Data alignment method and device

Abstract

The invention discloses a data alignment method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining target cabin sound data and target flight data corresponding to a target flight terminal; performing parameter analysis on the target flight data to obtain a plurality of air-ground dialogue moments; sorting the plurality of air-ground dialogue moments according to time to obtain a first time sequence corresponding to the plurality of air-ground dialogue moments; cutting the target cabin sound data to obtain a second time sequence corresponding to a plurality of cabin sound moments; and determining the alignment moment of the target cabin sound data and the target flight data according to the overlapping degree of the first time sequence and the second time sequence. According to the embodiment, the alignment moment between the target cabin sound data and the target flight data can be accurately determined, so that effective alignment between the target cabin sound data and the target flight data is realized, and the accuracy of data analysis in subsequent accident analysis and flight quality evaluation is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method and device for data alignment. Background Art

[0002] In the aviation field, flight data and cabin voice data are important bases for accident analysis and flight quality evaluation. However, due to abnormal problems such as different data sources, inconsistent timestamp formats, and data missing of flight data and cabin voice data, there may be a problem of data misalignment between flight data and cabin voice data in the same flight segment, thus affecting the accuracy and reliability of subsequent data analysis. Therefore, there is an urgent need for a method and device capable of realizing data alignment between flight data and cabin voice data. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and device for data alignment. By separately processing target flight data and target cabin voice data, and based on the overlap degree between the first time series corresponding to the target flight data and the second time series corresponding to the target cabin voice data, the alignment moment between the target cabin voice data and the target flight data can be accurately determined, so as to realize effective alignment between the target cabin voice data and the target flight data, and greatly improve the accuracy of subsequent data analysis in accident analysis and flight quality evaluation.

[0004] To achieve the above object, according to one aspect of the embodiments of the present invention, a method for data alignment is provided.

[0005] A method for data alignment according to an embodiment of the present invention includes: obtaining target cabin voice data and target flight data corresponding to a target flight terminal; performing parameter analysis on the target flight data to obtain a plurality of ground-air conversation moments; sorting the plurality of ground-air conversation moments in time to obtain a first time series corresponding to the plurality of ground-air conversation moments; cutting the target cabin voice data to obtain a second time series corresponding to a plurality of cabin voice moments; and determining an alignment moment between the target cabin voice data and the target flight data according to the overlap degree between the first time series and the second time series.

[0006] Optionally, the obtaining target cabin voice data and target flight data corresponding to a target flight terminal includes: obtaining target cabin voice data corresponding to a target flight terminal; determining a plurality of flight segments corresponding to the target flight terminal according to the target cabin voice data; respectively obtaining flight data corresponding to each flight segment, and determining the target flight data from the plurality of flight data.

[0007] Optionally, performing parameter analysis on the target flight data to obtain multiple air-ground dialogue moments includes: performing very high frequency (VHF) parameter analysis on the target flight data to generate a VHF parameter result corresponding to each flight moment; in response to the VHF parameter result indicating that the VHF parameter result is in an enabled state, using the flight moment corresponding to the VHF parameter result as the air-ground dialogue moment.

[0008] Optionally, sorting the multiple air-ground dialogue moments by time to obtain a first time series corresponding to the multiple air-ground dialogue moments includes: sorting the multiple air-ground dialogue moments by time to generate an intermediate time series; performing binary conversion on the intermediate time series to obtain the first time series.

[0009] Optionally, cutting the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments includes: cutting the target cabin sound data according to a preset time period to obtain multiple cabin sound moments; generating the second time series according to whether there is a voice signal at the cabin sound moment; wherein, if there is a voice signal at the cabin sound moment, it is recorded as 1; if there is no voice signal at the cabin sound moment, it is recorded as 0.

[0010] Optionally, determining the alignment moment between the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series includes: for each target cabin sound moment in the second time series: performing a sliding dot product operation on the target cabin sound moment and all moments in the second time series to determine the target overlap degree between the target cabin sound moment and the second time series; determining the alignment moment between the target cabin sound data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to the respective target cabin sound moments.

[0011] Optionally, determining the alignment moment between the target cabin sound data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to the respective target cabin sound moments includes: obtaining the machine sound data of the target flight terminal; using the target cabin sound moment with the largest target overlap degree among the target overlap degrees respectively corresponding to the respective target cabin sound moments as the preliminary alignment moment, and determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment; if so, using the preliminary alignment moment as the alignment moment.

[0012] Optionally, the method further includes: if not, using the target cabin sound moment with the second largest target overlap degree among the target overlap degrees respectively corresponding to the respective target cabin sound moments as the preliminary alignment moment, and repeating the step of determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment until the alignment moment is determined.

[0013] Optionally, the method further includes: performing length alignment on the target cabin sound data and the target flight data; and / or, determining that the target cabin sound data and the target flight data include mandatory fields; and / or, performing missing value processing on the target cabin sound data and the target flight data; and / or, performing format conversion on the target cabin sound data and the target flight data.

[0014] To achieve the above object, according to another aspect of the embodiments of the present invention, a data alignment device is provided.

[0015] A data alignment device according to an embodiment of the present invention includes: An acquisition module, which acquires target cabin sound data and target flight data corresponding to a target flight terminal; An analysis module, which is used to perform parameter analysis on the target flight data to obtain multiple ground-air conversation moments; A first sorting module, which is used to sort multiple ground-air conversation moments in time to obtain a first time series corresponding to multiple ground-air conversation moments; A second sorting module, which is used to cut the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments; A determination module, which is used to determine the alignment moment of the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series.

[0016] To achieve the above object, according to another aspect of the embodiments of the present invention, an electronic device for data alignment is provided.

[0017] An electronic device for data alignment according to an embodiment of the present invention includes: one or more processors; a storage device, which is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a data alignment method according to an embodiment of the present invention.

[0018] To achieve the above object, according to yet another aspect of the embodiments of the present invention, a computer-readable storage medium is provided.

[0019] A computer-readable storage medium according to an embodiment of the present invention, on which a computer program is stored. When the program is executed by a processor, it implements a data alignment method according to an embodiment of the present invention.

[0020] To achieve the above object, according to yet another aspect of the embodiments of the present invention, a computer program product is provided.

[0021] A computer program product according to an embodiment of the present invention, when the program is executed by a processor, implements a data alignment method according to an embodiment of the present invention.

[0022] One embodiment of the above invention has the following advantages or beneficial effects: By separately processing the target flight data and the target cabin voice data, and based on the overlap degree between the first time series corresponding to the target flight data and the second time series corresponding to the target cabin voice data, the alignment moment between the target cabin voice data and the target flight data can be accurately determined, thereby realizing the effective alignment between the target cabin voice data and the target flight data, and greatly improving the accuracy of data analysis in subsequent accident analysis and flight quality evaluation.

[0023] The further effects of the above non-conventional optional methods will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Among them: Figure 1 is a schematic diagram of the main process of the data alignment method according to an embodiment of the present invention; Figure 2 is a schematic diagram of the main process of obtaining target cabin voice data and target flight data according to an embodiment of the present invention; Figure 3 is a schematic diagram of the main process of obtaining multiple ground-air dialogue moments according to an embodiment of the present invention; Figure 4 is a schematic diagram of the main process of obtaining the first time series according to an embodiment of the present invention; Figure 5 is a schematic diagram of the main process of obtaining the second time series according to an embodiment of the present invention; Figure 6 is a schematic diagram of the main process of determining the alignment moment between the target cabin voice data and the target flight data according to an embodiment of the present invention; Figure 7 is a schematic diagram of the main modules of the data alignment device according to an embodiment of the present invention; Figure 8 is an exemplary system architecture diagram to which an embodiment of the present invention can be applied; Figure 9 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0025] The exemplary embodiments of the present invention will be described below in conjunction with the accompanying drawings. Various details of the embodiments of the present invention are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0026] It should be noted that, without conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0027] It should be noted that in the technical solutions of the present disclosure, in terms of the collection, gathering, updating, analysis, processing, use, transmission, storage, etc. of the user's personal information, they all comply with the provisions of relevant laws and regulations, are used for legal purposes, and do not violate public order and good customs. Necessary measures are taken for the user's personal information to prevent illegal access to the user's personal information data, and to safeguard the security of the user's personal information, network security, and national security.

[0028] Figure 1 It is a schematic diagram of the main steps of the data alignment method according to the embodiments of the present invention.

[0029] As Figure 1 shown, the data alignment method of the embodiments of the present invention mainly includes the following steps: Step S101: Obtain the target cabin sound data and target flight data corresponding to the target flight terminal; Step S102: Perform parameter analysis on the target flight data to obtain multiple air-ground conversation moments; Step S103: Sort the multiple air-ground conversation moments according to time to obtain a first time series corresponding to the multiple air-ground conversation moments; Step S104: Cut the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments; Step S105: Determine the alignment moment between the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series.

[0030] Among them, the data alignment method provided by the present invention can be particularly applied in the civil aviation field. Usually, the cabin voice data and flight data are for a single civil airliner. Therefore, the target flight terminal in the embodiments of the present invention can be understood as a single civil airliner. It can be seen from the above process that in the embodiments of the present invention, the target cabin voice data and target flight data are actually processed respectively to obtain a first time series corresponding to the target flight data and a second time series corresponding to the target cabin voice data. Then, by matching the overlap degree of the first time series and the second time series, the alignment moment of the target flight data and the target cabin voice data is obtained. It can be understood that for different flight terminals, the cabin voice data and flight data are also different. Therefore, the target cabin voice data and target flight data in the embodiments of the present invention are both corresponding to the target flight terminal. Only by obtaining the target cabin voice data and target flight data corresponding to the target flight terminal can the effective alignment of the target cabin voice data and the target flight data be realized through a series of subsequent analysis processes.

[0031] Specifically, the cabin voice data refers to the sound data in the flight terminal recorded by the cabin voice recorder. Usually, the cabin voice data starts to be recorded after the flight terminal is started until the flight terminal is closed, that is, the data recorded between the start-up and shutdown of the flight terminal, which may include: machine sound data (i.e., the machine voice broadcast sound corresponding to different states of the flight terminal) and air-ground dialogue data (i.e., the dialogue sound between the ground-air control center and the captain). Exemplarily, when the flight speed of the flight terminal reaches V1, the machine will broadcast the sound of "V one". At this time, the cabin voice recorder will record the sound of "V one". When the flight terminal is in the landing phase and the radio altitude is 100 feet, the machine will broadcast the sound of "one hundred". At this time, the cabin voice recorder will record the sound of "one hundred". When the flight terminal is in the landing phase and the radio altitude is 50 feet, the machine broadcasts the sound of "fifty". At this time, the cabin voice recorder will record the sound of "fifty".

[0032] The flight data refers to the data between the takeoff and landing of the flight terminal. That is to say, the recording lengths of the flight data and the cabin voice data are usually inconsistent, which is also the analysis difficulty encountered in analyzing the flight data and the cabin voice data in the prior art. Exemplarily, the flight data may include various parameters of the flight terminal, such as flight altitude, airspeed, acceleration, pitch attitude, thrust lever position, reverse thrust state, etc. Only after the effective alignment of the cabin voice data and the flight data can it be accurately judged whether the captain's operation is in error during the subsequent accident analysis, so as to determine the cause of the accident.

[0033] Next, the embodiments of the present invention will separately and elaborately describe the process of obtaining the target cabin sound data and the target flight data in step S101, as well as the specific alignment processes of steps S102 to S105.

[0034] For the process of obtaining the target cabin sound data and the target flight data in step S101, in an alternative embodiment, it is necessary to determine from multiple flight segments corresponding to the target flight terminal, that is, as Figure 2 shown, including: Step S201: Obtain the target cabin sound data corresponding to the target flight terminal; Step S202: Determine multiple flight segments corresponding to the target flight terminal according to the target cabin sound data; Step S203: Obtain the flight data corresponding to each flight segment respectively, and determine the target flight data from the multiple flight data.

[0035] Exemplarily, for a civil airliner, a civil airliner usually flies multiple flight segments continuously in a startup state: for example, it first flies from airport A to airport B, then continues to fly to airport C, and finally returns to airport A. Then the flight segments corresponding to this civil airliner actually include three segments: segment A - B, segment B - C, and segment C - A. However, the civil airliner is always in a startup state, so the multiple flight segments actually correspond to one piece of cabin sound data. In the embodiments of the present invention, the multiple flight segments corresponding to the target flight terminal can be determined first according to the data duration of the target cabin sound data, then the flight data corresponding to each flight segment can be obtained respectively, and finally the flight data to be compared can be used as the target flight data.

[0036] In an alternative embodiment, for the specific process of obtaining multiple air - ground conversation times in step S102 of the embodiments of the present invention, it can be as Figure 3 shown, including: Step S301: Obtain the target flight data corresponding to the target flight terminal; Step S302: Perform very high frequency (VHF) parameter analysis on the target flight data to generate VHF parameter results corresponding to each flight moment; Step S303: In response to the VHF parameter result indicating that the VHF parameter is in an enabled state, use the flight moment corresponding to the VHF parameter result as the air - ground conversation time.

[0037] Among them, the target flight data is often stored in the QAR (Quick Access Recorder Data) data recorder of the flight terminal, which is mainly used in the fields of flight quality monitoring, safety assessment, maintenance, and accident investigation. The QAR very high frequency (VHF) parameter is a parameter that records whether the VHF communication is enabled. The specific parameter values include emit and not emit. Among them, the parameter value is emit in the enabled state and not emit in the disabled state.

[0038] In the actual application process, the air-ground conversation moment is a time dimension, and a large amount of computing and storage space are required in the data processing process. Therefore, in the embodiments of the present invention, the air-ground conversation moment is converted. By converting it into a binary first time series, the computational amount of data calculation in the subsequent data alignment process can be effectively improved. Specifically, the process of obtaining the first time series in step S103 is as Figure 4 shown, including: Step S401: Obtain the target flight data corresponding to the target flight terminal; Step S402: Analyze the VHF parameters of the target flight data to generate the VHF parameter results corresponding to each flight moment; Step S403: In response to the VHF parameter being in the enabled state, use the flight moment corresponding to the VHF parameter result as the air-ground conversation moment; Step S404: Sort the multiple air-ground conversation moments in time to generate an intermediate time series; Step S405: Perform binary conversion on the intermediate time series to obtain the first time series.

[0039] Exemplarily, taking the intermediate time series T={t1, t2, ⋯, ti} arranged by multiple air-ground conversation moments as an example, where ti represents the i-th air-ground conversation moment, and each air-ground conversation moment is 1 / 8 second (i.e., the time accuracy is 125 milliseconds). By performing binary conversion on the above intermediate time series T, the first time series S={s1, s2, ⋯, sn} can be obtained, where n = total flight data duration (seconds) × 8. If there is a corresponding t in sn, then sn = 1; otherwise, sn = 0.

[0040] Through the above process, the first time series is determined from the target flight data. Next, the process of obtaining the second time series will be specifically described. In an optional embodiment, the process of obtaining the second time series in step S104 is as Figure 5 shown, including: Step S501: Obtain the target flight data corresponding to the target flight terminal; Step S502: Cut the target cabin sound data according to a preset time period to obtain multiple cabin sound moments; Step S503: Generate a second time series according to whether there is a voice signal at the cabin sound moment; Among them, if there is a voice signal at the cabin sound moment, it is recorded as 1; if there is no voice signal at the cabin sound moment, it is recorded as 0.

[0041] Among them, the preset time period can be the same as the unit of the ground-air dialogue moment in the target flight data, or set to 1 / 8 second (125 milliseconds). Exemplarily, the second time series can be represented by C, C = {c1, c2, ⋯, cn}. If there is a voice signal in cn, then cn = 1, otherwise cn = 0. It can be seen that in the embodiments of the present invention, both the first time series corresponding to the target flight data and the second time series corresponding to the target cabin sound data are represented in binary, and both the voice signal and the time signal are converted into quantifiable numerical sequences, thereby achieving data alignment.

[0042] Specifically, for step S105, in an alternative embodiment, it includes: for each target cabin sound moment in the second time series: perform a sliding dot product operation on the target cabin sound moment and all moments in the first time series to determine the target overlap degree between the target cabin sound moment and the first time series; determine the alignment moment between the target cabin sound data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to each of the target cabin sound moments.

[0043] Exemplarily, reverse the above second time series C (from cn to c1) and perform a sliding dot product operation with the first time series S (from s1 to sn) respectively. The sliding dot product operation formula is as follows formula (1): Formula (1) Among them, j represents the sliding window, N represents the maximum value of the number of moments in the first time series and the second time series, and this maximum value is obtained by aligning the lengths based on sn and cn; , when is not within the range from 1 to sn, , when k is not within the range from 1 to cn, ; for each sliding window, there corresponds a dot product value. The larger the dot product value, the higher the time overlap degree between the cabin sound moment in the target cabin sound data and the ground-air dialogue moment in the target flight data, and the higher the probability of matching and alignment. Therefore, in an alternative embodiment, the sliding window with the largest dot product value can be used as the alignment moment between the target cabin sound data and the target flight data.

[0044] However, during the flight of the actual flight terminal, the machine sound data can also provide an important basis for accident analysis and flight quality evaluation. Therefore, in a further optional embodiment, whether there is machine sound data can be further referred to as the criterion for determining the alignment moment. As Figure 6 shown, determining the alignment moment of the target cabin sound data and the target flight data includes: Step S601: For each target cabin sound moment in the second time series: perform a sliding dot product operation on the target cabin sound moment and all the moments in the second time series to determine the target overlap degree between the target cabin sound moment and the second time series; Step S602: Obtain the machine sound data of the target flight terminal; Step S603: Use the target cabin sound moment with the largest target overlap degree corresponding to each target cabin sound moment as the preliminary alignment moment, and determine whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment; If so, execute Step S604: Use the preliminary alignment moment as the alignment moment; If not, execute Step S605: Use the target cabin sound moment with the second largest target overlap degree corresponding to each target cabin sound moment as the preliminary alignment moment, and repeat the step of determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment until the alignment moment is determined.

[0045] Among them, for the process of determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment in Step S603, a preset time offset can be set, and it is determined whether there is a target machine sound that matches the preliminary alignment moment within the preset time offset. Through the above Steps S601 to S605, it is possible to further determine whether the preliminary alignment moment can be used as the alignment moment in combination with the machine sound data, effectively improving the accuracy of the determined alignment moment.

[0046] In an optional embodiment, after Step S101 and before Step S102, the data alignment method provided by the present invention further includes: performing length alignment on the target cabin sound data and the target flight data. Specifically, when the total durations of the target cabin sound data and the target flight data are inconsistent, the data with the shorter total duration can be extended to the same length as the data with the longer total duration by padding zeros at the end of the data, that is, without changing the original data time series, the consistency of the total durations of the target cabin sound data and the target flight data is achieved by filling invalid values, so as to ensure that each time point in the target cabin sound data and the target flight data can correspond one by one.

[0047] In an alternative embodiment, after step S101 and before step S102, the method for data alignment provided by the present invention further includes: determining that the target cabin sound data and the target flight data include mandatory fields. Exemplarily, the mandatory fields in the target flight data may be qar data (such as qar start time, qar end time, etc.), very high frequency parameters, radio altitude, landing altitude 100, landing altitude 50, etc. The mandatory fields in the target cabin sound data may be audio start time and audio end time, etc.

[0048] In a further alternative embodiment, after obtaining the target cabin sound data and the target flight data, it is also necessary to check the continuity and rationality of the target cabin sound data and the target flight data to ensure that each time point corresponds to unique data, and when data is missing, perform missing value processing on the target cabin sound data and the target flight data. Exemplarily, the missing value processing may include filling missing values and repairing outliers. For missing values, they can be reasonably filled according to the context data, and for missing values that cannot be filled, they can be marked as special values for subsequent manual filling. For outliers, statistical methods can be used for identification, and the identified outliers can be corrected or removed according to the context.

[0049] In a further alternative embodiment, format conversion can also be performed on the target cabin sound data and the target flight data. Specifically, the timestamps in the target cabin sound data and the target flight data can be unified to UTC time, Beijing time, or QAR time, and the minimum unit of time is 1 / 8 second, to ensure that the timestamps in the target cabin sound data and the target flight data are in the same time zone and use a unified time format and time unit.

[0050] According to the method for data alignment of the embodiments of the present invention, by separately processing the target flight data and the target cabin sound data, and based on the overlap degree between the first time series corresponding to the target flight data and the second time series corresponding to the target cabin sound data, the alignment moment between the target cabin sound data and the target flight data can be accurately determined, thereby realizing the effective alignment between the target cabin sound data and the target flight data, and greatly improving the accuracy of data analysis in subsequent accident analysis and flight quality evaluation.

[0051] Figure 7 It is a schematic diagram of the main modules of the device for data alignment according to the embodiments of the present invention.

[0052] As Figure 7 shown, the device 700 for data alignment according to the embodiments of the present invention includes: An acquisition module 701, which acquires the target cabin sound data and the target flight data corresponding to the target flight terminal; An analysis module 702, configured to perform parameter analysis on the target flight data to obtain multiple ground-air dialogue moments; A first sorting module 703, configured to sort the multiple ground-air dialogue moments according to time to obtain a first time series corresponding to the multiple ground-air dialogue moments; A second sorting module 704, configured to cut the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments; A determination module 705, configured to determine the alignment moment between the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series.

[0053] In an optional embodiment of the present invention, the acquisition module 701 is further configured to acquire target cabin sound data corresponding to a target flight terminal; determine multiple flight segments corresponding to the target flight terminal according to the target cabin sound data; respectively acquire flight data corresponding to each flight segment, and determine the target flight data from the multiple flight data.

[0054] In an optional embodiment of the present invention, the analysis module 702 is further configured to perform very high frequency (VHF) parameter analysis on the target flight data to generate a VHF parameter result corresponding to each flight moment; in response to the VHF parameter result being in an enabled state, use the flight moment corresponding to the VHF parameter result as the ground-air dialogue moment.

[0055] In an optional embodiment of the present invention, the first sorting module 703 is further configured to sort the multiple ground-air dialogue moments according to time to generate an intermediate time series; perform binary conversion on the intermediate time series to obtain the first time series.

[0056] In an optional embodiment of the present invention, the second sorting module 704 is further configured to cut the target cabin sound data according to a preset time period to obtain multiple cabin sound moments; generate the second time series according to whether there is a voice signal at the cabin sound moment; wherein, if there is a voice signal at the cabin sound moment, record it as 1; if there is no voice signal at the cabin sound moment, record it as 0.

[0057] In an optional embodiment of the present invention, the determination module 705 is further configured to, for each target cabin sound moment in the second time series: perform a sliding dot product operation on the target cabin sound moment and all moments in the first time series to determine the target overlap degree between the target cabin sound moment and the first time series; determine the alignment moment between the target cabin sound data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to the respective target cabin sound moments.

[0058] In an alternative embodiment of the present invention, the determining module 705 is further configured to obtain the machine sound data of the target flight terminal; use the target cabin sound moment corresponding to the largest target overlap degree among all the target cabin sound moments as the preliminary alignment moment, and determine whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment; if so, use the preliminary alignment moment as the alignment moment.

[0059] In an alternative embodiment of the present invention, the determining module 705 is further configured to, if not, use the target cabin sound moment corresponding to the second largest target overlap degree among all the target cabin sound moments as the preliminary alignment moment, and repeat the step of determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment until the alignment moment is determined.

[0060] In an alternative embodiment of the present invention, the apparatus for data alignment further includes: an inspection module, configured to perform length alignment on the target cabin sound data and the target flight data; and / or, determine that the target cabin sound data and the target flight data include necessary fields; and / or, perform missing value processing on the target cabin sound data and the target flight data; and / or, perform format conversion on the target cabin sound data and the target flight data.

[0061] According to the apparatus for data alignment of the embodiments of the present invention, by separately processing the target flight data and the target cabin sound data, and based on the overlap degree between the first time series corresponding to the target flight data and the second time series corresponding to the target cabin sound data, the alignment moment between the target cabin sound data and the target flight data can be accurately determined, thereby realizing the effective alignment between the target cabin sound data and the target flight data, and greatly improving the accuracy of data analysis in subsequent accident analysis and flight quality evaluation.

[0062] Figure 8 An exemplary system architecture 800 is shown to which the method for data alignment or the apparatus for data alignment of the embodiments of the present invention can be applied.

[0063] As Figure 8 shown, the system architecture 800 may include flight terminals 801, 802, 803, a network 804, and a server 805. The network 804 is used to provide a medium for communication links between the flight terminals 801, 802, 803 and the server 805. The network 804 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0064] Users can use flight terminals 801, 802, and 803 to interact with server 805 via network 804 to receive or send data, etc. Various sensors can be installed on flight terminals 801, 802, and 803 to monitor various flight data of the flight terminals in real time.

[0065] Server 805 can be a server that provides various services. For example, it can be a background management server that supports the target cabin sound data and target flight data sent by users using flight terminals 801, 802, and 803. The background management server can analyze and process data such as the received target cabin sound data and target flight data, and perform accident analysis, etc. based on the processing results (such as the alignment time).

[0066] It should be noted that the data alignment method provided in the embodiments of the present invention is generally executed by server 805. Correspondingly, the data alignment device is generally set in server 805.

[0067] It should be understood that Figure 8 the numbers of the terminal devices, networks, and servers in

[0068] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 9 is a schematic structural diagram of a computer system 900 of a terminal device suitable for implementing the embodiments of the present invention. Figure 9 The terminal device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0069] As Figure 9 shown, computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to the program stored in read-only memory (ROM) 902 or the program loaded from storage section 908 into random access memory (RAM) 903. In RAM 903, various programs and data required for the operation of system 900 are also stored. CPU 901, ROM 902, and RAM 903 are connected to each other via bus 904. Input / output (I / O) first interface 905 is also connected to bus 904.

[0070] The following components are connected to the first I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a first network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the first I / O interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.

[0071] Specifically, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product including a computer program carried on a computer-readable medium, the computer program including program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by a central processing unit (CPU) 901, the above-described functions defined in the system of the present invention are performed.

[0072] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0074] The modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described modules can also be provided in a processor. For example, it can be described as: a processor includes an acquisition module, an analysis module, a first sorting module, a second sorting module, and a determination module. Among them, the names of these modules do not constitute a limitation to the module itself in some cases. For example, the acquisition module can also be described as "a module for acquiring target cabin sound data and target flight data corresponding to a target flight terminal".

[0075] As another aspect, the present invention also provides a computer-readable medium. The computer-readable medium can be included in the device described in the above embodiments; it can also exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by the device, the device includes: acquiring target cabin sound data and target flight data corresponding to a target flight terminal; performing parameter analysis on the target flight data to obtain multiple air-ground conversation moments; sorting the multiple air-ground conversation moments in time to obtain a first time series corresponding to the multiple air-ground conversation moments; cutting the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments; and determining an alignment moment between the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series.

[0076] According to the technical solution of the embodiments of the present invention, by separately processing the target flight data and the target cabin sound data, and based on the overlap degree between the first time series corresponding to the target flight data and the second time series corresponding to the target cabin sound data, the alignment moment between the target cabin sound data and the target flight data can be accurately determined, so as to realize the effective alignment between the target cabin sound data and the target flight data, and greatly improve the accuracy of data analysis in subsequent accident analysis and flight quality evaluation.

[0077] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for data alignment, characterized in that, Including: Obtaining target cabin audio data and target flight data corresponding to a target flight terminal; Performing parameter analysis on the target flight data to obtain multiple air-ground conversation moments; Sorting the multiple air-ground conversation moments by time to obtain a first time series corresponding to the multiple air-ground conversation moments; Cutting the target cabin audio data to obtain a second time series corresponding to multiple cabin audio moments; Determining an alignment moment between the target cabin audio data and the target flight data according to the overlap degree between the first time series and the second time series.

2. The method according to claim 1, characterized in that, The obtaining of the target cabin audio data and the target flight data corresponding to the target flight terminal includes: Obtaining target cabin audio data corresponding to the target flight terminal; Determining multiple flight segments corresponding to the target flight terminal according to the target cabin audio data; Respectively obtaining flight data corresponding to each flight segment, and determining the target flight data from the multiple flight data.

3. The method according to claim 1, characterized in that, The performing of parameter analysis on the target flight data to obtain multiple air-ground conversation moments includes: Performing very high frequency (VHF) parameter analysis on the target flight data to generate VHF parameter results corresponding to each flight moment; In response to the VHF parameter results indicating that the VHF parameter is in an enabled state, using the flight moment corresponding to the VHF parameter results as the air-ground conversation moment.

4. The method according to claim 1, characterized in that, The sorting of the multiple air-ground conversation moments by time to obtain a first time series corresponding to the multiple air-ground conversation moments includes: Sorting the multiple air-ground conversation moments by time to generate an intermediate time series; Performing binary conversion on the intermediate time series to obtain the first time series.

5. The method according to claim 4, characterized in that, The cutting of the target cabin audio data to obtain a second time series corresponding to multiple cabin audio moments includes: Cutting the target cabin audio data according to a preset time period to obtain multiple cabin audio moments; Generating the second time series according to whether there is a voice signal at the cabin audio moment; Wherein, if there is a voice signal at the cabin audio moment, it is recorded as 1; if there is no voice signal at the cabin audio moment, it is recorded as 0.

6. The method according to claim 1, wherein The determining of the alignment moment between the target cabin audio data and the target flight data according to the overlap degree between the first time series and the second time series includes: For each target cabin audio moment in the second time series: performing a sliding dot product operation between the target cabin audio moment and all moments in the first time series to determine the target overlap degree between the target cabin audio moment and the first time series; Determining the alignment moment between the target cabin audio data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to the respective target cabin audio moments.

7. The method according to claim 6, characterized in that, The determining of the alignment moment between the target cabin audio data and the target flight data according to the magnitudes of the target overlap degrees respectively corresponding to the respective target cabin audio moments includes: Obtaining machine voice data of the target flight terminal; Using the target cabin sound moment corresponding to the largest target overlap degree among each of the target cabin sound moments as the preliminary alignment moment, determine whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment; If so, use the preliminary alignment moment as the alignment moment.

8. The method according to claim 7, wherein Further includes: If not, use the target cabin sound moment corresponding to the second largest target overlap degree among each of the target cabin sound moments as the preliminary alignment moment, and repeatedly execute the step of determining whether there is a target machine sound in the machine sound data that matches the preliminary alignment moment until the alignment moment is determined.

9. The method according to claim 1, characterized in that Further includes: Perform length alignment on the target cabin sound data and the target flight data; And / or, Determine that the target cabin sound data and the target flight data include mandatory fields; And / or, Perform missing value processing on the target cabin sound data and the target flight data; And / or, Perform format conversion on the target cabin sound data and the target flight data.

10. A data alignment device, characterized in that, Includes: An acquisition module that acquires target cabin sound data and target flight data corresponding to a target flight terminal; An analysis module for performing parameter analysis on the target flight data to obtain multiple ground-air dialogue moments; A first sorting module for sorting the multiple ground-air dialogue moments in time to obtain a first time series corresponding to the multiple ground-air dialogue moments; A second sorting module for cutting the target cabin sound data to obtain a second time series corresponding to multiple cabin sound moments; A determination module for determining the alignment moment of the target cabin sound data and the target flight data according to the overlap degree between the first time series and the second time series.

11. An electronic device for data alignment, characterized in that, Includes: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-9.

12. A computer-readable medium having a computer program stored thereon, characterized in that, The program, when executed by a processor, implements the method according to any one of claims 1-9.

13. A computer program product, including a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images