Method and apparatus for synchronizing ai algorithm models for household robot, and device and storage medium

Abstract

Disclosed in the present invention are a method and apparatus for synchronizing AI algorithm models for a household robot, and a device and a storage medium, which are used for solving the problem of it being difficult to meet requirements for large-scale, efficient and automated upgrades due to the upgrade of AI algorithm models of existing household robots relying on manual operations and a centralized management policy. The method of the present invention comprises: acquiring position information of a household robot; receiving device information, an operating state and current home environment information which are sent by the household robot; on the basis of the position information, determining a device state of the household robot; on the basis of the device state, the device information, the operating state and the current home environment information, matching several target AI algorithm models from a preset AI algorithm library; and synchronizing the target AI algorithm models to the household robot.

Description

Methods, devices, equipment and storage media for synchronizing AI algorithm models for home robots Technical Field

[0001] This invention relates to the field of home robot technology, and in particular to a method, apparatus, device, and storage medium for synchronizing AI algorithm models for home robots. Background Technology

[0002] With the development of the Internet of Things (IoT) and Artificial Intelligence (AI), the smart home market is experiencing explosive growth. More and more smart devices and sensors are being incorporated into smart home construction, and numerous AI algorithms are being deployed in smart home robots, such as robotic vacuum cleaners, humanoid robots, and quadruped robots. These robots, equipped with many AI algorithms, possess the ability to process large amounts of sensory data (such as images, sound, and sensor data) and make real-time decisions.

[0003] The home environment places different demands on the data processing capabilities of various robots, namely, the AI ​​algorithms, chips, and sensors they are equipped with. For example, robotic vacuum cleaners need to process indoor environmental data in real time to plan cleaning paths. Through built-in sensors and cameras, the robot can perceive its surroundings and perform operations such as path planning and obstacle avoidance to ensure efficient cleaning. Humanoid robots, on the other hand, require more powerful data processing capabilities and more complex algorithms to achieve natural interaction with family members and perform diverse tasks. They need to process various perceptual data, including speech recognition, natural language processing (NLP), image recognition, and motion control, to provide functions such as home services, companionship, and security monitoring. Quadruped robots also need to process perceptual data such as images and sounds to move flexibly in complex home environments, avoid obstacles, execute predetermined patrol routes, and ensure timely response in emergencies, such as an instant alarm function when abnormal situations are detected.

[0004] As modern home environments become increasingly diverse and complex, the AI ​​algorithms used in robots within smart homes require continuous updates and iterations. However, the rapid iteration of AI algorithms and the diversification of terminal chip models have significantly increased the complexity and workload of targeted upgrades for robots.

[0005] Traditional methods for solving terminal upgrade problems mainly rely on manual operation and centralized management strategies, which are difficult to meet the needs of large-scale, high-efficiency, and automated upgrades. Summary of the Invention

[0006] This invention provides a method, apparatus, device, and storage medium for synchronizing AI algorithm models for home robots, which addresses the problem that existing upgrades of AI algorithm models for home robots rely on manual operation and centralized management strategies, making it difficult to meet the needs of large-scale, high-efficiency, and automated upgrades.

[0007] This invention provides a method for synchronizing AI algorithm models for home robots, applied to a synchronization management platform. The method includes:

[0008] Obtain the location information of the home robot;

[0009] Receive device information, operating status, and current home environment information sent by the home robot;

[0010] The device status of the home robot is determined based on the location information;

[0011] Based on the device status, device information, operating status, and current home environment information, several target AI algorithm models are matched in a preset AI algorithm library;

[0012] The target AI algorithm model is synchronized to the home robot.

[0013] Optionally, the step of obtaining the location information of the home robot includes:

[0014] The propagation time of signals emitted by a home robot to a preset receiver is obtained;

[0015] The transmission distance of the signal is calculated based on the propagation time;

[0016] The location information of the home robot is determined based on the transmission distance.

[0017] Optionally, the step of determining the device status of the home robot based on the location information includes:

[0018] Based on the location information, determine whether the home robot is in a preset charging position or whether the static duration has reached a preset threshold.

[0019] If not, the device status of the home robot is determined to be non-updatable;

[0020] If so, the device status of the home robot is determined to be updatable.

[0021] Optionally, the device information includes carrying capacity and computing resources; the step of synchronizing the target AI algorithm model to the home robot includes:

[0022] The target AI algorithm model is compressed based on the carrying capacity and the computing resources to obtain the target compressed AI algorithm model.

[0023] The target compression model is segmented into blocks to obtain cloud model blocks;

[0024] Calculate the cloud hash value of each cloud model block;

[0025] The target AI algorithm model is matched with the home robot to obtain the terminal AI algorithm model;

[0026] The terminal AI algorithm model is segmented to obtain terminal model blocks;

[0027] Calculate the terminal hash value for each of the terminal model blocks;

[0028] By comparing the cloud hash value and the terminal hash value, the differences in cloud model blocks are determined;

[0029] The data corresponding to the differential cloud model blocks is transmitted to the home robot.

[0030] Optionally, after the step of synchronizing the target AI algorithm model to the home robot, the method further includes:

[0031] Receive the self-test report of the home robot.

[0032] This invention also provides a home robot AI algorithm model synchronization device, applied to a synchronization management platform, the device comprising:

[0033] The location information acquisition module is used to acquire the location information of the home robot;

[0034] The device information, operating status, and current home environment information receiving module is used to receive device information, operating status, and current home environment information sent by the home robot;

[0035] The device status determination module is used to determine the device status of the home robot based on the location information.

[0036] The matching module is used to match several target AI algorithm models in a preset AI algorithm library based on the device status, the device information, the operating status and the current home environment information.

[0037] The synchronization module is used to synchronize the target AI algorithm model to the home robot.

[0038] Optionally, the location information acquisition module includes:

[0039] The propagation time acquisition submodule is used to acquire the propagation time of the signal emitted by the home robot to the preset receiving end;

[0040] A transmission distance calculation submodule is used to calculate the transmission distance of the signal based on the propagation time;

[0041] The location information determination submodule is used to determine the location information of the home robot based on the transmission distance.

[0042] Optionally, the device status determination module includes:

[0043] The judgment submodule is used to determine whether the home robot is in a preset charging position or whether the static time has reached a preset threshold based on the location information.

[0044] The non-updatable state determination submodule is used to determine that the device status of the home robot is non-updatable if no;

[0045] The updatable state determination submodule is used to determine if the device state of the home robot is updatable.

[0046] The present invention also provides an electronic device, the device comprising a processor and a memory:

[0047] The memory is used to store program code and transmit the program code to the processor;

[0048] The processor is used to execute the home robot AI algorithm model synchronization method as described above, according to the instructions in the program code.

[0049] The present invention also provides a computer-readable storage medium for storing program code for executing the home robot AI algorithm model synchronization method as described in any of the preceding claims.

[0050] As can be seen from the above technical solution, the present invention has the following advantages: The present invention acquires the location information of the home robot; receives the operating status and current home environment information sent by the home robot; determines the device status of the home robot based on the location information; matches several target AI algorithm models in a preset AI algorithm library based on the device status, operating status, and current home environment information; and synchronizes the target AI algorithm models to the home robot. This achieves large-scale, high-efficiency, and automated AI algorithm model upgrades. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 is a flowchart of the steps of a home robot AI algorithm model synchronization method provided in an embodiment of the present invention;

[0053] Figure 2 is a flowchart of the steps of a home robot AI algorithm model synchronization method according to another embodiment of the present invention;

[0054] Figure 3 is an overall architecture diagram of a home robot AI algorithm provided in an embodiment of the present invention;

[0055] Figure 4 is a structural block diagram of a home robot AI algorithm model synchronization device provided in an embodiment of the present invention. Detailed Implementation

[0056] This invention provides a method, apparatus, device, and storage medium for synchronizing AI algorithm models for home robots, which addresses the problem that existing upgrades of AI algorithm models for home robots rely on manual operation and centralized management strategies, making it difficult to meet the needs of large-scale, high-efficiency, and automated upgrades.

[0057] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0058] Please refer to Figure 1, which is a flowchart of the steps of a home robot AI algorithm model synchronization method provided by an embodiment of the present invention.

[0059] This invention provides a method for synchronizing AI algorithm models for home robots, applied to a synchronization management platform, which may specifically include the following steps:

[0060] Step 101: Obtain the location information of the home robot;

[0061] In this embodiment of the invention, the home robot can be a robotic vacuum cleaner, a humanoid robot, a quadruped robot, etc. These robots, equipped with numerous AI algorithms, possess the ability to process large amounts of sensory data (such as images, sound, and sensor data) and make real-time decisions.

[0062] In practical implementation, to achieve remote data updates for home robots, it is first necessary to obtain the location information of the home robot in order to determine whether the home robot is in an updatable state.

[0063] Step 102: Receive device information, operating status, and current home environment information sent by the home robot;

[0064] In practical implementation, the device information of a home robot determines the AI ​​algorithm model it can use. This device information can include processor information, memory and storage information, power supply and battery life, sensor type and performance, etc. The synchronous management platform provides the corresponding AI algorithm model based on the robot's device information.

[0065] The operating status information of the home robot (such as battery level and workload) and the current home environment information (such as light level and noise level) can be used to dynamically adjust the parameters of the AI ​​algorithm model or enable different sub-models to achieve optimal performance and energy efficiency. Specifically, this can be dynamically adjusted according to the actual situation of the selected home robot, and this embodiment of the invention does not impose specific limitations on this.

[0066] Step 103: Determine the device status of the home robot based on the location information;

[0067] In this embodiment of the invention, in order not to affect the normal operation of the home robot, the AI ​​algorithm model can be distributed using an idle time distribution strategy. Therefore, the device status of the home robot can be whether it is charging at the terminal charging point or in a long-term stationary state, etc.

[0068] Step 104: Based on the device status, device information, operating status and current home environment information, match several target AI algorithm models in the preset AI algorithm library;

[0069] In this embodiment of the invention, after obtaining the device status, device information, operating status and current home environment information, several target AI algorithm models can be matched in a preset AI algorithm library.

[0070] Step 105: Synchronize the target AI algorithm model to the home robot.

[0071] After determining the target AI algorithm model for updating the home robot, the target AI algorithm model can be synchronized to the home robot to achieve the AI ​​algorithm model update of the home robot.

[0072] This invention achieves large-scale, efficient, and automated AI algorithm model upgrades by acquiring the location information of a home robot; receiving its operational status and current home environment information; determining the robot's device status based on the location information; matching several target AI algorithm models from a pre-set AI algorithm library based on the device status, operational status, and current home environment information; and synchronizing the target AI algorithm models to the home robot.

[0073] Please refer to Figure 2, which is a flowchart illustrating the steps of a home robot AI algorithm model synchronization method according to another embodiment of the present invention. Specifically, it may include the following steps:

[0074] Step 201: Obtain the propagation time of the signal emitted by the home robot to the preset receiving end;

[0075] Step 202: Calculate the signal transmission distance based on the propagation time;

[0076] Step 203: Determine the location information of the home robot based on the transmission distance;

[0077] In this embodiment of the invention, a ToA positioning algorithm based on ranging can be used to measure the propagation time of a signal emitted by a home robot to multiple preset receiving terminals. The transmission distance of the signal to each receiving terminal can be calculated based on the propagation time, and then the position of the signal can be determined based on the transmission distance, that is, the current position of the home robot can be determined.

[0078] Step 204: Receive device information, operating status, and current home environment information sent by the home robot;

[0079] In practical implementation, the device information of a home robot determines the AI ​​algorithm model it can use. This device information can include processor information, memory and storage information, power supply and battery life, sensor type and performance, etc. The synchronous management platform matches the corresponding AI algorithm model based on the robot's device information.

[0080] The operating status information of the home robot (such as battery level and workload) and the current home environment information (such as light level and noise level) can be used to dynamically adjust the parameters of the AI ​​algorithm model or enable different sub-models to achieve optimal performance and energy efficiency. Specifically, this can be dynamically adjusted according to the actual situation of the selected home robot, and this embodiment of the invention does not impose specific limitations on this.

[0081] Step 205: Determine the device status of the home robot based on the location information;

[0082] In this embodiment of the invention, in order not to affect the normal operation of the home robot, the AI ​​algorithm model can be distributed using an idle time distribution strategy. Therefore, the device status of the home robot can be whether it is charging at the terminal charging point or in a long-term stationary state, etc.

[0083] In one example, the steps for determining the device status of a home robot based on location information include:

[0084] S51, determine whether the home robot is in a preset charging position or whether the static time has reached a preset threshold based on the location information;

[0085] S52, if not, determine that the device status of the home robot is not updatable;

[0086] S53, if so, determine that the device status of the home robot is updatable.

[0087] In practical implementation, the location information of the home robot can be used to determine whether it is in a preset charging position or has been stationary for a long time. If so, it indicates that transmitting the AI ​​algorithm model to the home robot will not affect its normal operation, and the home robot can be determined to be in an updatable state. Otherwise, the home robot is determined to be in a non-updatable state.

[0088] Step 206: Based on the device status, device information, operating status and current home environment information, match several target AI algorithm models in the preset AI algorithm library;

[0089] In this embodiment of the invention, an AI algorithm library can be pre-built on the synchronization management platform to store the latest AI algorithm models available for home robots.

[0090] In one example, an AI algorithm library can be categorized by algorithmic functional modules: A library can be built containing various AI algorithm modules, each targeting a specific task type, such as:

[0091] Image recognition: including object detection, scene understanding, face recognition, and other functions;

[0092] Speech recognition: Handling tasks such as speech recognition and speech synthesis;

[0093] Sentiment analysis: Analyzes the emotional tendencies in text or speech, and is applicable to emotional understanding in human-computer interaction;

[0094] Natural Language Processing (NLP): Supports language understanding, semantic parsing, dialogue generation, etc.

[0095] Path planning: Used for robot navigation and obstacle avoidance in dynamic environments.

[0096] At the same time, standardized interfaces are designed for each functional module to ensure seamless combination and integration between modules, supporting flexible configuration and deployment.

[0097] In this embodiment of the invention, after obtaining the device status, device information, operating status and current home environment information, several target AI algorithm models can be matched in a preset AI algorithm library.

[0098] Step 207: Synchronize the target AI algorithm model to the home robot.

[0099] After determining the target AI algorithm model for updating the home robot, the target AI algorithm model can be synchronized to the home robot to achieve the AI ​​algorithm model update of the home robot.

[0100] In one example, device information includes carrying capacity and computing resources; the steps to synchronize the target AI algorithm model to the home robot include:

[0101] S71, compress the target AI algorithm model according to the carrying capacity and computing resources to obtain the target compressed AI algorithm model;

[0102] S72, performs block processing on the target compressed model to obtain cloud model blocks;

[0103] S73, calculate the cloud hash value of each cloud model block;

[0104] S74, match the target AI algorithm model with the home robot to obtain the terminal AI algorithm model;

[0105] S75, the terminal AI algorithm model is segmented into blocks to obtain terminal model blocks;

[0106] S76, calculate the terminal hash value of each terminal model block;

[0107] S77, compare the cloud hash value and the terminal hash value to determine the difference in cloud model blocks;

[0108] S78 transmits data corresponding to the different cloud model blocks to the home robot.

[0109] In this invention, based on the carrying capacity and computing resources of a home robot, the size of the target AI algorithm model can be appropriately reduced through a model compression algorithm. This reduces the burden on the home robot and ensures optimal performance under specific hardware conditions. The model compression algorithm may include model quantization, model pruning, and model distillation.

[0110] Next, during transmission, differential synchronization technology based on hash verification can be employed. Specifically, the target compressed model can be segmented into cloud model blocks, and a cloud hash value is calculated for each cloud model block. Simultaneously, the corresponding terminal AI algorithm model is obtained from the home robot, and then segmented into terminal model blocks, with a hash value calculated for each block. Finally, the cloud hash value and the terminal hash value are compared one by one to identify the differences, thus determining the differential cloud model blocks. The data corresponding to these differential cloud model blocks is then transmitted to the home robot. Differential synchronization technology can significantly reduce the amount of data that needs to be transmitted, especially when network bandwidth is limited or the updated content is small, significantly improving data transmission efficiency and reducing network resource consumption.

[0111] Furthermore, to ensure the integrity and efficiency of data transmission, the network connection status can be considered to determine whether to initiate algorithm update operations, thus avoiding large-scale data transmission in adverse environments.

[0112] Furthermore, the synchronization management platform can also integrate incremental learning technology, which automatically optimizes transmission and update strategies based on the usage and feedback data of terminal devices (home robots). For example, by analyzing the usage frequency and resource consumption of terminal devices, it prioritizes updating devices with high usage rates and pushes lightweight algorithm versions that are more suitable for the device's hardware conditions.

[0113] Furthermore, once synchronization is complete, the home robot will immediately initiate a self-test program. This program will perform a series of functional and performance tests on the new AI algorithm model to ensure it functions correctly and achieves the expected results, and will then send a self-test report to the synchronization management platform.

[0114] For ease of understanding, the embodiments of the present invention will be described using a robotic vacuum cleaner as an example:

[0115] The synchronization management platform acquires the latest AI algorithm model from the cloud and performs algorithm compression based on the robot vacuum's hardware type, including algorithm quantization and trimming. Then, using range-based spatial positioning technology, such as the ToA positioning algorithm, it monitors the robot vacuum's location in the home in real time. Combining the robot vacuum's location data and movement trajectory, the synchronization management platform can intelligently determine its working status: if the robot vacuum's position is constantly changing and its movement trajectory matches the characteristics of cleaning operations (such as moving along walls or moving between rooms), it is determined that the robot vacuum is in working mode; conversely, if the robot vacuum stays in the same location for a long time (such as at the charging station) and its coordinates do not change significantly, it is determined that the robot vacuum is in idle mode. In this case, the synchronization management platform transmits the latest AI algorithm model to the robot vacuum. The specific transmission method can be differential synchronization technology based on hash verification. After synchronization is complete, the robot vacuum immediately starts a self-test program. The self-test program performs a series of functional and performance tests on the new AI algorithm model to ensure that it can work normally and achieve the expected results. If any problems are found during the self-check, the robot vacuum will send an error report to the synchronization management platform and automatically roll back to the previous stable algorithm version.

[0116] This invention achieves large-scale, efficient, and automated AI algorithm model upgrades by acquiring the location information of a home robot; receiving its operational status and current home environment information; determining the robot's device status based on the location information; matching several target AI algorithm models from a pre-set AI algorithm library based on the device status, operational status, and current home environment information; and synchronizing the target AI algorithm models to the home robot.

[0117] Please refer to Figure 3, which is an overall architecture diagram of a home robot AI algorithm provided in an embodiment of the present invention.

[0118] The synchronous management platform can select and adapt AI algorithms. Based on collected device information (such as CPU, GPU, memory, etc.), it automatically selects suitable AI algorithm types (such as image recognition, speech recognition, path planning, NLP, sentiment analysis, etc.) from the AI ​​algorithm library using a matching algorithm. Based on the robot's carrying capacity and computing resources, it appropriately reduces the model size through model compression algorithms (such as model distillation, model quantization, model pruning, etc.) to reduce the robot's carrying burden and ensure optimal performance in specific hardware environments. Finally, through idle-time algorithm delivery, the compressed AI algorithm model is transmitted to home robots (including quadruped robots, humanoid robots, and robotic vacuum cleaners).

[0119] Please refer to Figure 4, which is a structural block diagram of a home robot AI algorithm model synchronization device provided in an embodiment of the present invention.

[0120] This invention provides a home robot AI algorithm model synchronization device, applied to a synchronization management platform. The device includes:

[0121] Location information acquisition module 401 is used to acquire the location information of the home robot;

[0122] The device information, operating status and current home environment information receiving module 402 is used to receive device information, operating status and current home environment information sent by the home robot;

[0123] The device status determination module 403 is used to determine the device status of the home robot based on the location information.

[0124] The matching module 404 is used to match several target AI algorithm models in a preset AI algorithm library based on the device status, device information, operating status and current home environment information.

[0125] Synchronization module 405 is used to synchronize the target AI algorithm model to the home robot.

[0126] In this embodiment of the invention, the location information acquisition module 401 includes:

[0127] The propagation time acquisition submodule is used to acquire the propagation time of the signal emitted by the home robot to the preset receiving end;

[0128] The transmission distance calculation submodule is used to calculate the transmission distance of the signal based on the propagation time.

[0129] The location information determination submodule is used to determine the location information of the home robot based on the transmission distance.

[0130] In this embodiment of the invention, the device status determination module 403 includes:

[0131] The judgment submodule is used to determine whether the home robot is in a preset charging position or whether the static time has reached a preset threshold based on the location information.

[0132] The "Cannot be updated" status determination submodule is used to determine if the home robot's device status is "cannot be updated" if not otherwise specified.

[0133] The updatable state determination submodule is used to determine if the device state of the home robot is updatable.

[0134] In this embodiment of the invention, the device information includes carrying capacity and computing resources; the synchronization module 405 includes:

[0135] The compression submodule is used to compress the target AI algorithm model according to the carrying capacity and computing resources to obtain the target compressed AI algorithm model;

[0136] The first block processing submodule is used to process the target compressed model into blocks to obtain cloud model blocks;

[0137] The cloud hash value calculation submodule is used to calculate the cloud hash value of each cloud model block;

[0138] The terminal AI algorithm model matching submodule is used to match the target AI algorithm model with the home robot to obtain the terminal AI algorithm model.

[0139] The second block processing submodule is used to process the terminal AI algorithm model into blocks to obtain terminal model blocks;

[0140] The terminal hash value calculation submodule is used to calculate the terminal hash value of each terminal model block;

[0141] The comparison submodule is used to compare cloud hash values ​​and terminal hash values ​​to determine the differences in cloud model blocks.

[0142] The transmission submodule is used to transmit data corresponding to the different cloud model blocks to the home robot.

[0143] In this embodiment of the invention, it further includes:

[0144] The self-test report receiving module is used to receive self-test reports from home robots.

[0145] This invention also provides an electronic device, which includes a processor and a memory:

[0146] The memory is used to store program code and transfer the program code to the processor;

[0147] The processor is used to execute the home robot AI algorithm model synchronization method of this invention according to the instructions in the program code.

[0148] This invention also provides a computer-readable storage medium for storing program code for executing the home robot AI algorithm model synchronization method of this invention.

[0149] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0150] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0151] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0152] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0153] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0154] These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable terminal equipment, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0155] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0156] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0157] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for synchronizing an AI algorithm model for a home robot, characterized in that, Applied to a synchronization management platform, the method includes: Obtain the location information of the home robot; Receive device information, operating status, and current home environment information sent by the home robot; The device status of the home robot is determined based on the location information; Based on the device status, device information, operating status, and current home environment information, several target AI algorithm models are matched in a preset AI algorithm library; The target AI algorithm model is synchronized to the home robot.

2. The method according to claim 1, characterized in that, The step of obtaining the location information of the home robot includes: The propagation time of signals emitted by a home robot to a preset receiver is obtained; The transmission distance of the signal is calculated based on the propagation time; The location information of the home robot is determined based on the transmission distance.

3. The method according to claim 1, characterized in that, The step of determining the device status of the home robot based on the location information includes: Based on the location information, determine whether the home robot is in a preset charging position or whether the static duration has reached a preset threshold. If not, the device status of the home robot is determined to be non-updatable; If so, the device status of the home robot is determined to be updatable.

4. The method according to claim 1, characterized in that, The device information includes carrying capacity and computing resources; the step of synchronizing the target AI algorithm model to the home robot includes: The target AI algorithm model is compressed based on the carrying capacity and the computing resources to obtain the target compressed AI algorithm model. The target compression model is segmented into blocks to obtain cloud model blocks; Calculate the cloud hash value of each cloud model block; The target AI algorithm model is matched with the home robot to obtain the terminal AI algorithm model; The terminal AI algorithm model is segmented to obtain terminal model blocks; Calculate the terminal hash value for each of the terminal model blocks; By comparing the cloud hash value and the terminal hash value, the differences in cloud model blocks are determined; The data corresponding to the differential cloud model blocks is transmitted to the home robot.

5. The method according to any one of claims 1-4, characterized in that, After the step of synchronizing the target AI algorithm model to the home robot, the method further includes: Receive the self-test report of the home robot.

6. A synchronization device for AI algorithm models of home robots, characterized in that, The device, used in a synchronization management platform, includes: The location information acquisition module is used to acquire the location information of the home robot; The device information, operating status, and current home environment information receiving module is used to receive device information, operating status, and current home environment information sent by the home robot; The device status determination module is used to determine the device status of the home robot based on the location information. The matching module is used to match several target AI algorithm models in a preset AI algorithm library based on the device status, the device information, the operating status and the current home environment information. The synchronization module is used to synchronize the target AI algorithm model to the home robot.

7. The apparatus according to claim 6, characterized in that, The location information acquisition module includes: The propagation time acquisition submodule is used to acquire the propagation time of the signal emitted by the home robot to the preset receiving end; A transmission distance calculation submodule is used to calculate the transmission distance of the signal based on the propagation time; The location information determination submodule is used to determine the location information of the home robot based on the transmission distance.

8. The apparatus according to claim 6, characterized in that, The device status determination module includes: The judgment submodule is used to determine whether the home robot is in a preset charging position or whether the static time has reached a preset threshold based on the location information. The non-updatable state determination submodule is used to determine, if not, that the device state of the home robot is non-updatable. The updatable state determination submodule is used to determine if the device state of the home robot is updatable.

9. An electronic device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the home robot AI algorithm model synchronization method according to any one of claims 1-5 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the home robot AI algorithm model synchronization method according to any one of claims 1-5.

Images