Electronic decision support device for the implementation of a critical function or of an assistance function by an avionics system, associated method and computer program

Abstract

An electronic decision support device for implementing a critical function or an assistance function by an avionics system in response to a query from an operator. The device includes a module for receiving the query and a current context, and a processing module configured for generating a recommendation in response to the query, and the processing module includes a similarity-based reasoning module configured for generating a recommendation from an algorithm based on the content of a reference database, a rule-based reasoning module configured for generating a recommendation from a deterministic algorithm, an ontology-based reasoning module configured for generating a recommendation from an ontology-based algorithm, and an activation module configured for activating at least one of the reasoning modules.

Claims

1. An electronic decision support device for the implementation of a critical function or of an assistance function by an avionics system in response to a query issued by an operator of the avionics system, the avionics system being suitable for operating according to a current context defined by at least one operating parameter of the avionics system, the electronic device comprising: a receiver module configured for receiving the query sent by the operator and for receiving the current context; a processing module configured for generating at least one recommendation in response to the query from the operator, the processing module comprising: a similarity-based reasoning module configured for generating a recommendation based on the query from the operator and the current context from an algorithm based on the content of a reference database, the reference database comprising a list of predetermined contexts, a list of predetermined queries and predetermined recommendations, each recommendation being associated with one of the predetermined contexts and one of the predetermined queries, the similarity-based reasoning module being configured for comparing the operator query and the current context with the predetermined queries and the predetermined contexts of the reference database according to a similarity metric, the recommendation generated by the similarity-based reasoning module being equal to the recommendation associated with the predetermined context and the predetermined query having the greatest similarity metric with the current context and the query from the operator, the recommendation being generated only if the similarity metric is greater than a predetermined threshold value; a rule-based reasoning module, configured for generating a recommendation from a deterministic algorithm based on the query from the operator and on the current context, the deterministic algorithm consisting of a succession of predetermined conditional instructions; an ontology-based reasoning module configured for generating a recommendation from an ontology-based algorithm depending upon the query from the operator and upon the current context, the ontology defining a structured set of concepts and relationships between the concepts modeling operation of the avionic system; and an activation module configured for activating at least one of the reasoning modules among said similarity-based reasoning module, said rule-based reasoning module, and said ontology-based reasoning module, each reasoning module being configured for generating an error message sent to the activation module if a recommendation is not generated by the reasoning module after the activation thereof by the activation module, and the activation module being configured for successively activating said similarity-based reasoning module, said rule-based reasoning module and said ontology-based reasoning module until one of the reasoning modules generates a recommendation; and a generation module configured for receiving at least one recommendation from said processing module and for generating an answer to the query from the operator, from the at least one recommendation received.

2. The electronic device according to claim 1, further comprising at least one module among: a display module configured for displaying the answer to the operator of the avionics system; and a transmission module configured for transmitting the answer to the avionics system for implementation of the critical function or of the assistance function according to the answer.

3. The electronic device according to claim 1, wherein said processing module comprises a preprocessing module configured for performing a semantic analysis of the query from the operator according to a predetermined formal rule, and activating one of the reasoning modules based on the result of the semantic analysis of the query from the operator.

4. The electronic device according to claim 1, wherein said activation module is configured for activating at least two of the reasoning modules, said processing module further comprising a control module configured for comparing the recommendations generated by the at least two reasoning modules and checking whether the recommendations are consistent with each other according to a predetermined consistency rule, said generation module being configured for generating the answer only if no inconsistency is detected by said control module.

5. The electronic device according to claim 1, wherein said generation module is further configured for sending the generated answer associated with the query of the operator and with the current context, to the reference database.

6. A control station comprising an electronic decision support device according to claim 1, the control station being selected from the group consisting of a control station arranged in an aircraft, a remote control station for an aircraft, and a control station arranged in an air traffic control station on the ground.

7. The control station of claim 6 wherein the remote control station for an aircraft comprises a remote control station for a drone.

8. A decision support method for the implementation of a critical function or of an assistance function by an avionics system in response to a query issued by an operator of the avionics system, the avionics system being suitable for operating according to a current context defined by at least one operating parameter of the avionics system, the method being implemented by an electronic decision support device according to claim 1, the method comprising: receiving the query issued by the operator; activating at least one of the reasoning modules of the electronic decision support device among the similarity-based reasoning module, the rule-based reasoning module, and the ontology-based reasoning module, each reasoning module being configured for generating an error message sent to the activation module of the electronic decision support device if a recommendation is not generated by the reasoning module after the activation thereof by the activation module, the activation including successive activations of the similarity-based reasoning module, the rule-based reasoning module and the ontology-based reasoning module until one of the reasoning modules generates a recommendation; generating at least one recommendation in response to the query; and receiving the at least one recommendation and generating an answer to the query of the operator from the at least one recommendation received.

9. A non-transitory computer-readable medium including a computer program comprising software instructions which, when executed by a computer, implement a method according to claim 8.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Such features and advantages of the invention will become clearer upon reading the following description, given only as a non-limiting example, and made with reference to the enclosed drawings, wherein:

[0046] FIG. 1 is a schematic representation of an aircraft and a control station each including an electronic device, in accordance with an embodiment of the present invention;

[0047] FIG. 2 is a schematic representation of the electronic device, in accordance with an embodiment of the present invention; and

[0048] FIG. 3 is a flowchart for a decision support method, in accordance with an embodiment of the present invention, for implementing a critical function by an avionics system implemented by the electronic device of FIG. 2.

DETAILED DESCRIPTION

[0049] A plurality of avionic electronic systems 10 are shown in FIG. 1.

[0050] Each avionics system 10 is in particular on-board an aircraft 12. The aircraft is typically an airplane, a helicopter, or a drone. In other words, aircraft 12 is a flying machine which can be piloted by an operator 14, herein a pilot, via a control station 16. Control station 16 is arranged inside aircraft 12 or remote from aircraft 12, in particular in the case of a drone.

[0051] As a variant, also shown in FIG. 1, each avionics system 10 is arranged in a ground control station 18, inter alia a control tower in an airfield. Operator 14 controls the air traffic and in particular aircraft 12 via control station 16 arranged in control station 18.

[0052] Control station 16 further includes a human-machine interface 20 configured for receiving a query from operator 14.

[0053] The query is in particular a search for information or a search for a solution to a query expressed by operator 14.

[0054] The human-machine interface 20 includes inter alia a keyboard and a microphone. Human-machine interface 20 can, e.g., format the query in a predetermined format. As a variant, the query is, e.g., formatted after a receiver module 26, introduced hereinafter, of the present description.

[0055] Control station 16 further includes a display 22. Display 22 is inter alia a heads-down display. The display is then a surface configured for displaying at least one image. Advantageously, the heads-down display is configured for displaying information relating to aircraft 12, such as speed, altitude, orientation of aircraft 12 and/or information relating to the external environment of aircraft 12, such as air traffic information and weather conditions around aircraft 12.

[0056] As a variant, display 22 is a heads-up display. Display 22 is then at least partially transparent. Advantageously, heads-up display 22 is a visor integrated into a helmet suitable for being worn by operator 14. As a variant, heads-up display 22 is a transparent surface attached in control station 16 and placed in front of operator 14. As a further variant, heads-up display 22 is a windscreen of aircraft 12.

[0057] In particular, each avionics system 10 is configured for implementing an avionic critical function or an avionic assistance function. The avionic critical function is typically selected inter alia from the group consisting of: aircraft 12 flight control, aircraft 12 trajectory calculation, selecting a destination airfield for aircraft 12, and an air traffic control command, changing the communication frequency for aircraft 12.

[0058] In addition or as a variant, each avionics system 10 is configured for implementing an avionic assistance function. The avionic assistance function is typically selected inter alia from a runway highlighting function, an optimized trajectory recommendation for aircraft 12, and an airport recommendation for aircraft 12 in the event of a change in flight plan.

[0059] However, a person skilled in the art understands that the invention is also suitable for other complex queries concerning critical functions or assistance functions, including inter alia assistance with vehicle fleet management, a nuclear reactor control process, temperature control in a furnace in a plant, navigation control of an autonomous motor vehicle, speed control in a railway vehicle, and route recommendation for an autonomous vehicle.

[0060] Each avionics system 10 is suitable for operating according to a current context defined by at least one operating parameter associated with the avionics system 10.

[0061] Each operating parameter is a datum which is characteristic of the current context. The current context corresponds to the set of circumstances under which avionics system 10 operates.

[0062] In particular, each operating parameter associated with avionics system 10 is chosen from the group consisting of: [0063] a flight parameter of aircraft 12 associated with avionics system 10, [0064] a flight plan associated with aircraft 12, [0065] a mission assigned to aircraft 12, [0066] a meteorological parameter associated with the environment of aircraft 12, and [0067] a parameter describing the operating status of avionics system 10.

[0068] The flight parameter is inter alia the geographical position of aircraft 12, the altitude of aircraft 12, the speed of aircraft 12, or the heading of aircraft 12.

[0069] The flight plan for aircraft 12 includes inter alia a set of expected crossing points for aircraft 12 between the departure and destination airfields.

[0070] The mission of aircraft 12 is the objective of the flight of aircraft 12, inter alia transporting passengers and/or goods to a certain destination, and reconnaissance or surveillance of an area of interest.

[0071] The meteorological parameter is inter alia the wind speed, the presence of bad weather, and the visibility of the environment for the pilot.

[0072] A parameter describing the operating status of avionics system 10 is inter alia a Boolean type datum indicating the automatic detection of system failures.

[0073] An electronic decision support device 24 for the implementation of a critical function or an assistance function, by one of avionics systems 10 in response to a query sent by operator 14 of the avionics system 10, is further shown in FIG. 1.

[0074] With reference to FIG. 2, the electronic device includes a receiver module 26, a processing module 28 and a generation module 30.

[0075] Advantageously, electronic device 24 further includes a display module 32 and a transmission module 34.

[0076] Receiver module 26 is configured for receiving the query sent by operator 14. In particular, receiver module 26 is configured for receiving the query formatted by human-machine interface 20 and for transmitting same to processing module 28.

[0077] Receiving module 26 is further configured for receiving the current context. In particular, receiver module 26 is configured for receiving the operating parameter(s) associated with avionics system 10 and for characterizing the current context. Receiver module 26 is suitable for receiving inter alia the flight parameters by the flight control system or the flight plan by the Flight Management System (FMS).

[0078] Processing module 28 is configured for generating at least one recommendation in response to the query from operator 14.

[0079] The recommendation is in particular, a suggested action on one of avionics systems 10, in particular a command acting on the avionics system 10 in order to modify the operation thereof in response to the query of operator 14.

[0080] The query of operator 14 is made inter alia following an event potentially affecting the safety of aircraft 12. The event is inter alia an event external to avionics system 10 presenting a possible risk for the safety of avionics system 10 or an event internal to avionics system 10, such as failure of one of the components of avionics system 10.

[0081] Processing module 28 includes three reasoning modules and an activation module 36.

[0082] Each reasoning module is configured for generating a recommendation as a function of the query of operator 14 and of the current context received by receiver module 26.

[0083] The three reasoning modules are in particular, a similarity-based reasoning module 38, a rule-based reasoning module 40, and an ontology-based reasoning module 42.

[0084] Similarity-based reasoning module 38 is configured for generating a recommendation according to the query of operator 14 and of the current context, from an algorithm based on the content of a reference database 44.

[0085] Reference database 44 includes a list of predetermined contexts, a list of predetermined queries, and predetermined recommendations. Each recommendation is associated with one of the predetermined contexts and one of the predetermined queries.

[0086] Thus, reference database 44 includes a set of queries and contexts already encountered or already envisaged upstream of the operation of avionics system or systems 10 and the associated recommendation. The content of reference database 44 has to be established, prior to the operation of avionics system 10, so that each recommendation is compliant with avionics safety rules applicable to avionics system 10.

[0087] Similarity-based reasoning module 38 is configured for comparing operator query 14 and the current context to the predetermined queries and predetermined contexts contained in reference database 44 according to a similarity metric.

[0088] The similarity metric is a function characterizing the similarity between two contexts and between two queries, in particular by comparing the different operating parameters of the two contexts and by comparing the keywords of the query.

[0089] The similarity metric is used for associating each pair {current context, operator query} with a measurement of similarity with the different pairs {context, query} contained in reference database 44. The higher the value of the measurement, the more similar are the two pairs according to the similarity metric used.

[0090] The similarity metric is inter alia the so-called cosine similarity function. Cosine similarity is used for calculating the similarity between two vectors to be compared. The cosine similarity is equal to the scalar product of the two vectors, divided by the norm of the two vectors. The result is thus comprised between −1 and 1. The value −1 indicates that the vectors are opposite, the value 0 indicates that the vectors are independent, and the value 1 indicates that the vectors are similar, in particular collinear. The intermediate values between −1 and 1 are used for evaluating the degree of similarity between the two vectors.

[0091] Thus, similarity-based reasoning module 38 is configured for calculating the value of the similarity metric between the pair {current context, operator query} and the different pairs {context, query} contained in reference database 44, and then for sorting the pairs {context, query} from the most similar to the least similar with respect to the pair {current context, operator query}, from the calculated metric values.

[0092] The recommendation generated by similarity-based reasoning module 38 is then equal to the recommendation associated with the predetermined context and to the predetermined query having the greatest similarity with the current context and with the query from operator 14. In other words, similarity-based reasoning module 38 selects the pair {context, query} contained in reference database 44, the similarity measurement of which with the pair {current context, operator query} is the highest.

[0093] Nevertheless, generation of the recommendation by similarity-based reasoning module 38 is inhibited if the similarity value is less than a predetermined threshold value. In other words, the recommendation is generated only if the similarity is greater than the predetermined threshold value.

[0094] The predetermined threshold value is determined so as to limit the safety risks for avionics system 10, and is used to make sure that the recommendation generated is sufficiently relevant to answer the query from operator 14 given the current context.

[0095] Similarity-based reasoning module 38 is configured for generating an error message sent to activation module 36 if a recommendation is not generated, in particular if the greatest similarity obtained is less than the predetermined threshold value. Indeed, this means that reference database 44 does not contain any pair {context, query} which is sufficiently similar to the current situation.

[0096] As an example, in the context of a query aiming to determine the landing runway of aircraft 12, reference database 44 includes in particular, the following data shown in the table below.

TABLE-US-00001 TABLE 1 Context Query Runway Runway Runway Solution Runway no. 1 no. 2 no. 3 Runway No. requested open open open selected 1 1 1 1 1 1 2 1 0 1 1 2 3 2 0 0 1 3 4 2 1 0 1 3

[0097] When aircraft 12 is in the current context “requested runway=1 and runway no. 1 open=0 and runway no. 2 open=1”, then similarity-based reasoning module 38 determines that the context of row 2 of the table is the most similar to the current context, and thus generates the recommendation to choose runway no. 2.

[0098] In particular, in the present case, the similarity metric is a measurement of the number of columns corresponding exactly to the current context. Row 1 herein corresponds to a similarity value of 2, row 2 corresponds to a similarity value of 3, row 3 corresponds to a similarity value of 1, and row 4 corresponds to a similarity value of 0. Thus, the highest similarity value is that corresponding to row 2 and therefore the recommendation chosen is the recommendation associated with that row.

[0099] Herein, the value of the predetermined threshold is to be at least equal to 3, and thus similarity-based reasoning module 38 indeed generates the recommendation to choose runway no. 2.

[0100] Rule-based reasoning module 40 is configured for generating a recommendation from a deterministic algorithm depending upon the query from operator 14 and on the current context.

[0101] The deterministic algorithm consists of a succession of predetermined conditional instructions.

[0102] In particular, the deterministic algorithm consists inter alia of a succession of “if, then” rules. Such rules are in particular constructed by a person skilled in the art or deduced from data coming from feedback from avionics system or systems 10, inter alia data contained in reference database 44.

[0103] If the conditional instructions lead to a solution, the solution is then generated as a recommendation by rule-based reasoning module 40.

[0104] If the conditional statements lead to an empty solution set, then rule-based reasoning module 40 is configured for generating an error message sent to activation module 36 indicating that a recommendation is not generated.

[0105] As an example, for the same case of a query aiming to determine the landing runway of aircraft 12, the predetermined conditional instructions are:

[0106] 1) Rule: Calculation of the runway distance required for landing depending upon the dynamics of aircraft 12, including speed and altitude thereof;

[0107] 2) Rule: If the distance of runway i is greater than the runway distance needed, then the landing is said to be “OK”; and

[0108] 3) Rule: If a plurality of runways “i” can be used for an “OK” landing, choose the runway with the highest runway distance.

[0109] Within such a framework, rule-based reasoning module 40 successively applies rules 1, 2 and then 3 so as to try to determine a solution to the query. E.g., if applying rule 1 leads to a required runway distance of 100 m and three runways are nearby, including a runway A with a length of 150 m length and a runway B with a length of 120 m and a runway C with a length of 80 m, then rule-based reasoning module 40 excludes runway C by applying rule 2, and then proposes runway A by applying rule 3.

[0110] Ontology-based reasoning module 42 is configured for generating a recommendation from an ontology-based algorithm depending upon the query of operator 14 and on the current context.

[0111] Ontology defines a structured set of concepts and relationships between concepts modeling operation of avionics system 10. In particular, ontology is a semantic network which groups together a set of concepts linked to each other by taxonomic relationships in order to prioritize concepts and semantics. Thus, knowledge is structured in the form of a model formalized in descriptive logic. An ontology-based reasoner may be used for deducing by inference, more than the knowledge strictly written in the initial ontology.

[0112] Ontology-based reasoning module 42 is configured for generating an error message sent to activation module 36 if a recommendation is not generated, in particular if the ontology does not allow a recommendation to be deduced.

[0113] As an example, still in the context of a query aimed at determining the landing runway of aircraft 12, the ontology includes an “airport” class with “runway” subclasses. The airport class may inter alia have name properties. The runway subclass contains as properties the name, the length of the runway and the status thereof, inter alia whether closed or open. There are X “airport” instances relating to the X modeled airports. There are “runway” instances relating to airport runways. The “Airport” instance and the “runway” instances are connected by a property {Airport Instance} a_for_runway {runway_Instance}. The ontology further includes an “aircraft” class with the properties of aircraft name, aircraft speed, minimum runway distance for landing, and a name of the intended runway. Current aircraft 12 is represented in this ontology by an instance, with the properties filled, in particular, by means of the current context. The “aircraft” instance is linked to a runway instance by the “will_land_at” property. Following sending of the query to “find runway for landing”, ontology-based reasoning module 42 sends a query to ontology asking same to search for the instance “runway” such as: [0114] runway length [“runway” instance]<minimum distance [“aircraft” instance], and [0115] runway status of the “runway” instance=open.

[0116] Activation module 36 is configured for activating at least one of the reasoning modules among similarity-based reasoning module 38, rule-based reasoning module 40, and ontology-based reasoning module 42.

[0117] Following activation thereof by activation module 36, the reasoning module generates a recommendation or generates an error message if a recommendation is not likely to be generated.

[0118] According to an advantageous embodiment of the invention, activation module 36 is configured for successively activating similarity-based reasoning module 38, rule-based reasoning module 40, and ontology-based reasoning module 42, until one of the reasoning modules generates a recommendation.

[0119] Thus, following reception of a query from operator 14, activation module 36 activates similarity-based reasoning module 38. If similarity-based reasoning module 38 generates a recommendation without generating an error message, processing module 28 transfers the recommendation to generation module 30. Conversely, if similarity-based reasoning module 38 generates an error message, activation module 36 then activates rule-based reasoning module 40. Similarly, if rule-based reasoning module 40 generates a recommendation, the recommendation is sent to generation module 30, and if an error message is generated, activation module 36 finally activates ontology-based reasoning module 42.

[0120] Activation module 36 may thus be used for adapting the reasoning load to the complexity of the query from operator 14. The more complex the query, the more complexity is needed from the reasoning module for solving the query. Indeed, a recommendation is obtained rapidly by similarity-based reasoning module 38 when the situation is already known, i.e., when a query and a similar current context are present in reference database 44 and a predetermined recommendation is associated therewith. In such a case, no calculation is needed, apart from the similarity calculation, which does not require complex calculations. When the situation does not exist in reference database 44, a simple rule-based reasoning is conducted in order to try to obtain a recommendation. Finally, when the situation is not encountered and rule-based reasoning module 40 cannot give a solution, then the ontology-based reasoning is conducted for finding a solution to the query and for obtaining a recommendation.

[0121] As a variant or as a complement, processing module 28 further includes a preprocessing module 50 configured for performing a semantic analysis of the query from operator 14 according to a predetermined formal rule when the query is received by processing module 28, and for activating one of the reasoning modules depending on the result of the analysis query from operator 14.

[0122] In particular, preprocessing module 50 is configured for analyzing keywords of the query from operator 14, and thus determining whether the query has a sufficient probability of being already known to the reference database 44, or otherwise, if the query has a sufficient probability of being processed correctly by rule-based reasoning module 40. The formal rule is inter alia associated with a predetermined list of keywords each associated with one of the reasoning modules.

[0123] Thus, following the reception of a query from operator 14, preprocessing module 50 analyzes the query and determines, inter alia by means of keywords of the query, that similarity-based reasoning module 38 has little chance to generate a recommendation, and directly activates rule-based reasoning module 40. Then, if rule-based reasoning module 40 generates a recommendation, the recommendation is sent to generation module 30, or if an error message is generated, activation module 36 activates ontology-based reasoning module 42.

[0124] As a variant or in addition, activation module 36 is configured for activating at least two of the reasoning modules.

[0125] In particular, activation module 36 is configured for activating one of the reasoning modules and the reasoning module with complexity just-above. E.g., if activation module 36 activates similarity-based reasoning module 38, same further activates rule-based reasoning module 40. If activation module 36 activates rule-based reasoning module 40, same further activates ontology-based reasoning module 42.

[0126] Processing module 28 further includes a control module 52 configured for receiving the recommendations generated by the two reasoning modules and for comparing same with each other. Control module 52 is configured inter alia for checking whether the recommendations are consistent with each other according to a predetermined consistency rule. The consistency rule is used to determine whether the two recommendations generated are intended for a similar or even identical implementation of the critical function or of the support function.

[0127] In the example of a query aiming to determine the landing runway of aircraft 12, two recommendations are consistent if same recommend the same runway.

[0128] Control module 52 is configured for sending generation module 30 an inconsistency message if an inconsistency is detected.

[0129] Generation module 30 is configured for receiving the recommendation from processing module 28 and for generating an answer to the query from operator 14, from the received recommendation.

[0130] The answer is, in particular, a solution to the information query from operator 14.

[0131] As a variant or in addition, the answer is a set point to be implemented by avionics system 10 in response to the query from operator 14.

[0132] In particular, the response corresponds to the recommendation received, shaped for possibly being applied by the corresponding avionics system 10.

[0133] Generation module 30 is configured for generating the response only if no inconsistency is detected by control module 52.

[0134] Advantageously, generation module 30 is further configured for sending the generated response associated with the query from operator 14 and with the current context, to reference database 44, in particular when the associated recommendation is generated by rule-based reasoning module 40 or by ontology-based reasoning module 42. Thus, reference database 44 includes an additional situation and similarity-based reasoning module 38 is likely to determine the associated recommendation directly at the next similar query in a similar current context.

[0135] Generation module 30 is configured for sending the generated response to display module 32 or to transmission module 34.

[0136] Display module 32 is configured for displaying the answer to operator 14, in particular on display 22. In particular, display module 32 is configured for displaying the answer on the heads-down display or the heads-up display in front of operator 14 who applies the instruction associated with the answer, if appropriate.

[0137] As an example, display module 32 displays the number of the landing runway determined by processing module 28.

[0138] As a variant or in addition, display module 32 is configured for displaying a button enabling the user either to accept or not accept the instruction associated with the answer. The electronic device then further includes an acquisition module configured for acquiring the choice of the operator and, if the operator accepts the instruction, for sending the instruction to transmission module 34.

[0139] Thus, if operator 14, herein the pilot, accepts the proposed landing runway, the answer is sent to the FMS.

[0140] Transmission module 34 is configured for transmitting the response to the corresponding avionics system 10 for implementation of the critical function or of the assistance function according to the instruction.

[0141] Thus, transmission module 34 is configured for sending the answer directly as soon as same is generated by generation module 30, to avionics system 10 so as to implement the critical function or the assistance function according to the query from operator 14.

[0142] In the example shown in FIG. 2, electronic device 24 includes an information processing unit including inter alia a memory and a processor associated with the memory. Receiver module 26, processing module 28, generation module 30, and advantageously display module 32 and transmission module 34 are each implemented in the form of a software program, or a software brick, which may be run by the processor. The memory is then apt to store a receiver software, a processing software, a generation software, and optionally, a display software and a transmission software. The processor is then apt to run each of these software programs.

[0143] In a variant (not shown), receiver module 26, processing module 28, generation module 30, and advantageously display module 32 and transmission module 34 are each produced in the form of a programmable logic component, such as a field programmable gate array (FPGA), or further in the form of a dedicated integrated circuit, such as an application specific integrated circuit (ASIC).

[0144] When electronic device 24 is produced in the form of one or a plurality of software programs, i.e., in the form of a computer program, same is further apt to be recorded on a computer-readable medium (not shown). The computer-readable medium is inter alia a medium apt to store the electronic instructions and to be coupled to a bus of a computer system. As an example, the readable medium is an optical disk, a magneto-optical disk, a ROM memory, a RAM memory, any type of non-volatile memory (e.g. EPROM, EEPROM, FLASH, NVRAM), a magnetic card, or an optical card. A computer program containing software instructions is then stored on the readable medium.

[0145] The operation of electronic decision support device 24 according to an embodiment of the invention will now be explained based on FIG. 3 which shows a flowchart for a decision support method according to an embodiment of the present invention, for the implementation of a critical function or of the assistance function by avionics system 10, in response to a query issued by operator 14 of avionics system 10.

[0146] Initially, operator 14 is installed in control station 16.

[0147] Control station 16 is installed in aircraft 12 or on the ground, inter alia in a control station 18, as shown in FIG. 1.

[0148] During an initial operation 100, receiver module 26 receives a query issued by operator 14. The query is, for example, a query for assigning a landing runway for aircraft 12. As another example, the query is a query for changing the flight path of aircraft 12. As yet another example, the query is a query for a reconfiguration solution following the detection of a failure of an avionics system 10.

[0149] During an optional operation 110, preprocessing module 50 analyzes the query, according to a formal rule, in particular by searching for keywords.

[0150] Then, during an operation 120, activation module 26 activates at least one of the reasoning modules, in particular the reasoning module corresponding to the analysis performed by preprocessing module 50.

[0151] In an operation 130, a recommendation is generated in response to the query.

[0152] As a variant, the method does not include operation 110, and during operation 120, activation module 36 is configured for successively activating similarity-based reasoning module 38, rule-based reasoning module 40, and ontology-based reasoning module 42, until one of reasoning modules 38, 40, 42 generates a recommendation during operation 130. The recommendation is then sent to generation module 30.

[0153] Thus, activation module 36 activates similarity-based reasoning module 38 during a sub-step 121. If similarity-based reasoning module 38 generates a recommendation without generating an error message during a sub-operation 131, processing module 28 transfers the recommendation to generation module 30.

[0154] Conversely, if similarity-based reasoning module 38 generates an error message, activation module 36 then activates rule-based reasoning module 40 during a sub-operation 122.

[0155] Similarly, if rule-based reasoning module 40 generates a recommendation during a sub-operation 132, the recommendation is sent to generation module 30.

[0156] If an error message is generated by rule-based reasoning module 40, activation module 36 finally activates ontology-based reasoning module 42 during a sub-operation 123, and ontology-based reasoning module 42 then generates a recommendation during a sub-operation 133.

[0157] Then, during an operation 140, generation module 30 receives the recommendation and generates an answer to be implemented by the corresponding avionics system 10 on the basis of the recommendation received.

[0158] During an operation 150, the answer is sent to display module 32, which displays the answer in front of operator on display 22.

[0159] As a variant or in addition, the answer is sent to transmission module 34, which sends the instruction associated with the answer to avionics system 10, for implementation of the critical function or of the assistance function according to the instruction, during an operation 160.

[0160] In this way, it can be understood that the present invention has a certain number of advantages.

[0161] Indeed, the invention makes it possible to generate a relevant answer concerning the implementation of a critical function or of an assistance function by adapting the complexity of the algorithm used, to the complexity of the query from operator 14, in particular by means of activation module 36 which may be used for adapting the reasoning load to the complexity of the query from operator 14.

[0162] When the situation is already known, a recommendation is obtained very quickly by similarity-based reasoning module 38. When the situation is not known, the rule-based reasoning module 40 is used for deducing the solution to be proposed. Finally, when the situation is not encountered and the application of the rules cannot give a solution, then the reasoning based on ontology is conducted in order to obtain a recommendation.

[0163] Thus, a parallel can be made between the electronic device according to the invention and the cognitive model of human reasoning described by Rasmussen. This cognitive model is called “SRK” signifying “Skills, Rules, Knowledge”. Same describes the reasoning in the form of three elements of increasing complexity: automatic skills used in the context of simple tasks, calculation rules derived from routines, and knowledge derived from complex reasoning, used in case of confrontation with the unknown.

[0164] Electronic decision support device 24 according to the invention may be used for proposing a solution to the query from operator 14, which is relevant, while being at the same time compatible with safety of the associated avionics system 10.