Automated device processing method and apparatus, device, medium, and product

Abstract

The present disclosure relates to the technical field of computers, and provides an automated device processing method and apparatus, a device, a medium, and a product. The automated device processing method comprises: acquiring assembling information of an automated device and a target task; using a first AI model to generate a preliminary program code of the automated device on the basis of the assembling information and the target task; and acquiring a target program code on the basis of the preliminary program code, and configuring the target program code for the automated device. According to the present disclosure, automated programming can be implemented, and automatic adjustment can be implemented when needed.

Description

Processing methods, devices, equipment, media and products of automated equipment Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a processing method, apparatus, device, medium, and product for automated equipment. Background Technology

[0002] With the rapid development of fields such as industrial manufacturing, aerospace, scientific research, smart homes, smart IoT devices, smart wearable devices, and embodied intelligent robots, automated equipment such as artificial intelligence (AI) devices often integrates multiple types of hardware devices, which are interconnected and collaborate through various communication protocols and buses. Summary of the Invention

[0003] This disclosure provides a processing method, apparatus, device, medium, and product for automated equipment.

[0004] According to one aspect of this disclosure, a method for processing automated equipment is provided, comprising: acquiring assembly information and target task of the automated equipment; using a first AI model to generate preliminary program code for the automated equipment based on the assembly information and the target task; acquiring target program code based on the preliminary program code; and configuring the target program code to the automated equipment.

[0005] According to another aspect of this disclosure, a processing apparatus for an automated device is provided, comprising: an acquisition module for acquiring assembly information and a target task of the automated device; a generation module for generating preliminary program code for the automated device based on the assembly information and the target task using a first AI model; and a configuration module for acquiring target program code based on the preliminary program code and configuring the target program code to the automated device.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein the memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the method as described in any of the foregoing aspects.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to any of the preceding aspects.

[0008] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any of the preceding aspects.

[0009] This disclosure enables automated programming and allows for automatic adjustments as needed.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0012] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0013] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0014] Figure 3 is a schematic diagram of the overall system architecture used to implement the embodiments of this disclosure;

[0015] Figure 4 is a schematic diagram according to a third embodiment of the present disclosure;

[0016] Figure 5 is a flowchart illustrating the deployment phase according to an embodiment of this disclosure;

[0017] Figure 6 is a flowchart illustrating the exception handling stage provided according to an embodiment of the present disclosure;

[0018] Figure 7 is a schematic diagram according to the fourth embodiment of the present disclosure;

[0019] Figure 8 is a schematic diagram of an electronic device used to implement the processing method of the automated device according to the embodiments of the present disclosure. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] Currently, the relevant information (such as program code) of automated equipment usually needs to be programmed manually, which leads to certain problems in terms of efficiency and accuracy.

[0022] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure. This embodiment provides a processing method for an automated device, as shown in Figure 1, the method including:

[0023] 101. Obtain assembly information and target tasks for automated equipment.

[0024] 102. Using the first AI model, based on the assembly information and the target task, generate preliminary program code for the automated equipment.

[0025] 103. Obtain the target program code based on the preliminary program code, and configure the target program code to the automated equipment.

[0026] Specifically, this method can be executed by the cloud or automated devices.

[0027] Automated equipment can be AI equipment, i.e., equipment with AI generation capabilities; or it can be ordinary equipment, such as personal computers (PCs), tablets, ordinary servers, or small servers (such as NAS).

[0028] Automated equipment typically consists of multiple hardware modules (or simply modules). These hardware modules are assembleable and can be programmed according to the user's own needs to achieve different functions.

[0029] Users can assemble modules locally and obtain the assembly results.

[0030] Users can assemble the model according to the existing instructions or by using a custom method to obtain the assembled model.

[0031] Hardware modules in automated equipment typically include a mainboard module and multiple functional modules. After the functional modules are installed on the mainboard module, the mainboard module can obtain assembly information based on the assembly results using pre-configured programs or models.

[0032] Assembly information may include: individual information of each module, and / or mutual information between different modules. Individual information includes, for example, a unique ID, type information, absolute pose (position and attitude) information, physical parameters (such as motor speed, sensor parameters), etc.; mutual information includes, for example, relative pose (position and attitude) information.

[0033] The target task is used to indicate the functional requirements of the automated equipment. For example, it may include the final functions that the assembled automated equipment will achieve, the custom physical parameters of each module, etc.

[0034] The target task can be user-defined. For example, users can input a custom target task through a preset application (APP).

[0035] The aforementioned app refers to an application designed to work with automated equipment. This app can be installed on a user terminal (such as a PC, mobile phone, or tablet). The user terminal and the automated equipment can communicate via Bluetooth, Wi-Fi, or other methods. Alternatively, if the automated equipment itself provides an interactive interface, the aforementioned app can also be deployed within the automated equipment.

[0036] The target task can also be generated automatically in the cloud or by the automated equipment itself, based on the assembly information.

[0037] For example, if a user assembles a vehicle with four wheels, the user may provide a custom target task, such as "This is a vehicle that can move freely and automatically avoid obstacles"; or, the user may leave it blank, that is, not inputting a target task. In this case, assuming that a heat source sensor and a water gun are also installed, the cloud or automated equipment itself can directly and automatically generate a target task based on this assembly information, such as "This is a fire truck".

[0038] The AI ​​model mentioned above can be a specially trained model, or it can be a Large Language Model (LLM). LLM is a hot topic in the field of AI in recent years. It is a pre-trained language model that is obtained by pre-training on massive amounts of data.

[0039] Based on the following description, AI models can be used for code generation and reconfiguration information generation.

[0040] The first AI model is used to generate code, and the second AI model is used to generate reconfiguration information.

[0041] The first AI model and the second AI model can be the same or different. Specifically, generative, supervised, unsupervised, or hybrid models can be selected according to the actual situation.

[0042] Taking an AI model as an example, the first LLM can be used to generate preliminary program code, and the second LLM can be used to generate reconfiguration information. The first LLM and the second LLM can be the same or different.

[0043] Preliminary program code refers to the code generated by the first AI model.

[0044] Target program code refers to the code that is ultimately configured for automated equipment.

[0045] The first AI model is used to generate preliminary program code based on assembly information and target task, and the target program code is obtained based on the initial program code.

[0046] Specifically, the preliminary program code can be used as the target program code. Or,

[0047] The initial program code is tested, and the initial program code that passes the test is used as the target program code. If the test fails, the first AI model is used to regenerate the code and retest it until the code generated by the first AI model passes the test. The code that passes the test is then used as the target program code.

[0048] Furthermore, the aforementioned preliminary program code can be generated during the initialization phase or after changes in the assembly information of the automated equipment. For example, during the initialization phase, initial control code is generated based on the original assembly information and target task of the automated equipment. After adding new hardware modules to the automated equipment or removing existing hardware modules, the preliminary program code can be regenerated based on the new assembly information.

[0049] Furthermore, the initial program code can be tested based on the simulation model.

[0050] Specifically, a simulation system can be pre-deployed to generate a simulation model based on the assembly information.

[0051] For example, the simulation system generates a simulation model based on the individual information of each model and the mutual information between different modules. The simulation model can be a 3D model corresponding to the real model assembled by the user, or it can be a simulation physics engine or a digital simulation (e.g., a simulation of tension, pressure, etc.).

[0052] After generating the simulation model, preliminary program code can be written into the simulation model. The simulation model is then run based on the initial program code. If the simulation model's running results meet the preset requirements, it indicates that the preliminary program code has passed the test and can be used as the target program code.

[0053] After obtaining the target program code, it is configured for use by the automated equipment. The automated equipment then runs based on this target program code, implementing the functions defined by the target task.

[0054] In this embodiment, a first AI model is used to generate preliminary program code based on assembly information and target tasks. The target program code is then obtained based on the preliminary program code and configured for the automated equipment, which can realize automated programming of the automated equipment and solve the problems of manual programming by users.

[0055] Taking automated programming as an example, this disclosure can not only realize automated programming, but also automatically adjust the program code of automated equipment.

[0056] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure. This embodiment provides a processing method for an automated device, as shown in Figure 2, the method including:

[0057] 201. Obtain assembly information and target tasks for automated equipment.

[0058] 202. Using the first AI model, based on the assembly information and the target task, generate preliminary program code for the automated equipment.

[0059] 203. Obtain the target program code based on the preliminary program code, and configure the target program code to the automated equipment.

[0060] 204. Monitor the status information of the automated equipment during operation, wherein the automated equipment runs based on the target program code and is decoupled from the computing power support of the first AI model during operation.

[0061] 205. When it is determined that the automated equipment has malfunctioned based on the status information, a second AI model is used to generate reconfiguration information for the automated equipment, so that the automated equipment can perform corresponding operations based on the reconfiguration information.

[0062] For details regarding 201 to 203, please refer to the relevant description in the previous embodiment.

[0063] After the target program code is configured for the automated equipment, the automated equipment can run based on the target program code, and during the operation, it can operate independently of the computing power support of the first AI model.

[0064] In other words, after the target program code is configured to the automated equipment, it runs automatically on the equipment, no longer relying on the AI ​​model. This reduces computational power consumption and latency compared to methods that continuously depend on AI models.

[0065] In addition, the status information of the automated equipment can be monitored during operation.

[0066] This status information can be used to determine whether an automated device has malfunctioned.

[0067] After determining that an automated device has malfunctioned, reconfiguration information is generated based on the second AI model.

[0068] Reconfiguration information may include one or more of the following: regenerated target program code, operating parameters of automated equipment, collaboration strategies between hardware modules within automated equipment, and switching of hardware modules.

[0069] After obtaining the reconfiguration information, the reconfiguration information is sent to the automation equipment. The automation equipment then performs corresponding operations based on the reconfiguration information, such as running based on the new target program code or operating parameters.

[0070] In this embodiment, by generating reconfiguration information when the automated equipment malfunctions, the automated equipment can be adaptively adjusted; by using an AI model to generate target program code and reconfiguration information, the processing efficiency and accuracy can be improved compared to manual processing; by operating without the computing power support of the AI ​​model, the AI ​​model can be invoked on demand without constantly maintaining a connection with the AI ​​model, thus reducing the cost and energy consumption of continuous operation of the AI ​​model.

[0071] Figure 3 is a schematic diagram of the overall system architecture used to implement the embodiments of this disclosure.

[0072] As shown in Figure 3, it mainly includes: automated equipment 301.

[0073] The automated equipment 301 is composed of hardware modules. Users can assemble the various hardware modules to obtain a three-dimensional real model after assembly.

[0074] The system includes a motherboard module and assemblable functional modules, which can be one or more, usually multiple, and these functional modules can be assembled onto the motherboard module.

[0075] The motherboard module can be pre-installed with an AI chip, which is used to obtain assembly information.

[0076] Optionally, a lightweight model can also be deployed within the AI ​​chip to perform some preliminary checks, such as determining whether the installation of the real model is correct based on the assembly information. If it is correct, it indicates that the assembly information has passed the check of the AI ​​chip.

[0077] Taking a user-defined target task as an example, as shown in Figure 3, the system may also include:

[0078] APP 302 is matched with the automation equipment 301. The APP can be deployed on the user terminal or within the automation equipment.

[0079] APP 302 is used to display an interactive interface to the user, where the user inputs a custom target task.

[0080] The above example uses a user-defined target task input via an app. Alternatively, the target task can be automatically generated based on assembly information from the cloud or automated equipment.

[0081] The generation and adjustment of code can be performed by automated equipment or by the cloud.

[0082] Taking execution from the cloud as an example, as shown in Figure 3, the system may also include: cloud 303.

[0083] In this architecture, the automated equipment sends the assembly information it has checked to the cloud. The cloud then calls upon the first AI model, which generates preliminary program code based on the checked assembly information and the target task. At this point, the motherboard module also has a pre-installed communication chip that transmits the assembly information to the cloud.

[0084] In addition, when executing on the automated equipment side, the automated equipment side (the automated equipment itself or the local computing module connected to the automated equipment) can generate preliminary program code based on the assembly information and the target task, and obtain the target program code based on the preliminary program code.

[0085] Whether executed in the cloud or on an automated device, the target program code can be preliminary program code that has passed testing.

[0086] Taking cloud-based execution as an example, a simulation system and a first AI model can be pre-deployed in the cloud. The simulation system generates a simulation model based on the assembly information, and the first AI model generates preliminary program code based on the assembly information and the target task. Then, the preliminary program code is written into the simulation model to trigger its execution. If the execution result meets the user-defined target task requirements, it indicates that the preliminary program code has passed the test, and the tested preliminary program code is used as the target program code.

[0087] After obtaining the target program code, the cloud can send it to the motherboard module; alternatively, the automated equipment itself can send the target program code to its own motherboard module. The motherboard module then runs the user-assembled real model based on the target program code, achieving automated programming of the automated equipment. Furthermore, the cloud and / or the motherboard module can save the target program code for future use.

[0088] The automated equipment runs based on the target program code, and during operation, it operates independently of the computing power support of the first AI model. Subsequently, based on the status information during operation, it can be determined whether the automated equipment has malfunctioned. If an malfunction occurs, a second AI model is used to generate reconfiguration information, and the automated equipment executes corresponding operations based on this reconfiguration information.

[0089] The reconfiguration information can be generated in the cloud using a second AI model, or it can be generated on the automated equipment side using a second AI model.

[0090] In addition, based on the overall system architecture described above, this disclosure also provides the following embodiments.

[0091] Figure 4 is a schematic diagram according to a third embodiment of the present disclosure. This embodiment provides a programming method for a modular hardware system. As shown in Figure 4, the method includes:

[0092] 401. Automated equipment acquires its own assembly information.

[0093] 402. The automated equipment uses its built-in AI chip to check the above assembly information.

[0094] For example, an AI chip is pre-installed on the motherboard module of an automated device to obtain assembly information. In addition, the AI ​​chip can also be pre-set with inspection rules to check the assembly information based on these rules.

[0095] 403. Obtain the target task.

[0096] For example, the target task can be obtained through an app, input by the user. Alternatively, the target task can be automatically generated by the cloud or automated equipment based on assembly information.

[0097] 404. Using the first AI model, based on the assembly information and target tasks obtained through inspection, generate preliminary program code for the automated equipment.

[0098] This step can be performed by the cloud or by automated equipment.

[0099] When executed in the cloud, the automated equipment sends the assembly information it has checked to the cloud. For example, if a user-defined target task is input through an APP, the APP sends the target task to the cloud. The cloud then calls the first AI model to generate preliminary program code based on the assembly information and target task mentioned above.

[0100] When the automated equipment is executing, the automated equipment itself or the local computing module connected to the automated equipment obtains the assembly information checked by the automated equipment itself, as well as the target task sent by the APP. The automated equipment calls the first AI model and generates preliminary program code based on the above assembly information and target task.

[0101] 405. Test the preliminary program code, use the preliminary program code that passes the test as the target program code, and configure the target program code to the automation equipment.

[0102] This step can be performed by the cloud or by automated equipment.

[0103] When executed in the cloud, a simulation system can be pre-deployed in the cloud. This system generates a simulation model based on the assembly information described above. After the cloud uses the first AI model to generate preliminary program code, it writes the preliminary program code into the simulation model and initially runs the simulation model based on the preliminary program code. If the running result meets the preset requirements, such as the requirements of the user-defined target task, it indicates that the preliminary program code has passed the test and is used as the target program code. Conversely, if the test fails, the cloud can send error information to the first AI model. After receiving the error information, the first AI model regenerates the preliminary program code based on the assembly information and target task described above. Then, the cloud sends the target program code to the automated equipment.

[0104] During execution on the automated equipment side, the automated equipment itself or its connected local computing module pre-deploys a simulation system, similar to a cloud-based processing flow. The simulation system determines whether the initial program code passes a test. The passed initial program code is used as the target program code; if it fails, the first AI model is triggered to regenerate the initial program code. Afterward, the automated equipment obtains the target program code and configures it.

[0105] 406. The automated equipment runs based on the target program code, and during operation, it is decoupled from the computing power support of the first AI model.

[0106] The deployment phase process can be seen in Figure 5.

[0107] As shown in Figure 5, the process mainly includes: acquiring assembly information of automated equipment (collecting information of connected equipment); generating preliminary program code using the first AI model (AI-generated code in stage 1); testing the preliminary program code (e.g., compiling first and then testing); using the preliminary program code that passes the test as the target program code; and deploying the target program code into the automated equipment (compiling, testing, and deploying code); and the automated equipment performing corresponding operations based on the deployed target program code (entering the normal operating mode).

[0108] 407. Monitor the status information of the automated equipment during operation, and determine whether the automated equipment has malfunctioned based on the status information. If so, proceed to 408; otherwise, repeat 407 and its subsequent steps.

[0109] Status information refers to relevant information during the operation of automated equipment, which may include one or more of the following: physical parameters, electrical parameters, performance parameters, and statistical data.

[0110] Physical parameters include one or more of the following: temperature, humidity, pressure, etc.; electrical parameters include one or more of the following: voltage, current, power, etc.; performance parameters include one or more of the following: speed, flow rate, accuracy, response time, etc.

[0111] Exceptions can include: known exceptions, or unknown exceptions.

[0112] The aforementioned abnormalities typically refer to abnormal equipment operation, such as a barometer not working; and / or may also include abnormal values ​​that do not meet expectations, such as a pressure of 1000 atmospheres detected at sea.

[0113] Anomalies can be determined through program parameters, database records, or arbitrary threshold setting mechanisms (such as sliding window, Bayesian update, etc.).

[0114] This step can be performed by the cloud or by the automated equipment itself (either the automated equipment itself or a local computing module connected to the automated equipment).

[0115] 408. Use the second AI model to generate reconfiguration information for the automated equipment.

[0116] The reconfiguration information may include: regenerated control code, and / or, operating parameters of the automated equipment.

[0117] In addition, reconfiguration information can be global or local.

[0118] For example, including but not limited to the following three methods:

[0119] Method 1: Aircraft (Global Reconfiguration)

[0120] During rocket launch, the first AI model generates control code based on the rocket's (automated equipment) engines, fuel tanks, sensors, and other devices, and deploys it to the flight control system. The first AI model does not require continuous involvement during operation. When an engine unit fails (an anomaly is detected by the anomaly detection module), the second AI model generates a global fuel allocation and thrust vector adjustment scheme to improve the mission completion rate of the spacecraft.

[0121] Option 2: Scientific research experimental platform (partial reconfiguration)

[0122] Before the experiment begins, the first AI model generates control code based on the list of experimental equipment (automated equipment). If some measuring instruments lose connection during the experiment, the second AI model generates a reconfiguration scheme specifically for the lost instruments, adjusting parameter mapping and calibration to ensure the experiment is completed as planned.

[0123] Method 3: Industrial robots (unit-level reconfiguration)

[0124] The first AI model generates control code based on the robot's (automated equipment's) hardware, such as joints and sensors. If a joint motor failure is detected during operation, the second AI model generates a compensation plan (such as reallocating power), and after implementation, the robot continues to complete the task.

[0125] In the above example, the preliminary program code obtained based on the first AI model is taken as an example. In actual implementation, it can also be the preliminary program code written manually by the user, or the code after the user adjusts the preliminary program code generated by the first AI model.

[0126] This step can be performed by the cloud or by the automated device itself. For example, the cloud can invoke a second AI model to generate the reconfiguration information for the automated device; or, the automated device itself or a local computing module connected to the automated device can invoke the second AI model to generate the reconfiguration information for the automated device.

[0127] 409. The automated equipment performs the corresponding operation based on the reconfiguration information.

[0128] If the reconfiguration information is generated in the cloud, the cloud will send the reconfiguration information to the automated device, and the automated device will perform the corresponding operation based on the reconfiguration information sent by the cloud. Alternatively, if the reconfiguration information is obtained by the automated device itself, the automated device will directly perform the corresponding operation based on the reconfiguration information it obtained. Alternatively, if the reconfiguration information is obtained from the local computing module, the local computing module will send the reconfiguration information to the automated device, and the automated device will perform the corresponding operation based on the reconfiguration information sent by the local computing module.

[0129] 410. Record the configuration information generated each time, and perform rollback operations when necessary.

[0130] The recorded configuration information may include: initial configuration information, such as the target program code mentioned above; and reconfiguration information generated after an exception occurs, such as one or more of the following: regenerated target program code, adjusted operating parameters of the automated equipment, adjusted collaboration strategy, and switch switching information.

[0131] In addition, the reconfiguration information corresponding to each exception can be recorded after each exception occurs.

[0132] The aforementioned recorded information can be stored in the cloud, in local files of automated devices, or in a database, and can include information such as timestamps and / or version numbers. Subsequently, rollback operations can be performed based on specified timestamps or version numbers, or based on custom rules.

[0133] 411. Process the results of the target task accordingly.

[0134] Once the automated equipment is running based on the control code and / or reconfiguration information, it will execute the target task and obtain the execution result of the target task.

[0135] The cloud or automated equipment can determine whether the target task meets the preset requirements based on the execution results (such as task completion rate, error threshold, etc.). If the requirements are met, the target task will be executed normally.

[0136] If the above execution result does not meet the preset requirements, the second AI model can be called again to regenerate the reconfiguration information, which means that 408 and its subsequent steps can be re-executed.

[0137] The process for the exception handling phase can be seen in Figure 6.

[0138] As shown in Figure 6, the process mainly includes detecting anomalies, including known and unknown anomalies; using the second AI model (AI processing module in startup phase 2) to generate global or local reconfiguration information; automated equipment performing corresponding operations based on the reconfiguration information (implementation plan); recording configuration information each time and rolling back when necessary (archiving and rolling back); and performing subsequent processing based on the execution results of the target task (monitoring and callback, and determining whether the target is met).

[0139] In this embodiment, the AI ​​model is only used when needed, eliminating the need for continuous invocation of the AI ​​model, which reduces energy consumption and computing costs. By invoking the AI ​​model for global or local reconfiguration when an anomaly occurs, the system's adaptability under unknown fault conditions can be improved. Code generation and reconfiguration through the AI ​​model support multiple communication buses and hardware types, allowing for flexible selection of various AI models and their threshold setting methods to adapt to different application scenarios. It supports single-machine or multi-machine collaborative work, has high scalability, and is suitable for various scenarios such as aircraft, scientific research experimental platforms, and industrial robots.

[0140] Figure 7 is a schematic diagram according to a fourth embodiment of the present disclosure, which provides a processing apparatus for an automated device. The apparatus 700 includes: an acquisition module 701, a generation module 702, and a configuration module 703.

[0141] The acquisition module 701 is used to acquire the assembly information and target task of the automated equipment; the generation module 702 is used to generate preliminary program code for the automated equipment based on the assembly information and the target task using a first AI model; the configuration module 703 is used to acquire target program code based on the preliminary program code and configure the target program code to the automated equipment.

[0142] In some embodiments, the generation module 702 is further configured to:

[0143] During the initialization phase, the first AI model generates the preliminary program code based on the initial assembly information and target task of the automated equipment; or...

[0144] After the assembly information of the automated equipment changes, the first AI model generates the preliminary program code based on the changed assembly information of the automated equipment.

[0145] In some embodiments, the configuration module 702 is further configured to:

[0146] The preliminary program code is used as the target program code; or...

[0147] The preliminary program code is tested, and the preliminary program code that passes the test is used as the target program code.

[0148] In some embodiments, the configuration module 702 is further configured to:

[0149] A simulation model is generated based on the assembly information;

[0150] The preliminary program code is written into the simulation model, and the simulation model is run based on the preliminary program code to obtain the running results;

[0151] If the running result meets the preset requirements, the preliminary program code will be used as the target program code.

[0152] In some embodiments, the device 700 further includes:

[0153] The regeneration module is used to send error information to the first AI model if it is determined that the preliminary program code has failed the test, so as to trigger the first AI model to regenerate the preliminary program code.

[0154] In some embodiments, the acquisition module 701 is further configured to:

[0155] The target task can be obtained from user input, or the target task can be generated based on the assembly information.

[0156] In some embodiments, the generation module 702 is further configured to:

[0157] The assembly information is checked using the AI ​​chip built into the automated equipment.

[0158] The first AI model is used to generate the preliminary program code based on the assembly information after inspection and the target task.

[0159] In some embodiments, the device 700 further includes:

[0160] The monitoring module is used to monitor the status information of the automated equipment during operation. The automated equipment runs based on the target program code and operates without the computing power support of the first AI model.

[0161] The reconfiguration module is used to generate reconfiguration information for the automated equipment using a second AI model when the status information determines that the automated equipment has malfunctioned, so that the automated equipment can perform corresponding operations based on the reconfiguration information.

[0162] In some embodiments, the reconfiguration information includes:

[0163] Global reconfiguration information, partial reconfiguration information, or unit-level reconfiguration information.

[0164] In some embodiments, the device 700 further includes:

[0165] The processing module is used to record the target program code and the reconfiguration information, so as to perform a rollback operation based on the recorded information; and / or, if the execution result of the automated device for the target task does not meet the preset requirements, the second AI model is used to reconfigure the automated device.

[0166] In some embodiments, the device 700 further includes:

[0167] A storage module is used to store the record information in at least one of the following: the cloud, a local file of the automated device, or a database.

[0168] In some embodiments, the first AI model and the second AI model may be the same or different.

[0169] It is understood that the same or similar content in different embodiments of this disclosure can be referred to each other.

[0170] It is understood that the terms "first" and "second" in the embodiments of this disclosure are only used for distinction and do not indicate the degree of importance or the order of events.

[0171] It is understandable that, unless otherwise specified, the order of steps in the process indicates that the temporal relationship between these steps is not limited.

[0172] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0173] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0174] Figure 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, lightweight terminal devices, and other suitable computers. Electronic device 800 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0175] As shown in Figure 8, the electronic device 800 includes a processor 801 and a memory 802, which can be connected via a bus. The processor 801 can perform various appropriate actions and processes according to the computer program stored in the memory 802.

[0176] Processor 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 801 performs the various methods and processes described above, such as the processing methods of an automated device. For example, in some embodiments, the processing methods of an automated device may be implemented as a computer software program tangibly contained in a machine-readable medium, such as memory 802. In some embodiments, part or all of the computer program may be loaded and / or installed onto the automated device 800 via memory 802. When the computer program is executed by processor 801, one or more steps of the processing methods of the automated device described above may be performed. Alternatively, in other embodiments, processor 801 may be configured to perform the processing methods of an automated device by any other suitable means (e.g., by means of firmware).

[0177] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0179] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0180] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0181] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), Bluetooth, Near Field Communication (NFC), and the Internet.

[0182] Computer systems can include clients and servers. Clients and servers interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. A server can also be a server for a distributed system, a server incorporating blockchain technology, or a locally deployed server.

[0183] A computer system can also be a local device, meaning it can be executed locally through automated equipment.

[0184] It should be understood that the various forms of processes shown above can be used to reorder, add, or cancel steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0185] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A processing method of an automated device, characterized by, include: Obtain assembly information and target tasks for automated equipment; Using a first AI model, preliminary program code for the automated equipment is generated based on the assembly information and the target task; The target program code is obtained based on the preliminary program code, and the target program code is configured to the automated equipment.

2. The method of claim 1, wherein, The first AI model is used to generate preliminary program code for the automated equipment based on the assembly information and the target task, including: During the initialization phase, the first AI model generates the preliminary program code based on the initial assembly information and target task of the automated equipment; or... After the assembly information of the automated equipment changes, the first AI model generates the preliminary program code based on the changed assembly information of the automated equipment.

3. The method of claim 1, wherein, The step of obtaining the target program code based on the preliminary program code includes: The preliminary program code is used as the target program code; or... The preliminary program code is tested, and the preliminary program code that passes the test is used as the target program code.

4. The method of claim 3, wherein, The step of testing the preliminary program code, and using the preliminary program code that passes the test as the target program code, includes: A simulation model is generated based on the assembly information; The preliminary program code is written into the simulation model, and the simulation model is run based on the preliminary program code to obtain the running results; If the running result meets the preset requirements, the preliminary program code will be used as the target program code.

5. The method of claim 3, wherein, Also includes: If the initial program code fails the test, an error message is sent to the first AI model to trigger the first AI model to regenerate the initial program code.

6. The method of claim 1, wherein, The acquisition of the target task includes: The target task can be obtained from user input, or the target task can be generated based on the assembly information.

7. The method of claim 1, wherein, The first AI model is used to generate preliminary program code for the automated equipment based on the assembly information and the target task, including: The assembly information is checked using the AI ​​chip built into the automated equipment. The first AI model is used to generate the preliminary program code based on the assembly information after inspection and the target task.

8. The method according to any one of claims 1 to 7, characterized in that, Also includes: The status information of the automated equipment during operation is monitored. The automated equipment runs based on the target program code and operates independently of the computing power support of the first AI model. When an abnormality is determined to occur in the automated equipment based on the status information, a second AI model is used to generate reconfiguration information for the automated equipment, so that the automated equipment can perform corresponding operations based on the reconfiguration information.

9. The method of claim 8, wherein, The reconfiguration information includes: Global reconfiguration information, partial reconfiguration information, or unit-level reconfiguration information.

10. The method of claim 8, wherein, Also includes: Record the target program code and the reconfiguration information to perform a rollback operation based on the recorded information; And / or, If the automated equipment fails to meet the preset requirements for the execution result of the target task, the second AI model is used to reconfigure the automated equipment.

11. The method of claim 10, wherein, Also includes: The record information is stored in at least one of the following: the cloud, a local file of the automated device, or a database.

12. The method according to claim 8, characterized in that, The first AI model and the second AI model may be the same or different.

13. A handling device of an automated apparatus, characterized in that include: The acquisition module is used to acquire assembly information and target tasks of automated equipment. A generation module is used to generate preliminary program code for the automated equipment based on the assembly information and the target task, using a first AI model; The configuration module is used to obtain the target program code based on the preliminary program code and configure the target program code to the automation equipment.

14. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.

15. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-12.

16. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-12.

Images