Flight training methods, equipment, and media based on flight status

Abstract

This invention provides a flight training method, device, and medium based on flight status, relating to the field of intelligent flight training technology. The method includes: if the target user is in the pilot's position, matching several standard commands; if the number of matched labeled commands is greater than 1, randomly determining one of the matched labeled commands as the target command corresponding to the target speech; a first matching degree threshold is determined comprehensively based on the target user's current training duration, current environmental noise intensity, current flight altitude, and current flight speed. Different flight statuses correspond to different first matching degree thresholds, resulting in different numbers of determined target matching degrees, and consequently, different probabilities that the determined target command is the actual command corresponding to the target speech. This makes the simulated training more in line with the actual scenario, and the method is not systematic, preventing the target user from grasping the patterns of erroneous commands, thereby improving the training effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent flight training, in particular to a flight training method based on flight state, equipment and medium. BACKGROUND

[0002] In a real flight scene, the co-pilot will execute the instructions issued by the pilot. With the increase of flight time and the change of flight state, the accuracy and efficiency of the co-pilot executing the instructions issued by the pilot will change. When training users to fly, in order to achieve the best training efficiency, it is necessary to simulate the real flight scene as much as possible. However, in the prior art, the scene of the real co-pilot executing the wrong instructions is simulated by programming the co-pilot to execute the wrong instructions. This method has a certain regularity and is easy to be mastered by the trainees, so that the trainees can take corresponding measures, resulting in poor training effect. SUMMARY

[0003] To solve the above technical problems, the technical solution adopted by the present application is as follows:

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

[0005] Q100, if the target user is located at the pilot position, the target voice issued by the target user is obtained; wherein the target user is any user who is training to fly.

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

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

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

[0009] Q500, execute the target instruction through a preset copilot control module.

[0010] a1 is determined through the following steps:

[0011] Q310, obtain the current training duration T of the target user now , the current environmental noise intensity J now , the current flight height H now and the current flight speed V now .

[0012] Q320, determine a1 according to T now , J now , H now and V now .

[0013] According to another aspect of the present application, a non-transitory computer readable storage medium is also provided, and the storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to realize the flight training method based on flight state.

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

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

[0016] The flight training method based on the flight state provided by the present application, if the target user is located at the main driving position, a plurality of standard instructions are matched according to the semantic information of the target voice, if the number of matched standard instructions is greater than 1, a matched standard 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 to the wrong standard instruction, so as to achieve the same situation as the actual flight, that is, the co-pilot will execute the wrong instruction; In addition, the first matching degree threshold is determined according to the current training time of the target user, the current environmental noise intensity, the current flight height and the current flight speed, and the corresponding first matching degree threshold is different in different flight states, so that the number of determined target matching degrees is also different, and the probability that the determined target instruction is the actual instruction corresponding to the target voice is also different, so that the simulation training is more in line with the actual scene, and the method has no regularity, and the target personnel cannot master the regularity of the wrong instruction, thereby improving the training effect. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor.

[0018] Figure 1 The flow chart of the flight training method based on the flight state provided by the present application is provided. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] It should be noted that based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, an apparatus and / or a method can be implemented using any number of the aspects set forth herein. In addition, this apparatus and / or method can be implemented using other structures and / or functionality in addition to or instead of one or more of the aspects set forth herein.

[0021] Embodiment one:

[0022] The flight training method based on flight states will be described below with reference to the flowchart of the flight training method based on flight states shown in the accompanying drawings. Figure 1 The flight training method based on flight states can include the following steps:

[0023] The flight training method based on flight states can include the following steps:

[0024] Q100, if the target user is located at the main driver position, obtaining a target voice issued by the target user; wherein the target user is any user who is performing flight training.

[0025] In this embodiment, it can be understood that when the target user is performing simulated flight training, the target user can train the main driver or the co-pilot. If the target user is located at the main driver position, the target user is performing simulated training as the main driver. Normally, the main driver issues a voice to the co-pilot, and the co-pilot executes the instructions corresponding to the voice issued by the main driver. When the target user is located at the main driver position and issues a voice, the target voice issued by the target user can be obtained. Whether the target user is located at the main driver position can be determined by image recognition or a human body detection sensor, which is not described here.

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

[0027] In this embodiment, a plurality of standard instructions are preset, for example, the standard instructions include turning left by 30°, climbing up by 1000m, etc. The target voice can be converted into text information first, and then the corresponding voice information is obtained. The standard instruction also corresponds to voice information. It should be noted that those skilled in the art can use existing semantic similarity determination methods according to actual needs to match the semantic information of the target voice with each preset standard instruction, which is not described here.

[0028] Q300, traversing A, if Ai≥α1, then Ai is determined as the target matching degree; to obtain a target matching list B=(B1, B2, …, Bj), j=1, 2, …, m; wherein Bj is the target matching degree corresponding to the j-th target voice. i i j m j ​​​​​​​m is the number of determined target matching degrees; and a1 is a preset first matching degree threshold.

[0029] In this embodiment, if A i ≥ a1, it indicates that the semantic information of the i-th standard instruction is relatively similar to the voice information corresponding to the target voice, and the i-th standard instruction is probably the standard instruction corresponding to the target voice.

[0030] Further, the value range of a1 is [0.7, 0.8]; for example, a1 = 0.8. a1 can be obtained according to experience or through a large number of experiments.

[0031] In this embodiment, a1 can be determined through the following steps:

[0032] Q310, obtaining the current training duration T now , the current environmental noise intensity J now , the current flight height H now , and the current flight speed V now of the target user.

[0033] In this embodiment, it can be understood that as the training duration of the target user increases, the environmental noise intensity changes, the current flight height changes, and the current flight speed changes, it will have a certain impact on the state of the target user; for example, the longer the simulation training duration, the more tired the target user, and the slower the reaction speed.

[0034] Q320, determining a1 according to T now , J now , H now , and V now .

[0035] Further, step Q320 can include the following steps:

[0036] Q321, determining the training duration weight ω1, the environmental noise intensity weight ω2, the flight height weight ω3, and the flight speed weight ω4 according to T now , J now , H now , and V now ; wherein ω1 = T now / TK; ω2 = J now / JK; ω3 = H now / HK; ω4 = V now / VK; TK is a preset planned training duration; JK is a preset maximum environmental noise intensity; HK is a preset maximum flight height; and VK is a preset maximum flight speed.

[0037] In this embodiment, through the above steps, Tnow , J now , H now , and V now are normalized so that ω1, ω2, ω3, and ω4 are all in the range of 0 to 1.

[0038] Q322, according to ω1, ω2, ω3, and ω4, the current fatigue level ρ now of the target user

[0039] In this embodiment, ρ now is in the range of 0 to 1; T now , J now , H now , and V now corresponding values are greater, indicating that the current fatigue of the target user is greater, the state of the target user is worse, and the reaction ability is also lower.

[0040] Q323, obtain a preset fatigue level and matching degree threshold group list RH=(RH1, RH2, …, RH e , …, RH f ), e=1, 2, …, f; where RH e is the e-th preset fatigue level and matching degree threshold group, f is the number of preset fatigue level and matching degree threshold groups; RH e =([RH e，1 , RH e，2 ), RH e，3 ); [RH e，1 , RH e，2 ) is the e-th preset 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 degree 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 ρ nowThe greater, the smaller the determined a1 is, so that m is greater, that is, the more the determined target matching degree, and the greater the probability that the target instruction is not the actual instruction corresponding to the target voice, which is equivalent to the greater the probability that the copilot control module makes a mistake.

[0043] Through the above steps, the flight state and the training duration are combined with the error probability of the copilot control module executing the instruction corresponding to the target voice, so that the simulation training is more in line with the actual flight scene, and the training effect is improved.

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

[0045] It can be understood that, under normal circumstances, the target voice corresponds to only one standard instruction, but at this time, not less than one standard instruction is determined, and the determined standard instruction contains the actual instruction corresponding to the target voice and also contains an error instruction; since a standard instruction corresponding to one of the target matching degrees in the target matching degree list is randomly determined as the target instruction corresponding to the target voice, the determined target instruction may be incorrect; thus, the real scene in which the copilot executes an error instruction is simulated; the error instruction is randomly generated and has no regularity, and the target personnel cannot predict in advance, thereby improving the training effect.

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

[0047] Q410, if m=1, determine the standard instruction corresponding to B1 as the target instruction corresponding to the target voice.

[0048] In this embodiment, if m=1, only one standard instruction is determined, and obviously, the standard instruction is the target instruction corresponding to the target voice.

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

[0050] Q420, if m=0, generate a preset voice error prompt; wherein the voice error prompt is used to prompt the target user to reissue 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 pronounces abnormally, and a preset voice error prompt is generated.

[0052] Q500, execute the target instruction through the preset copilot control module.

[0053] Further, after step Q500, the method further comprises the following steps:

[0054] Q600, if the target instruction is different from the actual instruction corresponding to the target voice, determining whether the target user issues a rectification instruction within a preset time period after the target instruction is executed by the copilot control module.

[0055] Further, step Q600 can comprise the following steps:

[0056] Q610, within the preset time period after the target instruction is executed by the copilot control module, an actual flight state vector is obtained every preset time interval to obtain an actual flight state vector list PK=(PK1, PK2, …, PK ε , …, PK σ ), ε=1, 2, …, σ; wherein 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 target instruction is executed by the copilot control module, the simulated flight state will continue to change, and an actual flight state vector can be obtained every preset time interval to obtain PK; the flight state vector can include flight height, flight speed, turn rate, climb rate, and descent rate, etc.

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

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

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

[0061] Q640, if the similarity in δ decreases in turn, it is determined that the target user does not issue a correction instruction within a preset time period after the target instruction is executed by the copilot control module.

[0062] In this embodiment, if the similarity in δ decreases in turn, it indicates that the difference between the actual flight state and the corresponding standard flight state is getting larger, and the target user does not issue a correction instruction.

[0063] Q650, if the similarity in δ increases first and then decreases in turn, it is determined that the target user issues a correction instruction within a preset time period after the target instruction is executed by the copilot control module.

[0064] In this embodiment, if the similarity in δ increases first and then decreases in turn, it indicates 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 a preset time period TP after the target instruction is executed by the copilot control module, it is determined that the target user is unqualified for training; otherwise, the time length TU from when the copilot control module executes the target instruction to when the target user issues the correction instruction is obtained.

[0066] Q800, according to TU, the correction reaction degree θ of the target user is determined as θ = TU / TP.

[0067] Through the above steps, it can be determined whether the target user's simulation training is qualified, and the target user's correction reaction degree can also be quantitatively evaluated.

[0068] The flight training method based on flight state in this embodiment, if the target user is located at the main driver position, a plurality of standard instructions are matched according to the semantic information of the target voice, if the number of matched standard instructions is greater than 1, a matched standard instruction is randomly determined as the target instruction corresponding to the target voice; At this time, the target instruction may or may not be the actual instruction corresponding to the target voice, so that the target voice has a certain probability of matching to the wrong standard instruction, so as to achieve the same situation as the copilot executing the wrong instruction during actual flight; In addition, the first matching degree threshold is determined according to the current training time of the target user, the current environmental noise intensity, the current flight height and the current flight speed, and the corresponding first matching degree threshold is different in different flight states, so that the number of determined target matching degrees is also different, and the probability that the determined target instruction is the actual instruction corresponding to the target voice is also different, so that the simulation training is more consistent with the actual scene, and the method has no regularity, and the target personnel cannot master the regularity of the wrong instruction, thereby improving the training effect.

[0069] Embodiment two:

[0070] Based on embodiment one, in the training process, in order to keep the same training effect as a real person, the error instruction is usually executed by the co-pilot control module in a fixed time program, thereby verifying the disposal ability of the training personnel in the main driver position about the error instruction; however, since the error instruction is pre-set by the co-pilot control module, the main driver training personnel can master certain rules, so that the main driver training personnel can know the execution of the error instruction in advance, resulting in poor training effect; based on this, the following method is provided:

[0071] S100, if the target user is in the main driver position, the target voice issued by the target user is acquired; wherein the target user is any user who performs flight training.

[0072] In this embodiment, it can be understood that when the target user is simulated for flight training, the target user can be trained for the main driver or the co-pilot; if the target user is in the main driver position, the target user is simulated as the main driver personnel, and under normal circumstances, the main driver personnel issues a voice to the co-pilot personnel, and the co-pilot personnel executes the instruction corresponding to the voice issued by the main driver personnel; when the target user is in the main driver position and issues a voice, the target voice issued by the target user can be acquired; whether the target personnel is in the main driver position can be determined by image recognition or human body detection sensor, which is not described here.

[0073] S200, according to the semantic information of the target voice and each preset standard instruction, a standard matching degree list corresponding to the target voice is obtained; wherein the standard matching degree list includes the standard matching degree of the semantic information of the target voice and each preset standard instruction.

[0074] Specifically, according to the semantic information of the target voice and each preset standard instruction, a standard matching degree list A=(A1, A2, …, An) corresponding to the target voice is obtained, i=1, 2, …, n; wherein Ai is the matching degree between the target voice and the ith standard instruction, and n is the number of preset standard instructions. i n i

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

[0076] S300, determining the standard matching degrees greater than or equal to the first preset matching degree threshold in the standard matching degree list 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, A is traversed, and if A i ≥α1, A i is determined as a target matching degree; to obtain a target matching list B=(B1, B2, …, B j , …, B m ), j=1, 2, …, m; wherein B j is the jth target matching degree determined, m is the number of target matching degrees determined; and α1 is a first matching degree threshold.

[0078] In this embodiment, if A i ≥α1, it indicates that the semantic information of the ith standard instruction is relatively similar to the voice information corresponding to the target voice, and the ith standard instruction is probably the standard instruction corresponding to the target voice.

[0079] Further, the value range of α1 is [0.7, 0.8]; for example, α1=0.8; α1 can be obtained according to 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, a standard instruction corresponding to a target matching degree in the target matching degree list is randomly determined 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 a target instruction corresponding to the target voice.

[0082] It can be understood that, under normal circumstances, the target voice corresponds to only one standard instruction, but at this time, not less than one standard instruction is determined, and the determined standard instruction includes the actual instruction corresponding to the target voice and also includes an error instruction; since a standard instruction corresponding to a target matching degree in the target matching degree list is randomly determined as a target instruction corresponding to the target voice, the determined target instruction may be an error; thereby simulating a real scene in which the copilot executes an error instruction; the error instruction is randomly generated and has no regularity, and the target personnel cannot predict 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 one target matching degree in the target matching degree list is greater than or equal to a second preset matching degree threshold, the standard instruction corresponding to the only one 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 voice; wherein, α2 is a preset second matching degree threshold; α2>α1.

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

[0086] Further, the value range of α2 is [0.9, 0.95]; for example, α2 = 0.92; α2 can be obtained according to 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 one target matching degree in the target matching degree list is less than the second preset matching degree threshold, the target voice is converted into the corresponding target text.

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

[0089] In the embodiment, if m = 1 and B1<α2, it indicates that the determined standard instruction may be the actual instruction corresponding to the target voice, and since B1<α2, the similarity of the two does not reach the degree that can be directly determined, therefore, it is necessary to further determine whether the determined standard instruction is the actual instruction corresponding to the target voice. It should be noted that the person skilled in the art can convert the target voice into the corresponding target text according to the actual need using the existing voice-to-text method, which is not described here.

[0090] S700, determining the target instruction corresponding to the target voice according to the target text, and executing the target instruction through a preset copilot control module.

[0091] Further, step S700 can include the following steps:

[0092] S710, performing initial keyword extraction on the target text to obtain an initial keyword list corresponding to the target text; wherein, the initial keyword list includes a plurality of initial keywords corresponding to the target text.

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

[0094] In this embodiment, the keyword can be a word other than a helping word and a modifier; a person skilled in the art can perform initial keyword extraction on the target text according to actual needs by using an existing keyword extraction method, which is not described herein.

[0095] S720, obtaining a confidence degree corresponding to each initial keyword in the initial keyword list to obtain an initial keyword confidence degree list corresponding to the initial keyword list; wherein the initial keyword confidence degree list includes a confidence degree corresponding to each initial keyword in the initial keyword list.

[0096] Specifically, a confidence degree corresponding to each initial keyword in C is obtained to obtain an initial keyword confidence degree list TC=(TC1, TC2, …, TCp, …, TCq) corresponding to C; wherein TCp is a confidence degree corresponding to Cp. P q P p

[0097] In this embodiment, the target text is obtained according to the target voice, and the target text is also generated word by word when the target voice is generated, so each word corresponds to a confidence degree.

[0098] S730, traversing the initial keyword confidence degree list, determining an initial keyword in the initial keyword confidence degree list that is less than a preset keyword confidence degree threshold as an intermediate keyword to obtain an intermediate keyword list.

[0099] Specifically, TC is traversed, and if TCp<β, Cp is determined as an intermediate keyword to obtain an intermediate keyword list D=(D1, D2, …, Dr, …, Ds), r=1, 2, …, s; wherein Dr is the rth intermediate keyword determined, s is the number of intermediate keywords determined, and β is the preset keyword confidence degree threshold. P P r s r

[0100] ​​​​​​​​​​​​In this embodiment, the keyword with low confidence may be an incorrect keyword obtained according to the target speech translation; for example, when the target user speaks the voice of climbing 1000m upward, the pronunciation of upward is relatively ambiguous, and the confidence of the keyword upward is relatively low.

[0101] Further, the value range of β is 0.5-0.7; for example, β=0.6; which can be obtained according to experience or through a large number of experiments.

[0102] S740, traversing the intermediate keyword list, if there is an intermediate keyword belonging to the preset instruction keyword library in the intermediate keyword list, determining the target instruction corresponding to the target speech through the preset reverse instruction mapping table; wherein the reverse instruction mapping table includes a plurality of standard instructions and the reverse instruction corresponding to each standard instruction.

[0103] Specifically, traversing D, if there is an intermediate keyword belonging to the preset instruction keyword library in D, determining the target instruction corresponding to the target speech through the preset reverse instruction mapping table QT.

[0104] In this embodiment, the instruction keyword library is preset, and the instruction keyword library includes a plurality of keywords corresponding to the standard instruction; if there is an intermediate keyword belonging to the preset instruction keyword library in D, it indicates that there is a keyword corresponding to the standard instruction in the determined intermediate keyword; that is, when the target user issues the target speech, the pronunciation of the key word is ambiguous, and the copilot may not be able to hear the actual target speech clearly; at this time, the target instruction corresponding to the target speech is determined through the preset reverse instruction mapping table QT.

[0105] Further, the determination of the target instruction corresponding to the target speech through the preset reverse instruction mapping table can include the following steps:

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

[0107] In this embodiment, the preset reverse instruction mapping table includes the reverse instruction corresponding to each standard instruction, for example, the reverse instruction corresponding to the standard instruction of climbing 1000m upward is: descending 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] Further, the determination of the target instruction corresponding to the target speech according to the target text can further include the following steps:

[0109] S750, if the intermediate keyword in the intermediate keyword list does not belong to the preset instruction keyword library, the same standard instruction corresponding to the unique target matching degree in the target matching degree list in the reverse instruction mapping table is determined as the target instruction corresponding to the target voice.

[0110] In this embodiment, if the intermediate keyword in the intermediate keyword list does not belong to the preset instruction keyword library, it indicates that when the target user issues the target voice, the keyword corresponding to the ambiguous place in the target voice is not the keyword of the preset instruction keyword library, and it is possible that the auxiliary word or the modified word part is fuzzy, resulting in that in step S200, the matching degree of the target voice and the standard instruction is low, but the unique standard instruction matched is also correct.

[0111] Further, the method can further include 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 reissue the voice.

[0113] In this embodiment, if the number of target matching degrees in the target matching degree list is equal to 0, it indicates that the standard instruction meeting the requirements cannot be matched, at this time, the pronunciation of the target user can be too fuzzy, resulting in that it cannot be recognized, therefore, the preset voice error prompt is generated to prompt the target user to reissue the voice.

[0114] In this embodiment, if the target user is located at the main driver position, a plurality of standard instructions are matched according to the semantic information of the target voice, if the number of matched standard instructions is greater than 1, a matched standard instruction is randomly determined as the target instruction corresponding to the target voice; at this time, the target instruction can be the actual instruction corresponding to the target voice or can not be the actual instruction corresponding to the target voice, so that the target voice has a certain probability to match the wrong standard instruction, so as to achieve the same situation as the actual flight, that is, the co-pilot will execute the wrong instruction, and the method has no regularity, the target personnel cannot master the regularity of the wrong instruction, and the training effect is improved.

[0115] Further, if the number of matched standard instructions is equal to 1, and the unique target matching degree in the target matching degree list is greater than or equal to the second preset matching degree threshold, the standard instruction corresponding to the unique 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; so as to ensure that the target voice can match the correct standard instruction in most cases, so as to achieve the purpose of simulation training.

[0116] Further, if the number of matched annotation instructions is equal to 1, and the only one target matching degree in the target matching degree list is less than the second preset matching degree threshold, the target voice is converted into the corresponding target text, and the target instruction corresponding to the target voice is determined according to the target text; at this time, the determined target instruction may be a correct instruction or an incorrect instruction, further making the simulation training conform to the actual scene and improving the training effect.

[0117] Embodiment three:

[0118] Based on the above embodiments, there is also a situation that the target user is located at the co-pilot position, in which case, training needs to be performed for the co-pilot, and the following training method is provided:

[0119] In this embodiment, a voice playing device is preset, which can simulate the voice issued by the main driver, and when the target user is the co-pilot, the target user can execute the corresponding instruction according to the voice issued by the voice playing device.

[0120] H100, if the target user is located at the co-pilot position, the time consumption of the instruction corresponding to each virtual voice executed by the target user in a preset sliding time window TH is obtained, to obtain a time consumption list T=(T1, T2, …, T x , …, T y ), x=1, 2, …, y; wherein T x is the time consumption of the instruction corresponding to the xth virtual voice executed by the target user 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 located at the co-pilot position, it means that the target user is performing simulation training for the co-pilot, and in the sliding time window TH, the target user has executed a number of instructions corresponding to virtual voices played by the voice playing device. When executing each instruction corresponding to a virtual voice, the time consumption of executing each instruction corresponding to a virtual voice can be recorded, and then T is obtained.

[0122] H200, according to T, the average time consumption T'=(1 / y)×∑ y x＝1 T x is determined.

[0123] In this embodiment, after obtaining the time consumption of each virtual voice executed by the target user 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 can be obtained according to experience, for example: T'=1min.

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

[0125] In this embodiment, it should be noted that the time consumed by the target user to execute the instruction corresponding to each virtual voice will not change too much under normal circumstances; if T' < T1, it means that the time consumed by the target user to execute the instruction corresponding to the virtual voice is too short, and the target user may have pre-judged the voice played by the virtual voice playing device and executed the corresponding instruction in advance; and if T' > T2, it means that the time consumed by the target user to execute the instruction corresponding to the virtual voice is too long, and the target user may be inattentive or tired, and the reaction is slow; at this time, the next virtual voice file YA to be played is obtained; T1 and T2 can be obtained according to experience or a large number of experiments, which will not be described here.

[0126] H400, if the instruction corresponding to YA has a preset reverse instruction, then using a 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 a text, and then semantic recognition is performed to obtain the corresponding instruction ZA; there is a reverse instruction mapping table, the reverse instruction mapping table contains a plurality of standard instructions and a reverse instruction corresponding to each standard instruction; whether the instruction corresponding to YA has a preset reverse instruction can be determined by traversing the reverse instruction mapping table;

[0128] Further, step H400 can include the following steps:

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

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

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

[0132] ​​​​​​In the embodiment, the keyword can be a word other than a helping word and a modifying word; a person skilled in the art can extract the keywords from ZA and ZA' according to actual needs by using an existing keyword extraction method, which is not described here.

[0133] H440, traversing GA and GA', if GA u is different from GA u , GA u is determined as the reverse keyword corresponding to ZA'.

[0134] In the embodiment, the standard instruction and the corresponding reverse instruction have a difference in keywords, for example, turning left by 30° corresponds to the reverse instruction of turning right by 30°; if GA u is different from GA u , it indicates that GA u is the reverse keyword corresponding to ZA'.

[0135] H450, adjusting 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 a preset reverse keyword volume weight, λ < 1.

[0136] In the 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 adjusted to obtain YB; the volume preset by the target user is the volume at which the target user can clearly hear the virtual voice; λ can be set according to actual needs or determined through a large number of experiments; for example, the value range of λ is 0.2 to 0.5.

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

[0138] H460, if the preset reverse instruction does not exist for the instruction corresponding to YA, a second preset virtual voice processing method is used to process YA to obtain the reverse virtual voice file YB corresponding to YA.

[0139] In the embodiment, the virtual voice can also correspond to a non-standard instruction, so that the preset reverse instruction does not exist for the instruction corresponding to YA. At this time, the second preset virtual voice processing method is used to process YA, and specifically, H460 can include the following steps:

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

[0141] In this embodiment, the target user has a 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, using a preset clustering algorithm, clustering the volumes in HE to obtain a plurality of clusters.

[0143] H463, determining 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 volumes in the cluster with the largest number of volumes represent the volumes frequently used by the target user, which conforms to the volume setting habits of the target user. 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, adjusting 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 reduced to simulate the real scenario that the co-driver user is in a poor state and the main driver user speaks in a small voice, and to train the target user's disposal ability as a co-driver.

[0147] H500, playing YB through the voice playing device, and obtaining the actual operation of the target user corresponding to the actual instruction YB' of YB.

[0148] In this embodiment, the virtual voice played by the voice playing device at this time may be an incorrect voice, or a correct voice with a small volume, thereby achieving the purpose of simulating a real scenario, and having no regularity, thereby improving the training effect.

[0149] H600, determining the completion degree of the target user for YA according to the instructions corresponding to YB' and YA.

[0150] Further, step H600 can include the following steps:

[0151] H610, if the instructions corresponding to YB' and YA are the same, obtaining the time length TG from the end of YB playing to the completion of YB' by the target user.

[0152] In the embodiment, if the instruction corresponding to YB' is the same as the instruction corresponding to YA, it indicates that the target user accurately identifies the instruction corresponding to the virtual voice; and the duration from the end of YB to the completion of YB' by the target user can be obtained.

[0153] Further, if the instruction corresponding to YB' is different from the instruction corresponding to YA, it indicates that the target user fails to accurately identify the instruction corresponding to the virtual voice, and the execution of the instruction is unqualified.

[0154] H620, if TG is in the range of [TG1, TG2], it is determined that the completion degree DQ of the target user for YA is (TG1 / 2+TG2 / 2) / TG; wherein TG1 is a preset minimum duration for completing the instruction, and TG2 is a preset maximum duration for completing the instruction.

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

[0156] H630, if TG is less than TG1 or greater than TG2, it is determined that the completion degree DQ of the target user for YA is 0.

[0157] In the embodiment, the duration in which the target user correctly executes the instruction corresponding to the virtual voice should be within the preset duration range, and the duration that is too long or too short indicates that the target user executes abnormally.

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

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

[0160] H710, according to FE, the average completion degree FE' of the target user is determined as (1 / d)∑ d c＝1 FE c .

[0161] H720, if FE' is greater than or equal to FR, it is determined that the target user is qualified for training; otherwise, it is determined that the target user is unqualified for training.

[0162] In this embodiment, the average completion degree of the target user in this training can be determined as a whole through the above steps, so as to specifically quantify whether the target user is qualified in the simulation training.

[0163] In this embodiment, if the target user is located at the co-pilot position, the average time consumption of the target user in executing the instructions corresponding to the virtual voice within the preset sliding time window TH is determined according to the time consumption of the instructions corresponding to each virtual voice executed by the target user within TH, if the average time consumption is less than the first preset time consumption or greater than the second preset time consumption, the next virtual voice file to be played is obtained, if the next virtual voice file to be played has a preset reverse instruction, the first preset virtual voice processing method is used to process the next virtual voice file to be played to obtain a corresponding reverse virtual voice file, and the reverse virtual voice file is played through the voice playing device. Since the reverse virtual voice file is generated based on the time length of the target user in executing the instructions, it does not have a certain regularity, so that the simulation of the target user for the co-pilot is more in line with the real flight scene.

[0164] Further, after the voice playing device plays the reverse virtual voice instruction, the actual instruction corresponding to the actual operation of the target user for the reverse virtual voice instruction is also obtained, and then the completion degree of the target user for the next virtual voice file to be played is determined, so as to realize the quantitative evaluation of the training of the target user.

[0165] In addition, although the various steps of the methods in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be divided into multiple steps, etc.

[0166] Embodiment four:

[0167] The embodiments of the present application also provide a non-transitory computer readable storage medium, which can be arranged in an electronic device to save at least one instruction or at least one program related to a method in the method embodiments, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the method provided by the above embodiments.

[0168] The program product can employ any combination of one or more computer-readable media. The computer-readable media can be a computer-readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0169] The computer-readable signal medium can include a computer-readable storage medium that is propagated as a carrier wave. The computer-readable signal medium can further be any computer-readable medium that is not a storage medium. The computer-readable signal medium can be a computer-readable storage medium that is a propagated signal.

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

[0171] The program code can be executed by one or more programmable processors, which can be implemented using one or more microprocessors, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any other devices suitable for retrieval and execution of instructions. The program code can execute entirely on a user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0172] Embodiment Five

[0173] Embodiments of the present disclosure also provide 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 bring any limitation to the functions and usage scope of the embodiments of the present disclosure.

[0175] The electronic device is in the form of a general purpose computing device. The components of the electronic device can include, but are not limited to, the at least one processor described above, the at least one memory described above, a bus that connects the different system components including the memory and the processor.

[0176] The memory stores a program code that can be executed by the processor, such that the processor performs the steps in the various embodiments described in this specification.

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

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

[0179] The bus can be representative of one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures.

[0180] The electronic device can also communicate with one or more external devices, such as a keyboard or a pointing device, through an I / O interface. Additionally, the electronic device can communicate with one or more devices that enable a user to interact with the electronic device, and / or one or more devices (e.g., a router, a modem, etc.) that enable the electronic device to communicate with one or more other computing devices. Such communication can occur via an I / O interface. Still yet, the electronic device can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or the public network, such as the Internet) through a network adapter. The network adapter communicates with the other modules of the electronic device via the bus. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with the electronic device. Such hardware would include, but is not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0181] Those skilled in the art can clearly understand the example embodiments described herein through the above description of the example embodiments, and the example embodiments described herein can be implemented by software or by software in combination with necessary hardware. Therefore, the technical solutions 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 disk, a mobile hard disk, or the like) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0182] Embodiments of the present disclosure also provide a computer program product comprising program code for causing an electronic device to perform the steps of the methods according to the various example embodiments of the present disclosure described above in the specification when the program product is run on the electronic device.

[0183] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for illustration, not for limiting the scope of the present disclosure. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present disclosure.

Claims

1. A flight training method based on flight state, characterized by, The method comprises the following steps: Q100, if the target user is located at the main driver position, obtaining the target voice issued by the target user; wherein the target user is any user who is undergoing flight training; Q200, match the semantic information of the target speech with each preset standard instruction to obtain a standard matching degree list A = (A1, A2, ..., A...). i A n ), i=1, 2,...,n; among them, A i Let n be the matching degree between the target speech and the i-th standard instruction, and n be the number of preset standard instructions; Q300, traverse A, if A i ≥ α1, then A i is determined as the target matching degree; to obtain a target matching list B = (B1, B2, …, B j , …, B m ), j = 1, 2, …, m; wherein B j is the jth target matching degree determined, m is the number of target matching degrees determined; and α1 is a preset first matching degree threshold. Q400, if m>1, randomly determining the standard instruction corresponding to one target matching degree in B as the target instruction corresponding to the target voice; Q500, executing the target instruction through the preset co-driver control module; α1 is determined by the following steps: Q310, obtaining a current training duration T of the target user now , a current ambient noise intensity J now , a current flight height H now , and a current flight speed V now ; Q320, according to T now , J now , H now and V now , determine a1.

2. The flight status-based flight training method of claim 1, wherein, Step Q320 comprises the following steps: Q321, according to T now , J now , H now and V now , determine training duration weight ω1, environmental noise intensity weight ω2, flight height weight ω3 and flight speed weight ω4; wherein, ω1=T now / TK; ω2=J now / JK; ω3=H now / HK; ω4=V now / VK; TK is a preset planned training duration; JK is a preset maximum environmental noise intensity; HK is a preset maximum flight height; VK is a preset maximum flight speed; Q322, from ω1, ω2, ω3, and ω4, the current fatigue level p of the target user now = (ω1+ ω2+ ω3+ ω4) / 4; Q323, obtain a preset fatigue level and matching degree threshold group list RH=(RH1, RH2, …, RH e , …, RH f ), e=1, 2, …, f; wherein RH e is the preset e-th fatigue level and matching degree threshold group, and f is the number of preset fatigue level and matching degree 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 degree 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 p now ∈ [RH e，1 , RH e，2 ], then determine a1= RH e，3 .

3. The flight status-based flight training method of claim 1, wherein, After step Q400 and before step Q500, the method further comprises the following steps: Q410, if m=1, determining the standard instruction corresponding to B1 as the target instruction corresponding to the target voice.

4. The flight status-based flight training method of claim 1, wherein, After step Q400 and before step Q500, the method further comprises the following steps: Q420, if m=0, generating a preset voice error prompt; wherein the voice error prompt is used to prompt the target user to reissue the voice.

5. The flight status-based flight training method of claim 1, wherein, After step Q500, the method further comprises the following steps: Q600, if the target instruction is different from the actual instruction corresponding to the target voice, determining whether the target user issues a rectification instruction within a preset time period after the co-driver control module executes the target instruction; Q700, if the target user does not issue a rectification instruction within a preset time period TP after the co-driver control module executes the target instruction, determining that the target user is unqualified for training; otherwise, obtaining the time length TU from when the co-driver control module executes the target instruction to when the target user issues the rectification instruction; Q800, determining the rectification reaction degree θ of the target user according to TU=TP.

6. The flight status-based flight training method of claim 1, wherein, Step Q600 comprises the following steps: Q610, within a preset time period after the target instruction is executed by the copilot control module, an actual flight state vector is obtained every preset time interval to obtain an actual flight state vector list PK= (PK1, PK2, …, PK ε , …, PK σ ), ε = 1, 2, …, σ; wherein PK ε is the εth actual flight state vector obtained, and σ is the number of actual flight state vectors obtained; Q620, obtain each standard flight state vector after executing the actual command corresponding to the target voice, so as to obtain the standard flight state vector list PK' = (PK'1, PK'2, ..., PK') for PK. ε , ...,PK' σ ); where PK' ε The ε-th standard flight state vector after executing the actual command corresponding to the target voice; Q630, obtaining the similarity between each actual flight state vector in the PK and the corresponding standard flight state vector in the PK' to obtain a similarity list δ = (δ1, δ2, …, δ ε ) σ ) ; wherein δ ε is the similarity between the PK ε and the PK' ε ​ Q640, if the similarities in δ decrease in turn, determining that the target user does not issue a rectification instruction within a preset time period after the co-driver control module executes the target instruction; Q650, if the similarities in δ increase first and then decrease in turn, determining that the target user issues a rectification instruction within a preset time period after the co-driver control module executes the target instruction.

7. The flight status-based flight training method of claim 1, wherein, The value range of α1 is [0.7, 0.8]. 8.A non-transitory computer readable storage medium having stored therein at least one instruction or at least one piece of program, characterized in that, The at least one instruction or the at least one program is loaded and executed by the processor to realize the flight training method based on the flight state according to any one of claims 1-7.

9. An electronic device, comprising: The processor and the non-transitory computer readable storage medium of claim 8. The processor and the non-transitory computer readable storage medium of claim 8.

Images