A method, apparatus, medium, and electronic equipment for flight testing of an intelligent flying vehicle.

Abstract

The present specification discloses a flight test method, device, medium and electronic equipment for an intelligent flying object, including: determining the test requirements of the intelligent flying object, inputting the test requirements into a pre-trained initial state generation model, and determining the first initial state of the intelligent flying object. According to the first initial state, determining the first test case of the intelligent flying object. According to the first test case, performing a flight test on the intelligent flying object. By using the initial state generation model based on the test requirements to generate the first initial state of the intelligent flying object, and performing a flight test on the intelligent flying object based on the first initial state, more flight attitudes can be covered, the test coverage can be maximized, the flight test blind spots can be reduced, the test cycle can be shortened, and the performance of the intelligent flying object can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a flight test method, device, medium and electronic equipment for an intelligent flying object. Background Art

[0002] With the continuous development of science and technology, flight simulation testing has received widespread attention.

[0003] At present, in flight simulation tests, in order to fully test and optimize the performance of intelligent flying bodies, it is usually necessary to set different initial states as test cases, and based on the test cases, perform flight tests on the intelligent flying bodies to obtain test results of the intelligent flying bodies. Among them, the intelligent flying body usually refers to an aircraft model with a certain degree of autonomy. The intelligent flying body can be a drone or any aircraft model that can be intelligently controlled, such as an airplane, a helicopter, a spacecraft, etc. The initial state may include initial values ​​such as the coordinates, state, and attitude of the intelligent flying body. The setting of the initial state will directly affect the coverage of the flight test of the intelligent flying body and the validity of the test results. Therefore, how to accurately set the initial state to perform flight tests on the intelligent flying body based on the initial state is a very important issue.

[0004] Based on this, this specification provides a flight test method for an intelligent flying object. Summary of the invention

[0005] This specification provides a flight test method, device, medium and electronic equipment for an intelligent flying object to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a flight test method for an intelligent flying object, including:

[0008] Determine the testing requirements for intelligent flying objects;

[0009] Inputting the test requirement into a pre-trained initial state generation model to determine a first initial state of the intelligent flying body; wherein the initial state generation model is a large language model;

[0010] Determining a first test case for the intelligent flying object according to the first initial state;

[0011] According to the first test case, a flight test is performed on the intelligent flying object.

[0012] Optionally, the method further comprises:

[0013] Determining a first test result of the intelligent flying object;

[0014] Using the first test result and the first initial state as first test data;

[0015] According to the first test data, adjusting the first initial state to determine a second initial state;

[0016] Determining a second test case for the intelligent flying object according to the second initial state;

[0017] According to the second test case, a flight test is performed on the intelligent flying object.

[0018] Optionally, determine the test requirements of the intelligent flying object, including:

[0019] Acquire historical test data of the intelligent flying object; wherein the historical test data includes basic information, historical test results and historical initial states of the intelligent flying object;

[0020] From the historical test data, determine the historical test data whose historical test result is a first result and use it as target test data;

[0021] The test requirements of the intelligent flying object are determined according to the target test data.

[0022] Optionally, determining the test requirements of the intelligent flying object according to the target test data specifically includes:

[0023] Displaying the target test data to the tester;

[0024] In response to a first input operation by the tester, a test requirement of the intelligent flying object is determined.

[0025] Optionally, the historical initial state includes several state parameters;

[0026] Determining the test requirements of the intelligent flying object according to the target test data, specifically including:

[0027] Determining a test scenario for the intelligent flying object;

[0028] When the test scenario is of the first type, determining a specified state parameter in a historical initial state included in the target test data;

[0029] When the specified state parameter is greater than a specified threshold, taking the historical initial state included in the target test data as a third initial state;

[0030] According to the third initial state, a test requirement of the intelligent flying object is determined.

[0031] Optionally, the third initial state includes several state parameters;

[0032] Determining the test requirements of the intelligent flying object according to the third initial state specifically includes:

[0033] Determine the priorities respectively corresponding to the state parameters included in the third initial state;

[0034] According to each priority level, determining a parameter to be adjusted from each state parameter included in the third initial state;

[0035] According to the parameters to be adjusted, the test requirements of the intelligent flying object are determined.

[0036] Optionally, determining the test requirements of the intelligent flying object according to the target test data specifically includes:

[0037] Determining a test scenario for the intelligent flying object;

[0038] When the test scenario is of the second type, analyzing the historical initial state included in the target test data to determine an analysis result;

[0039] According to the analysis result, the test requirements of the intelligent flying object are determined.

[0040] This specification provides a flight test device for an intelligent flying object, including:

[0041] A determination module is used to determine the test requirements of the intelligent flying body;

[0042] An initial state generation module, used for inputting the test requirement into a pre-trained initial state generation model to determine a first initial state of the intelligent flying body; wherein the initial state generation model is a large language model;

[0043] A test case generation module, used for determining a first test case of the intelligent flying object according to the first initial state;

[0044] A flight test module is used to perform a flight test on the intelligent flying object according to the first test case.

[0045] The present specification provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the flight test method of the intelligent flying object described above is implemented.

[0046] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned flight test method for an intelligent flying object when executing the program.

[0047] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0048] The flight test method of the intelligent flying object provided in this specification determines the test requirements of the intelligent flying object, inputs the test requirements into a pre-trained initial state generation model, determines the first initial state of the intelligent flying object, determines the first test case of the intelligent flying object based on the first initial state, and performs a flight test on the intelligent flying object based on the first test case.

[0049] It can be seen from the above method that when the present application performs a flight test on an intelligent flying body, the test requirements of the intelligent flying body can be first determined, and the test requirements can be input into a pre-trained initial state generation model to determine the first initial state of the intelligent flying body. Then, based on the first initial state, the first test case of the intelligent flying body is determined, and based on the first test case, a flight test is performed on the intelligent flying body. By generating a first initial state that meets the test requirements through the initial state generation model, there is no need to rely on manually setting the first initial state, thus avoiding subjective influences when setting the first initial state, and thus avoiding the introduction of additional errors. Subsequently, based on the first initial state, a flight test is performed on the intelligent flying body, so that more flight attitudes can be covered, the test coverage can be maximized, the flight test blind spots can be reduced, the test cycle can be shortened, and the performance of the intelligent flying body can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0051] Figure 1 A schematic diagram of a flight test method for an intelligent flying object provided in this specification;

[0052] Figure 2 A schematic diagram of a flight test process provided in this specification;

[0053] Figure 3 A schematic diagram of the flight test provided in this manual;

[0054] Figure 4 A schematic diagram of a flight test device for an intelligent flying object provided in this specification;

[0055] Figure 5 A method corresponding to the Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0057] At present, in flight simulation tests, different initial states are usually set manually, that is, the tester sets the initial state of the intelligent flying body based on manual experience, and generates test cases based on the initial state. Then, based on the test case, the intelligent flying body is subjected to flight test to obtain the test results of the intelligent flying body. The setting of the initial state will directly affect the coverage of the flight test of the intelligent flying body and the validity of the test results. However, it is difficult to cover various complex situations that may occur in the air by setting the initial state through this manual method, and the setting of the initial state will be subject to subjective influences, introducing additional errors, resulting in low validity of the test results obtained after testing based on the initial state.

[0058] Based on this, this specification provides a flight test method, device, medium and electronic setting of an intelligent flying object. The following is a detailed description of the technical solutions provided by each embodiment of this specification in conjunction with the accompanying drawings.

[0059] Figure 1 The following is a flow chart of a flight test method for an intelligent flying object provided in this specification, comprising the following steps:

[0060] S100: Determine the testing requirements of the intelligent flying object.

[0061] In this specification, the equipment used for flight testing can determine the test requirements of the intelligent flying body. Among them, the equipment used for flight testing can be a server, or it can be an electronic device such as a desktop computer, a laptop computer, etc. For the convenience of description, the method of flight testing of the intelligent flying body provided in this specification is described below with the server as the execution subject. The above-mentioned intelligent flying body generally refers to an aircraft model with a certain degree of autonomy. The intelligent flying body can be a drone or any aircraft model that can be intelligently controlled, such as an airplane, a helicopter, a spacecraft, etc., and this specification does not make specific limitations. It should be noted that there may be multiple intelligent flying bodies in this specification. For the convenience of description, the following description will take a single intelligent flying body as an example.

[0062] The above-mentioned test requirements are texts describing the flight test of the intelligent flying body. The test requirements may include the basic information of the intelligent flying body, and the basic information of the intelligent flying body may include the hardware parameter information such as the model, volume, and sensor accuracy of the intelligent flying body. Of course, the test requirements may also include the test scene, test environment, and test tasks of the intelligent flying body. The test scene may include scenes such as single-machine flight test and confrontation flight test. The test environment may include the humidity, temperature, pressure, wind speed, and wind direction of the atmosphere. The test task may be a flight task of the intelligent flying body, and the test task may include the flight path, target position, and altitude limit. In addition, since the intelligent flying body performs flight tests in a simulation environment, the above-mentioned test requirements may also include parameter information required to configure the simulation environment, and the parameter information may include the name, identification, and memory of the simulation software.

[0063] In this specification, when the intelligent flying object is subjected to flight test for the first time, the above test requirements are text input by the tester, and the test requirements include at least basic information of the intelligent flying object, and of course, may also include parameter information required for configuring the test scene, test environment, and simulation environment, etc., which are not specifically limited in this specification. Based on this, the server can determine the test requirements of the intelligent flying object input by the tester in response to the tester's input operation.

[0064] In addition, any one or several of the basic information of the above-mentioned intelligent flying body, test scenarios, test environments, and parameter information required to configure the simulation environment can be pre-set. Therefore, in addition to responding to the input operations of the testers and determining the test requirements input by the testers, the server can also directly determine the test requirements of the intelligent flying body.

[0065] S102: Inputting the test requirement into a pre-trained initial state generation model to determine a first initial state of the intelligent flying body; wherein the initial state generation model is a large language model.

[0066] In this specification, the server may input the test requirements into the pre-trained initial state generation model to determine the first initial state of the intelligent flying body. Among them, the initial state generation model may be a model pre-trained by the server, or a model obtained after fine-tuning based on any existing large language model. The initial state generation model may be a large language model. The above-mentioned first initial state may include several state parameters of the intelligent flying body, and the state parameters may include position (i.e., coordinates), attitude, speed, and state. The speed may include linear velocity, angular velocity, etc. The attitude may include pitch angle, yaw angle, and roll angle, etc. The state may be the state of the sensor in the intelligent flying body and the state of the actuator. The sensor may be GPS, gyroscope, etc., and the actuator may be a propeller, etc. The state may be one of a normal state (i.e., a normal working state) and an abnormal state (i.e., an abnormal working state). Of course, the state may also be one of a standby state and a shutdown state, which is not specifically limited in this specification. Of course, the above-mentioned state parameters may also include environmental parameters, which may include atmospheric parameters, wind speed, wind direction, and gravity acceleration, etc. The atmospheric parameters may include air density, temperature, humidity, and pressure, etc.

[0067] S104: Determine a first test case of the intelligent flying object according to the first initial state.

[0068] S106: Perform a flight test on the intelligent flying object according to the first test case.

[0069] In this specification, the server may determine the first test case of the intelligent flying object according to the first initial state. Then, according to the first test case, the intelligent flying object is subjected to a flight test. Among them, the first test case may include the first initial state. Specifically, the server may directly use the first initial state as the first test case of the intelligent flying object. Then, according to the first test case, the intelligent flying object is subjected to a flight test.

[0070] When the flight test of the intelligent flying body is performed according to the first test case, the server can initialize the simulation environment according to the first test case, and perform a flight test on the intelligent flying body in the simulation environment to determine the test result. The test result can be one of a test pass and a test fail. When the test result of the intelligent flying body is a test pass, it means that no abnormal situation occurred during the test of the intelligent flying body, or the test task was completed. When the test result of the intelligent flying body is a test fail, it means that an abnormal situation occurred during the test of the intelligent flying body, or the test task was not completed.

[0071] It can be seen from the above method that when the present application performs a flight test on an intelligent flying body, the server can first determine the test requirements of the intelligent flying body, input the test requirements into a pre-trained initial state generation model, and determine the first initial state of the intelligent flying body. Then, based on the first initial state, determine the first test case of the intelligent flying body, and perform a flight test on the intelligent flying body based on the first test case. By generating a first initial state that meets the test requirements through the initial state generation model, there is no need to rely on manually setting the first initial state, avoiding subjective influences when setting the first initial state, and thus avoiding the introduction of additional errors. Subsequently, based on the first initial state, a flight test is performed on the intelligent flying body, so that more flight attitudes can be covered, the test coverage can be maximized, the flight test blind spots can be reduced, the test cycle can be shortened, and the performance of the intelligent flying body can be improved.

[0072] In this specification, the above test requirements may be the test requirements input by the tester when the intelligent flying object is subjected to the flight test for the first time (i.e., the first round). The test requirements may also be the test requirements when the intelligent flying object is subjected to the flight test for any time after the first time. That is, the server may conduct multiple flight tests on the intelligent flying object. The test requirements may be the test requirements during other rounds of tests except the first test. Based on this, when the current test is not the first time the intelligent flying object is subjected to the flight test, when the above step S100 determines the test requirements of the intelligent flying object, the server may obtain the historical test data of the intelligent flying object, and determine the test requirements of the intelligent flying object according to the historical test data. Among them, the historical test data is the test data generated when the intelligent flying object is tested before the current test. The historical test data includes the basic information of the intelligent flying object, the historical test results, and the historical initial state. The basic information of the intelligent flying object may be the test requirements input by the tester during the first test, or the test requirements pre-set and determined during the first test. This specification does not make specific restrictions.

[0073] When determining the test requirements of the intelligent flying object based on historical test data, the historical test data is displayed to the tester so that the tester can determine the test requirements of the current test of the intelligent flying object and input the test requirements to the server. Therefore, the server can determine the test requirements of the intelligent flying object in response to the tester's first input operation.

[0074] In addition, in order to focus on test cases that lead to poor test results, thereby continuously challenging and improving the robustness and adaptability of the intelligent flying body, in the above step S100, the server can obtain historical test data of the intelligent flying body, and from the historical test data, determine the historical test data with the historical test result as the first result, and use it as the target test data. Then, based on the target test data, determine the test requirements of the intelligent flying body. Among them, the first result may be a test failure. The target test data is the historical test data with the historical test result of a test failure.

[0075] When the target test data is used to determine the test requirements of the intelligent flying body, the server can display the target test data to the tester, and determine the test requirements of the intelligent flying body in response to the first input operation of the tester. The specific process is similar to the above-mentioned process of determining the test requirements of the intelligent flying body based on the historical test data, and will not be repeated here.

[0076] In addition, the server can perform flight tests of multiple test scenarios on the intelligent flying body, and the test requirements of each test scenario are different. For example, a single-machine flight test only needs to describe the relevant information of a single intelligent flying body, while a confrontational flight test needs to describe the relevant information of the other intelligent flying body in addition to describing the relevant information of one party's intelligent flying body. Therefore, when generating the test requirements of the intelligent flying body, it is necessary to consider the test scenario of the intelligent flying body. Specifically, taking the above-mentioned determination of the test requirements of the intelligent flying body according to the target test data as an example, since the above-mentioned process of determining the test requirements of the intelligent flying body according to the historical test data is similar to the process of determining the test requirements of the intelligent flying body according to the target test data, it will not be repeated here. Based on this, when determining the test requirements of the intelligent flying body according to the target test data, the server can also determine the test scenario of the intelligent flying body. When the test scenario is of the first type, the server can determine the specified state parameter in the historical initial state included in the target test data. When the specified state parameter is greater than the specified threshold, the historical initial state included in the target test data is used as the third initial state. According to the third initial state, the test requirements of the intelligent flying body are determined.

[0077] Among them, the first type mentioned above is a single-machine flight test. The above-mentioned historical initial state may include several state parameters, and the designated state parameter may be pre-set. The designated state parameter may be all state parameters included in the historical initial state, or may be part of the state parameters included in the historical initial state, that is, the designated state parameter may be at least one of the state parameters included in the historical initial state. The above-mentioned designated threshold may be pre-set, specifically, it may be pre-set by the tester according to manual experience, or it may be pre-set by the tester according to the target test data, and this specification does not make specific restrictions. It should be noted that each state parameter has a corresponding designated threshold, that is, there are as many designated thresholds as there are the above-mentioned designated state parameters, and the designated threshold corresponding to each designated state parameter may be the same or different. Based on this, when any designated state parameter in the historical initial state included in the target test data is greater than the designated threshold corresponding to the designated state parameter, the server may use the historical initial state as the third initial state. By determining from the target test data a historical initial state in which a specified state parameter is greater than a specified threshold, a test case for an abnormal state is obtained, namely, an abnormal initial state (i.e., the third initial state). Based on the abnormal initial state, the test requirements for the intelligent flying body are determined, thereby enhancing the importance of the abnormal initial state, so that the intelligent flying body can be flight tested under a more difficult initial state, which helps to discover potential defects of the intelligent flying body in advance, thereby reducing the risk of subsequent application processes of the intelligent flying body and helping to improve the performance of the intelligent flying body.

[0078] When determining the test requirements of the intelligent flying body according to the third initial state, the server may determine the initial state of the previous round of tests of the current test and use it as the initial state to be adjusted. The test requirements of the intelligent flying body are generated according to the initial state to be adjusted and the third initial state. Among them, the test requirement may be to adjust the initial state of the previous round of tests of the current test (i.e., the initial state to be adjusted) to an initial state similar to the third initial state. Therefore, when generating the test requirements of the intelligent flying body according to the initial state to be adjusted and the third initial state, the server may generate the test requirements of the intelligent flying body according to the initial state to be adjusted and the third initial state using a preset first template. The initial state to be adjusted is the initial state of the previous round of tests of the current test. The preset first template is used to splice the initial state to be adjusted and the third initial state. The first template may be "adjust [the initial state to be adjusted] to an initial state similar to [the third initial state]". By dynamically determining the test requirements based on the initial state to be adjusted, the first initial state of the current test can be dynamically generated according to the test requirements, so as to improve the coverage and effectiveness of the flight test of the intelligent flying body, thereby shortening the test cycle, increasing the speed of the flight test of the intelligent flying body, and saving test time.

[0079] In addition, the server may also determine the priorities corresponding to the state parameters included in the third initial state. According to the priorities, the parameters to be adjusted are determined from the state parameters included in the third initial state. Then, according to the parameters to be adjusted, the test requirements of the intelligent flying body are determined. Among them, the priorities corresponding to the state parameters included in the third initial state may be preset, and the priorities characterize the importance of the state parameters and determine the adjustment order of the state parameters. The importance refers to the degree of influence of the state parameter on the historical test results. When determining the parameters to be adjusted from the state parameters included in the third initial state according to the priorities, the server may sort the state parameters included in the third initial state in order from large to small according to the priority to obtain a parameter sequence, and then determine a specified number of state parameters according to the parameter sequence as the parameters to be adjusted. The specified number is preset, and the specified number is greater than or equal to 1.

[0080] When determining the test requirements of the intelligent flying body according to the parameters to be adjusted, the server may determine the initial state of the previous round of testing of the current test and use it as the initial state to be adjusted. The test requirements of the intelligent flying body are generated according to the initial state to be adjusted, the parameters to be adjusted and the third initial state. Among them, the test requirements may be to adjust the parameters to be adjusted in the initial state of the previous round of testing of the current test (i.e., the initial state to be adjusted) to state parameters similar to the parameters to be adjusted in the third initial state. Therefore, when generating the test requirements of the intelligent flying body according to the initial state to be adjusted, the parameters to be adjusted and the third initial state, the server may generate the test requirements of the intelligent flying body according to the initial state to be adjusted, the parameters to be adjusted and the third initial state using a preset second template. The initial state to be adjusted is the initial state of the previous round of testing of the current test. The preset second template is used to splice the initial state to be adjusted, the parameters to be adjusted and the third initial state. The second template may be "adjust the [parameter to be adjusted] in the [initial state to be adjusted] to a state parameter similar to the [parameter to be adjusted] in the [third initial state]. By determining the parameters to be adjusted based on the priority of each state parameter, and dynamically generating test requirements based on the initial state to be adjusted, the parameters to be adjusted, and the third initial state, the first initial state of the current test can be dynamically generated based on the test requirements, so that the server can give priority to adjusting the state parameters that have a great impact on the test results, thereby increasing the difficulty of the flight test of the intelligent flying body, helping to discover the potential defects of the intelligent flying body in advance, thereby reducing the risks of the subsequent application process of the intelligent flying body, and helping to improve the performance of the intelligent flying body. At the same time, the coverage and effectiveness of the flight test of the intelligent flying body are improved, thereby shortening the test cycle, increasing the speed of the flight test of the intelligent flying body, and saving test time.

[0081] In the present specification, when the test requirements of the intelligent flying body are determined according to the target test data. The server can determine the test scenario of the intelligent flying body. When the test scenario is of the second type, the historical initial state included in the target test data is analyzed to determine the analysis result. Then, based on the analysis result, the test requirements of the intelligent flying body are determined. Among them, the above-mentioned second type is an adversarial flight test. The analysis result may be the reason why the historical test result is the first result, and the reason may be the historical initial state or a state parameter in the historical initial state. The analysis result may be obtained based on a pre-set analysis algorithm or a pre-trained machine learning model, or obtained by manual analysis, and this specification does not make specific limitations.

[0082] When determining the test requirements of the intelligent flying body according to the analysis results, the server can determine the initial state of the previous round of tests of the current test and use it as the initial state to be adjusted, and generate the test requirements of the intelligent flying body according to the initial state to be adjusted and the analysis results. Among them, the test requirement can be to adjust the initial state of the previous round of tests of the current test (i.e., the initial state to be adjusted) according to the analysis results. Therefore, when generating the test requirements of the intelligent flying body according to the initial state to be adjusted and the analysis results, the server can use the preset third template to generate the test requirements of the intelligent flying body according to the initial state to be adjusted and the analysis results. The initial state to be adjusted is the initial state of the previous round of tests of the current test. The preset third template is used to splice the initial state to be adjusted and the analysis results. The second template can be "adjust [the initial state to be adjusted] according to [the analysis results]". By analyzing the historical initial state in the target test data, the reason that caused the historical test result to be the first result is found, that is, the historical initial state or state parameter that caused the historical test result to be the first result, and then dynamically generate test requirements according to the analysis results and the initial state to be adjusted, so that the first initial state of the current test can be dynamically generated according to the test requirements, so that the server adjusts the historical initial state or state parameter that caused the historical test result to be the first result, thereby increasing the difficulty of the flight test of the intelligent flying body, helping to discover the potential defects of the intelligent flying body in advance, thereby reducing the risk of the subsequent application process of the intelligent flying body, and helping to improve the performance of the intelligent flying body. At the same time, the coverage and effectiveness of the flight test of the intelligent flying body are improved, thereby shortening the test cycle, increasing the speed of the flight test of the intelligent flying body, and saving test time.

[0083] In the present specification, after performing a flight test on the intelligent flying body, the server can determine a first test result of the intelligent flying body, and the first test result is obtained by performing a flight test on the intelligent flying body based on a first test case, and the first test result is the test result of the current test. After obtaining the first test result, the server can use the first test result and the first initial state as the first test data. Afterwards, the first initial state is adjusted according to the first test data to determine the second initial state. According to the second initial state, a second test case of the intelligent flying body is determined, and according to the second test case, a flight test is performed on the intelligent flying body. The second initial state is the initial state used in the next round of testing of the current test, and the second test case is a test case for the next round of testing of the above-mentioned current test. Based on the second test case, the process of performing a flight test on the intelligent flying body is actually the process of the next round of testing of the above-mentioned current test, that is, Figure 1 The process of the next round of testing after the flight test process is shown.

[0084] In addition, when the first initial state is adjusted according to the first test data and the second initial state is determined, the server can determine the test requirements of the intelligent flying body according to the first test data, and then input the determined test requirements into the pre-trained initial state generation model to determine the second initial state of the intelligent flying body. The above test requirements are obviously not the test requirements input by the tester when the intelligent flying body is first tested in flight, so the process of determining the test requirements of the intelligent flying body according to the first test data is similar to the process of determining the test requirements of the intelligent flying body according to the historical test data, and will not be repeated here. It should be noted that if the above first test data is the data generated when the intelligent flying body is first tested in flight, the server can directly determine the test requirements of the intelligent flying body according to the first test data. If the above first test data is not the data generated when the intelligent flying body is first tested in flight, the server needs to obtain other historical test data of the intelligent flying body, and the other historical test data is the test data generated when the intelligent flying body is tested in flight in history without the first test data. Then determine the test requirements of the intelligent flying body according to the other historical test data and the first test data.

[0085] In this manual, if Figure 2 As shown, Figure 2The present invention is a schematic diagram of a process of a flight test provided in this specification. The server may first respond to the input operation of the tester to determine the test requirements input by the tester. Then the test requirements are input into the pre-trained initial state generation model to determine the first initial state of the intelligent flying body, and the first test case of the intelligent flying body is determined according to the first initial state. According to the first test case, the intelligent flying body is subjected to a flight test, and the first test result is determined. Afterwards, it is determined whether the flight test end condition is met, and if so, the flight test of the intelligent flying body is determined to be over. If not, the first test result and the first initial state are used as the first test data, and the test requirements are regenerated according to the first test data, and the regenerated test requirements are continuously input into the pre-trained initial state generation model to re-determine the first initial state of the intelligent flying body, and the first test case of the intelligent flying body is re-determined according to the first initial state, and the flight test of the intelligent flying body is continued according to the newly determined first test case until the flight test end condition is met. Among them, the flight test end condition may be that the number of tests reaches a preset threshold, or the tester manually stops the flight test on the intelligent flying body, which is not specifically limited in this specification.

[0086] Based on this, take the first flight test of the intelligent flying body and two rounds of tests on the intelligent flying body as an example. Figure 3 As shown, Figure 3 As a schematic diagram of the flight test provided in this specification, the server may first respond to the input operation of the tester to determine the test requirements input by the tester. Then the test requirements are input into the pre-trained initial state generation model to determine the first initial state of the intelligent flying body, and the first test case of the intelligent flying body is determined according to the first initial state. According to the first test case, the intelligent flying body is subjected to a flight test, and a first test result is determined. Afterwards, the first test result and the first initial state are used as the first test data, and the test requirements are regenerated according to the first test data, and the regenerated test requirements are continuously input into the pre-trained initial state generation model to determine the second initial state of the intelligent flying body, and the second test case of the intelligent flying body is determined according to the second initial state. According to the second test case, the intelligent flying body is subjected to a flight test, and a second test result is determined.

[0087] In this specification, the first initial state, the second initial state and the third initial state may be multiple, the historical test data or the target test data may include multiple historical test results and multiple historical initial states. Furthermore, the first initial state, the second initial state or the third initial state may include multiple state parameters.

[0088] In this specification, the initial state generation model can be a large language model pre-trained by the server. Therefore, when pre-training the initial state generation model, the server can obtain the simulation data of the intelligent flying body in history, determine the test information included in the simulation data, and use it as a training sample, and determine the initial state corresponding to the test information, and use it as a label of the training sample. According to the training sample and the label, the initial state generation model to be trained is trained to obtain the trained initial state generation model. Among them, the intelligent flying body can be any type of intelligent flying body that has been tested for flight simulation in history, and the intelligent flying body can be multiple. The simulation data is the data generated when the intelligent flying body was tested for flight simulation in history. The simulation data includes test information and the initial state corresponding to the test information. The test information can be the test requirements proposed when the intelligent flying body is tested for flight simulation, and the test information can be proposed by the tester. The initial state generation model to be trained can be a large language model with randomly initialized model parameters, and can also be any existing large language model, that is, a large language model that has been trained. The initial state generation model to be trained can be fine-tuned directly according to the training samples and the labels.

[0089] When the initial state generation model to be trained is trained based on the training samples and annotations, the server can input the training samples into the initial state generation model to be trained, determine the predicted initial state output by the initial state generation model to be trained, determine the loss based on the predicted initial state and the annotations, and adjust the initial state generation model to be trained based on the loss.

[0090] In addition, in order to better train the initial state generation model, the server can determine prompt information, input the prompt information and the training sample into the initial state generation model to be trained, and determine the predicted initial state output by the initial state generation model to be trained. The prompt information can be determined by the tester based on the training sample and uploaded to the server.

[0091] The above are one or more implementation methods of this specification. Based on the same idea, this specification also provides a corresponding flight test device for an intelligent flying object, such as Figure 4 shown.

[0092] Figure 4 A schematic diagram of a flight test device for an intelligent flying object provided in this specification includes:

[0093] A determination module 200 is used to determine the test requirements of the intelligent flying object;

[0094] The initial state generation module 202 is used to input the test requirements into a pre-trained initial state generation model to determine the first initial state of the intelligent flying body; wherein the initial state generation model is a large language model;

[0095] A test case generating module 204, configured to determine a first test case for the intelligent flying object according to the first initial state;

[0096] The flight test module 206 is used to perform a flight test on the intelligent flying object according to the first test case.

[0097] Optionally, the flight test module 206 is also used to determine a first test result of the intelligent flying body; use the first test result and the first initial state as first test data; adjust the first initial state according to the first test data to determine a second initial state; determine a second test case for the intelligent flying body according to the second initial state; and perform a flight test on the intelligent flying body according to the second test case.

[0098] Optionally, the determination module 200 is specifically used to obtain historical test data of the intelligent flying body; wherein the historical test data includes basic information, historical test results and historical initial states of the intelligent flying body; from the historical test data, determine the historical test data whose historical test results are the first results, and use them as target test data; and determine the test requirements of the intelligent flying body based on the target test data.

[0099] Optionally, the determination module 200 is specifically configured to display the target test data to a tester; and determine a test requirement of the intelligent flying object in response to a first input operation of the tester.

[0100] Optionally, the historical initial state includes several state parameters;

[0101] The determination module 200 is specifically used to determine the test scenario of the intelligent flying object; when the test scenario is of the first type, determine the specified state parameters in the historical initial state included in the target test data;

[0102] When the designated state parameter is greater than a designated threshold, the historical initial state included in the target test data is used as a third initial state; and the test requirements of the intelligent flying body are determined according to the third initial state.

[0103] Optionally, the third initial state includes several state parameters;

[0104] The determination module 200 is specifically used to determine the priorities corresponding to the various state parameters included in the third initial state; determine the parameters to be adjusted from the various state parameters included in the third initial state according to the priorities; and determine the test requirements of the intelligent flying body according to the parameters to be adjusted.

[0105] Optionally, the determination module 200 is specifically used to determine a test scenario for the intelligent flying body; when the test scenario is of the second type, analyze the historical initial state included in the target test data to determine an analysis result; and determine the test requirements for the intelligent flying body based on the analysis result.

[0106] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A flight test method for an intelligent flying object is provided.

[0107] This manual also provides Figure 5 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 5 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The flight test method of the intelligent flying object.

[0108] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0109] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0110] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0111] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0112] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0113] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0118] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0120] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0121] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0123] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0124] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A flight test method for an intelligent flying object, characterized in that: The method comprises: Determine the testing requirements for intelligent flying objects; Inputting the test requirement into a pre-trained initial state generation model to determine a first initial state of the intelligent flying body; wherein the initial state generation model is a large language model; and the first initial state includes initial values ​​of several state parameters of the intelligent flying body; Determining a first test case for the intelligent flying object according to the first initial state; According to the first test case, a flight test is performed on the intelligent flying object.

2. The method according to claim 1, characterized in that The method further comprises: Determining a first test result of the intelligent flying object; Using the first test result and the first initial state as first test data; According to the first test data, adjusting the first initial state to determine a second initial state; Determining a second test case for the intelligent flying object according to the second initial state; According to the second test case, a flight test is performed on the intelligent flying object.

3. The method according to claim 1, characterized in that Determine the test requirements for intelligent flying objects, including: Acquire historical test data of the intelligent flying object; wherein the historical test data includes basic information, historical test results and historical initial states of the intelligent flying object; From the historical test data, determine the historical test data whose historical test result is a first result and use it as target test data; The test requirements of the intelligent flying object are determined according to the target test data.

4. The method according to claim 3, characterized in that Determining the test requirements of the intelligent flying object according to the target test data, specifically including: Displaying the target test data to the tester; In response to a first input operation by the tester, a test requirement of the intelligent flying object is determined.

5. The method according to claim 3, characterized in that The historical initial state includes several state parameters; Determining the test requirements of the intelligent flying object according to the target test data, specifically including: Determining a test scenario for the intelligent flying object; When the test scenario is of the first type, determining a specified state parameter in a historical initial state included in the target test data; When the specified state parameter is greater than a specified threshold, taking the historical initial state included in the target test data as a third initial state; According to the third initial state, a test requirement of the intelligent flying object is determined.

6. The method according to claim 5, characterized in that The third initial state includes several state parameters; According to the third initial state, determining the test requirements of the intelligent flying object specifically includes: Determine the priorities respectively corresponding to the state parameters included in the third initial state; According to each priority level, determining a parameter to be adjusted from each state parameter included in the third initial state; According to the parameters to be adjusted, the test requirements of the intelligent flying object are determined.

7. The method according to claim 3, characterized in that Determining the test requirements of the intelligent flying object according to the target test data, specifically including: Determining a test scenario for the intelligent flying object; When the test scenario is of the second type, analyzing the historical initial state included in the target test data to determine an analysis result; According to the analysis result, the test requirements of the intelligent flying object are determined.

8. A flight test device for an intelligent flying object, characterized in that: include: A determination module is used to determine the test requirements of the intelligent flying body; An initial state generation module is used to input the test requirements into a pre-trained initial state generation model to determine a first initial state of the intelligent flying body; wherein the initial state generation model is a large language model; and the first initial state includes initial values ​​of several state parameters of the intelligent flying body; A test case generation module, used for determining a first test case of the intelligent flying object according to the first initial state; A flight test module is used to perform a flight test on the intelligent flying object according to the first test case.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images