Robot data processing method and apparatus, and computer device and storage medium

Abstract

The present application relates to a robot data processing method and apparatus, and a computer device, a storage medium and a computer program product. The method comprises: on the basis of target feature engineering information sent by a cloud server, determining a target data source of a robot; from the target data source, receiving transmission data to be processed that matches the target feature engineering information; on the basis of the target feature engineering information, determining a preset data filtering condition and a preset data processing objective; and on the basis of the preset data filtering condition, the preset data processing objective and said transmission data, obtaining target robot data transmitted to the cloud server. Using the method can reduce the amount of transmitted data and improve the stability of data transmission.

Description

Robot data processing method, device, computer equipment and storage medium Technical Field

[0001] The present application relates to the field of edge-cloud collaborative technology, and in particular to a robot data processing method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] As automation in enterprises continues to advance, the trend of robots replacing human workers is becoming increasingly evident. In this process, it is necessary to collect robot-related data for further analysis and research.

[0003] However, based on progress in robotics research and development both domestically and internationally, a single robot can now collect data at a frequency of less than 10ms, collecting approximately gigabytes of data daily. Based on a typical automotive production line (over 200 robots), the robots generate nearly terabytes of data daily, resulting in a correspondingly large amount of uploaded data. This large amount of data can easily lead to data transmission anomalies.

[0004] Summary of the Invention

[0005] Based on this, it is necessary to provide a robot data processing method, device, computer equipment, computer-readable storage medium and computer program product that can transmit robot data more stably to address the above technical problems.

[0006] In a first aspect, the present application provides a robot data processing method, applied to an edge server, the method comprising:

[0007] Determine the robot's target data source based on the target feature engineering information sent by the cloud server;

[0008] Receiving, from the target data source, transmission data to be processed that matches the target feature engineering information;

[0009] Determining preset data screening conditions and preset data processing targets based on the target feature engineering information;

[0010] According to the preset data screening condition, the preset data processing target and the transmission data to be processed, the target robot data transmitted to the cloud server is obtained.

[0011] In one embodiment, obtaining the target robot data transmitted to the cloud server according to the preset data screening condition, the preset data processing target, and the to-be-processed transmission data includes:

[0012] Determining the target data type according to the preset data screening condition;

[0013] Filtering target transmission data corresponding to the target data type from the transmission data to be processed;

[0014] According to the preset data processing target and the target transmission data, the target robot data transmitted to the cloud server is obtained.

[0015] In one embodiment, obtaining target robot data transmitted to the cloud server according to the preset data processing target and the target transmission data includes:

[0016] Determining a target data processing method according to the preset data processing target;

[0017] The target data processing method is used to process the target transmission data to obtain target robot data that is transmitted to the cloud server.

[0018] In one embodiment, the target data processing method is used to process the target transmission data to obtain target robot data transmitted to the cloud server, including:

[0019] Adopting a sliding window to sequentially intercept and obtain transmission data of each sub-target from the target transmission data;

[0020] Using the target data processing method, data processing is performed on the data transmitted by each sub-target to obtain candidate target robot data;

[0021] From the candidate target robot data, the candidate target robot data having the highest matching degree with the preset data processing target is screened out as the target robot data.

[0022] In one embodiment, receiving the target robot identification and target feature engineering information sent by the cloud server;

[0023] Determine a target robot that matches the target robot identifier from multiple robots;

[0024] Determining the target data source of the robot based on the target feature engineering information sent by the cloud server includes:

[0025] The target data source of the target robot is determined based on the target feature engineering information.

[0026] In a second aspect, the present application further provides a robot data processing method, which is applied to a cloud server, and the method comprises:

[0027] Sending target feature engineering information to an edge server; the edge server is used to determine a target data source of the robot based on the target feature engineering information sent by the cloud server; receiving to-be-processed transmission data that matches the target feature engineering information from the target data source; determining a preset data screening condition and a preset data processing target based on the target feature engineering information; obtaining target robot data transmitted to the cloud server based on the preset data screening condition, the preset data processing target, and the to-be-processed transmission data;

[0028] Receive target robot data transmitted by the edge server.

[0029] In one embodiment, sending the target feature engineering information to the edge server includes:

[0030] Determine the corresponding target robot identification according to the target feature engineering information;

[0031] Determining, according to the target robot identifier, a target edge server connected to the target robot from a plurality of edge servers;

[0032] Send the target feature engineering information to the target edge server.

[0033] In a third aspect, the present application further provides a robot data processing device, applied to an edge server, comprising:

[0034] The source determination module is used to determine the source of the robot's target data based on the target feature engineering information sent by the cloud server;

[0035] A data acquisition module, configured to receive, from the target data source, the to-be-processed transmission data that matches the target feature engineering information;

[0036] A processing determination module, configured to determine preset data screening conditions and preset data processing targets based on the target feature engineering information;

[0037] The data processing module is used to obtain the target robot data transmitted to the cloud server according to the preset data screening condition, the preset data processing target and the transmission data to be processed.

[0038] In a fourth aspect, the present application further provides a robot data processing device, which is applied to a cloud server, and the device includes:

[0039] An information sending module is configured to send target feature engineering information to an edge server; the edge server is configured to determine a target data source for the robot based on the target feature engineering information sent by the cloud server; receive, from the target data source, pending transmission data that matches the target feature engineering information; determine preset data screening conditions and preset data processing targets based on the target feature engineering information; and obtain target robot data transmitted to the cloud server based on the preset data screening conditions, the preset data processing targets, and the pending transmission data;

[0040] The data receiving module is used to receive the target robot data transmitted by the edge server.

[0041] In a fifth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0042] Determine the robot's target data source based on the target feature engineering information sent by the cloud server;

[0043] Receiving, from the target data source, transmission data to be processed that matches the target feature engineering information;

[0044] Determining preset data screening conditions and preset data processing targets based on the target feature engineering information;

[0045] According to the preset data screening condition, the preset data processing target and the transmission data to be processed, the target robot data transmitted to the cloud server is obtained.

[0046] In a sixth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0047] Sending target feature engineering information to an edge server; the edge server is used to determine a target data source of the robot based on the target feature engineering information sent by the cloud server; receiving to-be-processed transmission data that matches the target feature engineering information from the target data source; determining a preset data screening condition and a preset data processing target based on the target feature engineering information; obtaining target robot data transmitted to the cloud server based on the preset data screening condition, the preset data processing target, and the to-be-processed transmission data;

[0048] Receive target robot data transmitted by the edge server.

[0049] In a seventh aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0050] Determine the robot's target data source based on the target feature engineering information sent by the cloud server;

[0051] Receiving, from the target data source, transmission data to be processed that matches the target feature engineering information;

[0052] Determining preset data screening conditions and preset data processing targets based on the target feature engineering information;

[0053] According to the preset data screening condition, the preset data processing target and the transmission data to be processed, the target robot data transmitted to the cloud server is obtained.

[0054] In an eighth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0055] Sending target feature engineering information to an edge server; the edge server is used to determine a target data source of the robot based on the target feature engineering information sent by the cloud server; receiving to-be-processed transmission data that matches the target feature engineering information from the target data source; determining a preset data screening condition and a preset data processing target based on the target feature engineering information; obtaining target robot data transmitted to the cloud server based on the preset data screening condition, the preset data processing target, and the to-be-processed transmission data;

[0056] Receive target robot data transmitted by the edge server.

[0057] In a ninth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0058] Determine the robot's target data source based on the target feature engineering information sent by the cloud server;

[0059] Receiving, from the target data source, transmission data to be processed that matches the target feature engineering information;

[0060] Determining preset data screening conditions and preset data processing targets based on the target feature engineering information;

[0061] According to the preset data screening condition, the preset data processing target and the transmission data to be processed, the target robot data transmitted to the cloud server is obtained.

[0062] In a tenth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0063] Sending target feature engineering information to an edge server; the edge server is used to determine a target data source of the robot based on the target feature engineering information sent by the cloud server; receiving to-be-processed transmission data that matches the target feature engineering information from the target data source; determining a preset data screening condition and a preset data processing target based on the target feature engineering information; obtaining target robot data transmitted to the cloud server based on the preset data screening condition, the preset data processing target, and the to-be-processed transmission data;

[0064] Receive target robot data transmitted by the edge server.

[0065] The above-mentioned robot data processing method, device, computer equipment, storage medium and computer program product first determine the target data source of the robot based on the target feature engineering information sent by the cloud server; then, receive the to-be-processed transmission data that matches the target feature engineering information from the target data source, first determine the target data source to narrow the scope of data acquisition, avoid unnecessary data collection, thereby reducing the data that needs to be transmitted, and also improve the efficiency of data processing; then, determine the preset data screening conditions and preset data processing targets based on the target feature engineering information; and obtain the target robot data transmitted to the cloud server based on the preset data screening conditions, preset data processing targets and to-be-processed transmission data, which helps to perform preliminary screening and processing of the data before transmission to ensure that only data that meets the conditions is transmitted, reduce the amount of transmitted data, meet the requirements of target feature engineering, and avoid unnecessary redundant information. In the above-mentioned method, by accurately determining the target data source, matching the screening conditions and processing targets corresponding to the target feature engineering, the data before transmission is processed, reducing the amount of transmitted data, improving the efficiency of data transmission, thereby saving bandwidth resources and reducing the risk of data transmission anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0067] FIG1 is a diagram illustrating an application environment of a robot data processing method according to an embodiment;

[0068] FIG2 is a schematic flow chart of a robot data processing method according to an embodiment;

[0069] FIG3 is a schematic flow chart of steps for obtaining target robot data in one embodiment;

[0070] FIG4 is a schematic flow chart of a robot data processing method according to another embodiment;

[0071] FIG5 is a schematic flow chart of a robot data processing method according to another embodiment;

[0072] FIG6 is a schematic diagram of the actual execution flow of a robot data processing method according to one embodiment;

[0073] FIG7 is a schematic diagram of information types included in robot data according to one embodiment;

[0074] FIG8 is a schematic structural diagram of a robot data processing system according to one embodiment;

[0075] FIG9 is a block diagram of a robot data processing device according to an embodiment;

[0076] FIG10 is a block diagram of a robot data processing device according to an embodiment;

[0077] FIG11 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0079] The robot data processing method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. In particular, the edge server 102 communicates with the server 104 and the robot 106 respectively through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The edge server 102 determines the target data source of the robot 106 based on the target feature engineering information sent by the cloud server 104; the edge server 102 receives the to-be-processed transmission data that matches the target feature engineering information from the target data source; the edge server 102 determines the preset data screening conditions and the preset data processing target based on the target feature engineering information; the edge server 102 obtains the target robot data transmitted to the cloud server 104 based on the preset data screening conditions, the preset data processing target and the to-be-processed transmission data. In particular, the edge server 102 and the cloud server 104 can be implemented as independent servers or a server cluster consisting of multiple servers. The robot 106 can be various robotic arms, automatic machines, humanoid machines, etc.

[0080] In an exemplary embodiment, as shown in FIG2 , a robot data processing method is provided. The method is described by applying the method to the edge server 102 in FIG1 as an example. The method includes the following steps:

[0081] Step S201: Determine the target data source of the robot based on the target feature engineering information sent by the cloud server.

[0082] The target data sources may be various monitoring sensors, actuators, internal control units, etc. on the robot.

[0083] Exemplarily, the edge server 102 parses the target feature engineering information sent by the cloud server 104 to understand the key information contained therein, and identifies the target data source of the robot through the parsed feature engineering information. Alternatively, the target feature engineering information may include the required information type, such as voltage, temperature, etc., and the edge server 102 may query a preset mapping relationship table based on the information type to obtain the target data source type, such as a sensor, actuator, or internal control unit, corresponding to the information type, and then determine the target data source identifier corresponding to the robot 106 based on the target data source type. Alternatively, the target feature engineering information may be identification information for the target feature engineering, and the edge server 102 may directly query a preset mapping relationship table based on the identification information to determine the target data source type, and then determine the target data source identifier corresponding to the robot 106 based on the target data source type.

[0084] Step S202: receiving, from a target data source, transmission data to be processed that matches the target feature engineering information.

[0085] Exemplarily, after the edge server 102 determines the source of the target data, it queries the target connection interface or target network address of the target data source, and receives the transmission data to be processed that matches the target feature engineering information through the target network interface or target network address. When receiving the transmission data to be processed, the edge server 102 also needs to determine the receiving protocol of the transmission data to be processed, including the data format, transmission mode, data packet structure, etc., to help avoid data loss or parsing errors. When receiving the transmission data to be processed, the edge server 102 can also verify the data quality, which may include checks on the integrity, accuracy, and timeliness of the data to ensure that the received data meets the expected standards.

[0086] Step S203: Determine preset data screening conditions and preset data processing targets based on target feature engineering information.

[0087] For example, each target feature engineering project has corresponding preset data screening conditions and preset data processing targets. The preset data screening conditions and preset data processing targets can be recorded in the target feature engineering information, and the edge server 102 can directly obtain them based on the target feature engineering information. The preset data screening conditions and preset data processing targets can also be pre-stored in the data storage system of the edge server 102, and the edge server 102 can query the data storage system based on the target feature engineering information to obtain the corresponding preset data screening conditions and preset data processing targets.

[0088] In step S204 , target robot data to be transmitted to the cloud server is obtained according to the preset data screening conditions, the preset data processing target, and the transmission data to be processed.

[0089] Exemplarily, edge server 102 determines the raw data required for target feature engineering based on preset screening conditions. Alternatively, edge server 102 constructs a target screening instruction based on the preset screening conditions and a preset screening instruction template, and executes the target screening instruction to select the raw data required for target feature engineering. Edge server 102 then processes the filtered data to be transmitted based on preset data processing objectives and employs a corresponding data processing method to obtain target robot data for transmission to cloud server 104. Terminal 102 may also aggregate and organize the target robot data to ensure that the data is transmitted in a format that meets the requirements of cloud server 104.

[0090] In the above-mentioned robot data processing method, first, the target data source of the robot is determined according to the target feature engineering information sent by the cloud server; then, the to-be-processed transmission data that matches the target feature engineering information is received from the target data source, and the target data source is first determined to narrow the scope of data acquisition, avoid unnecessary data collection, thereby reducing the data that needs to be transmitted, and also improve the efficiency of data processing; then, according to the target feature engineering information, the preset data screening conditions and the preset data processing targets are determined; and according to the preset data screening conditions, the preset data processing targets and the to-be-processed transmission data, the target robot data transmitted to the cloud server is obtained, which helps to perform preliminary screening and processing of the data before transmission to ensure that only data that meets the conditions is transmitted, reduce the amount of transmitted data, meet the requirements of the target feature engineering, and avoid unnecessary redundant information. In the above-mentioned method, by accurately determining the target data source, matching the screening conditions and processing targets corresponding to the target feature engineering, the data before transmission is processed, the amount of transmitted data is reduced, the efficiency of data transmission is improved, thereby saving bandwidth resources and reducing the risk of data transmission anomalies.

[0091] In an exemplary embodiment, as shown in FIG3 , step S204 obtains target robot data transmitted to the cloud server based on preset data screening conditions, preset data processing targets, and the data to be processed, and can also be implemented by the following steps:

[0092] Step S301: Determine the target data type according to preset data screening conditions.

[0093] Step S302: Filter out target transmission data corresponding to the target data type from the transmission data to be processed.

[0094] Step S303 , obtaining target robot data to be transmitted to the cloud server according to the preset data processing target and target transmission data.

[0095] Exemplarily, the edge server determines the target data type to be filtered based on the preset data filtering conditions; for example, for the target data source being the sensor's pending transmission data, it may include sensor identification information, data packet header information (such as checksum, serial number, etc.), metadata (such as sensor sampling rate, sensor status information, etc.), transmission-related information (such as transmission protocol, etc.), and the physical information collected by the sensor and the timestamp of the physical information required for the target feature engineering; for the target data source being the robot's internal control unit, it may include data such as the number of times a certain action of the robot is triggered and the robot's working time, but the target feature engineering requires only one type of data. Then, the edge server filters out the target transmission data corresponding to the target data type from the pending transmission data; the edge server may filter out the target transmission data from the pending transmission data based on the type identifier of the data type. Finally, the edge server processes the target transmission data according to the preset data processing target to obtain the target robot data transmitted to the cloud server.

[0096] In this embodiment, the target data type is defined in detail according to the preset data screening conditions, which ensures more accurate screening of the robot data, reduces the amount of data, and avoids irrelevant data from being transmitted to the cloud server.

[0097] In an exemplary embodiment, the above-mentioned step S303 obtains the target robot data transmitted to the cloud server according to the preset data processing target and the target transmission data, and also includes: determining the target data processing method according to the preset data processing target; using the target data processing method to process the target transmission data to obtain the target robot data transmitted to the cloud server.

[0098] Exemplarily, the edge server determines the corresponding target data processing method from the preset mapping relationship table based on the preset data processing target, which may include using specific algorithms and models to perform data cleaning, aggregation, conversion and other processing methods. Then, the edge server uses the target data processing method to process the target transmission data, and obtains the target robot data transmitted to the cloud server, so that the cloud server can directly apply the target robot data to the target feature engineering. The target data processing method can include mathematical operation processing methods, such as maximum (minimum) value calculation, cumulative value calculation, range calculation, frequency calculation, etc. The target data processing method can also include feature dimensionality reduction, feature fusion, etc.

[0099] In this embodiment, by executing the curtain data processing method corresponding to the preset data processing target on the edge server, the cloud server is helped to process the data in advance, and the processed target robot data is transmitted to the cloud server, which can effectively reduce the amount of transmitted data and ensure the stability of transmission.

[0100] In an exemplary embodiment, the target transmission data includes streaming data;

[0101] The above-mentioned target data processing method is used to process the target transmission data to obtain target robot data transmitted to the cloud server, and also includes: using a sliding window to sequentially intercept each sub-target transmission data from the target transmission data; using the target data processing method to process each sub-target transmission data to obtain candidate target robot data; from the candidate target robot data, screening out the candidate target robot data with the highest matching degree with the preset data processing target as the target robot data.

[0102] For example, the edge server can optimize sliding window parameters, such as window size and sliding step size, to accommodate streaming data of different types and frequencies. At the same time, the sliding windows are overlapped to ensure a certain amount of data overlap between adjacent windows, avoiding information loss or inaccuracy due to window boundaries. Next, the edge server uses a sliding window to intercept and obtain each sub-target transmission data in chronological order. The edge server then employs a parallel processing strategy for each sub-target transmission data to improve data processing efficiency. After processing each sub-target transmission data, the edge server summarizes the data processing results, specifically selecting the candidate target robot data with the highest degree of match with the preset data processing target from the candidate target robot data as the target robot data. For example, to determine the maximum value in the target transmission data, the following steps are performed: first, determine the candidate maximum values ​​for each sub-target transmission data, and then determine the largest candidate maximum value, which is the target robot data.

[0103] In this embodiment, a sliding window approach is used to continuously process streaming data, improving the real-time processing efficiency of streaming data and ensuring that the system can handle data generated at a high frequency. Subsequent parallel processing strategies can be used to more efficiently process the data transmitted by each sub-target, fully utilizing computing resources and improving the parallelism and overall efficiency of data processing.

[0104] In an exemplary embodiment, before the above step S201 determines the target data source of the robot based on the target feature engineering information sent by the cloud server, it also includes: receiving the target robot identifier and target feature engineering information sent by the cloud server; and determining a target robot that matches the target robot identifier from multiple robots.

[0105] Furthermore, in an exemplary embodiment, the above-mentioned step S201 determines the target data source of the robot based on the target feature engineering information sent by the cloud server, and also includes: determining the target data source of the target robot based on the target feature engineering information.

[0106] For example, a single edge server can connect to multiple robots. Therefore, the cloud server also sends the target robot's identifier to the edge server. The edge server first determines the target robot based on the target robot's identifier. Then, when determining the target data source, the edge server queries all data sources corresponding to the target robot and identifies the target data source that corresponds to the target feature engineering information.

[0107] In this embodiment, the edge server can connect to multiple target robots simultaneously, enabling collaborative data processing between them. This improves the overall processing efficiency of the system and fully utilizes the computing resources of the edge server. By matching identifiers and querying the source of target data, the edge server can flexibly adapt to changes in robots, including the addition, removal, or replacement of robots.

[0108] In another exemplary embodiment, as shown in FIG4 , a robot data processing method is provided. The method is applied to an edge server and includes the following steps:

[0109] Step S401: Receive the target robot identification and target feature engineering information sent by the cloud server.

[0110] Step S402: Determine a target robot that matches the target robot identifier from multiple robots.

[0111] Step S403: Determine the target data source of the target robot based on the target feature engineering information.

[0112] Step S404: receiving the to-be-processed transmission data that matches the target feature engineering information from the target data source.

[0113] Step S405: Determine preset data screening conditions and preset data processing targets based on target feature engineering information.

[0114] Step S406: Determine the target data type according to the preset data screening condition.

[0115] Step S407: Filter out target transmission data corresponding to the target data type from the transmission data to be processed.

[0116] Step S408: determining a target data processing method according to a preset data processing target.

[0117] Step S409: using a sliding window to sequentially intercept each sub-target transmission data from the target transmission data.

[0118] The target transmission data includes streaming data.

[0119] Step S410: Using a target data processing method, the data transmitted by each sub-target is processed to obtain candidate target robot data.

[0120] Step S411 : Filter out candidate target robot data having the highest matching degree with a preset data processing target from the candidate target robot data as target robot data.

[0121] In this embodiment, by accurately determining the source of target data and matching the screening conditions and processing targets corresponding to the target feature engineering, the data before transmission is processed, which reduces the amount of data transmitted and improves the efficiency of data transmission, thereby saving bandwidth resources and reducing the risk of data transmission anomalies.

[0122] In an exemplary embodiment, as shown in FIG5 , a robot data processing method is provided. The method is described by taking the cloud server 104 in FIG1 as an example. The method includes the following steps:

[0123] Step S501: Send target feature engineering information to the edge server.

[0124] Among them, the edge server is used to determine the target data source of the robot based on the target feature engineering information sent by the cloud server; receive the to-be-processed transmission data that matches the target feature engineering information from the target data source; determine the preset data screening conditions and preset data processing targets based on the target feature engineering information; and obtain the target robot data transmitted to the cloud server based on the preset data screening conditions, the preset data processing targets and the to-be-processed transmission data.

[0125] Step S502: Receive target robot data transmitted by the edge server.

[0126] For example, when the cloud server needs to obtain robot data for target feature engineering, it sends the target feature engineering information to the edge server, so that the edge server obtains the robot data based on the target feature engineering information and pre-processes the robot data. Then, the cloud server receives the target robot data processed by the edge server and performs subsequent target feature engineering.

[0127] In this embodiment, by accurately determining the source of target data and matching the screening conditions and processing targets corresponding to the target feature engineering on the edge server, the data is processed before transmission, which reduces the amount of data transmitted to the cloud server and improves the efficiency of data transmission, thereby saving bandwidth resources and reducing the risk of data transmission anomalies.

[0128] In an exemplary embodiment, the above-mentioned step S501 sends the target feature engineering information to the edge server, and also includes: determining the corresponding target robot identifier based on the target feature engineering information; determining the target edge server connected to the target robot from multiple edge servers based on the target robot identifier; and sending the target feature engineering information to the target edge server.

[0129] For example, a cloud server can be connected to multiple edge servers. When the cloud server needs robot data, it first determines the target robot corresponding to the robot data, and then queries the preset mapping relationship table according to the target robot identifier to determine the target edge server corresponding to the target robot; finally, according to the network address or connection interface corresponding to the target edge server, the target feature engineering information is sent to the target edge server.

[0130] In this embodiment, the cloud server can simultaneously connect to multiple edge servers, enabling distributed computing and processing. This improves overall computing power and enables the cloud to simultaneously process data from multiple edge servers. By connecting to multiple edge servers, the cloud server has greater scalability, can flexibly handle robot swarms of varying sizes and complexities, and can be easily expanded and upgraded based on demand.

[0131] In an exemplary embodiment, in order to more clearly illustrate the robot data processing method provided by the embodiment of the present application, the robot data processing method is specifically described below using a specific embodiment. As shown in Figure 6, in one embodiment, a schematic diagram of the actual execution process of a robot data processing method includes: the user determines the lean production modeling requirements based on the industrial process, and then models and obtains multiple feature engineering models. Then, based on the target feature engineering to be performed and the corresponding business type, the cloud server and the edge server jointly execute a robot data processing method to obtain the final feature engineering results as lean production data support to achieve lean production.

[0132] Furthermore, as shown in Figure 7, the types of information included in robot data in one embodiment are shown. Robot data includes internal data and external data. Internal data includes robot start / stop data, robot axis angles, robot cycle energy consumption, robot axis data, robot alarm data, and other internal data. Robot axis data includes xyz angle data, payload data, axis identifier, current data, and voltage data. External data includes vibration data, temperature data, current data, voltage data, power data, robot spatial axis data, and other external data. Robot spatial axis data includes actual xyz coordinates, projection data, and multimodal data.

[0133] The target data source specifically refers to the data types shown in Figure 7. For example, for feature engineering related to energy consumption, the required data includes internal data such as robot cycle energy consumption and robot axis data, and external data such as current, voltage, power, and actual xyz coordinates. For feature engineering related to motion analysis, the required data includes internal data such as robot axis angles and robot axis data, and external data such as actual xyz coordinates and projection data.

[0134] As shown in FIG8 , the present application also provides a robot data processing system, including a device side, an edge server, a cloud server, and a business display side, wherein:

[0135] The device side contains multiple robots.

[0136] The edge server includes an MQTT (Message Queuing Telemetry Transport) message server, an edge streaming processing engine, and a database. The MQTT message server can use EMQ X Server, the edge streaming processing engine can use ekuiper, and the database can use the time series database InfluxDB.

[0137] The cloud server includes a stream processing platform, a database, a workflow task scheduling system, and a model library. The stream processing platform can utilize Kafka (a high-throughput distributed publish-subscribe messaging system); the database can utilize Clickhouse (a columnar database with an MPP (Massively Parallel Processor) architecture for online analytical processing (OLAP), capable of generating real-time analytical data reports using SQL queries); and the workflow task scheduling system can utilize Apache Dolphin Scheduler (an open-source, distributed, scalable, and visual DAG (Directed Acyclic Graph) workflow task scheduling system).

[0138] For example, ① the robot serves as the MQTT data source in the edge server. ② Then, ekuiper can set different data source parsing rules based on different data source inputs, ultimately parsing different types of data sinks. When filtering data based on preset data filtering conditions, ekuiper can use the where command. Ekuiper can also define sliding windows to perform data processing to obtain target robot data that meets the preset data processing objectives. ③ The Kafka message queue, due to its strong scalability and extreme data processing performance, is often used as a core data transmission component in cloud computing. Kafka can be used to connect data from multiple edge servers. ④ ClickHouse has two functions: first, it acts as a consumer to consume Kafka data. As a component of cloud computing big data, ClickHouse is highly compatible with Kafka. Second, it provides OLAP functionality, enabling real-time online analysis using SQL and providing relatively fast cloud data processing capabilities. ⑤ The Dolphin Scheduler is primarily used for ETL (Extract-Transform-Load) operations. Deeply integrated with ClickHouse during cloud computing, it retrieves core Python code and data source configuration based on specific business needs. Using the cloud-based robot data, it ultimately calculates the models required for its business. This allows for the gradual construction of a library of robot-based algorithm models (including motion models, process models, diagnostic models, mechanism models, and energy consumption models), providing a path for the subsequent expansion of robot-related businesses, the construction of a digital twin system for robots, and the establishment of a digital-based lean production system.

[0139] In this embodiment, a technical solution system for robot data processing is jointly constructed by combining edge computing technology, cloud computing technology and edge-cloud collaborative technology. On the edge server side, edge streaming processing is combined with the edge-side time series database to achieve data volume degradation and improve the stability of the overall data; and combined with cloud computing ETL technology and OLAP database technology, fast real-time calculation of data and real-time output of derived report data are achieved. At the same time, it is also possible to gradually build a robot-based algorithm model library (motion model, process model, energy consumption model, etc.), which provides a foundation for the subsequent expansion of robot-related businesses, the construction of a digital twin system for robots, and the construction of a lean production system based on digitalization.

[0140] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0141] Based on the same inventive concept, the present application also provides two robot data processing devices for implementing the aforementioned robot data processing method. The solutions provided by these devices are similar to those described in the aforementioned method. Therefore, the specific limitations of one or more robot data processing device embodiments provided below can be found in the above-described limitations of the robot data processing method and will not be further elaborated here.

[0142] In an exemplary embodiment, as shown in FIG9 , a robot data processing device is provided, comprising: a source determination module 901 , a data acquisition module 902 , a processing determination module 903 , and a data processing module 904 , wherein:

[0143] The source determination module 901 is used to determine the source of the robot's target data based on the target feature engineering information sent by the cloud server;

[0144] The data acquisition module 902 is used to receive the to-be-processed transmission data that matches the target feature engineering information from the target data source;

[0145] The processing determination module 903 is used to determine the preset data screening conditions and the preset data processing targets according to the target feature engineering information;

[0146] The data processing module 904 is used to obtain the target robot data to be transmitted to the cloud server according to the preset data screening conditions, the preset data processing targets and the transmission data to be processed.

[0147] In one embodiment, the above-mentioned data processing module 904 is also used to determine the target data type based on preset data screening conditions; filter out target transmission data corresponding to the target data type from the transmission data to be processed; and obtain target robot data transmitted to the cloud server based on the preset data processing target and target transmission data.

[0148] In one embodiment, the data processing module 904 is further configured to determine a target data processing method based on a preset data processing target; and process the target transmission data using the target data processing method to obtain target robot data transmitted to the cloud server.

[0149] In one embodiment, the target transmission data includes streaming data; the above-mentioned data processing module 904 is also used to use a sliding window to sequentially intercept each sub-target transmission data from the target transmission data; use a target data processing method to process each sub-target transmission data to obtain candidate target robot data; from the candidate target robot data, filter out the candidate target robot data with the highest matching degree with the preset data processing target as the target robot data.

[0150] In one embodiment, the robot data processing device further includes a robot determination module for receiving a target robot identification and target feature engineering information sent by a cloud server; and determining a target robot that matches the target robot identification from a plurality of robots.

[0151] In one embodiment, the source determination module 901 is further configured to determine the target data source of the target robot based on target feature engineering information.

[0152] In an exemplary embodiment, as shown in FIG10 , another robot data processing device is provided, comprising: an information sending module 1001 and a data receiving module 1002 , wherein:

[0153] The information sending module 1001 is used to send target feature engineering information to the edge server; the edge server is used to determine the target data source of the robot based on the target feature engineering information sent by the cloud server; receive the to-be-processed transmission data that matches the target feature engineering information from the target data source; determine the preset data screening conditions and the preset data processing target based on the target feature engineering information; and obtain the target robot data transmitted to the cloud server based on the preset data screening conditions, the preset data processing target, and the to-be-processed transmission data;

[0154] The data receiving module 1002 is used to receive the target robot data transmitted by the edge server.

[0155] In one embodiment, the above-mentioned information sending module 1001 is also used to determine the corresponding target robot identifier based on the target feature engineering information; determine the target edge server connected to the target robot from multiple edge servers based on the target robot identifier; and send the target feature engineering information to the target edge server.

[0156] Each module in the aforementioned robot data processing device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0157] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 11. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store target feature engineering information data. The I / O interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, a robot data processing method is implemented.

[0158] Those skilled in the art will understand that the structure shown in FIG11 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0160] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0161] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0162] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0163] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0164] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0165] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A robot data processing method, characterized in that: Applied to an edge server, the method includes: Determine the robot's target data source based on the target feature engineering information sent by the cloud server; Receiving, from the target data source, transmission data to be processed that matches the target feature engineering information; Determining preset data screening conditions and preset data processing targets based on the target feature engineering information; According to the preset data screening condition, the preset data processing target and the transmission data to be processed, the target robot data transmitted to the cloud server is obtained.

2. The method according to claim 1, characterized in that The step of obtaining target robot data transmitted to the cloud server according to the preset data screening condition, the preset data processing target, and the to-be-processed transmission data includes: Determining the target data type according to the preset data screening condition; Filtering target transmission data corresponding to the target data type from the transmission data to be processed; According to the preset data processing target and the target transmission data, the target robot data transmitted to the cloud server is obtained.

3. The method according to claim 2, characterized in that According to the preset data processing target and the target transmission data, the target robot data transmitted to the cloud server is obtained, including: Determining a target data processing method according to the preset data processing target; The target data processing method is used to process the target transmission data to obtain target robot data that is transmitted to the cloud server.

4. The method according to claim 3, characterized in that The target transmission data includes streaming data; The target data processing method is used to process the target transmission data to obtain target robot data transmitted to the cloud server, including: Adopting a sliding window to sequentially intercept and obtain transmission data of each sub-target from the target transmission data; Using the target data processing method, data processing is performed on the data transmitted by each sub-target to obtain candidate target robot data; From the candidate target robot data, the candidate target robot data having the highest matching degree with the preset data processing target is screened out as the target robot data.

5. The method according to claim 1, wherein Before determining the robot's target data source based on the target feature engineering information sent by the cloud server, it also includes: Receiving the target robot identification and target feature engineering information sent by the cloud server; Determine a target robot that matches the target robot identifier from multiple robots; Determining the target data source of the robot based on the target feature engineering information sent by the cloud server includes: The target data source of the target robot is determined based on the target feature engineering information.

6. A robot data processing method, characterized in that: Applied to a cloud server, the method includes: Sending target feature engineering information to an edge server; the edge server is used to determine a target data source of the robot based on the target feature engineering information sent by the cloud server; receiving to-be-processed transmission data that matches the target feature engineering information from the target data source; determining a preset data screening condition and a preset data processing target based on the target feature engineering information; obtaining target robot data transmitted to the cloud server based on the preset data screening condition, the preset data processing target, and the to-be-processed transmission data; Receive target robot data transmitted by the edge server.

7. The method according to claim 6, characterized in that The sending of target feature engineering information to the edge server includes: Determine the corresponding target robot identification according to the target feature engineering information; Determining, according to the target robot identifier, a target edge server connected to the target robot from a plurality of edge servers; Send the target feature engineering information to the target edge server.

8. A robot data processing device, characterized in that: Applied to an edge server, the device includes: The source determination module is used to determine the source of the robot's target data based on the target feature engineering information sent by the cloud server; A data acquisition module, configured to receive, from the target data source, the to-be-processed transmission data that matches the target feature engineering information; A processing determination module, configured to determine preset data screening conditions and preset data processing targets based on the target feature engineering information; The data processing module is used to obtain the target robot data transmitted to the cloud server according to the preset data screening condition, the preset data processing target and the transmission data to be processed.

9. A robot data processing device, characterized in that: Applied to a cloud server, the device includes: An information sending module is configured to send target feature engineering information to an edge server; the edge server is configured to determine a target data source for the robot based on the target feature engineering information sent by the cloud server; receive, from the target data source, pending transmission data that matches the target feature engineering information; determine preset data screening conditions and preset data processing targets based on the target feature engineering information; and obtain target robot data transmitted to the cloud server based on the preset data screening conditions, the preset data processing targets, and the pending transmission data; The data receiving module is used to receive the target robot data transmitted by the edge server.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images