A robot utilization optimization suggestion generation system

Abstract

The present invention discloses a robot utilization optimization suggestion generation system. It includes a data acquisition module for collecting usage data of different types of robots; a data analysis engine for calculating the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of robot automation, and the depth of robot-human collaboration based on the usage data; and calculating the robot utilization index through a weighted algorithm; and also for analyzing and processing the robot utilization index according to the business needs of the enterprise and the development trend of robot technology, and generating robot utilization optimization suggestions; a user interface for displaying the robot utilization index and robot utilization optimization suggestions. The scheme of the present invention provides a comprehensive evaluation and optimization suggestions for the automation level of an enterprise through real-time monitoring and analysis of the use of robots in the enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent robots, and in particular to a robot utilization optimization suggestion generation system. Background Art

[0002] With the rapid development of Industry 4.0 and intelligent manufacturing technology, robots are increasingly being used in enterprises. More and more companies are beginning to deploy various types of robots to improve production efficiency, reduce costs and improve work quality.

[0003] However, after deploying robots, many companies find it difficult to fully understand the extent of robot application in business processes and the benefits they bring, and lack effective tools to measure robot utilization. Current measurement methods are usually limited to the number of robots, ignoring the depth of application and impact of robots in different processes. In this case, companies cannot make scientific decisions on the robot automation process, nor can they make targeted optimization adjustments. Therefore, it is particularly important to develop a system that can systematically and quantitatively evaluate the utilization of enterprise robots to help companies more scientifically evaluate the degree of automation and input-output benefits. Summary of the invention

[0004] In order to solve the technical problem that the existing enterprise measurement method of robot utilization ignores the application depth and impact of robots in different processes, an embodiment of the present invention provides a robot utilization optimization suggestion generation system.

[0005] The technical solution of the embodiment of the present invention is achieved as follows:

[0006] The embodiment of the present invention provides a robot utilization optimization suggestion generation system, the robot utilization optimization suggestion generation system comprising: a data acquisition module, used to collect usage data of different types of robots from business processes of multiple robot platforms; the robot types include industrial robots, service robots and software robots; the usage data include robot types and quantities, robot working hours, task completion status, task execution success rate and function execution frequency; a data analysis engine, used to calculate the total number and types of robots, the functional diversity of robots, the complexity of robot execution tasks, the degree of robot automation, and the depth of robot and human collaboration according to the usage data; and using the total number and types of robots, the functional diversity of robots, the complexity of robot execution tasks, the degree of robot automation, and the depth of robot and human collaboration, calculate the robot utilization index through a weighted algorithm; and further used to analyze and process the robot utilization index according to the business needs of the enterprise and the development trend of robot technology, and generate robot utilization optimization suggestions; the robot utilization optimization suggestions include increasing the deployment of a first type of robot, adjusting the automation degree of a first process and improving the complexity of robot tasks; a user interface, used to display the robot utilization index and the robot utilization optimization suggestions.

[0007] In one embodiment, the data acquisition module includes an interface component, a data collector, a preprocessing module, a data storage module and a data transmission module: the interface component supports multiple communication protocols for connecting and communicating with various data sources, and the communication protocols include API communication protocol, MQTT communication protocol and OPC-UA communication protocol; the data sources include robot control systems, enterprise business management systems and sensor networks; the data collector is used to extract data information from the data stream received by the interface component, and the data information includes robot type, task completion status, working time, task execution success rate and function execution frequency; the preprocessing module is used to perform preliminary processing on the data, including data cleaning, filtering and formatting; the data storage module uses relational database or big data storage technology to temporarily store and cache the collected data; the data transmission module is used to use a transmission protocol to transmit the preliminarily processed data in batches or in real time to the utilization index calculation module; the transmission protocol includes HTTP transmission protocol, WebSocket transmission protocol and gRPC transmission protocol.

[0008] In one embodiment, the interface component is specifically used to obtain operational data of the robot during operation from the robot control system, including status, execution commands, and task progress; obtain background data from the enterprise business management system, including task scheduling information, production line task arrangements, and resource allocation; and obtain environmental data and operational data from the sensor network.

[0009] In one embodiment, the data collector is specifically used to mark and classify different types of robots to determine the type of robot; extract the progress, success rate and completion time of each robot in completing the task as the task completion status; extract the actual working time of the robot in different tasks, including the start and end time of the task execution, as the working time; obtain the success rate of the robot in performing the task, including whether the task is completed as required, whether interruptions or failures occur, as the success rate of task execution; obtain the frequency of use of the robot's grasping, carrying and detection functions during work as the function execution frequency.

[0010] In one embodiment, the preprocessing module is specifically used to use interpolation methods to fill missing data or delete unreasonable data for null values ​​or abnormal values ​​appearing in sensor data; filter out useless idle time data in task sections that are inactive for a long time; unify timestamps in different formats, or convert and standardize data in different units.

[0011] In one embodiment, the data analysis engine includes a data classifier, a penetration calculation module and an algorithm module: the data classifier is used to automatically assign data to corresponding analysis paths according to the source of the data, robot type, function, and task complexity, so as to classify different types of data; the source of the data includes robot control systems, sensor networks, and business management systems; the robot types include collaborative robots, assembly robots, and transport robots; the functions include grasping, detection, and handling; the task complexity includes multi-step assembly tasks and simple handling; the penetration calculation module is used to calculate the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of robot automation, and the depth of collaboration between robots and humans; and the robot utilization index is calculated through a weighted algorithm using the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of robot automation, and the depth of collaboration between robots and humans; the algorithm module is used to provide a variety of algorithm libraries that support utilization calculations, including weighted average algorithms, fuzzy logic algorithms, and machine learning models.

[0012] In one embodiment, the penetration calculation module is specifically used to calculate the total number and types of robots using the following indicators:

[0013] (1) Number of robots: the total number of robots in the enterprise;

[0014] (2) Robot type diversity: the number of different types of robots;

[0015] (3) Scenario coverage: the number of business scenarios covered by the robot;

[0016] (4) Robot density per scenario: the number of robots in each business scenario;

[0017] The following indicators are used to calculate task complexity:

[0018] (1) Task complexity scoring: Tasks are divided into simple, medium and complex levels, with corresponding scores. Scores are quantified based on task process steps and decision points.

[0019] (2) Decision logic level: the decision level involved in the robot task, including simple logic, conditional judgment, and machine learning;

[0020] (3) Ability to adapt to dynamic environments: Whether the robot is capable of handling dynamically changing environments, including real-time obstacle avoidance and adaptive path planning;

[0021] (4) Data processing and feedback capability: The robot’s ability to process, analyze data and provide feedback during the task;

[0022] The following indicators were used to calculate functional diversity:

[0023] (1) Number of robot functions: the number of functions performed by the robot, including handling, welding, assembly, and quality inspection;

[0024] (2) Modular function realization rate: the proportion of using different modules or plug-ins to realize multiple functions;

[0025] (3) Function switching flexibility: the efficiency and speed of the robot switching functions in different time periods or scenarios;

[0026] (4) Functional innovation: whether the robot contains innovative functions, including vision-based autonomous detection and intelligent path planning;

[0027] The degree of robot automation is calculated using the following indicators:

[0028] (1) Task automation rate: the ratio of tasks that can be completed fully automatically to the total number of tasks;

[0029] (2) Autonomous learning and optimization capabilities: Can the robot autonomously optimize the workflow through data accumulation, including automatic optimization based on machine learning?

[0030] (3) Autonomous movement and navigation capabilities: The robot's ability to move autonomously, including whether it has navigation, obstacle avoidance, and path planning;

[0031] (4) Automatic fault detection and self-repair capability: The robot's ability to automatically monitor and handle faults, including early warning and self-repair;

[0032] The following indicators are used to calculate the degree of collaboration between robots and humans:

[0033] (1) Proportion of human-robot collaborative tasks: the proportion of tasks completed jointly by humans and robots in the total tasks;

[0034] (2) Human-machine interaction efficiency: the time and interaction frequency required by humans in robot operation or task control;

[0035] (3) Safety and trust: the safety score of the robot or the trust of humans in the robot in a human-robot collaborative environment;

[0036] (4) Collaborative task complexity: the complexity of human-machine collaborative tasks.

[0037] In one embodiment, the data analysis engine also includes an optimization analysis module and a visualization engine module: the optimization analysis module is used to generate optimization suggestions for the enterprise automation process based on the results of utilization calculation by analyzing robot usage data and business needs; the visualization engine module is used to convert the analysis results into a graphical output format, including charts, trend charts and pie charts, so as to present them to users more intuitively.

[0038] In one embodiment, the optimization analysis module is specifically used to recommend increasing the deployment of robots in specific production links, or reducing the use of robots in inefficient tasks; recommending further automation of processes with low automation levels and relying on a large number of manual operations; recommending the introduction of collaborative robots in specific tasks, or replacing old model robots.

[0039] In one embodiment, the user interface includes a data display module, a graphical display module, a historical data query module, an optimization suggestion display module and a report generation module: the data display module is used to display the utilization index, robot usage and the degree of automation of each business process; the graphical display module is used to display the data analysis results in a graphical manner; the historical data query module is used for users to query and compare historical data, analyze the long-term usage of robots and its impact on business processes; the optimization suggestion display module is used to display the optimization suggestions generated by the system; the report generation module is used to generate a detailed report according to user needs, and the report content includes robot utilization analysis, task completion evaluation, and automation optimization suggestions.

[0040] This embodiment has the following beneficial effects:

[0041] This embodiment can automatically collect and analyze data, reducing the burden of manual statistics for enterprises; evaluate robot utilization in multiple dimensions to provide more comprehensive analysis results; provide real-time monitoring and dynamic reporting to help enterprises adjust automation strategies at any time; and provide personalized optimization suggestions to help enterprises improve robot utilization and enhance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the structure of a system for generating robot utilization optimization suggestions according to an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the overall architecture of a robot utilization optimization suggestion generation system according to an embodiment of the present invention;

[0044] Figure 3 The following is a schematic diagram of the working process of the data acquisition module according to an embodiment of the present invention;

[0045] Figure 4 Schematic diagram of the processing flow of the data analysis engine according to an embodiment of the present invention;

[0046] Figure 5 A schematic diagram of a user interface displaying a utilization index according to an embodiment of the present invention;

[0047] Figure 6 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0049] The embodiment of the present invention provides a robot utilization optimization suggestion generation system, such as Figure 1 As shown, the robot utilization optimization suggestion generation system includes:

[0050] The data collection module 100 is used to collect usage data of different types of robots from the business processes of various robot platforms; the robot types include industrial robots, service robots and software robots; the usage data includes robot type and quantity, robot working time, task completion status, task execution success rate and function execution frequency;

[0051] The data analysis engine 200 is used to calculate the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of automation of robots, and the depth of collaboration between robots and humans based on the usage data; and to calculate the robot utilization index by a weighted algorithm using the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of automation of robots, and the depth of collaboration between robots and humans; and to analyze and process the robot utilization index according to the business needs of the enterprise and the development trend of robot technology to generate robot utilization optimization suggestions; the robot utilization optimization suggestions include increasing the deployment of the first type of robots, adjusting the degree of automation of the first process, and improving the complexity of robot tasks;

[0052] The user interface 300 is used to display the robot utilization index and the robot utilization optimization suggestion.

[0053] This embodiment relates to a system for measuring the utilization rate of enterprise robots. The system collects data on various types of robots used within the enterprise, evaluates the degree of application of robots in different business processes, and provides a comprehensive utilization index. The index is calculated based on multiple dimensions, including the number of robots, types of functions, task complexity, degree of automation, depth of collaboration with humans, etc. The system uses a data acquisition module, a utilization index calculation module, an optimization suggestion generation module, and a user interface, which can track and report the use of robots in real time, and provide optimization suggestions to improve the utilization rate of robots within the enterprise. Through this system, enterprises can fully understand the status of their automation process and provide a decision-making basis for further robot deployment.

[0054] Below, this solution will be described in detail based on a specific application embodiment.

[0055] The embodiment of the present invention provides a system for measuring the utilization rate of enterprise robots. By collecting data from different production processes of the enterprise and combining multi-dimensional information such as the application frequency, coverage, and performance improvement of the robots, a comprehensive penetration evaluation system is constructed. The system can not only analyze the existing robot application situation, but also provide guidance for optimizing the deployment of future robots. Figure 2 , the system of this embodiment specifically includes the following modules:

[0056] Data collection module 100: Responsible for collecting data related to robot operation and performance from various data sources within the enterprise (such as robot control systems, sensors, business management systems, etc.). This module ensures the effective collection, processing and transmission of data to support the subsequent data analysis process. It is responsible for real-time collection of relevant data in various production processes within the enterprise, including robot type and quantity, robot working hours, task completion status, task execution success rate, function execution frequency, etc.

[0057] Data processing module 200: Process the collected data and standardize the collected data, including noise removal, data cleaning and other operations. Through data analysis algorithms, key indicators related to robot applications are extracted, such as task complexity, functional diversity, robot automation level, robot-human collaboration level, etc., and a penetration index is generated. Through the collaborative work of different functional modules, the data analysis engine can provide enterprises with in-depth robot penetration assessment, optimization suggestions and intuitive data display, helping enterprises improve robot usage efficiency and optimize automation processes.

[0058] User interface 300: It is an interactive window between the system and the user, used to display the robot penetration and system analysis results, and provide optimization suggestions. Through this interface, the user can clearly and intuitively understand the application status of the robot and the degree of automation of the business process, and adjust the automation strategy.

[0059] (I) Data acquisition module 100

[0060] The data acquisition module 100 is responsible for collecting robot-related data from different sources such as the robot control system, sensors, and business management system within the enterprise. Its main components include:

[0061] Interface component 110: used to connect and communicate with various data sources (such as robot control systems, enterprise business management systems, sensor networks, etc.). This component supports multiple communication protocols, such as API, MQTT, OPC-UA, etc., to ensure that the system can seamlessly connect with different types of robots and data sources.

[0062] Data collector 120: responsible for extracting relevant information from the data stream received by the interface component, covering specific data such as robot type, task completion status, working time, task execution success rate, function execution frequency, etc.

[0063] Preprocessing module 130: Before sending the data to the analysis engine, the data is preliminarily processed, including data cleaning, filtering and formatting. It can remove noise data, process missing values, and correct erroneous information to ensure the quality of input data.

[0064] Data storage module 140: used to temporarily store and cache the collected data to ensure that the data is available during the analysis process. The data storage module can use a relational database or big data storage technology to ensure that it can process a large amount of real-time data.

[0065] Data transmission module 150: responsible for transmitting the processed data to the data analysis engine 200 to ensure the timeliness and integrity of the data. The transmission module adopts an efficient transmission protocol and supports batch data transmission and real-time data streaming.

[0066] 2. Data Analysis Engine 200

[0067] The data analysis engine 200 is the core part of the system, responsible for in-depth analysis of the collected data and generating the robot penetration index. Its main components include:

[0068] Data classifier 210: classifies different types of data. According to the data source, robot type, function, task complexity and other dimensions, the data is automatically assigned to the corresponding analysis path to ensure the accuracy of subsequent analysis.

[0069] Penetration calculation module 220: This module is one of the core functions of the analysis engine and is responsible for calculating the enterprise robot penetration index. The calculation process takes into account multiple dimensions, including the total number of robots, task complexity, functional diversity, robot automation level, robot-human collaboration level, etc. The calculation results are output in the form of a weighted algorithm, and the weights can be customized according to the needs of the enterprise.

[0070] Algorithm module 230: provides a variety of algorithm libraries that support penetration calculations, including but not limited to weighted average algorithms, fuzzy logic algorithms, machine learning models, etc., to help more intelligently evaluate the performance of robots in different business processes.

[0071] Optimization analysis module 240: Based on the results of the penetration calculation, it generates optimization suggestions for the enterprise automation process. This module analyzes the robot usage data and business needs and proposes specific suggestions for improving robot utilization and process efficiency.

[0072] Visualization engine 250: Converts the analysis results into graphical output formats, including charts, trend charts, pie charts, etc., so as to present them to users more intuitively. The visualization engine can be seamlessly integrated with the user interface 300 to achieve dynamic data display.

[0073] (III) User Interface 300

[0074] The user interface 300 is a window for the system to interact with the user. The user can view the robot penetration index, analysis results, and optimization suggestions proposed by the system through the interface. The user interface consists of:

[0075] Data display module 310: used to display the penetration index, robot usage and the degree of automation of each business process. This module supports data screening and filtering, and users can customize the data viewing according to time, robot type, business process and other conditions.

[0076] Graphical display module 320: Displays the data analysis results in a graphical form. Users can view trend graphs of robot usage, comparison graphs of penetration of different types of robots, and automation degree graphs of various business processes, helping enterprises to intuitively understand the current situation.

[0077] Historical data query module 330: allows users to query and compare historical data to analyze the long-term use of robots and their impact on business processes. Users can view the changes in robot penetration over different time periods to evaluate the long-term effectiveness of automation strategies.

[0078] Optimization suggestion display module 340: Users can view the optimization suggestions generated by the system through this module. The suggestions include increasing the deployment of certain types of robots, adjusting the automation level of certain processes, increasing the complexity of robot tasks, etc. Users can adjust their automation strategies based on these suggestions.

[0079] Report generation module 350: The system can generate detailed reports based on user needs, including robot penetration analysis, task completion assessment, and automation optimization suggestions. The reports can be exported in multiple formats such as PDF and Excel for internal sharing and decision-making reference.

[0080] See also Figure 3 In the robot penetration measurement system of this embodiment, the data acquisition module 100 is one of the core modules of the system, responsible for collecting data related to robot operation and performance from various data sources within the enterprise (such as robot control systems, sensors, business management systems, etc.). This module ensures the effective collection, processing and transmission of data to support the subsequent data analysis process. The following is a detailed description of each component:

[0081] 1. Interface component 110

[0082] The interface component 110 is the core connection module of the data acquisition module, ensuring that the system can seamlessly connect with different data sources within the enterprise and exchange data. Its functions cover various types of data sources and communication protocols:

[0083] Multi-source connection: The interface component collects real-time data of robot operation by adapting to different data sources. These data sources include:

[0084] a. Robot control system: The interface component is connected to the company's robot control system to obtain various operation data during the robot operation, such as status, execution commands, task progress, etc.

[0085] b. Enterprise business management system (ERP, MES, etc.): By connecting to the enterprise's business management system, the interface component can obtain task scheduling information, production line task arrangements, and resource allocation, providing background data for subsequent analysis.

[0086] c. Sensor network: Collects environmental data and operational data from various sensors (such as pressure, temperature, and position sensors) installed on the production line or robot to provide a basis for analyzing the environmental conditions in which the robot operates.

[0087] Protocol support:

[0088] a. API interface: Supports data communication based on API (application programming interface), allowing data exchange with control systems on the cloud or local servers. The API interface has high compatibility and can support requests and responses in different formats (such as JSON, XML).

[0089] b.MQTT (Message Queue Telemetry Transport Protocol): MQTT is a lightweight communication protocol suitable for low-bandwidth, high-latency scenarios, especially for data exchange between Internet of Things (IoT) devices. It enables efficient message transmission between robots and other devices.

[0090] c.OPC-UA (Open Platform Communications Unified Architecture): OPC-UA is widely used in the field of industrial automation and supports cross-platform communication protocols. It not only transmits data, but also provides complex data models for integration with a variety of industrial equipment and control systems. Through OPC-UA, the system can seamlessly connect with a wide range of industrial robots.

[0091] 2. Data Collector 120

[0092] The data collector 120 is responsible for extracting key information related to the robot from the data stream obtained by the interface component to ensure the accuracy and comprehensiveness of data collection.

[0093] Multi-type data extraction: The data collector can extract multi-dimensional data related to the robot's work, covering the following aspects:

[0094] a. Robot types: Different types of robots (such as collaborative robots, mobile robots, industrial robots, etc.) have different task execution capabilities. The data collector will mark and classify each type of robot for subsequent analysis of different robot types.

[0095] b. Task completion status: including the progress, success rate and completion time of each robot in completing the task. This data can help the system analyze the performance of robots in different tasks and provide a basis for penetration calculation.

[0096] c. Working time: Collect the actual working time of the robot in different tasks, including the start and end time of the task execution. This is crucial for evaluating the efficiency of the robot and the rationality of task allocation.

[0097] d. Task execution success rate: records the success rate of the robot in executing tasks, including whether the task is completed as required, whether there are interruptions or failures, etc. This data can be used to analyze the performance of the robot and its penetration performance.

[0098] e. Function execution frequency: Extract the usage frequency of each function (such as grasping, handling, detection, etc.) of the robot during work to provide data support for subsequent functional analysis.

[0099] 3. Preprocessing module 130

[0100] The pre-processing module 130 performs preliminary processing on the raw data before passing the data to the analysis engine to ensure the accuracy and consistency of the data. The main responsibility of this module is to clean, filter and format the data to ensure high-quality data input.

[0101] Data cleaning: The preprocessing module can identify and process invalid and missing values ​​in the data. For example, for null values ​​or abnormal values ​​in sensor data, the system will use interpolation methods to fill in missing data or delete unreasonable data.

[0102] Data filtering: The module removes irrelevant or noisy data to ensure that the dataset retains only the part that is useful for analysis. For example, in a task segment with long periods of inactivity, the system may filter out useless idle time data.

[0103] Data formatting: Converting data from different data sources into a unified format to make subsequent analysis and storage more efficient. For example, data formatting may involve unifying timestamps in different formats, or converting and standardizing data in different units.

[0104] 4. Data storage module 140

[0105] The data storage module 140 is used to temporarily store and cache various types of collected data to ensure the availability and integrity of the data during the analysis process. This module supports an efficient storage and retrieval mechanism and can process large-scale, real-time robot operation data.

[0106] Relational database: If the data is highly structured (such as task records, robot operation status, etc.), the system can use a relational database (such as MySQL, PostgreSQL) to store it. This database stores data in a tabular manner and supports complex query operations and data relationship management.

[0107] Big data storage technology: For large-scale, semi-structured or unstructured data (such as real-time sensor data streams, log files, etc.), the system can use big data storage technology (such as Hadoop, NoSQL database, etc.). This type of technology has strong scalability, can handle large-scale, real-time data streams and support fast data retrieval.

[0108] Data caching mechanism: To improve data transmission efficiency, the storage module supports a data caching mechanism that can temporarily save frequently accessed data to avoid repeated reading from the database, thereby improving system response speed.

[0109] 5. Data transmission module 150

[0110] The data transmission module 150 is responsible for transmitting the pre-processed high-quality data from the data acquisition module to the data analysis engine 200, ensuring that the data is delivered in a timely and complete manner during the analysis process.

[0111] a. Efficient transmission protocol: In order to ensure the timeliness of data, the transmission module adopts efficient data transmission protocols (such as HTTP, WebSocket, gRPC, etc.), which can achieve low-latency real-time data transmission and adapt to different network environments.

[0112] b. Batch transmission and real-time data streaming: The system supports two modes of batch data transmission and real-time data streaming transmission according to specific needs. In some scenarios, the system can batch transmit task data within a period of time to reduce the transmission frequency. For time-sensitive tasks, the system supports real-time data streaming to ensure that the execution status of each task can be transmitted to the analysis engine as soon as possible for real-time calculation and feedback.

[0113] c. Data integrity and verification: The transmission module has a built-in data integrity verification mechanism to ensure that data will not be lost or damaged during transmission. Through verification and technology (such as CRC verification), the system can detect and correct errors in transmission to ensure that every piece of data received by the analysis engine is complete and accurate.

[0114] join Figure 4The data analysis engine 200 processes the collected data and generates a penetration index. Through the collaborative work of different functional modules, the data analysis engine 200 can provide enterprises with in-depth robot penetration assessment, optimization suggestions and intuitive data display, helping enterprises improve robot usage efficiency and optimize automation processes. The main components are as follows:

[0115] 1. Data Classifier 210

[0116] Data Classifier 210: Responsible for classifying the data collected from different sources and robots into categories so that subsequent analysis can be more efficient and accurate. This module adopts a multi-dimensional classification method to ensure that the data can be processed in an orderly manner according to business needs.

[0117] Multi-dimensional data classification: Data classifiers classify data based on multiple dimensions, ensuring that the analysis process is optimized for the specific requirements of each dimension:

[0118] a. Data source: The system collects data from multiple data sources (such as robot control systems, sensor networks, business management systems, etc.). Data from different sources may have different formats and semantics, so the classifier first classifies the data by source.

[0119] b. Robot type: Different types of robots (such as collaborative robots, assembly robots, transport robots, etc.) have different functions and tasks. The classifier classifies the data according to the robot type so that the specific functions and operational performance of each robot can be evaluated in subsequent analysis.

[0120] c. Task complexity: The classifier divides the data into different categories based on the difficulty and complexity of the task. For example, a high-complexity task may include a multi-step assembly task, while a low-complexity task may be just a simple handling task. Classifying the complexity of tasks helps to accurately evaluate the performance of the robot in different tasks.

[0121] d. Functional dimension: The system will classify the data according to the specific functions of the robot (such as grasping, detection, handling, etc.) in order to evaluate the frequency of use and execution efficiency of each function.

[0122] Dynamic data path allocation: The data classifier can dynamically allocate data to the corresponding analysis path based on the classification results. Each analysis path is optimized according to the characteristics of the classified data to ensure the accuracy and efficiency of the analysis. This modular data allocation mechanism makes the system highly flexible when processing data of different dimensions.

[0123] 2. Permeability calculation module 220

[0124] The penetration calculation module 220 is the core part of the analysis engine, responsible for comprehensively calculating the robot penetration index of the enterprise based on multiple dimensions. This module combines various parameters and uses a weighted algorithm to generate a comprehensive index to help enterprises intuitively understand the depth and breadth of their robot use.

[0125] Multi-dimensional penetration calculation: Penetration calculation is not just a simple data summary, but an in-depth analysis based on multiple dimensions, taking into account the following factors:

[0126] a. Total number and types of robots: The total number and types of robots used in an enterprise is a basic reference indicator of penetration, indicating the coverage of robot technology within the enterprise. Specifically, the following indicators may be included: ① Number of robots: The total number of robots in the enterprise, divided into types (such as industrial robots, collaborative robots, mobile robots, etc.). ② Diversity of robot types: The number of types of robots of different types, the more the higher the breadth of application. ③ Scenario coverage: The number of business scenarios covered by robot use (for example, production, logistics, quality inspection, etc.), which can be used as a reflection of breadth. ④ Density of robots per scenario: The number of robots in each business scenario, showing the depth of application.

[0127] b. Task complexity: Task complexity reflects the adaptability of robots in performing different tasks. The more complex tasks there are, the more companies rely on robots to complete more complex tasks, and the higher the penetration rate. Specifically, the following indicators may be included: ① Task complexity score: Tasks are divided into simple, medium and complex levels, corresponding to different scores, which can be quantified according to task process steps, decision points, etc. ② Decision logic level: The decision level contained in the robot task (such as simple logic, conditional judgment, machine learning, etc.) reflects the difficulty of the task. ③ Environmental dynamic adaptability: Whether the robot has the ability to handle dynamically changing environments (such as real-time obstacle avoidance, adaptive path planning, etc.). ④ Data processing and feedback capability: The robot's ability to process, analyze data and provide feedback during the task reflects the complexity of intelligence.

[0128] c. Functional diversity: If the robots in an enterprise can perform multiple functions and the functions are used frequently, it means that the enterprise relies heavily on robots in many aspects and has a higher penetration rate. Specifically, the following indicators may be included: ① Number of robot functions: the number of types of functions that the robot can perform (such as handling, welding, assembly, quality inspection, etc.). ② Modular function realization rate: the proportion of using different modules or plug-ins to realize multiple functions, representing functional scalability. ③ Function switching flexibility: the efficiency and speed of the robot switching functions in different time periods or scenarios (such as the time required, labor costs, etc.). ④ Functional innovation: whether the robot contains innovative functions (such as vision-based autonomous detection, intelligent path planning, etc.).

[0129] d. Robot automation level: refers to the ability of the robot system to complete tasks without human operation. The less the robot relies on manpower to complete the work, the higher the enterprise robot penetration. Specifically, the following indicators may be included: ① Task automation rate: the proportion of tasks that can be completed completely automatically to the total tasks. The higher the automation rate, the deeper the enterprise relies on robots to perform tasks. ② Autonomous learning and optimization capabilities: whether the robot can autonomously optimize the workflow through data accumulation (such as automatic optimization based on machine learning). ③ Autonomous movement and navigation capabilities: the robot's ability to move autonomously, whether it has navigation, obstacle avoidance, path planning, etc. ④ Automatic fault detection and self-repair capabilities: the robot's ability to automatically monitor and handle faults (such as early warning, self-repair).

[0130] e. The degree of collaboration between robots and humans: The collaboration between robots and humans is an important dimension in penetration assessment. This module analyzes the role of robots in collaborative work with humans, the proportion of work, and the efficiency of collaboration, and measures the depth of automation. Specifically, the following indicators may be included: ① The proportion of human-machine collaborative tasks: The proportion of tasks completed by humans and robots together in the total tasks, reflecting the depth of collaboration. ② Human-machine interaction efficiency: The time and frequency of interaction required by humans in robot operation or task control. Higher efficiency indicates seamless collaboration. ③ Safety and trust: The safety score of robots in human-machine collaborative environments or the degree of trust people have in robots (which can be evaluated through employee feedback or accident records, etc.). ④ Complexity of collaborative tasks: The complexity of human-machine collaborative tasks. If advanced human-machine interaction is required, the collaboration requirements are higher.

[0131] Weighted algorithm: The penetration calculation module uses a weighted algorithm to sum up the values ​​of the above multiple dimensions according to the weights to obtain the final penetration index. Enterprises can customize the weight of each dimension according to actual needs, thereby adjusting the focus of the calculation results. For example, some companies may pay more attention to task complexity, while others may pay more attention to the total number of robots or functional diversity.

[0132] 3. Algorithm module 230

[0133] The algorithm module 230 provides multiple algorithm support to help the system calculate robot penetration in a diversified way and intelligently evaluate the performance of robots in the enterprise automation process. This module provides a rich algorithm library to ensure the flexibility and accuracy of calculations.

[0134] a. Weighted average algorithm: This is the most basic algorithm, which is used to combine data from various dimensions according to weights to generate a penetration index. This algorithm is simple and intuitive, and is suitable for most application scenarios. Enterprises can adjust the weights of each indicator according to their own needs or actual application scenarios, so as to flexibly customize a robot application index that suits their own situation.

[0135] The application steps are as follows:

[0136] ① Indicator weight allocation: According to the importance that enterprises attach to different dimensions of robots, weights are set for each detailed indicator. For example, if the type of robots is more important to the enterprise, the weights of the number of robots and the diversity of robot types can be higher.

[0137] ② Calculate individual scores: Each detailed indicator is scored based on the company's current application data, and the score range can be standardized to 0-100 points.

[0138] ③ Weighted calculation of partial scores: Multiply the detailed indicator scores of each part by the corresponding weights, calculate the weighted sum, and get the score of each part.

[0139] ④ Calculate the total score: Summarize the scores of the five parts with appropriate weights into the final comprehensive index. The comprehensive index formula can be expressed as:

[0140] Comprehensive index = w1 S1+w2 S2+w3 S3+w4 S4+wi Si

[0141] Among them, Si is the score of each part and wi is the corresponding weight.

[0142] b. Fuzzy logic algorithm: Fuzzy logic algorithm is suitable for processing data with uncertainty and fuzzy boundaries. In actual operations, enterprises may not be able to accurately define the complexity of certain tasks or the ratio of robot-human collaboration. Fuzzy logic algorithm can handle these uncertain data more flexibly and generate a more adaptive penetration index by introducing fuzzy set theory. In the evaluation of the depth and breadth of robot use, the data of some indicators may be unclear or subjective, such as "task complexity score" or "human-computer interaction efficiency". Fuzzy logic algorithm can quantify these fuzzy indicators. The application steps are as follows:

[0143] ① Establish fuzzy sets: define the fuzzy sets of each fuzzy indicator. For example, the task complexity score can be divided into three fuzzy sets: "simple", "medium" and "complex".

[0144] ② Set the membership function: Define the membership function of each fuzzy set to convert qualitative data into quantitative data. For example, set the membership of different scoring segments to map the scores of "complex" tasks to high scores.

[0145] ③ Fuzzy reasoning: Use fuzzy rules to reason about fuzzy indicators. For example, if the task complexity score is "complex" and the decision logic level is "high", the final score should tend to be higher.

[0146] ④ Fuzzy decomposition: convert the fuzzy results into numerical values ​​for comprehensive index calculation.

[0147] c. Machine learning model: Machine learning models are mainly used to predict and optimize the weight configuration of modules and refine the standardized scores of indicators, making index calculation more intelligent and accurate. For example, regression models, cluster analysis or neural network algorithms can be applied to optimize the weight setting and score division of weighted algorithms or fuzzy logic algorithms. The application steps are as follows:

[0148] ① Data collection and cleaning: Collect the company’s robot application data over multiple time periods, including historical detailed indicators and actual comprehensive effects.

[0149] ② Training model: Use data to train supervised or unsupervised learning models to predict and optimize the weights and mapping relationships of detailed indicator scores.

[0150] ③ Tuning and feedback: According to the results of the model output, adjust the module weights or score mapping relationships to form a more reasonable scoring system.

[0151] ④ Model iteration: After long-term data accumulation, the comprehensive index algorithm is made more in line with changes in the actual needs of the enterprise through regular retraining and optimization of the model.

[0152] Comprehensive application examples

[0153] Assume that Company A sets the weights of each part as follows: total number and types of robots: 20%, task complexity: 25%, functional diversity: 20%, degree of robot automation: 20%, and degree of collaboration between robots and humans: 15%.

[0154] Using a weighted average algorithm, the scores of each detailed indicator are aggregated according to the weight to generate a score for the five parts. Fuzzy logic is used to calculate subjective or fuzzy indicators such as "task complexity score" and "collaborative task complexity", and the machine learning model automatically adjusts these weights through historical data to make the scoring results more suitable for practical applications.

[0155] 4. Optimization analysis module 240

[0156] The optimization analysis module 240 is the intelligent decision-making part of the analysis engine, which is responsible for generating optimization suggestions for enterprise robot deployment based on the calculation results of the penetration index. This module proposes practical improvement suggestions through in-depth data analysis to help enterprises improve automation efficiency.

[0157] Robot utilization optimization: Based on the penetration index and robot usage frequency, the system can identify under- or over-use of robots and provide adjustment suggestions. For example, the system may recommend increasing robot deployment in specific production links to improve production efficiency, or reducing the use of robots in inefficient tasks to avoid wasting resources.

[0158] Process efficiency optimization: By analyzing the performance of robots in different tasks, the system can identify which processes have a low degree of automation and recommend optimization of these processes. For example, if certain processes have a low degree of automation and rely on a lot of manual operations, the system can recommend further automation of these processes.

[0159] Robot type adjustment: Based on robot performance data, the system can analyze the suitability of different types of robots in various processes and make adjustment recommendations. For example, the system may recommend introducing collaborative robots in certain tasks to improve flexibility, or replacing older models of robots to improve efficiency.

[0160] 5. Visualization Engine 250

[0161] The visualization engine 250 is responsible for converting complex data analysis results into graphical output so that users can intuitively understand the permeability index and related data. Through dynamic graphical display, users can quickly obtain key information and make decisions. The specific display methods are:

[0162] Chart display: The penetration index and analysis results generated by the system will be presented in various chart forms, including line charts, bar charts, pie charts, etc. Through these charts, users can quickly identify the changing trend of robot penetration, the contribution of each dimension, and the overall use of robots.

[0163] Trend chart display: The visualization engine can display the trend of the penetration index over time, allowing users to see the long-term development of the enterprise automation process. Through the trend chart, users can determine whether recent optimization measures are effective or identify potential automation bottlenecks.

[0164] Multi-dimensional data display: Users can switch data display in different dimensions through the interactive interface, such as displaying analysis results by robot type, task complexity or time period. The visualization engine is seamlessly integrated with the user interface, and users can flexibly customize the data display method according to their needs.

[0165] Dynamic update and interaction: The visualization engine supports dynamic interaction with users. Users can view the latest penetration analysis results in real time or filter and screen data according to different conditions. At the same time, the analysis results will be dynamically updated in the user interface to ensure that users always have the latest robot usage and optimization suggestions. Through the collaborative work of these functional modules, the data analysis engine 200 can provide enterprises with in-depth robot penetration assessment, optimization suggestions and intuitive data display, helping enterprises improve robot usage efficiency and optimize automation processes.

[0166] See also Figure 5 The user interface 300 is an interactive window between the system and the user, which is used to display the robot penetration and system analysis results, and provide optimization suggestions. Through this interface, the user can clearly and intuitively understand the application status of the robot and the degree of automation of the business process, and adjust the automation strategy. The user interface includes the following modules:

[0167] 1. Data display module 310

[0168] This module is responsible for presenting the robot penetration index, robot usage, and the degree of automation of each business process in the form of data. Users can quickly obtain the core information of system analysis, and support flexible screening and filtering to meet the needs of different scenarios.

[0169] Penetration Index Display: Displays the overall penetration rate of different types of robots in the enterprise business. The index is usually calculated based on parameters such as the number of robot deployments, the frequency of task completion, and the scope of covered processes.

[0170] Degree of business process automation: List the automation coverage of each core process of the enterprise, such as the automation level of financial settlement, customer service and logistics management.

[0171] Multi-dimensional filtering function: Supports filtering data by time period, robot type, business process, etc. For example, users can view the usage of a certain type of robot in a specific month, or select the automation improvement history of a certain process.

[0172] Customized data views: Users can customize views based on the company's focus, present key data in tables or briefings, and improve data analysis efficiency.

[0173] 2. Graphical display module 320

[0174] This module presents the system analysis results in various charts to help users intuitively understand the automation level of business processes and the changing trends in robot usage in a visual way.

[0175] Trend chart: Displays the historical changes in robot usage, helping users analyze the effectiveness of automation strategies over a period of time. For example, you can view the trend of robot usage frequency over quarters.

[0176] Comparison chart: The penetration of different types of robots is compared horizontally to show their application effects in various business fields, such as comparing the application of intelligent customer service robots and warehousing robots in different departments.

[0177] Process automation level chart: Displays the automation level of different processes in the form of a bar chart or pie chart, and highlights processes with higher and lower automation levels to help users identify optimization priorities.

[0178] Interactive charts: Users can click on specific data points in the chart to get detailed information and analysis results. For example, clicking on a data point for a quarter can display the robot deployment and usage scenarios during that period.

[0179] 3. Historical data query module 330

[0180] Through this module, users can easily trace back and query historical data on robot penetration within the enterprise, and conduct comparative analysis over multiple time periods to evaluate the long-term effects of automation strategies.

[0181] Time filtering: supports users to query data for a custom time period, such as viewing monthly changes in the past year, or comparing robot penetration in different years.

[0182] Data comparison analysis: allows users to select data from multiple time periods for comparison. For example, you can view the penetration trend of robots in 2022 and 2023.

[0183] Key event marking: Supports marking key events such as business strategy adjustments, robot updates, or major project launches in historical data to help users analyze the impact of these events on penetration.

[0184] Data backtracking and prediction: Based on the trends of historical data, the system can also generate predictions for future usage to help companies adjust their automation strategies in advance.

[0185] 4. Optimization suggestion display module 340

[0186] This module automatically generates optimization suggestions based on current data to help companies improve their automation level and increase the efficiency of robot applications. Users can obtain actionable strategic suggestions through this module and apply them to business adjustments.

[0187] Robot deployment suggestions: The system analyzes the weak links in the existing process and proposes a deployment plan to add a certain type of robot. For example, if the automation level of the logistics link is low, the system will recommend adding a storage robot.

[0188] Process optimization suggestions: Identify inefficient or redundant processes and suggest improving their automation level. For example, the system may suggest replacing certain manual approval steps with automated review.

[0189] Suggestions for improving task complexity: The system analyzes the tasks currently performed by the robot and makes suggestions for improving task complexity to help companies fully tap the potential of robots. For example, upgrading the robot from simple customer Q&A to complex order processing.

[0190] Real-time feedback and execution tracking: The system can record whether the user adopts the suggestions and track the execution effect of the suggestions for subsequent optimization.

[0191] 5. Report generation module 350

[0192] The report generation module 350 allows users to generate detailed analysis reports based on business needs and export them in multiple formats. The report content comprehensively covers robot penetration analysis, task completion assessment, and optimization suggestions.

[0193] Analysis report: The system will automatically generate an analysis report on robot penetration, including robot deployment status, automation level of each process, and recommended directions for future optimization.

[0194] Task completion assessment: The report lists in detail the task completion rate, efficiency assessment and bottleneck analysis of different robots in various business scenarios to help companies identify problems during use.

[0195] Optimization strategy records: Contains the company's historical records of adjustments to automation and their effect analysis, such as the increase in robot utilization after the implementation of a certain strategy.

[0196] Export and sharing function: Supports exporting reports to PDF, Excel, Word and other formats, which is convenient for internal sharing and archiving within the company, and can also be used as a reference for strategic decision-making by management.

[0197] Automated report templates: Users can select different report templates to quickly generate standardized reports, such as monthly, quarterly or annual automated reports.

[0198] Based on the hardware implementation of the above program module, an embodiment of the present invention further provides an electronic device (computer device). Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, the method of any one of the above embodiments is implemented. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0199] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0200] The device provided by the embodiment of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the method of any one of the above embodiments is implemented.

[0201] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0202] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0203] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0204] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0205] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0206] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0207] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0208] It can be understood that the memory of the embodiment of the present invention can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0209] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0210] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A robot utilization optimization suggestion generation system, characterized in that: The robot utilization optimization suggestion generation system comprises: A data collection module is used to collect usage data of different types of robots from the business processes of various robot platforms; the robot types include industrial robots, service robots and software robots; the usage data includes robot type and quantity, robot working time, task completion status, task execution success rate and function execution frequency; A data analysis engine, for calculating the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of automation of robots, and the depth of collaboration between robots and humans based on the usage data; and calculating the robot utilization index by a weighted algorithm using the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of automation of robots, and the depth of collaboration between robots and humans; and for analyzing and processing the robot utilization index according to the business needs of the enterprise and the development trend of robot technology to generate robot utilization optimization suggestions; the robot utilization optimization suggestions include increasing the deployment of a first type of robot, adjusting the degree of automation of a first process, and improving the complexity of robot tasks; A user interface, used to display the robot utilization index and the robot utilization optimization suggestion; Among them, the following indicators are used to calculate the task complexity: (1) Task complexity scoring: Tasks are divided into simple, medium and complex levels, with corresponding scores. Scores are quantified based on task process steps and decision points. (2) Decision logic level: the decision level involved in the robot task, including simple logic, conditional judgment, and machine learning; (3) Ability to adapt to dynamic environments: Whether the robot is capable of handling dynamically changing environments, including real-time obstacle avoidance and adaptive path planning; (4) Data processing and feedback capability: The robot’s ability to process, analyze data and provide feedback during the task; The following indicators were used to calculate functional diversity: (1) Number of robot functions: the number of functions performed by the robot, including handling, welding, assembly, and quality inspection; (2) Modular function realization rate: the proportion of using different modules or plug-ins to realize multiple functions; (3) Function switching flexibility: the efficiency and speed of the robot switching functions in different time periods or scenarios; (4) Functional innovation: Whether the robot contains innovative functions, including vision-based autonomous detection and intelligent path planning.

2. The robot utilization optimization suggestion generation system according to claim 1, characterized in that: The data acquisition module includes an interface component, a data collector, a preprocessing module, a data storage module and a data transmission module: The interface component supports multiple communication protocols for connecting and communicating with various data sources, including API communication protocol, MQTT communication protocol and OPC-UA communication protocol; the data sources include robot control systems, enterprise business management systems and sensor networks; The data collector is used to extract data information from the data stream received by the interface component, wherein the data information includes the type of robot, task completion status, working time, success rate of task execution and function execution frequency; The preprocessing module is used to perform preliminary processing on the data, including cleaning, filtering and formatting of the data; The data storage module uses a relational database or big data storage technology to temporarily store and cache the collected data; The data transmission module is used to transmit the preliminarily processed data in batches or in real time to the utilization index calculation module using a transmission protocol; The transmission protocols include HTTP transmission protocol, WebSocket transmission protocol, and gRPC transmission protocol.

3. The robot utilization optimization suggestion generation system according to claim 2, characterized in that: The interface component is specifically used to obtain operational data of the robot during operation from the robot control system, including status, execution commands, and task progress; obtain background data from the enterprise business management system, including task scheduling information, production line task arrangements, and resource allocation; and obtain environmental data and operational data from the sensor network.

4. The robot utilization optimization suggestion generation system according to claim 2, characterized in that: The data collector is specifically used to mark and classify different types of robots to determine the type of robot; extract the progress, success rate and completion time of each robot in completing the task as the task completion status; extract the actual working time of the robot in different tasks, including the start and end time of the task execution, as the working time; obtain the success rate of the robot in performing the task, including whether the task is completed as required, whether interruptions or failures occur, as the success rate of task execution; obtain the frequency of use of the robot's grasping, carrying and detection functions during work as the function execution frequency.

5. The robot utilization optimization suggestion generation system according to claim 2, characterized in that: The preprocessing module is specifically used to fill in missing data or delete unreasonable data using interpolation methods for null values ​​or abnormal values ​​appearing in sensor data; filter out useless idle time data in task sections with long periods of inactivity; unify timestamps in different formats, or convert and standardize data in different units.

6. The robot utilization optimization suggestion generation system according to claim 1, characterized in that: The data analysis engine includes a data classifier, a permeability calculation module and an algorithm module: The data classifier is used to automatically assign data to corresponding analysis paths according to the data source, robot type, function, and task complexity, so as to classify different types of data; the data source includes robot control systems, sensor networks, and business management systems; the robot types include collaborative robots, assembly robots, and transport robots; the functions include grasping, detection, and handling; the task complexity includes multi-step assembly tasks and simple handling; The penetration calculation module is used to calculate the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of robot automation, and the depth of collaboration between robots and humans; and calculate the robot utilization index through a weighted algorithm using the total number and types of robots, the functional diversity of robots, the complexity of tasks performed by robots, the degree of robot automation, and the depth of collaboration between robots and humans; The algorithm module is used to provide a variety of algorithm libraries supporting utilization calculation, including weighted average algorithm, fuzzy logic algorithm and machine learning model.

7. The robot utilization optimization suggestion generation system according to claim 6, characterized in that: The penetration calculation module is specifically used to calculate the total number and types of robots using the following indicators: (1) Number of robots: the total number of robots in the enterprise; (2) Robot type diversity: the number of different types of robots; (3) Scenario coverage: the number of business scenarios covered by the robot; (4) Robot density per scenario: the number of robots in each business scenario; The degree of robot automation is calculated using the following indicators: (1) Task automation rate: the ratio of tasks that can be completed fully automatically to the total number of tasks; (2) Autonomous learning and optimization capabilities: Can the robot autonomously optimize the workflow through data accumulation, including automatic optimization based on machine learning? (3) Autonomous movement and navigation capabilities: The robot's ability to move autonomously, including whether it has navigation, obstacle avoidance, and path planning; (4) Automatic fault detection and self-repair capability: The robot's ability to automatically monitor and handle faults, including early warning and self-repair; The following indicators are used to calculate the degree of collaboration between robots and humans: (1) Proportion of human-robot collaborative tasks: the proportion of tasks completed jointly by humans and robots in the total tasks; (2) Human-machine interaction efficiency: the time and interaction frequency required by humans in robot operation or task control; (3) Safety and trust: the safety score of the robot or the trust of humans in the robot in a human-robot collaborative environment; (4) Collaborative task complexity: the complexity of human-machine collaborative tasks.

8. The robot utilization optimization suggestion generation system according to claim 1, characterized in that: The data analysis engine also includes an optimization analysis module and a visualization engine module: The optimization analysis module is used to generate optimization suggestions for the enterprise automation process based on the utilization calculation results by analyzing the robot usage data and business needs; The visualization engine module is used to convert the analysis results into graphical output formats, including charts, trend charts and pie charts, so as to present them to users more intuitively.

9. The robot utilization optimization suggestion generation system according to claim 8, characterized in that: The optimization analysis module is specifically used to recommend increasing the deployment of robots in specific production links, or reducing the use of robots in inefficient tasks; recommend further automation of processes with low automation levels and relying on a large number of manual operations; recommend the introduction of collaborative robots in specific tasks, or the replacement of old model robots.

10. The robot utilization optimization suggestion generation system according to claim 1, characterized in that: The user interface includes a data display module, a graphical display module, a historical data query module, an optimization suggestion display module and a report generation module: The data display module is used to display the utilization index, robot usage and the degree of automation of each business process; The graphical display module is used to display the data analysis results in a graphical manner; The historical data query module is used for users to query and compare historical data, analyze the long-term use of robots and their impact on business processes; The optimization suggestion display module is used to display the optimization suggestions generated by the system; The report generation module is used to generate detailed reports according to user needs. The report content includes robot utilization analysis, task completion evaluation, and automation optimization suggestions.

Images