare amounts dynamically spliced ​​together, showing a high degree of flexibility and irregularity. In traditional technical solutions, the parsing of the fare calculation column relies on a static rule base, which relies on manual maintenance and is difficult to cope with the flexible fare rules of the civil aviation industry. It is impossible to achieve accurate splitting of the fare calculation column and it is difficult to accurately obtain the civil aviation ticket fare amount, resulting in the automation efficiency and accuracy of civil aviation ticket settlement being affected. Therefore, a ticket fare amount association method based on the fare calculation column is urgently needed to solve the above problems. Summary of the Invention

[0004] An embodiment of the present invention provides a method for associating a coupon fare amount based on a fare calculation column, for achieving precise splitting of the fare calculation column, ensuring accurate matching of the fare amount with the coupon flight segments, and accurately obtaining the civil aviation coupon fare amount, thereby improving the automated efficiency and accuracy of civil aviation ticket settlement. The method includes:

[0005] Identifying a corresponding character string from a fare calculation column in the civil aviation system; the character string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket coupon information in the civil aviation system;

[0006] Identify the space characters in the string, use the space characters as delimiters to split the string, and obtain multiple first-level strings;

[0007] Traverse the first-level strings and select candidate first-level strings that contain a combination of the terminal substring and the carrier substring; use a machine learning algorithm to split the candidate first-level strings to generate second-level strings;

[0008] According to the preset parsing order, the departure station, carrier information, and arrival station in the second-level character string are parsed in sequence, and the departure station, carrier information, and arrival station are associated to form a parsed flight segment;

[0009] When the fare amount in the second-level character string is parsed according to the preset parsing order, the parsed fare amount is associated with the parsed flight segment to generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment;

[0010] Match the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and match the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested; after successful matching, associate the fare amount information in the fare unit with the ticket coupon information to be tested.

[0011] The embodiment of the present invention further provides a device for associating a coupon fare amount based on a fare calculation column, which is used to accurately split the fare calculation column, ensure accurate matching of the fare amount with the coupon flight segment, accurately obtain the civil aviation coupon fare amount, and improve the automation efficiency and accuracy of civil aviation ticket settlement. The device includes:

[0012] A fare calculation column string recognition module is used to identify a corresponding string from the fare calculation column of the civil aviation system; the string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket information in the civil aviation system;

[0013] The first-level string generation module is used to identify space characters in a string and split the string using the space characters as delimiters to obtain multiple first-level strings;

[0014] The second-level string generation module is used to traverse the first-level strings and screen out candidate first-level strings that contain a combination of the terminal substring and the carrier substring; it uses a machine learning algorithm to split the candidate first-level strings to generate second-level strings;

[0015] The parsing segment generation module is used to parse the departure station, carrier information, and arrival station in the second-level character string in a preset parsing order, and associate the departure station, carrier information, and arrival station to form a parsed segment;

[0016] The fare unit generation module is used to associate the parsed fare amount with the parsed flight segment when the fare amount in the second-level character string is parsed according to the preset parsing order, and generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment;

[0017] The fare amount association module for the ticket coupon to be tested is used to match the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and to match the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested; after successful matching, the fare amount information in the fare unit is associated with the ticket coupon information to be tested.

[0018] An embodiment of the present 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, the method for associating the ticket coupon fare amount based on the fare calculation column is implemented.

[0019] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for associating the ticket coupon fare amount based on the fare calculation column is implemented.

[0020] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for associating ticket coupon fare amounts based on the fare calculation column.

[0021] In an embodiment of the present invention, a corresponding character string is identified from the fare calculation column of the civil aviation system; the character string includes a carrier substring, an airport substring and a fare amount substring; the fare calculation column is pre-built based on the historical ticket information of the civil aviation system; a space character in the character string is identified, and the character string is split using the space character as a separator to obtain multiple first-level character strings; the first-level character string is traversed to screen out candidate first-level character strings containing a combination of the airport substring and the carrier substring; a machine learning algorithm is used to split the candidate first-level character strings to generate second-level character strings; and a preset parsing algorithm is used to perform the splitting of the candidate first-level character strings. The first step is to parse the second-level character string in sequence, and then parse the departure station, carrier information, and arrival station in the second-level character string, and associate the departure station, carrier information, and arrival station to form a parsed flight segment; when the fare amount in the second-level character string is parsed according to the preset parsing order, the parsed fare amount is associated with the parsed flight segment to generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment; the carrier information of the fare unit is matched with the carrier information of the ticket information to be associated, and the flight segment of the fare unit is matched with the flight segment of the ticket information to be tested; after the match is successful, the fare amount information in the fare unit is associated with the ticket information to be tested. In the above process, the embodiment of the present invention parses the character string in the fare calculation column, combines the machine learning algorithm to intelligently segment the contiguous combination of flight station and carrier, and accurately associates the flight segment with the fare amount based on the preset parsing order, thereby solving the problems of flight segment attribution confusion and amount binding errors caused by the rigidity of the static rule base and character-by-character parsing in the traditional method. This enables the refined splitting of the fare calculation column, ensures the precise matching of the fare amount with the ticket segment, and can accurately obtain the civil aviation ticket fare amount, significantly improving the automation efficiency and accuracy of civil aviation ticket settlement. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. 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 work. In the drawings:

[0023] Figure 1 Flowchart of a method for associating a ticket coupon fare amount based on a fare calculation column in an embodiment of the present invention;

[0024] Figure 2 A flowchart of generating a second-level character string in an embodiment of the present invention;

[0025] Figure 3 A flowchart for forming parsed flight segments in an embodiment of the present invention;

[0026] Figure 4 Schematic diagram of a device for associating a ticket coupon fare amount based on a fare calculation column in an embodiment of the present invention;

[0027] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0030] Figure 1 Flowchart of a method for associating a coupon fare amount based on a fare calculation column in an embodiment of the present invention. The method includes:

[0031] Step 101: Identify a corresponding character string from a fare calculation column in the civil aviation system; the character string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket coupon information in the civil aviation system;

[0032] Step 102: identifying space characters in the character string, and using the space characters as separators to split the character string to obtain multiple first-level character strings;

[0033] Step 103: traverse the first-level strings to select candidate first-level strings that contain a combination of the terminal substring and the carrier substring; use a machine learning algorithm to split the candidate first-level strings to generate second-level strings;

[0034] Step 104: parse the second-level character string in sequence according to a preset parsing order to obtain the departure station, carrier information, and arrival station, and associate the departure station, carrier information, and arrival station to form a parsed flight segment.

[0035] Step 105: When the fare amount in the second-level character string is parsed according to the preset parsing order, the parsed fare amount is associated with the parsed flight segment to generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment;

[0036] Step 106, matching the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and matching the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested; after successful matching, the fare amount information in the fare unit is associated with the ticket coupon information to be tested.

[0037] Each step is described in detail below.

[0038] In step 101, a corresponding character string is identified from the fare calculation column of the civil aviation system; the character string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket information of the civil aviation system.

[0039] In a specific embodiment, a bidirectional parsing method is used to identify the end string END of the freight rate calculation column from left to right. For example, the freight rate calculation column is "04JUL21YINCZURC170.00CNY170.00END**(IN)". The calculation column is first pre-processed. Among them, "04JUL21" is the ticket issuance date and can be ignored from the freight rate calculation column. Therefore, after pre-processing, the effective freight rate calculation column is: "YINCZURC170.00CNY170.00END**(IN)".

[0040] Parse from right to left again: find the ending string "END" and the string that follows it as the points substring. Parse leftward until the string "END" is complete, and "170.00" is the total amount in the freight calculation column. To the left of this amount is the corresponding currency code, "CNY." This yields the total amount in the freight calculation column, the currency code CNY, and the amount 170.00. After this parsing, the longer string "URC170.00CNY170.00END" is successfully simplified to "URC170.00," and the effective freight calculation column is updated to "YINCZURC170.00."

[0041] In step 102, a space character in a character string is identified, and the character string is split using the space character as a separator to obtain a plurality of first-level character strings.

[0042] In a specific embodiment, the effective freight rate calculation column is split into multiple first-level character strings by space characters from left to right. When the effective freight rate calculation column is updated to "YINCZURC170.00", the character strings are parsed from left to right.

[0043] The process of splitting into multiple first-level strings by space characters is as follows: split "YINCZURC170.00" into:

[0044] YIN

[0045] CZ

[0046] URC170.00

[0047] Identify whether YIN is an airline station. Since the string exists in the station set: {YIN, URC}, YIN is the departure station of the first flight segment. Identify whether CZ is a carrier. Since the string exists in the carrier set: {CZ}, CZ is the carrier of the first flight segment. When identifying URC170.00, similarly, URC exists in the station set: {YIN, URC}, so URC is the arrival station of the first flight segment.

[0048] In step 103, the first-level strings are traversed to select candidate first-level strings containing a combination of the terminal substring and the carrier substring; and a machine learning algorithm is used to split the candidate first-level strings to generate second-level strings.

[0049] Figure 2 This is a flowchart of generating a second-level character string in an embodiment of the present invention. In one embodiment, before using a machine learning algorithm to split the candidate first-level character strings to generate the second-level character strings, the process includes:

[0050] Step 201: Input the candidate first-level string into a trained string splitting model, and output the split positions of the airline station code and carrier code. The string splitting model is trained on a convolutional neural network model using the historical candidate first-level string as input and the split positions of the airline station code and carrier code in the string as output.

[0051] Step 202: Split the candidate first-level character strings based on the split positions of the terminal code and the carrier code to generate second-level character strings.

[0052] In a specific embodiment, candidate first-level strings are screened based on the concatenated combination of the terminal substring and the carrier substring. The candidate first-level strings are split and parsed according to the terminal and the carrier to obtain second-level strings. The candidate first-level strings are screened again until no candidate first-level strings exist in the first-level strings.

[0053] In step 104, the departure station, carrier information, and arrival station in the second-level character string are parsed in sequence according to a preset parsing order, and the departure station, carrier information, and arrival station are associated to form a parsed flight segment.

[0054] Figure 3 The flowchart of forming a parsed flight segment in an embodiment of the present invention is as follows. In one embodiment, the origin station, carrier information, and arrival station in the second-level character string are parsed in sequence according to a preset parsing order, and the origin station, carrier information, and arrival station are associated to form a parsed flight segment, including:

[0055] Step 301: Match the parsed terminal information (departure station and arrival station) with the terminal information stored in the dynamic dictionary, and match the parsed carrier information with the carrier information stored in the dynamic dictionary.

[0056] Step 302: After the match is successful, the flight segments are analyzed based on the departure station, carrier information, and arrival station in the flight station information.

[0057] In one embodiment, the parsed terminal information (departure station and arrival station) is matched with the terminal information stored in the dynamic dictionary, and the parsed carrier information is matched with the carrier information stored in the dynamic dictionary, further comprising:

[0058] If the match fails, call the civil aviation system API to query the terminal information or carrier information that is not entered into the dynamic dictionary, and add the query results to the dynamic dictionary.

[0059] In a specific embodiment, priority is given to identifying whether the currently parsed terminal information and carrier information exist in the generated dynamic dictionary. If so, it is confirmed that the currently parsed string is the terminal information and carrier; if not, a request is made to call the API interface to identify whether it is other industry site codes. If so, the currently parsed string is the terminal information; if not, it continues to identify whether it is the carrier or the freight rate amount.

[0060] In step 105, when the fare amount in the second-level character string is parsed according to the preset parsing order, the parsed fare amount is associated with the parsed flight segment to generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment.

[0061] In a specific embodiment, the flight segments are: departure station 1-carrier 1-arrival station 1. For any flight segment, the substring after the arrival station may contain the amount, the carrier, or the value-added type.

[0062] [1] If it is an amount, it means that the flight segment before the amount is a fare unit. At this time, the fare group information unit number is generated, that is, fare unit 1 is obtained: {fare origin station, fare arrival station, fare amount, fare number}, and the fare group number (fare number of fare unit 1) of the flight segment is marked.

[0063] [2] If it is a carrier, then the current segment is a continuous segment of the previous segment. The arrival point of the previous segment is the departure point of the current carrier segment. The fare unit of the previous segment has not yet ended. You need to continue reading in sequence until you encounter the amount: --> arrival point --> carrier --> arrival point... carrier -> arrival point --> amount. At this time, the same as [1], get fare unit 1 and number it. All segments before the current amount belong to the same fare unit. Mark the fare group number (the fare number of fare unit 1) for the segment.

[0064] 【3】If it is a value-added type, it means that you have encountered an additional freight amount scenario. You need to read the value-added amount -> carrier -> destination station... carrier -> destination station -> amount in sequence. At this time, you will get two amounts. The first amount belongs to the additional freight amount, and the additional freight amount unit information {value-added type, value-added amount, value-added departure station, value-added arrival station} is generated; the second amount is the current freight unit amount. Same as 【1】 and 【2】, generate freight unit 1 and number it, and mark the fare group number (fare number of fare unit 1) of the flight segment before the second amount. This will give you the flight segment 1 and fare unit 1 in the following fare calculation column.

[0065] Segment 1 in the Rate Calculation column

[0066] {Original station: YIN

[0067] Carrier: CZ

[0068] Arrival station: URC

[0069] Rate Number: 1

[0070] Freight rate group number: 1}

[0071] Freight Unit 1

[0072] {Freight No.: 1

[0073] Freight rate group number: 1

[0074] Freight amount: 170.00}

[0075] In step 106, the carrier information of the fare unit is matched with the carrier information of the ticket coupon information to be associated, and the flight segment of the fare unit is matched with the flight segment of the ticket coupon information to be tested; after the match is successful, the fare amount information in the fare unit is associated with the ticket coupon information to be tested.

[0076] In a specific embodiment, the ticket coupon information is compared with the flight segment departure station, carrier, and arrival station of the fare unit. If a match is successful, the fare amount in the fare unit is the ticket coupon amount. Therefore, the ticket coupon fare group information is bound according to the flight segment fare number in the fare calculation column, and the split result is output.

[0077] In one embodiment, matching the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and matching the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested, further includes:

[0078] If the carrier information or flight segment information fails to match, an exception log of the unmatched information will be output to trigger a manual review operation.

[0079] The present invention also provides a device for associating a fare amount with a ticket coupon based on the fare calculation column, as described in the following embodiments. Since the principle behind this device is similar to the method for associating a fare amount with a ticket coupon based on the fare calculation column, the implementation of this device can be referenced to the implementation of the method for associating a fare amount with a ticket coupon based on the fare calculation column, and any repetitions will not be repeated.

[0080] Figure 4 Schematic diagram of a device for associating a coupon fare amount based on a fare calculation column in an embodiment of the present invention, the device comprising:

[0081] The fare calculation column string recognition module 401 is used to identify a corresponding string from the fare calculation column of the civil aviation system; the string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-built based on historical ticket information in the civil aviation system;

[0082] A first-level string generation module 402 is used to identify space characters in a string and use the space characters as separators to split the string to obtain multiple first-level strings;

[0083] The second-level string generation module 403 is configured to traverse the first-level strings and select candidate first-level strings containing a combination of the terminal substring and the carrier substring; and to use a machine learning algorithm to split the candidate first-level strings to generate second-level strings.

[0084] The parsed flight segment generation module 404 is configured to parse the second-level character string in sequence according to a preset parsing order to obtain the departure station, carrier information, and arrival station, and associate the departure station, carrier information, and arrival station to form a parsed flight segment;

[0085] The fare unit generation module 405 is configured to associate the parsed fare amount with the parsed flight segment after parsing the fare amount in the second-level character string according to the preset parsing order, and generate a corresponding fare unit; the fare unit is configured to store the association information between the fare amount and the flight segment;

[0086] The test coupon fare amount associating module 406 is used to match the carrier information of the fare unit with the carrier information of the test coupon information, and match the flight segments of the fare unit with the flight segments of the test coupon information; after successful matching, the fare amount information in the fare unit is associated with the test coupon information.

[0087] In one embodiment, the second-level character string generation module 403 is specifically configured to:

[0088] The candidate first-level strings are input into a trained string splitting model, which outputs the split positions of the airline station code and carrier code. The string splitting model is trained on a convolutional neural network model using the historical candidate first-level strings as input and the split positions of the airline station code and carrier code in the strings as output.

[0089] Based on the split positions of the terminal code and the carrier code, the candidate first-level character strings are split to generate second-level character strings.

[0090] In one embodiment, the parsed flight segment generation module 404 is specifically configured to:

[0091] Match the parsed terminal information (departure station and arrival station) with the terminal information stored in the dynamic dictionary, and match the parsed carrier information with the carrier information stored in the dynamic dictionary;

[0092] After a successful match, the flight segments are analyzed based on the departure station, carrier information, and arrival station in the terminal information.

[0093] In one embodiment, the parsed flight segment generation module 404 is further configured to:

[0094] The parsed terminal information: departure station and arrival station, is matched with the terminal information stored in the dynamic dictionary. If the match fails, the civil aviation system API is called to query the terminal information or carrier information that is not entered into the dynamic dictionary, and the query results are added to the dynamic dictionary.

[0095] In one embodiment, the module 406 for associating the amount of the interline fare to be tested is further configured to:

[0096] Match the carrier information of the fare unit with the carrier information of the ticket coupon to be associated. If the carrier information or flight segment information fails to match, an exception log of the unmatched information will be output to trigger a manual review operation.

[0097] An embodiment of the present invention further provides a computer device, Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, the above-mentioned method for associating ticket coupon fare amounts based on the fare calculation column is implemented.

[0098] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for associating the ticket coupon fare amount based on the fare calculation column is implemented.

[0099] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for associating ticket coupon fare amounts based on the fare calculation column.

[0100] In an embodiment of the present invention, a corresponding character string is identified from the fare calculation column of the civil aviation system; the character string includes a carrier substring, an airport substring and a fare amount substring; the fare calculation column is pre-built based on the historical ticket information of the civil aviation system; a space character in the character string is identified, and the character string is split using the space character as a separator to obtain multiple first-level character strings; the first-level character string is traversed to screen out candidate first-level character strings containing a combination of the airport substring and the carrier substring; a machine learning algorithm is used to split the candidate first-level character strings to generate second-level character strings; and a preset parsing algorithm is used to perform the splitting of the candidate first-level character strings. The first step is to parse the second-level character string in sequence, and then parse the departure station, carrier information, and arrival station in the second-level character string, and associate the departure station, carrier information, and arrival station to form a parsed flight segment; when the fare amount in the second-level character string is parsed according to the preset parsing order, the parsed fare amount is associated with the parsed flight segment to generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment; the carrier information of the fare unit is matched with the carrier information of the ticket information to be associated, and the flight segment of the fare unit is matched with the flight segment of the ticket information to be tested; after the match is successful, the fare amount information in the fare unit is associated with the ticket information to be tested. In the above process, the embodiment of the present invention parses the character string in the fare calculation column, combines the machine learning algorithm to intelligently segment the contiguous combination of flight station and carrier, and accurately associates the flight segment with the fare amount based on the preset parsing order, thereby solving the problems of flight segment attribution confusion and amount binding errors caused by the rigidity of the static rule base and character-by-character parsing in the traditional method. This enables the refined splitting of the fare calculation column, ensures the precise matching of the fare amount with the ticket segment, and can accurately obtain the civil aviation ticket fare amount, significantly improving the automation efficiency and accuracy of civil aviation ticket settlement.

[0101] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is 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 in the scope of protection of the present invention.

Claims

1. A method for associating a ticket coupon fare amount based on a fare calculation column, characterized in that: include: Identifying a corresponding character string from a fare calculation column in the civil aviation system; the character string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket coupon information in the civil aviation system; Identify the space characters in the string, use the space characters as delimiters to split the string, and obtain multiple first-level strings; Traverse the first-level strings and select candidate first-level strings that contain a combination of the terminal substring and the carrier substring; use a machine learning algorithm to split the candidate first-level strings to generate second-level strings; According to the preset parsing order, the departure station, carrier information, and arrival station in the second-level character string are parsed in sequence, and the departure station, carrier information, and arrival station are associated to form a parsed flight segment; When the freight rate amount in the second-level character string is parsed according to the preset parsing order, the parsed freight rate amount is associated with the parsed flight segment to generate a corresponding freight rate unit; The freight rate unit is used to store the association information between the freight rate amount and the flight segment; Match the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and match the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested; after successful matching, associate the fare amount information in the fare unit with the ticket coupon information to be tested.

2. The method according to claim 1, wherein Before using a machine learning algorithm to split the candidate first-level strings and generate second-level strings, the following steps are performed: The candidate first-level strings are input into a trained string splitting model, which outputs the split positions of the airline station code and carrier code. The string splitting model is trained on a convolutional neural network model using the historical candidate first-level strings as input and the split positions of the airline station code and carrier code in the strings as output. Based on the split positions of the terminal code and the carrier code, the candidate first-level character strings are split to generate second-level character strings.

3. The method according to claim 1, wherein According to the preset parsing order, the departure station, carrier information, and arrival station in the second-level string are parsed in sequence, and the departure station, carrier information, and arrival station are associated to form the parsed flight segments, including: Match the parsed terminal information (departure station and arrival station) with the terminal information stored in the dynamic dictionary, and match the parsed carrier information with the carrier information stored in the dynamic dictionary; After a successful match, the flight segments are analyzed based on the departure station, carrier information, and arrival station in the terminal information.

4. The method according to claim 3, wherein Match the parsed terminal information (departure station and arrival station) with the terminal information stored in the dynamic dictionary, and match the parsed carrier information with the carrier information stored in the dynamic dictionary. Also included: If the match fails, call the civil aviation system API to query the terminal information or carrier information that is not entered into the dynamic dictionary, and add the query results to the dynamic dictionary.

5. The method according to claim 1, wherein Matching the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and matching the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested, further comprising: If the carrier information or flight segment information fails to match, an exception log of the unmatched information will be output to trigger a manual review operation.

6. A device for associating a ticket coupon fare amount based on a fare calculation column, characterized in that: include: A fare calculation column string recognition module is used to identify a corresponding string from the fare calculation column of the civil aviation system; the string includes a carrier substring, an airport substring, and a fare amount substring; the fare calculation column is pre-constructed based on historical ticket information in the civil aviation system; The first-level string generation module is used to identify space characters in a string and split the string using the space characters as delimiters to obtain multiple first-level strings; The second-level string generation module is used to traverse the first-level strings and screen out candidate first-level strings that contain a combination of the terminal substring and the carrier substring; it uses a machine learning algorithm to split the candidate first-level strings to generate second-level strings; The parsing segment generation module is used to parse the departure station, carrier information, and arrival station in the second-level character string in a preset parsing order, and associate the departure station, carrier information, and arrival station to form a parsed segment; The fare unit generation module is used to associate the parsed fare amount with the parsed flight segment when the fare amount in the second-level character string is parsed according to the preset parsing order, and generate a corresponding fare unit; the fare unit is used to store the association information between the fare amount and the flight segment; The fare amount association module for the ticket coupon to be tested is used to match the carrier information of the fare unit with the carrier information of the ticket coupon information to be associated, and to match the flight segments of the fare unit with the flight segments of the ticket coupon information to be tested; after successful matching, the fare amount information in the fare unit is associated with the ticket coupon information to be tested.

7. The device according to claim 6, characterized in that The second-level string generation module is specifically used for: The candidate first-level strings are input into a trained string splitting model, which outputs the split positions of the airline station code and carrier code. The string splitting model is trained on a convolutional neural network model using the historical candidate first-level strings as input and the split positions of the airline station code and carrier code in the strings as output. Based on the split positions of the terminal code and the carrier code, the candidate first-level character strings are split to generate second-level character strings.

8. The device according to claim 6, wherein Parsing segment generation module, specifically used for: Match the parsed terminal information (departure station and arrival station) with the terminal information stored in the dynamic dictionary, and match the parsed carrier information with the carrier information stored in the dynamic dictionary; After a successful match, the flight segments are analyzed based on the departure station, carrier information, and arrival station in the terminal information.

9. The device according to claim 8, wherein The flight segment generation module is also used to: The parsed terminal information: departure station and arrival station, is matched with the terminal information stored in the dynamic dictionary. If the match fails, the civil aviation system API is called to query the terminal information or carrier information that is not entered into the dynamic dictionary, and the query results are added to the dynamic dictionary.

10. The device according to claim 6, wherein The module for associating the intermodal price amount of the ticket to be tested is also used for: Match the carrier information of the fare unit with the carrier information of the ticket coupon to be associated. If the carrier information or flight segment information fails to match, an exception log of the unmatched information will be output to trigger a manual review operation.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images