Flight training method and device based on flight state and medium

Abstract

The invention provides a flight training method and device based on a flight state and a medium, and relates to the technical field of intelligent flight training.The method comprises the steps that if a target user is located at a main driving position, a plurality of standard instructions are obtained through matching, and if the number of matched marking instructions is larger than 1, the target user does not need to be trained; if yes, randomly determining one matched annotation instruction as a target instruction corresponding to the target voice; the first matching degree threshold value is comprehensively determined according to the current training time length, the current environment noise intensity, the current flight height and the current flight speed of the target user, and the corresponding first matching degree threshold values are different in different flight states, so that the determined number of target matching degrees is also different, and the target user experience is improved. Therefore, the probability that the determined target instruction is the actual instruction corresponding to the target voice is different, simulation training is more in line with an actual scene, the method does not have regularity, target personnel cannot master the rule of wrong instructions, and the training effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent flight training, and in particular to a flight training method, equipment and medium based on flight status. Background Art

[0002] In a real flight scenario, the co-pilot will execute the instructions issued by the pilot. As the flight time increases and the flight status changes, the accuracy and efficiency of the co-pilot's execution of the instructions issued by the pilot will vary. When conducting flight training for users, in order to optimize the training efficiency, it is necessary to simulate real flight scenarios as much as possible. However, in the existing technology, the co-pilot is programmed to execute erroneous instructions to simulate the real scenario of the co-pilot executing erroneous instructions. This method has a certain regularity, which is easy for trainees to grasp and then take corresponding targeted measures, resulting in poor training results. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] According to a first aspect of the present application, a flight training method based on flight status is provided, the method comprising the following steps:

[0005] Q100, if the target user is in the main driving position, obtain the target voice emitted by the target user; wherein, the target user is any user who is undergoing flight training.

[0006] Q200, matching the semantic information of the target speech with each preset standard instruction to obtain a standard matching list A corresponding to the target speech = (A1, A2, ..., A i ,…,A n ), i=1, 2,...,n; where, A i is the matching degree between the target speech and the i-th standard instruction, and n is the number of preset standard instructions.

[0007] Q300, traverse A, if A i ≥α1, then A i Determine the target matching degree; to obtain the target matching list B = (B1, B2, ..., B j ,…,B m ), j = 1, 2, ..., m; where B j is the determined j-th target matching degree, m is the number of determined target matching degrees; α1 is a preset first matching degree threshold.

[0008] Q400, if m>1, then randomly determine a standard instruction corresponding to a target matching degree in B as the target instruction corresponding to the target voice; where NUM1 is the number of target matching degrees.

[0009] Q500 executes the target instruction through a preset co-pilot control module.

[0010] α1 is determined by the following steps:

[0011] Q310, obtain the target user’s current training time T now , current environmental noise intensity J now 、Current flight altitude H now and the current flight speed V now .

[0012] Q320, according to T now 、J now 、H now and V now , determine α1.

[0013] According to another aspect of the present application, a non-transitory computer-readable storage medium is also provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned flight status-based flight training method.

[0014] According to another aspect of the present application, an electronic device is provided, including a processor and the above-mentioned non-transitory computer-readable storage medium.

[0015] The present invention has at least the following beneficial effects:

[0016] The flight training method based on flight status of the present invention is as follows: if the target user is in the pilot's seat, a plurality of standard instructions are matched based on the semantic information of the target voice. If the number of matched labeled instructions is greater than one, one of the matched labeled instructions is randomly determined as the target instruction corresponding to the target voice. In this case, the target instruction may or may not be the actual instruction corresponding to the target voice, thereby ensuring that the target voice is matched with an incorrect standard instruction with a certain probability, thereby achieving the same situation as in actual flight where the co-pilot will execute an incorrect instruction. In addition, a first matching degree threshold is comprehensively determined based on the target user's current training time, current ambient noise intensity, current flight altitude, and current flight speed. Different flight states have different corresponding first matching degree thresholds, thereby resulting in different numbers of determined target matching degrees, and thus different probabilities that the determined target instructions are the actual instructions corresponding to the target voice. This makes the simulation training more consistent with actual scenarios. In addition, this method lacks regularity, and the target personnel cannot grasp the pattern of incorrect instructions, thereby improving the training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 The present invention provides a flowchart of a flight training method based on flight status. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] It should be noted that, based on this disclosure, those skilled in the art will appreciate that an aspect described herein can be implemented independently of any other aspect, and that two or more of these aspects can be combined in various ways. For example, any number of the aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement such an apparatus and / or practice such a method.

[0021] Example 1:

[0022] The following will refer to Figure 1 The flowchart of the flight training method based on flight status shown in the figure introduces a flight training method based on flight status.

[0023] The flight training method based on flight status may include the following steps:

[0024] Q100, if the target user is in the main driving position, obtain the target voice emitted by the target user; wherein, the target user is any user who is undergoing flight training.

[0025] In this embodiment, it can be understood that when the target user is undergoing simulated flight training, the target user can be trained for the main pilot or the co-pilot; if the target user is in the main pilot position, the target user is simulated trained as the main pilot. Under normal circumstances, the main pilot speaks to the co-pilot, and the co-pilot executes the instructions corresponding to the voice issued by the main pilot; when the target user is in the main pilot position and speaks, the target voice issued by the target user can be obtained; whether the target person is in the main pilot position can be determined by image recognition or human body detection sensor, which will not be elaborated here.

[0026] Q200, matching the semantic information of the target speech with each preset standard instruction to obtain a standard matching list A corresponding to the target speech = (A1, A2, ..., A i ,…,A n ), i=1, 2,...,n; where, A i is the matching degree between the target speech and the i-th standard instruction, and n is the number of preset standard instructions.

[0027] In this embodiment, several standard instructions are preset, for example: standard instructions include turning left 30°, climbing 1000m, etc.; the target voice can be converted into text information first, and then the corresponding voice information is obtained, and the standard instructions also correspond to voice information; it should be noted that those skilled in the art can use the existing semantic similarity determination method according to actual needs, and match the semantic information of the target voice with each preset standard instruction, which will not be elaborated here.

[0028] Q300, traverse A, if A i ≥α1, then A i Determine the target matching degree; to obtain the target matching list B = (B1, B2, ..., B j ,…,B m ), j = 1, 2, ..., m; where B jis the determined j-th target matching degree, m is the number of determined target matching degrees; α1 is a preset first matching degree threshold.

[0029] In this embodiment, if A i ≥α1, indicating that the semantic information of the i-th standard instruction is similar to the phonetic information corresponding to the target speech, and the i-th standard instruction is likely to be the standard instruction corresponding to the target speech.

[0030] Furthermore, the value range of α1 is [0.7, 0.8]; for example: α1=0.8; α1 can be obtained based on experience or through a large number of experiments.

[0031] In this embodiment, α1 can be determined by the following steps:

[0032] Q310, obtain the target user’s current training time T now , current environmental noise intensity J now 、Current flight altitude H now and the current flight speed V now .

[0033] In this embodiment, it can be understood that as the target user's simulation training time increases, the ambient noise intensity changes, the current flight altitude changes, and the current flight speed changes, the target user's state will be affected to a certain extent; for example: the longer the simulation training time, the more tired the target user will be, and the slower the reaction speed will be.

[0034] Q320, according to T now 、J now 、H now and V now , determine α1.

[0035] Furthermore, step Q320 may include the following steps:

[0036] Q321, according to T now 、J now 、H now and V now , determine the training time weight ω1, environmental noise intensity weight ω2, flight altitude weight ω3 and flight speed weight ω4; where ω1 = T now / TK;ω2=J now / JK;ω3=H now / HK;ω4=V now / VK; TK is the preset planned training duration; JK is the preset maximum ambient noise intensity; HK is the preset maximum flight altitude; VK is the preset maximum flight speed.

[0037] In this embodiment, the above steps are performed tonow 、J now 、H now and V now Normalization is performed so that ω1, ω2, ω3, and ω4 are all within the range of 0 to 1.

[0038] Q322, based on ω1, ω2, ω3 and ω4, the target user's current fatigue level ρ now =(ω1+ω2+ω3+ω4) / 4.

[0039] In this embodiment, ρ now In the range of 0 to 1; T now 、J now 、H now and V now The larger the corresponding value is, the greater the target user's current fatigue is, the worse the target user's condition is, and the lower the reaction ability is.

[0040] Q323, obtain the preset fatigue level and matching threshold group list RH = (RH1, RH2, ..., RH e ,…,RH f ), e=1, 2, ..., f; where RH e is the preset e-th fatigue level and matching threshold group, f is the number of preset fatigue level and matching threshold groups; RH e =([RH e，1 , RH e，2 ), RH e，3 ); [RH e，1 , RH e，2 ) is the preset e-th fatigue level range; RH e，1 is the minimum value of the e-th fatigue level range, RH e，2 is the maximum value of the e-th fatigue level range; RH e，3 is the matching threshold corresponding to the e-th fatigue level range; RH g，2 =RH g+1，1 , g=1,2,…,f-1;RH g，3 <RH g+1，3 .

[0041] Q324, traverse RH, if ρ now ∈[RH e，1 , RH e，2 ), then determine α1=RH e，3 .

[0042] In this embodiment, it can be understood that, nowThe larger it is, the smaller the determined α1 is, which makes m larger, that is, the more target matching degrees are determined. Correspondingly, the probability that the target instruction is not the actual instruction corresponding to the target voice is also greater, which is equivalent to the greater probability of error in the co-pilot control module.

[0043] Through the above steps, the flight status and training duration can be combined with the error probability of the co-pilot control module executing the instructions corresponding to the target voice, making the simulation training more consistent with the actual flight scenario and improving the training effect.

[0044] Q400, if m>1, then randomly determine a standard instruction corresponding to a target matching degree in B as the target instruction corresponding to the target voice; where NUM1 is the number of target matching degrees.

[0045] It is understandable that, under normal circumstances, the target voice corresponds to only one standard instruction. However, at this time, no less than one standard instruction is determined, and the determined standard instructions include the actual instructions corresponding to the target voice, as well as erroneous instructions. Since a standard instruction corresponding to a target match in the target matching list is randomly determined as the target instruction corresponding to the target voice, the determined target instruction may be erroneous, thereby simulating a real scenario in which the co-pilot executes an erroneous instruction. The erroneous instructions are generated randomly and without regularity, and the target personnel cannot predict them in advance, thereby improving the training effect.

[0046] Furthermore, after step Q400 and before step Q500, the method further includes the following steps:

[0047] Q410, if m=1, the standard instruction corresponding to B1 is determined as the target instruction corresponding to the target speech.

[0048] In this embodiment, if m=1, it means that only one standard instruction is determined. Obviously, the standard instruction is the target instruction corresponding to the target speech.

[0049] Furthermore, after step Q400 and before step Q500, the method further includes the following steps:

[0050] Q420, if m=0, a preset voice error prompt is generated; wherein the voice error prompt is used to prompt the target user to re-send the voice.

[0051] In this embodiment, if m=0, it means that the standard instruction cannot be matched, and it is possible that the target user has an abnormal pronunciation, so a preset voice error prompt is generated.

[0052] Q500 executes the target instruction through a preset co-pilot control module.

[0053] Furthermore, after step Q500, the method further includes the following steps:

[0054] Q600, if the target command is different from the actual command corresponding to the target voice, determine whether the target user issues a correction command within a preset time period after the co-pilot control module completes the execution of the target command.

[0055] Furthermore, step Q600 may include the following steps:

[0056] Q610, within a preset time period after the co-pilot control module completes the execution of the target command, obtain the actual flight state vector once every preset time interval to obtain the actual flight state vector list PK = (PK1, PK2, ..., PK ε ,…,PK σ ), ε=1, 2,...,σ; where, PK ε is the εth actual flight state vector obtained, and σ is the number of actual flight state vectors obtained.

[0057] In this embodiment, after the co-pilot control module executes the target instruction, the simulated flight state will continue to change, and the actual flight state vector can be obtained once every preset time interval to obtain PK; the flight state vector may include flight altitude, flight speed, turning rate, climb rate and descent rate, etc.

[0058] Q620, obtain each standard flight state vector after executing the actual instruction corresponding to the target voice, to obtain the standard flight state vector list PK' corresponding to PK = (PK'1, PK'2, ..., PK' ε ,…,PK' σ ); where PK' ε is the εth standard flight state vector after executing the actual instruction corresponding to the target voice.

[0059] If the actual instruction corresponding to the target voice is executed by the co-pilot control module, a standard flight state vector will be preset at each preset time interval within a preset time period after the execution to obtain PK'.

[0060] Q630, obtain the similarity between each actual flight state vector in PK and the corresponding standard flight state vector in PK' to obtain a similarity list δ = (δ1, δ2, ..., δ ε ,…,δ σ ); where δ ε PK ε With PK' ε The similarity between them.

[0061] Q640, if the similarities in δ decrease successively, it is determined that the target user has not issued a correction instruction within a preset time period after the co-pilot control module has completed executing the target instruction.

[0062] In this embodiment, if the similarity in δ decreases successively, it means that the difference between the actual flight state and the corresponding standard flight state is getting bigger and bigger, and the target user has not issued a correction instruction.

[0063] Q650, if the similarity in δ increases first and then decreases, it is determined that the target user issues a correction instruction within a preset time period after the co-pilot control module completes the execution of the target instruction.

[0064] In this embodiment, if the similarity in δ increases first and then decreases, it means that the difference between the actual flight state and the corresponding standard flight state increases first and then decreases, indicating that the target user issues a correction instruction.

[0065] Q700, if the target user does not issue a correction instruction within the preset time period TP after the co-pilot control module completes the execution of the target instruction, it is determined that the target user training is unqualified; otherwise, the time TU from the co-pilot control module completing the execution of the target instruction to the target user issuing the correction instruction is obtained.

[0066] Q800, based on TU, determines the target user's correction response degree θ = TU / TP.

[0067] Through the above steps, it is possible to determine whether the target user's simulation training is qualified, and it is also possible to specifically quantify and evaluate the target user's degree of correction reaction.

[0068] In the flight state-based flight training method of this embodiment, if the target user is in the pilot's seat, several standard commands are matched based on the semantic information of the target speech. If the number of matched labeled commands is greater than one, one of the matched labeled commands is randomly determined as the target command corresponding to the target speech. In this case, the target command may or may not be the actual command corresponding to the target speech, thereby ensuring a certain probability that the target speech will match an incorrect standard command, thereby achieving the same situation as in actual flight where the co-pilot will execute an incorrect command. In addition, the first matching degree threshold is determined based on the target user's current training time, current ambient noise intensity, current flight altitude, and current flight speed. Different flight states correspond to different first matching degree thresholds, resulting in different numbers of determined target matches and, in turn, different probabilities that the determined target command is the actual command corresponding to the target speech. This makes the simulation training more consistent with actual scenarios. In addition, this method lacks regularity, and the target personnel cannot grasp the patterns of incorrect commands, thereby improving training effectiveness.

[0069] Example 2:

[0070] Based on the first embodiment, during the training process, in order to maintain the same training effect as a real person, the co-pilot control module is usually programmed to execute erroneous commands at a fixed time, thereby verifying the trainee's ability to handle erroneous commands when in the main driver's seat. However, because the erroneous commands are pre-set by the co-pilot control module, the main driver trainee can grasp certain patterns, allowing the main driver trainee to be aware of the execution of erroneous commands in advance, resulting in poor training results. Based on this, the following method is provided:

[0071] S100: If the target user is located at the main pilot position, a target voice emitted by the target user is obtained; wherein the target user is any user who is undergoing flight training.

[0072] In this embodiment, it can be understood that when the target user is undergoing simulated flight training, the target user can be trained for the main pilot or the co-pilot; if the target user is in the main pilot position, the target user is simulated trained as the main pilot. Under normal circumstances, the main pilot speaks to the co-pilot, and the co-pilot executes the instructions corresponding to the voice issued by the main pilot; when the target user is in the main pilot position and speaks, the target voice issued by the target user can be obtained; whether the target person is in the main pilot position can be determined by image recognition or human body detection sensor, which will not be elaborated here.

[0073] S200, matching the semantic information of the target speech with each preset standard instruction to obtain a standard matching degree list corresponding to the target speech; wherein the standard matching degree list includes the standard matching degree between the semantic information of the target speech and each preset standard instruction.

[0074] Specifically, the semantic information of the target speech is matched with each preset standard instruction to obtain a standard matching list A corresponding to the target speech = (A1, A2, ..., A i ,…,A n ), i=1, 2,...,n; where, A i is the matching degree between the target speech and the i-th standard instruction, and n is the number of preset standard instructions.

[0075] In this embodiment, several standard instructions are preset, for example: standard instructions include turning left 30°, climbing 1000m, etc.; the target voice can be converted into text information first, and then the corresponding voice information is obtained, and the standard instructions also correspond to voice information; it should be noted that those skilled in the art can use the existing semantic similarity determination method according to actual needs, and match the semantic information of the target voice with each preset standard instruction, which will not be elaborated here.

[0076] S300: Determine the standard matching degrees in the standard matching degree list that are greater than or equal to a first preset matching degree threshold as target matching degrees to obtain a target matching degree list; wherein the target matching degree list includes a plurality of target matching degrees.

[0077] Specifically, traverse A, if A i ≥α1, then A i Determine the target matching degree; to obtain the target matching list B = (B1, B2, ..., B j ,…,B m ), j = 1, 2, ..., m; where B j is the determined j-th target matching degree, m is the number of determined target matching degrees; α1 is a preset first matching degree threshold.

[0078] In this embodiment, if A i ≥α1, indicating that the semantic information of the i-th standard instruction is similar to the phonetic information corresponding to the target speech, and the i-th standard instruction is likely to be the standard instruction corresponding to the target speech.

[0079] Furthermore, the value range of α1 is [0.7, 0.8]; for example: α1=0.8; α1 can be obtained based on experience or through a large number of experiments.

[0080] S400: If the number of target matching degrees in the target matching degree list is greater than 1, randomly determine a standard instruction corresponding to a target matching degree in the target matching degree list as a target instruction corresponding to the target voice.

[0081] Specifically, if m>1, a standard instruction corresponding to a target matching degree in B is randomly determined as the target instruction corresponding to the target voice.

[0082] It is understandable that, under normal circumstances, the target voice corresponds to only one standard instruction. However, at this time, no less than one standard instruction is determined, and the determined standard instructions include the actual instructions corresponding to the target voice, as well as erroneous instructions. Since a standard instruction corresponding to a target match in the target matching list is randomly determined as the target instruction corresponding to the target voice, the determined target instruction may be erroneous, thereby simulating a real scenario in which the co-pilot executes an erroneous instruction. The erroneous instructions are generated randomly and without regularity, and the target personnel cannot predict them in advance, thereby improving the training effect.

[0083] S500, if the number of target matching degrees in the target matching degree list is equal to 1, and the only target matching degree in the target matching degree list is greater than or equal to the second preset matching degree threshold, then the standard instruction corresponding to the only target matching degree in the target matching degree list is determined as the target instruction corresponding to the target voice; the first preset matching degree threshold is less than the second preset matching degree threshold.

[0084] Specifically, if m=1, and B1≥α2, the standard instruction ZL corresponding to B1 is determined as the target instruction corresponding to the target speech; wherein α2 is a preset second matching degree threshold; α2>α1.

[0085] In this embodiment, if m=1, and B1≥α2, and α2>α1, it means that the only standard instruction determined is the same as the actual instruction corresponding to the target voice; this situation indicates that the actual instruction corresponding to the target voice has been determined, which is a relatively normal situation; this situation can be handled when the target user speaks clearly and standardly.

[0086] Furthermore, the value range of α2 is [0.9, 0.95]; for example: α2=0.92; α2 can be obtained based on experience or through a large number of experiments.

[0087] S600: If the number of target matching degrees in the target matching degree list is equal to 1, and the only target matching degree in the target matching degree list is less than a second preset matching degree threshold, convert the target speech into a corresponding target text.

[0088] Specifically, if m=1, and B1<α2, the target speech is converted into the corresponding target text.

[0089] In this embodiment, if m = 1 and B1 < α2, the determined standard instruction is likely the actual instruction corresponding to the target speech. Since B1 < α2, the similarity between the two is not high enough to be directly determined. Therefore, it is necessary to further determine whether the determined standard instruction is the actual instruction corresponding to the target speech. It should be noted that those skilled in the art can use existing speech-to-text methods to convert the target speech into the corresponding target text according to actual needs, and this will not be elaborated here.

[0090] S700: Determine a target instruction corresponding to the target voice according to the target text, and execute the target instruction through a preset co-pilot control module.

[0091] Furthermore, step S700 may include the following steps:

[0092] S710 , extracting initial keywords from the target text to obtain an initial keyword list corresponding to the target text; wherein the initial keyword list includes a number of initial keywords corresponding to the target text.

[0093] Specifically, the target text is subjected to initial keyword extraction to obtain an initial keyword list C corresponding to the target text = (C1, C2, ..., C p ,…,C q ), p=1, 2, ..., q; where C p is the pth initial keyword obtained by performing initial keyword extraction on the target file, and q is the number of initial keywords obtained by performing initial keyword extraction on the target file.

[0094] In this embodiment, keywords may be words other than auxiliary words and modifiers; those skilled in the art can use existing keyword extraction methods to perform initial keyword extraction on the target text according to actual needs, which will not be elaborated here.

[0095] S720: Obtain the confidence corresponding to each initial keyword in the initial keyword list to obtain an initial keyword confidence list corresponding to the initial keyword list; wherein the initial keyword confidence list includes the confidence corresponding to each initial keyword in the initial keyword list.

[0096] Specifically, the confidence level corresponding to each initial keyword in C is obtained to obtain the initial keyword confidence level list TC corresponding to C = (TC1, TC2, ..., TC P ,…,TC q ), among which, TC P C p The corresponding confidence level.

[0097] In this embodiment, the target text is obtained based on the target speech. When the target text is generated based on the target speech, it is also generated word by word. Therefore, each word has a corresponding confidence level.

[0098] S730: traverse the initial keyword confidence list, and determine the initial keywords in the initial keyword confidence list that are less than a preset keyword confidence threshold as intermediate keywords to obtain an intermediate keyword list.

[0099] Specifically, traverse TC, if TC P <β, then C P Determine as the intermediate keyword to obtain the intermediate keyword list D=(D1, D2, ..., D r ,…,D s ), r=1, 2,…, s; where D r is the rth intermediate keyword determined, s is the number of intermediate keywords determined; β is the preset keyword confidence threshold.

[0100] In this embodiment, keywords with lower confidence may be incorrect keywords obtained by translating the target speech. For example, when the target user says "climb 1000m up", the pronunciation of "up" is relatively vague, and the confidence of the keyword "up" is relatively low.

[0101] Furthermore, the value range of β is 0.5-0.7; for example, β=0.6; it can be obtained based on experience or through a large number of experiments.

[0102] S740, traverse the intermediate keyword list. If there is an intermediate keyword belonging to the preset instruction keyword library in the intermediate keyword list, determine the target instruction corresponding to the target speech through the preset reverse instruction mapping table; wherein the reverse instruction mapping table includes several standard instructions and the reverse instruction corresponding to each standard instruction.

[0103] Specifically, traverse D, and if there is an intermediate keyword belonging to the preset instruction keyword library in D, the target instruction corresponding to the target voice is determined through the preset reverse instruction mapping table QT.

[0104] In this embodiment, a command keyword library is preset, which contains several keywords corresponding to standard commands. If there are intermediate keywords belonging to the preset command keyword library in D, it means that there are keywords corresponding to standard commands among the determined intermediate keywords. That is, when the target user pronounces the target voice, the pronunciation of the key words is blurred, and the co-pilot may not be able to hear the actual target voice clearly. At this time, the target command corresponding to the target voice is determined through the preset reverse command mapping table QT.

[0105] Furthermore, determining the target instruction corresponding to the target speech through a preset reverse instruction mapping table may include the following steps:

[0106] S741, traverse the reverse instruction mapping table, and determine the reverse instruction mapped to the same standard instruction as the only standard instruction corresponding to the target matching degree in the target matching degree list as the target instruction corresponding to the target speech.

[0107] In this embodiment, the preset reverse instruction mapping table contains the reverse instructions corresponding to each standard instruction. For example, the reverse instruction corresponding to the standard instruction to climb 1000m is: descend 1000m. In step S200, a standard instruction is matched, and the reverse instruction corresponding to the standard instruction can be obtained through the preset reverse instruction mapping table.

[0108] Furthermore, the step of determining the target instruction corresponding to the target voice according to the target text may further include the following steps:

[0109] S750, if there is no intermediate keyword belonging to the preset instruction keyword library in the intermediate keyword list, the standard instruction in the reverse instruction mapping table that is the same as the standard instruction corresponding to the only target matching degree in the target matching degree list is determined as the target instruction corresponding to the target voice.

[0110] In this embodiment, if there is no intermediate keyword belonging to the preset instruction keyword library in the intermediate keyword list, it means that when the target user utters the target voice, the keyword corresponding to the ambiguous part of the target voice is not a keyword in the preset instruction keyword library. It is possible that the pronunciation of the auxiliary word or the modifier part is ambiguous, resulting in a low matching degree between the target voice and the standard instruction in step S200, but the only standard instruction matched is also correct.

[0111] Furthermore, the method may further comprise the following steps:

[0112] S800: If the number of target matching degrees in the target matching degree list is equal to 0, a preset voice error prompt is generated; wherein the voice error prompt is used to prompt the target user to re-send the voice.

[0113] In this embodiment, if the number of target matching degrees in the target matching degree list is equal to 0, it means that the standard instruction that meets the requirements cannot be matched. At this time, the pronunciation of the target user may be too vague to be recognized. Therefore, a preset voice error prompt is generated to prompt the target user to re-speak.

[0114] In this embodiment, if the target user is in the main pilot position, a number of standard instructions are matched according to the semantic information of the target voice. If the number of matched labeled instructions is greater than 1, a matched labeled instruction is randomly determined as the target instruction corresponding to the target voice. At this time, the target instruction may be the actual instruction corresponding to the target voice or may not be the actual instruction corresponding to the target voice, so that the target voice has a certain probability of matching the wrong standard instruction, so as to achieve the same situation as in actual flight that the co-pilot will execute the wrong instruction. Moreover, this method does not have regularity, and the target personnel cannot grasp the pattern of the wrong instructions, thereby improving the training effect.

[0115] Furthermore, if the number of matched labeled instructions is equal to 1, and the only target matching degree in the target matching degree list is greater than or equal to the second preset matching degree threshold, then the standard instruction corresponding to the only target matching degree in the target matching degree list is determined as the target instruction corresponding to the target voice; at this time, the matched target instruction is the actual instruction corresponding to the target voice, that is, the correct instruction; thereby ensuring that the target voice can be matched to the correct standard instruction in most cases, so as to achieve the purpose of simulation training.

[0116] Furthermore, if the number of matched labeled instructions is equal to 1, and the only target matching degree in the target matching degree list is less than the second preset matching degree threshold, the target speech is converted into the corresponding target text, and the target instruction corresponding to the target speech is determined according to the target text; at this time, the determined target instruction may be a correct instruction or an incorrect instruction, which further makes the simulation training conform to the actual scenario and improves the training effect.

[0117] Example 3:

[0118] Based on the above embodiment, there is also a situation where the target user is in the passenger seat. In this situation, training is required for the passenger seat. The following training method is provided:

[0119] In this embodiment, a voice playback device is preset to simulate the voice of the main driver. When the target user is the co-driver, he can execute corresponding instructions according to the voice issued by the voice playback device.

[0120] H100, if the target user is in the passenger seat, obtain the time taken by the target user to execute each instruction corresponding to the virtual voice within the preset sliding time window TH to obtain a time-consuming list T = (T1, T2, ..., T x ,…,T y ), x=1, 2, …, y; where T x is the time it takes for the target user to execute the instruction corresponding to the xth virtual voice in TH, and y is the number of instructions corresponding to the virtual voice executed by the target user in TH.

[0121] In this embodiment, if the target user is in the passenger seat, it means that the target user is performing simulation training for the passenger seat. Within the sliding time window TH, the target user executes several instructions corresponding to virtual voices played by the voice playback device. When executing the instructions corresponding to each virtual voice, the time consumed in executing the instructions corresponding to each virtual voice can be recorded to obtain T.

[0122] H200, based on T, determine the average time it takes for the target user to execute the command corresponding to the virtual voice in TH, T' = (1 / y) × ∑ y x＝1 T x .

[0123] In this embodiment, after obtaining the time taken by the target user to execute the instruction corresponding to each virtual voice in TH, T' can be obtained; T' can represent the current reaction ability of the target user; T' can be set according to actual needs or obtained based on experience, for example: T'=1min.

[0124] H300, if T'<T1 or T'>T2, then obtain the next virtual voice file YA to be played; wherein T1 is the first preset time threshold, T2 is the second preset time threshold; T1<T2.

[0125] In this embodiment, it should be noted that, under normal circumstances, the time taken by the target user to execute the instructions corresponding to each virtual voice will not change much; if T'<T1, it means that the time taken by the target user to execute the instructions corresponding to the virtual voice is too short, and the target user may have predicted the voice played by the virtual voice playback device based on experience and executed the corresponding instructions in advance; and if T'>T2, it means that the time taken by the target user to execute the instructions corresponding to the virtual voice is too long, and the target user may be inattentive or tired and react slowly; at this time, the next virtual voice file YA to be played is obtained; T1 and T2 can be obtained based on experience or a large number of experiments, and will not be elaborated here.

[0126] H400, if the instruction corresponding to YA has a preset reverse instruction, use the first preset virtual voice processing method to process YA to obtain a reverse virtual voice file YB corresponding to YA.

[0127] In this embodiment, YA can be converted into text, and then semantic recognition is performed to obtain the corresponding instruction ZA; a reverse instruction mapping table is preset, which includes several standard instructions and the reverse instruction corresponding to each standard instruction; the reverse instruction mapping table can be traversed to determine whether the instruction corresponding to YA has a preset reverse instruction;

[0128] Furthermore, step H400 may include the following steps:

[0129] H410, get the instruction ZA corresponding to YA.

[0130] H420, obtain the reverse instruction ZA' corresponding to ZA.

[0131] H430, perform keyword extraction on ZA and ZA' to obtain a keyword list GA corresponding to ZA = (GA1, GA2, ..., GA u ,…,GA v ) and the keyword list GA' corresponding to ZA' = (GA'1, GA'2, ..., GA' u ,…,GA' v ),u=1,2,…,v; among them, GA u is the u-th keyword corresponding to ZA, GA' u is the u-th keyword corresponding to ZA', and v is the number of keywords corresponding to ZA and ZA'.

[0132] In this embodiment, keywords may be words other than auxiliary words and modifiers; those skilled in the art can use existing keyword extraction methods to extract keywords from ZA and ZA' according to actual needs, which will not be elaborated here.

[0133] H440, traverse GA and GA', if GA u with GA' u If different, GA' u Determine the reverse keyword corresponding to ZA'.

[0134] In this embodiment, there are differences in keywords between the standard instruction and its corresponding reverse instruction. For example, the reverse instruction corresponding to turning left 30° is turning right 30°. u with GA' u Different, it means GA' u It is the reverse keyword corresponding to ZA'.

[0135] H450, adjust the volume of the voice file segment corresponding to the reverse keyword to a first volume YL1 to obtain YB; wherein YL1 = λ×YL; YL is the volume preset by the target user; λ is the preset reverse keyword volume weight, λ<1.

[0136] In this embodiment, the reverse instruction corresponds to a virtual voice, and the reverse keyword in the reverse instruction corresponds to a voice segment in the virtual voice corresponding to the reverse instruction. The volume of the reverse voice segment can be turned down to obtain YB; the volume preset by the target user is the volume at which the target user can normally hear the virtual voice clearly; λ can be set according to actual needs, or it can be determined through a large number of experiments; for example: the value range of λ is 0.2 to 0.5.

[0137] Furthermore, after step H400 and before step H500, the at least one instruction or the at least one program segment is loaded and executed by the processor, and the following steps are also implemented:

[0138] H460, if there is no preset reverse instruction for the instruction corresponding to YA, use the second preset virtual voice processing method to process YA to obtain the reverse virtual voice file YB corresponding to YA.

[0139] In this embodiment, the virtual voice may also correspond to a non-standard instruction, so that the instruction corresponding to YA does not have a preset reverse instruction. In this case, the second preset virtual voice processing method is used to process YA. Specifically, H460 may include the following steps:

[0140] H461, obtain each preset volume corresponding to the target user in the preset historical time period to obtain a historical preset volume list HE=(HE1, HE2, ..., HE a,…,HE b ), a=1, 2, ..., b; where HE a is the ath preset volume corresponding to the target user within the preset historical time period, and b is the number of preset volumes corresponding to the target user within the preset historical time period.

[0141] In this embodiment, the target user will have a corresponding historical preset volume in each historical training process, and each preset volume corresponding to the target user in the preset historical time period can be obtained to obtain HE.

[0142] H462, uses a preset clustering algorithm to cluster the volume in HE to obtain several clusters.

[0143] H463, determine the average volume corresponding to the cluster with the largest number of volumes as the target volume ML corresponding to YA.

[0144] In this embodiment, the volume in the cluster with the largest number of volumes represents the volume frequently used by the target user and is consistent with the target user's volume setting habit. Therefore, the average volume corresponding to the cluster with the largest number of volumes is determined as the target volume corresponding to YA.

[0145] H464, adjust the volume of YA to a second volume YL2 to obtain YB; wherein YL2=η×ML; η is a preset volume adjustment weight; η<1.

[0146] In this embodiment, the value range of η can be 0.3 to 0.4; for example, η = 0.35; the volume of YA is turned down to simulate a real scenario in which the co-pilot user is in poor condition and the main driver speaks in a low voice, so as to train the target user's handling ability as a co-pilot.

[0147] H500, play YB through the voice playback device, and obtain the actual instruction YB' corresponding to the actual operation of the target user on YB.

[0148] In this embodiment, the virtual voice played by the voice playback device may be an erroneous voice, or it may be a correct voice with a lower volume, thereby achieving the purpose of simulating real scenes without regularity, thereby improving the training effect.

[0149] H600, based on the instructions corresponding to YB' and YA, determine the target user's completion degree for YA.

[0150] Furthermore, step H600 may include the following steps:

[0151] H610, if the instructions corresponding to YB' and YA are the same, then obtain the time TG from the end of YB playback to the target user completing YB'.

[0152] In this embodiment, if the instructions corresponding to YB' and YA are the same, it means that the target user accurately recognizes the instruction corresponding to the virtual voice; the time from the end of YB playback to the completion of YB' by the target user can be obtained.

[0153] Furthermore, if the instructions corresponding to YB' and YA are different, it means that the target user fails to accurately recognize the instruction corresponding to the virtual voice, and the execution of this instruction fails.

[0154] H620, if TG∈[TG1,TG2], then determine the target user's completion degree DQ for YA = (TG1 / 2+TG2 / 2) / TG; where TG1 is the preset minimum time for completing the instruction, and TG2 is the preset maximum time for completing the instruction.

[0155] In this embodiment, TG1 and TG2 can be set according to actual needs or obtained through a large number of experiments; a larger DQ indicates a higher target user completion degree, and a smaller DQ indicates a lower target user completion degree.

[0156] H630: If TG < TG1 or TG > TG2, the target user's completion degree DQ for YA is determined to be 0.

[0157] In this embodiment, the time duration for the target user to correctly execute the instruction corresponding to the virtual voice should be within a preset time range. A time duration that is too long or too short indicates that the target user has performed abnormally.

[0158] Furthermore, after step H600, the at least one instruction or the at least one program segment is loaded and executed by the processor, and the following steps are also implemented:

[0159] H700, obtain the target user's completion degree for each virtual voice corresponding instruction to obtain a completion degree list FE=(FE1, FE2, ..., FE c ,…,FE d ), c=1, 2, …, d; where FE c is the completion degree of the target user’s instruction corresponding to the cth virtual voice, and d is the number of virtual voices.

[0160] H710, based on FE, determine the average completion degree corresponding to the target user FE' = (1 / d)∑ d c＝1 FE c .

[0161] H720, if FE'≥FR, it is determined that the target user training is qualified; otherwise, it is determined that the target user training is unqualified.

[0162] In this embodiment, through the above steps, the average completion degree of the target user's training can be determined as a whole, thereby specifically quantifying whether the target user's simulation training is qualified.

[0163] In this embodiment, if the target user is located in the co-pilot position, the average time consumed by the target user to execute the instructions corresponding to the virtual voice within the preset sliding time window TH is determined based on the time consumed by the target user to execute each instruction corresponding to the virtual voice within the preset sliding time window TH; if the average time consumed is less than the first preset time consumed or greater than the second preset time consumed, the next virtual voice file to be played is obtained, and if the next voice file to be played contains a preset reverse instruction, the next voice file to be played is processed using the first preset virtual voice processing method to obtain a corresponding reverse virtual voice file; the reverse virtual voice file is played by the voice playback device. Since the reverse virtual voice file is generated based on the duration of the target user executing the instruction, it does not have a certain regularity, so that when the target user is simulated for the co-pilot, it is more in line with the real flight scene.

[0164] Furthermore, after the voice playback device plays the reverse virtual voice instruction, it also obtains the actual instruction corresponding to the target user's actual operation of the reverse virtual voice instruction, and then determines the target user's completion degree for the next voice file to be played, thereby realizing a quantitative evaluation of the target user training.

[0165] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0166] Example 4:

[0167] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0168] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0169] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0170] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0171] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0172] Embodiment 5:

[0173] An embodiment of the present invention further provides an electronic device including a processor and the aforementioned non-transitory computer-readable storage medium.

[0174] The electronic device is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0175] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the at least one processor, the at least one memory, and a bus connecting different system components (including the memory and the processor).

[0176] The memory stores program codes, which can be executed by the processor, so that the processor performs the steps of various embodiments described in this specification.

[0177] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0178] The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0179] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0180] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0181] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0182] An embodiment of the present invention further provides a computer program product comprising program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0183] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A flight training method based on flight status, characterized in that: The method comprises the following steps: Q100, if the target user is in the main pilot position, obtaining a target voice message from the target user; wherein the target user is any user undergoing flight training; Q200, matching the semantic information of the target speech with each preset standard instruction to obtain a standard matching list A corresponding to the target speech = (A1, A2, ..., A i ,…,A n ), i=1, 2,...,n; where, A i is the matching degree between the target speech and the i-th standard instruction, and n is the number of preset standard instructions; Q300, traverse A, if A i ≥α1, then A i Determine the target matching degree; to obtain the target matching list B = (B1, B2, ..., B j ,…,B m ), j = 1, 2, ..., m; where B j is the determined j-th target matching degree, m is the number of determined target matching degrees; α1 is the preset first matching degree threshold; Q400, if m>1, then randomly determine a standard instruction corresponding to a target matching degree in B as the target instruction corresponding to the target speech; where NUM1 is the number of target matching degrees; Q500, executing the target instruction through a preset co-pilot control module; α1 is determined by the following steps: Q310, obtain the target user’s current training time T now , current environmental noise intensity J now 、Current flight altitude H now and the current flight speed V now ; Q320, according to T now 、J now 、H now and V now , determine α1.

2. The flight training method based on flight status according to claim 1, characterized in that: Step Q320 includes the following steps: Q321, according to T now 、J now 、H now and V now , determine the training time weight ω1, environmental noise intensity weight ω2, flight altitude weight ω3 and flight speed weight ω4; where ω1 = T now / TK;ω2=J now / JK;ω3=H now / HK;ω4=V now / VK; TK is the preset planned training duration; JK is the preset maximum ambient noise intensity; HK is the preset maximum flight altitude; VK is the preset maximum flight speed; Q322, based on ω1, ω2, ω3 and ω4, the target user's current fatigue level ρ now =(ω1+ω2+ω3+ω4) / 4; Q323, obtain the preset fatigue level and matching threshold group list RH = (RH1, RH2, ..., RH e ,…,RH f ), e=1, 2, ..., f; where RH e is the preset e-th fatigue level and matching threshold group, f is the number of preset fatigue level and matching threshold groups; RH e =([RH e，1 , RH e，2 ), RH e，3 ); [RH e，1 , RH e，2 ) is the preset e-th fatigue level range; RH e，1 is the minimum value of the e-th fatigue level range, RH e，2 is the maximum value of the e-th fatigue level range; RH e，3 is the matching threshold corresponding to the e-th fatigue level range; RH g，2 =RH g+1，1 , g=1,2,…,f-1;RH g，3 <RH g+1，3 ; Q324, traverse RH, if ρ now ∈[RH e，1 , RH e，2 ), then determine α1=RH e，3 .

3. The flight training method based on flight status according to claim 1, characterized in that: After step Q400 and before step Q500, the method further includes the following steps: Q410, if m=1, the standard instruction corresponding to B1 is determined as the target instruction corresponding to the target speech.

4. The flight training method based on flight status according to claim 1, characterized in that: After step Q400 and before step Q500, the method further includes the following steps: Q420, if m=0, a preset voice error prompt is generated; wherein the voice error prompt is used to prompt the target user to re-send the voice.

5. The flight training method based on flight status according to claim 1, characterized in that: After step Q500, the method further includes the following steps: Q600, if the target command is different from the actual command corresponding to the target voice, determining whether the target user issues a correction command within a preset time period after the passenger control module completes executing the target command; Q700: If the target user does not issue a correction command within a preset time period TP after the co-pilot control module completes the target command, the target user training is determined to be unqualified. Otherwise, the time duration TU from the co-pilot control module completing the target command to the target user issuing the correction command is obtained. Q800, based on TU, determines the target user's correction response degree θ = TU / TP.

6. The flight training method based on flight status according to claim 1, characterized in that: Step Q600 includes the following steps: Q610, within a preset time period after the co-pilot control module completes the execution of the target command, obtain the actual flight state vector once every preset time interval to obtain the actual flight state vector list PK = (PK1, PK2, ..., PK ε ,…,PK σ ), ε=1, 2,...,σ; where, PK ε is the εth actual flight state vector obtained, σ is the number of actual flight state vectors obtained; Q620, obtain each standard flight state vector after executing the actual instruction corresponding to the target voice, to obtain the standard flight state vector list PK' corresponding to PK = (PK'1, PK'2, ..., PK' ε ,…,PK' σ ); where PK' ε is the εth standard flight state vector after executing the actual instruction corresponding to the target voice; Q630, obtain the similarity between each actual flight state vector in PK and the corresponding standard flight state vector in PK' to obtain a similarity list δ = (δ1, δ2, ..., δ ε ,…,δ σ ); where δ ε PK ε With PK' ε similarity between Q640, if the similarities in δ decrease successively, it is determined that the target user has not issued a correction command within a preset time period after the co-pilot control module has completed executing the target command; Q650, if the similarity in δ increases first and then decreases, it is determined that the target user issues a correction instruction within a preset time period after the co-pilot control module completes the execution of the target instruction.

7. The flight training method based on flight status according to claim 1, characterized in that: The value range of α1 is [0.7, 0.8].

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by a processor to implement the flight status-based flight training method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: The device comprises a processor and the non-transitory computer-readable storage medium of claim 8.

Images