Intelligent test adjustment method, electronic equipment, system and storage medium

Abstract

The invention provides an intelligent test adjustment method, an electronic device, a system and a storage medium, which are used in the test of an automated guided vehicle, and the method comprises the following steps: setting a test item and a test environment, and setting a chained test instruction according to the test item; performing quantification processing on the test instruction of the test content to form an expected behavior vector; executing the test instruction, and obtaining an actual behavior vector of the automated guided vehicle; calculating the matching degree between the expected behavior vector and the actual behavior vector; and when the matching degree is lower than a preset value, correcting based on a preset knowledge base. According to the technical scheme, the error correction function is achieved while performance testing is achieved. According to the scheme, automatic performance testing of the AGV is achieved, intelligent deviation correction is carried out, the running precision of the automated guided vehicle is greatly improved, and the testing effect and stability are improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent automation equipment, and in particular to intelligent testing and adjustment methods, electronic equipment, systems, and storage media. Background Art

[0002] Automated Guided Vehicle (AGV), also known as automatic guided transport vehicle or automated guided transport vehicle. AGV is an industrial vehicle that loads goods automatically or manually, automatically drives along a set route or pulls a cargo trolley to a designated location, and then automatically or manually loads and unloads goods. The continuous development of computer hardware technology, parallel and distributed processing technology, automatic control technology, sensor technology, and software development environment has provided the necessary technical foundation for the research and application of AGV. The development of artificial intelligence technologies such as understanding and search, task and path planning, fuzzy and neural network control technology has enabled AGV to develop in the direction of intelligence and autonomy. The research and development of AGV integrates artificial intelligence, information processing, and image processing, involving multiple disciplines such as computers, automatic control, information communication, mechanical design, and electronic technology, and has become one of the hot spots in logistics automation research.

[0003] Despite years of research on AGVs, several key technologies still require advancement and breakthroughs to further improve AGV performance, reduce manufacturing costs, and minimize operating expenses. In this process, it is crucial to test the accuracy, stability, and other performance characteristics of automated guided vehicles to ensure their high-quality, efficient operation. Existing testing often relies on manual setup, performing each test individually. When problems are discovered, there is no automated troubleshooting, and testing often relies on the tester's judgment and experience. This results in low efficiency, poor test results, and poor stability. Summary of the Invention

[0004] In order to help improve the problems of low efficiency, poor test results and poor stability, the present application provides an intelligent test adjustment method, electronic device, system and storage medium.

[0005] In a first aspect, the present application provides an intelligent test adjustment method for use in testing an automated guided vehicle, the method comprising:

[0006] Set up test items and test environment, and set up chained test instructions according to the test items;

[0007] Quantify the test instructions of the test content to form an expected behavior vector;

[0008] Execute test instructions to obtain the actual behavior vector of the automatic guided vehicle;

[0009] Calculate the matching degree between the expected behavior vector and the actual behavior vector;

[0010] When the matching degree is lower than the preset value, correction is performed based on the preset knowledge base.

[0011] In a second aspect, the present application provides an electronic device, which adopts the following technical solution:

[0012] An electronic device, comprising:

[0013] at least one processor;

[0014] Memory;

[0015] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above intelligent test adjustment method.

[0016] In a third aspect, the present application provides an intelligent testing system, which includes: an automated guided vehicle test site, testing hardware, and electronic equipment, wherein the electronic equipment is used to execute the intelligent testing adjustment method described above.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0018] A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute any one of the intelligent test adjustment methods provided in the first aspect.

[0019] In summary, the technical solution of this application is used to perform a certain type of performance test of an automated guided vehicle. The test indicators of the test content are quantified in advance to form an expected behavior vector, and then the actual behavior vector of the vehicle body is obtained. The matching degree between the expected behavior vector and the actual behavior vector is calculated to achieve performance testing. It can also further adjust the test data based on the knowledge base to maximize the matching degree and realize the error correction function. This solution realizes the automated performance test of the AGV and performs intelligent deviation correction, which greatly improves the operating accuracy of the automated guided vehicle and enhances the test effect and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of an intelligent test adjustment method provided in an embodiment of the present application;

[0021] Figure 2 This is a schematic diagram of a two-layer network architecture of an intelligent test adjustment method provided in an embodiment of the present application;

[0022] Figure 3This is a partial flow chart of an intelligent test adjustment method provided by another embodiment of the present application;

[0023] Figure 4 This is a schematic diagram of the processing flow of the hardware performance factor portion of an intelligent test adjustment method provided by another embodiment of the present application;

[0024] Figure 5 This is a schematic diagram of a processing flow of the environmental factor portion of an intelligent test adjustment method provided by another embodiment of the present application;

[0025] Figure 6 This is a schematic diagram of the processing flow of the software configuration factor portion of an intelligent test adjustment method provided by another embodiment of the present application;

[0026] Figure 7 This is a schematic diagram of the module principle of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-7 It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0028] The embodiments of the present application provide an intelligent test adjustment method for use in an automated guided vehicle test system.

[0029] This embodiment uses the test system of an automated guided vehicle as an application example to specifically illustrate the above method. In actual implementation, the above method can also be used to test other automated equipment, and this embodiment does not limit this.

[0030] Specific reference Figure 1 As shown, the present invention proposes an intelligent test adjustment method, the method comprising:

[0031] S10: Set the test items and test environment, and set chained test instructions according to the test items;

[0032] S20: quantizing the test instructions of the test content to form an expected behavior vector;

[0033] S30: Execute the test instruction to obtain the actual behavior vector of the automatic guided vehicle;

[0034] S40: Calculating the matching degree between the expected behavior vector and the actual behavior vector;

[0035] S50: When the matching degree is lower than a preset value, correction is performed based on a preset knowledge base.

[0036] The technical solution of this application is used to perform performance testing of automated guided vehicles (AGVs). This performance test is achieved by calculating the degree of match between the expected behavior vector and the actual behavior vector. The solution can further adjust the test data based on the knowledge base to maximize the match and implement error correction. This solution implements automated performance testing of AGVs and intelligently corrects errors, significantly improving the operating accuracy of the AGV and enhancing both test results and stability.

[0037] In an embodiment of the present invention, the method is implemented through a two-layer comparison architecture. The first layer of the two-layer comparison architecture uses a two-layer network to compare the actual behavior vector of the test item with the expected behavior vector. When the matching degree is lower than a preset value, the second layer of the two-layer comparison architecture uses a knowledge base composed of three two-layer networks to compare, search for problem-solution pairings, and repair the anomaly.

[0038] This solution utilizes a two-layer network and two-tier comparison architecture. The first tier compares the current behavior vector of the test item with the expected behavior vector, implemented through a two-layer network. If the current behavior vector matches the expected behavior vector poorly, the triggering element of the behavior vector with the poor match is located. A second tier comparison is then performed using a knowledge base comprised of three two-layer networks. The knowledge base searches for problem-solution pairings and resolves the cause of the anomaly.

[0039] Refer to the attached Figure 2 To the attached Figure 6 As shown, on this basis, further, the first layer and the second layer of the two-layer comparison architecture are both designed in vector format, and each element thereof is an element of a vector structure.

[0040] Among them, each element x_i in the first layer of the two-layer comparison architecture has a connection weight w_ij with each element y_j in the second layer;

[0041] Assume that the initial value of the connection weight w_ij is 1, and the connection weight w_ij is updated by the following formula: w_ij new =β*(I∧w_ij old )+(1-β)*w_ij old ;

[0042] Among them, ij old is the connection weight before updating, w_ij new is the updated connection weight, I is the actual behavior vector, and β is a parameter ranging from 0 to 1;

[0043] The following formula is used to calculate whether the ratio of the similarity between the current actual behavior vector I and the connection weight w_ij relative to the current behavior vector is greater than or equal to the threshold ρ: |I∧w j |>ρ×|I|; where ρ is a parameter ranging from 0 to 1:

[0044] If it is greater than or equal to the threshold ρ, the updated connection weight w_ij is returned; if it is less than the threshold ρ, the behavioral structure indicator element that triggers the mismatch is located.

[0045] It is understandable that the matching degree between the current behavior vector of the test item and the expected behavior vector is calculated first. If the matching degree is lower than the threshold ρ, |I∧w j |≤ρ×|I|, the network is modified based on the knowledge base.

[0046] Refer to the attached Figure 2 As shown, the first layer of the architecture is designed in vector format, where each element represents a current behavior vector structure element, and I{I_1, I_1···I_n} represents a current behavior vector;

[0047] The second layer of the architecture is designed in vector format, where each element encodes a desired behavior vector, and T = {T_1(I)···T_M(I)} represents the set of desired behavior vectors;

[0048] Each element of the first layer is connected to each element of the second layer by a connection w_ij. The current behavior vector I encodes the corresponding expected behavior vector T_j(I) through the connection weight vector w_j.

[0049] Before encoding, each current behavior vector is compared with the existing expected behavior vector. If the matching degree is high, the expected behavior vector corresponding to the existing current behavior vector is called: T J (I)=max j T j (I);

[0050] If the matching degree is low, then a new expected behavior vector corresponding to the current behavior vector is established:

[0051] T j (I)=|I∧w j | / (a+|w j |).

[0052] It is understandable that since the input data of the network's first run is the expected behavior vector of each test item, the expected behavior vector of each test item is encoded in the network by updating the connection weight w_j vector. When the current behavior vector I matches the existing expected behavior vector sufficiently, T J (I)=max j T j (I); where T j (I)=|I∧w j | / (α+|w j |), represents the expected behavior vector corresponding to the current behavior vector.

[0053] If the current behavior vector I matches all expected behavior vectors poorly, a new element T is created. j (I)=|I∧w j | / (α+|w j |).

[0054] In this embodiment of the present invention, the knowledge base includes three dual-layer networks that adapt to hardware factors, software configuration factors, and environmental factors respectively; the behavioral structure indicator elements include hardware factors, software configuration factors, and environmental factors. Of course, it can also include other factors and corresponding networks, which are not limited to the description in this embodiment.

[0055] On this basis, further, the execution steps of the two-layer network included in the second-layer comparison of the two-layer comparison architecture include:

[0056] Update the connection weights;

[0057] The similarity between actual behavior and connection weight is calculated in each cycle;

[0058] If the similarity meets the standard, the existing element with the maximum value is selected; if the similarity does not meet the standard, a new element is created;

[0059] Perform automatic software repair or notify manual repair.

[0060] It should be noted that the above manual repair refers to the pairing of the output problem solutions of two double-layer networks in the knowledge base. Figures 3 to 6 When the knowledge base's [Hardware Performance] two-layer network is called, the output problem solution requires manual inspection of the hardware, parameter modification, and retesting to obtain a new current behavior vector. Similarly, when the knowledge base's [Environmental Factors] two-layer network is called, the output problem solution requires manual inspection of the environmental factors and retesting to obtain a new current behavior vector.

[0061] In an embodiment of the present invention:

[0062] The data of the knowledge base network is the problem solution result vector, and its structure includes:

[0063] Hardware performance, I^hdw = {index element, hardware device, hardware parameter};

[0064] Environmental factors, I^env={indicator element, environmental factor, change measure};

[0065] and software configuration, I^sfw={index element, software algorithm, software parameter};

[0066] Among them, the indicator elements are problems, hardware equipment, hardware parameters, environmental factors, change measures, software algorithms and software parameters are solutions to the problems;

[0067] When the actual behavior vector matches the expected behavior vector poorly and triggers mismatch element location, the knowledge base network traverses the input of the following data until the matching degree meets the requirements:

[0068] Hardware performance, I^hdw = {index element, non-measured device, non-measured parameter};

[0069] Environmental factors, I^env = {indicator element, non-measured environmental factor, non-measured parameter};

[0070] Software configuration, I^sfw = {index element, non-measured algorithm, non-measured parameter};

[0071] The output of the knowledge base network is a problem-solution structure vector.

[0072] It is understandable that the knowledge base of this solution is composed of three double-layer networks, representing the three major reasons why the expected behavior vector of each test item does not match the current behavior vector, namely [hardware performance], [software configuration], and [environmental factors]. Now let's take three cases as examples to illustrate the calculation process of the network. Please see the attached Figures 3 to 6 .

[0073] Example 1, speed mismatch [hardware performance]: Assume that the expected behavior vector obtained based on the test item analysis is

[0074] {Action type: forward (or driving)

[0075] Target value: Specified speed (e.g. 1.0m / s)

[0076] Unit: m / s (meters per second)

[0077] Tolerance: ±0.1m / s

[0078] Indicator element: actual speed vs expected speed},

[0079] When comparing the expected behavior vector with the current behavior vector, the matching degree is lower than the threshold ρ. The mismatch indicator element is located as the actual speed does not meet the expected speed. Therefore, the knowledge base's [Hardware Performance] two-layer network is called to perform the second-layer comparison of the solution.

[0080] When the first expected behavior vector does not match the current behavior vector, the knowledge base's [Hardware Performance] two-layer network input data is

[0081] I^hdw=[speed mismatch, any device, any parameter],

[0082] If the second-level comparison conditions are met, the maximum value T^hdw_J is automatically selected; if the second-level comparison conditions are not met, a new element T_j(I^hdw) is created.

[0083] When the second expected behavior vector does not match the current behavior vector or continues to not match, the knowledge base's [Hardware Performance] two-layer network input data is

[0084] I^hdw=[speed mismatch, non-selected hardware, any parameters],

[0085] Based on the second-level comparison conditions, call existing problem solutions to pair or create new elements.

[0086] The knowledge base's [Hardware Performance] dual-layer network output problem-solution pairing example can be

[0087] T_J(I^hdw)=[speed mismatch, check motor, check motor power],

[0088] T_J(I^hdw)=[speed mismatch, check battery, check battery level],

[0089] Or other hardware-related problem solutions.

[0090] The output of the problem solution for [Hardware Performance] requires manual intervention, that is, notifying the tester to check the specified parameters of the specified hardware.

[0091] Check the hardware, modify the parameters, and retest to obtain a new current behavior vector. Then, perform a first comparison with the expected behavior vector of the test item through the network's two-layer comparison architecture. If the match continues to be low, perform a second comparison through the three two-layer networks of the knowledge base to search and determine the problem-solution pairing that meets the expected behavior vector.

[0092] In Example 2, the positioning accuracy error [Software Configuration]: Assume that the expected behavior vector obtained based on the test item analysis is

[0093] {Action type: Positioning (using sensors for positioning)

[0094] Target value: precisely positioned at a certain coordinate point (such as point A)

[0095] Unit: meter (m)

[0096] Tolerance: ±5mm

[0097] Indicator element: actual coordinates vs target coordinates},

[0098] When comparing the expected behavior vector with the current behavior vector, the matching degree is lower than the threshold ρ. The indicator element of the positioning mismatch is that the actual coordinates do not match the target coordinates. Therefore, the knowledge base's [Software Configuration] two-layer network is called to perform the second-layer comparison of the solution.

[0099] When the first expected behavior vector does not match the current behavior vector, the knowledge base's [Software Configuration] two-layer network input data is:

[0100] I^sfw=[positioning accuracy error, any algorithm, any parameters],

[0101] If the second-level comparison conditions are met, the maximum value T^sfw_J is automatically selected; if the second-level comparison conditions are not met, a new element T_j(I^sfw) is created.

[0102] When the second expected behavior vector does not match the current behavior vector or continues to do so, the knowledge base's [Software Configuration] two-layer network input data is:

[0103] I^sfw=[positioning accuracy error, non-selected algorithm, any parameters],

[0104] Based on the second-level comparison conditions, call existing problem solutions to pair or create new elements.

[0105] The knowledge base's [software configuration] dual-layer network output problem-solution pairing example can be

[0106] T_J(I^sfw)=[positioning accuracy error, check SLAM algorithm, check configuration parameters],

[0107] T_J(I^sfw)=[positioning accuracy error, check sensor fusion algorithm, check fusion parameters],

[0108] Or other software-related problem solutions.

[0109] The problem solution output of [Software Configuration] does not require human intervention and can be automatically repaired by automatically modifying parameters.

[0110] Check the software, modify the configuration parameters, and retest to obtain a new current behavior vector. Then, perform a first comparison with the expected behavior vector of the test item through the network's two-layer comparison architecture. If the match continues to be low, perform a second comparison through the three two-layer networks of the knowledge base to search and determine the problem-solution pairing that meets the expected behavior vector.

[0111] In Example 3, ambient light affects sensor accuracy [environmental factors]: Assume that the expected behavior vector obtained based on the test item analysis is:

[0112] {Action type: obstacle avoidance

[0113] Target value: Avoid obstacles

[0114] Unit: meter (m)

[0115] Tolerance: ±10mm

[0116] Index elements: actual obstacle avoidance distance vs expected obstacle avoidance distance},

[0117] When comparing the expected behavior vector with the current behavior vector, the matching degree is lower than the threshold ρ. The indicator element of the positioning mismatch is that the actual obstacle avoidance distance does not meet the expected obstacle avoidance distance. Therefore, the knowledge base's [Environmental Factors] two-layer network is called to perform the second-layer comparison of the solutions.

[0118] When the first expected behavior vector does not match the current behavior vector, the input data of the knowledge base's [environmental factors] two-layer network is:

[0119] I^env=[ambient light affects sensor accuracy, any environmental factors, any parameters],

[0120] If the second-level comparison conditions are met, the maximum value T^env_J is automatically selected; if the second-level comparison conditions are not met, a new element T_j(I^env) is created.

[0121] When the second expected behavior vector does not match the current behavior vector or continues to do so, the input data of the knowledge base's [environmental factors] two-layer network is:

[0122] I^env=[Ambient light affects sensor accuracy, non-selected environmental factors, any parameters],

[0123] Based on the second-level comparison conditions, call existing problem solutions to pair or create new elements.

[0124] The knowledge base's environmental factors: Two-layer network output problem-solution pairing examples can be

[0125] T_J(I^env)=[Ambient light affects sensor accuracy, check ambient light, check the impact on LiDAR],

[0126] T_J(I^env)=[Ambient light affects sensor accuracy, check ambient light, check the impact on the camera],

[0127] Or other environmental factors related problem solution pairing.

[0128] The output of the problem solution for [Environmental Factors] requires manual intervention, that is, notifying the tester to check the specified environmental factors and their impact on the corresponding hardware.

[0129] After checking the environmental factors, retest to obtain a new current behavior vector, and then perform the first comparison with the expected behavior vector of the test item through the network's two-layer comparison architecture. If the matching degree continues to be low, the second comparison, search, and decision on the problem-solution pairing that meets the expected behavior vector are performed again through the three two-layer networks of the knowledge base.

[0130] It should be noted that, because the input data of the network's first run is the expected behavior vector of each test item, the expected behavior vector of each test item is encoded in the network by updating the connection weight w_j vector. When the current behavior vector I matches the existing expected behavior vector sufficiently well,

[0131] T J (I)=max j T j (I)

[0132] Where T j (I)=|I∧w j | / (α+|w j |)

[0133] Represents the expected behavior vector corresponding to the current behavior vector.

[0134] If the current behavior vector I has a low matching degree with all expected behavior vectors, a new element is created:

[0135] T j (I)=|I∧w j | / (α+|w j |).

[0136] It's understandable that if the first-level comparison shows a low match between the current behavior vector and the expected behavior vector, the cause can be determined based on the indicator elements of the behavior structure: the indicator elements do not meet the expected values. A high match indicates that the indicator elements meet the expected values. The second-level comparison then searches for a matching problem solution that matches the expected behavior vector. Therefore, the first-level comparison in the solution identifies the behavior structure factors, while the second-level comparison determines matching solutions based on these factors, and then performs the matching comparison again using the aforementioned method.

[0137] The present application also provides an electronic device, such as Figure 7 As shown, Figure 7 The electronic device 700 shown includes a processor 701 and a memory 703. The processor 701 and the memory 703 are connected, for example, via a bus 702. Optionally, the electronic device 700 may further include a transceiver 704. It should be noted that in actual applications, the number of transceivers 704 is not limited to one, and the structure of the electronic device 700 does not constitute a limitation on the embodiments of the present application.

[0138] Processor 701 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or other programmable logic devices, transistor logic devices, hardware components, or any other combination. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 701 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0139] The bus 702 may include a path for transmitting information between the above components. The bus 702 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 702 may be divided into an address bus, a data bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0140] The memory 703 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0141] The memory 703 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 701. The processor 701 is used to execute the application code stored in the memory 703 to implement the content shown in the above method embodiment.

[0142] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), and PADs (tablet computers), and fixed terminals such as digital TVs and desktop computers, and may also be servers. Figure 7 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0143] The present application also provides an intelligent testing system, which includes: an automated guided vehicle test site, testing hardware, and electronic equipment, wherein the electronic equipment is used to execute the intelligent testing adjustment method described above.

[0144] The test items may include the following:

[0145]

[0146]

[0147] Among them, when calculating the current behavior vector, it is necessary to extract features from the collected sensor data. The features are extracted according to the expected behavior measurement indicators to evaluate whether the AGV achieves the expected performance.

[0148] First, the feature recognition of the current behavior is mainly based on the following sensor data:

[0149] sensor Data Type unit effect Odometer / UWB Position (X, Y, θ) m,rad Calculate path and deviation wheel speedometer speed m / s Calculation running status IMU acceleration <![CDATA[m / s 2 ]]> Recognize acceleration and deceleration actions IMU Angular velocity rad / s Identify turning and rotation movements Camera Visual Data Pixel Identify trajectories and obstacles LiDAR Distance, obstacles m Calculate obstacle avoidance

[0150] The core features extracted include

[0151] Position features: current position (X, Y, θ), motion trajectory (path deviation);

[0152] Velocity characteristics: linear velocity v (m / s), angular velocity ω (rad / s);

[0153] Acceleration characteristics: Linear acceleration a(m / s 2 ), angular acceleration α(rad / s 2 );

[0154] Time features: task execution time T(s), timestamps of key actions;

[0155] Error characteristics: deviation ΔX, ΔY (m), angular error Δθ (rad);

[0156] Environmental characteristics (optional): road smoothness, obstacle distribution;

[0157] The following features are then converted into quantifiable measurements to calculate the current behavior vector:

[0158]

[0159] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the intelligent test adjustment method provided in the above embodiment.

[0160] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps and they may be performed in other orders.

[0161] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An intelligent test adjustment method, characterized in that: In testing an automated guided vehicle, the method includes: Set up test items and test environment, and set up chained test instructions according to the test items; Quantify the test instructions of the test content to form an expected behavior vector; Execute test instructions to obtain the actual behavior vector of the automatic guided vehicle; Calculate the matching degree between the expected behavior vector and the actual behavior vector; When the matching degree is lower than the preset value, correction is performed based on the preset knowledge base.

2. The intelligent testing and adjustment method according to claim 1, characterized in that: The system includes a two-layer comparison architecture, the first layer of which uses a two-layer network to compare the actual behavior vector of the test item with the expected behavior vector. When the matching degree is lower than a preset value, the second layer of the two-layer comparison architecture uses a knowledge base composed of three two-layer networks to compare, search for problem-solution pairings, and repair the anomaly.

3. The intelligent test adjustment method according to claim 2, characterized in that: The first layer and the second layer of the two-layer comparison architecture are both designed in vector format, and each element thereof is an element of a vector structure.

4. The intelligent test adjustment method according to claim 3, characterized in that: Each element x_i in the first layer of the two-layer contrast architecture has a connection weight w_ij with each element y_j in the second layer; Assume that the initial value of the connection weight w_ij is 1, and the connection weight w_ij is updated by the following formula: w_ij new =β*(I∧w_ij old )+(1-β)*w_ij old ; Among them, ij old is the connection weight before updating, w_ij new is the updated connection weight, I is the actual behavior vector, and β is a parameter ranging from 0 to 1; The following formula is used to calculate whether the ratio of the similarity between the current actual behavior vector I and the connection weight w_ij relative to the current behavior vector is greater than or equal to the threshold ρ: |I∧w j |>ρ×|I|; where ρ is a parameter ranging from 0 to 1: If it is greater than or equal to the threshold ρ, the updated connection weight w_ij is returned; if it is less than the threshold ρ, the behavioral structure indicator element that triggers the mismatch is located.

5. The intelligent test adjustment method according to claim 4, characterized in that: The knowledge base includes three double-layer networks respectively adapted to hardware factors, software configuration factors and environmental factors; the behavior structure indicator elements include hardware factors, software configuration factors and environmental factors.

6. The intelligent test adjustment method according to claim 5, characterized in that: The steps performed by the second layer of the double-layer network of the double-layer comparison architecture include: Update the connection weights; The similarity between actual behavior and connection weight is calculated in each cycle; If the similarity meets the standard, the existing element with the maximum value is selected; if the similarity does not meet the standard, a new element is created; Perform automatic software repair or notify manual repair.

7. The intelligent test adjustment method according to claim 6, characterized in that: in: The data of the knowledge base network is the problem solution result vector, and its structure includes: Hardware performance, I^hdw = {index element, hardware device, hardware parameter}; Environmental factors, I^env={indicator element, environmental factor, change measure}; and software configuration, I^sfw={index element, software algorithm, software parameter}; Among them, the indicator elements are problems, hardware equipment, hardware parameters, environmental factors, change measures, software algorithms and software parameters are solutions to the problems; When the actual behavior vector matches the expected behavior vector poorly and triggers mismatch element location, the knowledge base network traverses the input of the following data until the matching degree meets the requirements: Hardware performance, I^hdw = {index element, non-measured device, non-measured parameter}; Environmental factors, I^env = {indicator element, non-measured environmental factor, non-measured parameter}; Software configuration, I^sfw = {index element, non-measured algorithm, non-measured parameter}; The output of the knowledge base network is a problem-solution structure vector.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the intelligent test adjustment method according to any one of claims 1 to 7.

9. An intelligent testing system, characterized in that: The intelligent testing system comprises: an automated guided vehicle test site, testing hardware, and electronic equipment, wherein the electronic equipment is used to execute the intelligent testing adjustment method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the intelligent test adjustment method according to any one of claims 1 to 7.

Images