Artificial intelligence-based police equipment command center
By constructing an AI-based police equipment command center system, the problems of data errors and low dispatch efficiency in traditional police equipment management have been solved, realizing intelligent management and rapid response throughout the entire equipment lifecycle, and improving the efficiency and security of police work.
Patent Information
- Application Number
- CN202510624189.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-15
- Publication Date
- 2026-11-17
AI Technical Summary
Traditional police equipment management relies on manual recording, which is prone to data errors and update delays. It is difficult to achieve real-time and accurate inventory management and equipment scheduling. The lack of scientific scheduling strategies leads to low equipment allocation efficiency, inability to respond quickly to emergencies, and difficulty in deeply mining management data to provide scientific decision support.
The system constructs an AI-based police equipment command center, employing multi-source heterogeneous data acquisition, distributed big data processing, AI analysis, and intelligent scheduling algorithms to achieve full lifecycle management of equipment. It integrates sensors and RFID tags for real-time data acquisition, combines big data processing and deep learning models for fault prediction and optimized scheduling, and provides a visual decision-making platform and personalized interactive interface.
It has achieved refined and intelligent equipment management, improved the scientific nature and response speed of equipment dispatch, enhanced the efficiency and safety of police work, provided accurate equipment configuration and fault warning, and supported rapid emergency response.
Abstract
Description
Technical Field
[0001] This invention belongs to the field of information management and intelligent command and dispatch technology for police equipment. Specifically, it relates to a police equipment command center system and method that integrates Internet of Things, big data and artificial intelligence technologies and has the functions of full life cycle management, intelligent dispatch and emergency command of equipment. It can be widely used in police equipment management scenarios of law enforcement departments such as public security and judicial departments. Background Technology
[0002] In modern policing systems, police equipment is diverse, numerous, and frequently used, encompassing various types such as body cameras, bulletproof vests, police vehicles, and communication devices. Traditional police equipment management models typically rely on manual ledger registration, paper-based approval processes, and experience-based dispatching, which have many drawbacks.
[0003] From an information management perspective, manual recording methods are prone to data entry errors and update delays, making it difficult to reflect information such as equipment inventory quantities, storage locations, usage status, and maintenance records in a real-time and accurate manner. For example, during the preparation for a large-scale security event, errors in manual statistics led to incorrect inventory counts for some critical equipment, resulting in insufficient equipment supply to meet mission requirements and severely impacting the smooth operation of the security work.
[0004] In terms of equipment deployment, the traditional model lacks scientific deployment strategies and algorithmic support. Commanders often rely on personal experience to allocate equipment, failing to comprehensively consider multiple factors such as mission urgency, equipment performance parameters, and police deployment locations. This results in low equipment deployment efficiency and difficulty in achieving rapid response in emergency situations. Taking emergency response as an example, the inability to quickly match suitable equipment resources may cause delays in response time and increase the safety risks for police officers.
[0005] Furthermore, with the continuous development of policing work, massive amounts of equipment management and policing operational data have been generated. However, traditional management models struggle to deeply mine and analyze this data, failing to achieve intelligent functions such as equipment demand forecasting, fault warning, and usage optimization. Consequently, they cannot provide strong data support and scientific basis for policing decision-making. Therefore, there is an urgent need for an intelligent police equipment command center system to improve the efficiency and scientific nature of police equipment management and dispatch. Summary of the Invention
[0006] (a) Purpose of the invention This invention aims to overcome the shortcomings of existing technologies and provide an artificial intelligence-based police equipment command center. By constructing an intelligent system integrating data collection, processing, analysis, and decision-making, it achieves intelligent management of police equipment throughout its entire lifecycle, from procurement and warehousing, daily management, dispatch and use to disposal, thereby improving the precision of equipment management. Simultaneously, it utilizes intelligent algorithms and models to achieve precise equipment dispatch and scientific decision-making, enhancing the response speed and execution efficiency of police work, and providing strong support for ensuring social security and stability. (II) Technical Solution
[0007] Data Acquisition Layer: This layer employs multi-source heterogeneous data acquisition technology to construct a comprehensive, real-time data acquisition network. At the police equipment end, various types of equipment are equipped with corresponding sensors and RFID tags. For electronic equipment, such as law enforcement recorders and walkie-talkies, built-in Bluetooth Low Energy (BLE) sensors, power sensors, and positioning sensors are used to collect data such as equipment power status, location information, and operating time in real time. For non-electronic equipment, such as bulletproof vests and batons, passive RFID tags are affixed, and RFID readers are used to achieve equipment entry and exit registration, location positioning, and inventory checks. Simultaneously, standardized data interfaces (such as RESTful APIs and Web Services) are used to connect with the public security integrated information system, police force deployment system, and task management system to obtain police-related data such as police force distribution, task type, task time, and task location, achieving integrated acquisition of equipment data and police business data.
[0008] Data Processing and Storage Layer: A distributed big data processing architecture is adopted to efficiently process and securely store the massive amounts of collected data. Using big data processing frameworks such as Apache Hadoop and Apache Spark, preprocessing operations such as cleaning, transformation, and aggregation are performed on the raw data to remove duplicate, noisy, and invalid data, unifying the data format into structured data that is easy to analyze and store. A storage approach combining a distributed file system (HDFS) and distributed databases (such as Cassandra and MongoDB) is used, with hierarchical storage based on data type, usage frequency, and importance. Hot data such as real-time equipment status data and high-frequency operation logs are stored in high-performance in-memory databases (such as Redis) to meet the needs of fast querying and real-time analysis; cold data such as historical equipment usage data and maintenance records are stored in the distributed file system to reduce storage costs. Simultaneously, a data warehouse is established, using ETL (Extract, Transform, Load) technology to extract, transform, and load data, constructing a multi-dimensional data model and providing a unified data platform for subsequent data analysis and mining.
[0009] Artificial Intelligence Analysis Layer: This layer integrates various artificial intelligence algorithms and models to achieve in-depth analysis and intelligent prediction of equipment and police data. In equipment failure prediction, a hybrid deep learning model based on Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) is constructed to extract and learn features from equipment sensor data, historical failure records, and usage environment data, establishing an equipment failure prediction model capable of predicting potential failure types and timing in advance, providing a basis for preventative maintenance. In equipment configuration optimization, reinforcement learning algorithms are used, with constraints such as task requirements, equipment performance, and usage costs, aiming to maximize equipment utilization efficiency and minimize costs, continuously optimizing equipment procurement plans, inventory allocation, and deployment strategies. In intelligent recommendation, based on collaborative filtering and content-based recommendation algorithms, combined with task type, police force characteristics, and equipment attributes, the most suitable equipment combination is recommended for specific tasks and officers. Furthermore, Natural Language Processing (NLP) technology is used to perform semantic analysis and understanding of police text data (such as task descriptions and incident reports), extracting key information to assist intelligent decision-making.
[0010] Command and Decision-Making Level: A visualized and intelligent command and decision-making platform is constructed, providing commanders with an intuitive and convenient operating interface and decision support. Data visualization technologies (such as ECharts and D3.js) are used to visually display information such as equipment status, police force distribution, mission progress, and dispatch plans in the form of maps, charts, and dashboards, enabling commanders to quickly grasp the overall situation. Based on intelligent dispatch algorithms and optimization models, combined with real-time mission requirements, equipment status, and police force locations, the optimal equipment allocation plan is automatically generated. The intelligent dispatch algorithm employs a hybrid optimization algorithm combining an improved genetic algorithm and a simulated annealing algorithm. By simulating biological evolution and physical annealing processes, it searches for the optimal solution in a complex solution space to minimize equipment allocation time, transportation costs, and mission completion time, while simultaneously meeting mission priority and equipment requirements. The system supports multi-dimensional plan evaluation and adjustment functions, allowing commanders to manually adjust and optimize the generated plans according to actual conditions. In addition, the system also has emergency command functions. When an emergency occurs, it can quickly activate the emergency plan, integrate resources from all parties, realize the rapid deployment and command and dispatch of emergency equipment, monitor the execution of emergency tasks in real time, adjust strategies in a timely manner, and ensure the smooth completion of emergency tasks.
[0011] Equipment Condition Monitoring and Fault Prediction: A technical system for equipment condition monitoring and fault prediction based on multi-sensor fusion and deep learning is constructed. By performing feature-level and decision-level fusion of data collected from multiple sensors on the equipment (such as temperature, vibration, voltage, and current), more comprehensive and accurate equipment condition information is obtained. Utilizing the powerful feature extraction capabilities of Convolutional Neural Networks (CNNs), feature learning and analysis are performed on the fused data to extract key features during equipment operation. Furthermore, combining the advantages of Long Short-Term Memory Networks (LSTMs) in processing time-series data, the temporal trends of equipment condition changes are modeled and predicted, enabling early warning of equipment faults. Simultaneously, an equipment fault knowledge base is established, structurally storing historical fault cases, causes, and solutions. Knowledge graph technology is used to achieve the association and reasoning of fault knowledge, providing more comprehensive support for fault diagnosis and maintenance. When the system predicts a potential equipment fault, it automatically generates a fault warning and pushes it to equipment management and maintenance personnel, reminding them to take timely maintenance measures.
[0012] Intelligent Scheduling Algorithm: A multi-objective optimization-based intelligent scheduling algorithm is designed, comprehensively considering multiple factors such as task requirements, equipment availability, police force distribution, transportation costs, and time constraints to establish a multi-objective optimization model. This model aims to minimize task completion time, equipment allocation costs, and task execution risks, while using constraints such as equipment quantity limits, task priorities, and equipment performance matching. An improved Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) is employed for solving the algorithm. Through fast non-dominated sorting, crowding calculation, and elite retention strategies, the Pareto front solution set is searched in the complex multi-objective solution space to obtain multiple optimal scheduling schemes that meet different needs. Simultaneously, a dynamic adjustment mechanism is introduced to dynamically optimize and adjust the scheduling scheme based on real-time changes during task execution (such as task delays, equipment damage, and traffic congestion), ensuring the timeliness and effectiveness of equipment scheduling.
[0013] Human-Computer Interface Design: Utilizing ergonomics and user experience design principles, a highly integrated and user-friendly human-computer interface was developed. The interface employs a modular design, divided into modules such as equipment management, task scheduling, data analysis, and emergency command. Users can quickly switch between different modules according to their actual needs. For graphical display, 3D visualization technology is used to virtually model equipment warehouses and police deployment areas, intuitively displaying the storage location, quantity, and status of equipment, as well as the distribution of police forces. Voice interaction and gesture operation functions are supported. Commanders can quickly query equipment information and issue dispatch orders via voice commands; gesture operations enable map zooming, chart switching, and other functions, improving operational efficiency. Furthermore, the interface has a personalization customization function, allowing users to set the interface layout, displayed content, and operation methods according to their personal habits, enhancing the user experience. Simultaneously, a security authentication and access control mechanism is adopted to ensure that only authorized users can access and operate related functions, guaranteeing system security and data confidentiality.
[0014] Equipment Inbound Management: After new equipment arrives, equipment managers use handheld RFID readers to scan the RFID tags on the equipment. The system automatically reads the basic information of the equipment (such as model, specifications, manufacturer, production date, etc.) and matches it with the purchase order information for verification. Upon successful verification, the system automatically assigns a unique identification code to the equipment and enters the equipment information into the equipment management database, updating inventory data. Simultaneously, electronic equipment undergoes initial setup, including configuring network parameters, installing necessary software and drivers, and performing functional tests to ensure the equipment is in normal working order. For non-electronic equipment, quality checks and performance tests are conducted, such as testing the bulletproof performance of bulletproof vests and the strength of batons. After testing, the results are entered into the system, generating an equipment inbound record.
[0015] Daily Equipment Management: The system monitors equipment status information in real time through IoT sensors, such as location, battery level, and usage duration, and uploads the data to the data processing and storage layer for analysis and processing. Based on the prediction results of the artificial intelligence analysis layer, the system automatically generates equipment maintenance plans and reminds equipment managers to perform maintenance via SMS, email, or system messages. For equipment that has not been used for a long time, the system conducts regular spot checks to check whether the equipment's performance and condition are normal. At the same time, equipment managers can use the system to perform operations such as borrowing, returning, and transferring equipment. The system automatically records operation information and updates equipment status and inventory data. In addition, the system also supports equipment inventory functions. By using RFID readers to scan equipment in the warehouse in batches, the system can quickly verify whether the actual inventory quantity matches the quantity recorded in the system, generate an inventory report, and promptly identify and address problems in equipment management.
[0016] Task Response and Equipment Allocation: When the command and decision-making level receives a new police task, the system first analyzes the task information, extracting key information such as task type, time, location, and participating police force. Then, the AI analysis layer, based on task requirements and combined with equipment inventory status, equipment performance parameters, and historical usage data, uses an intelligent recommendation algorithm to select a suitable equipment list for the task. Next, the intelligent scheduling algorithm generates the optimal equipment allocation plan based on equipment storage location, police force distribution, and transportation routes, including equipment collection location, allocation order, and transportation method. After the command personnel review and confirm the allocation plan, the system sends equipment collection notifications to relevant officers via SMS, mobile applications, etc., and simultaneously updates the equipment status to "allocated." When officers collect the equipment, they scan the equipment tag using an RFID reader for confirmation of release, and the system records the equipment release time and the information of the personnel collecting the equipment.
[0017] Mission Execution and Feedback: During mission execution, officers use mobile devices (such as police mobile phones and tablets) to provide real-time feedback on equipment usage and mission progress. These mobile devices connect to the system via a wireless network, uploading real-time equipment status (e.g., whether the equipment is functioning properly, whether any malfunctions have occurred), photos, videos, and text descriptions of the mission site. Upon receiving feedback, the system updates the equipment status in real time and displays mission progress information on a visual interface for command and decision-making, facilitating command personnel's understanding of mission execution. If equipment malfunctions during use, officers can submit a malfunction report via their mobile devices. The system automatically pushes the malfunction information to equipment management and maintenance personnel and readjusts the equipment allocation plan based on the severity of the malfunction and the urgency of the mission to ensure successful mission execution. After the mission, officers return the equipment to the designated location. Equipment management personnel inspect and accept the equipment, confirming its normal condition. They then perform an inventory check through the system, updating the equipment status to "returned," and recording and analyzing the equipment's usage to provide data support for subsequent equipment management and optimization.
[0018] System Setup
[0019] RFID readers and sensor gateways are deployed in locations such as police equipment warehouses, police vehicle parking areas, and police equipment storage points. The RFID readers are ultra-high frequency RFID readers (such as the Impinj Speedway RevolutionR420), which feature long reading distances, fast reading speeds, and strong anti-interference capabilities, enabling rapid inventory checks and real-time monitoring of large quantities of equipment within the warehouse. The sensor gateways are industrial-grade IoT gateways (such as Advantech ARK-3500), supporting multiple communication protocols (such as Wi-Fi, 4G, LoRa, etc.). They aggregate and convert the data collected by the sensors, transmitting it wirelessly to the data processing and storage layer.
[0020] Police equipment is equipped with corresponding sensors and RFID tags. For law enforcement recorders, built-in GPS positioning sensors, accelerometers, and battery sensors are used, and data is transmitted via Bluetooth to a sensor gateway. Passive RFID tags are affixed to equipment such as bulletproof vests and police helmets, storing the equipment's unique identification code and basic information. Simultaneously, a data acquisition interface program is developed to connect with existing public security information systems via API, enabling automatic collection and synchronization of police data.
[0021] A big data processing cluster is built, employing the Hadoop distributed computing framework to construct the data processing platform. NameNode, DataNode, and JobTracker nodes are deployed to achieve distributed data storage and parallel computing. The Spark big data processing framework is installed for rapid processing and analysis of real-time and batch data.
[0022] Deploy the distributed database Cassandra in a cluster mode, distributing data across multiple nodes to improve storage capacity and read / write performance. Configure a Redis in-memory database to store real-time equipment status data and frequently accessed data, enabling fast data querying and updates.
[0023] Establish a data warehouse and use ETL tools (such as Talend and Kettle) to extract, transform, and load the collected data. Construct a star or snowflake data model and organize and store the data according to themes such as equipment information, mission information, and police force information to provide basic data for data analysis and mining.
[0024] A deep learning computing platform was built, using NVIDIA GPU servers (such as NVIDIA DGX A100) as computing hardware, and deep learning frameworks such as TensorFlow and PyTorch were installed to train and deploy deep learning models for equipment fault prediction, intelligent recommendation, and other purposes.
[0025] To develop an equipment failure prediction model, a large amount of historical equipment failure data and operational status data was collected. The data was preprocessed and feature-engineered to construct training and testing sets. The model was trained using LSTM and CNN network architectures, and the prediction accuracy was continuously improved by adjusting network parameters and optimizing the algorithm.
[0026] Implement an intelligent scheduling algorithm using Java or Python programming languages. Write improved genetic and simulated annealing algorithm code and integrate the algorithms into the system. Generate and optimize equipment scheduling schemes by calling the algorithm interface. Simultaneously, develop an intelligent recommendation algorithm module, implementing collaborative filtering and content recommendation algorithms to suggest suitable equipment for tasks and officers.
[0027] A command and decision-making system was developed based on web technologies, using Vue.js as the front-end framework and Spring Boot as the back-end framework to construct a front-end and back-end separated system architecture. Data visualization libraries such as ECharts and D3.js were used to develop equipment status visualization interfaces, task scheduling visualization interfaces, and data analysis visualization interfaces, enabling intuitive data display and interactive operations.
[0028] Integrating intelligent scheduling algorithms and emergency command modules, a human-computer interaction interface was developed, supporting voice recognition and gesture operation functions. Voice recognition technologies (such as Baidu Voice Recognition API and iFlytek Voice Recognition API) were used to parse and execute voice commands; gesture operation functions, such as map zooming and chart switching, were implemented through gesture recognition libraries (such as Leap Motion). Simultaneously, a user access control system was established, setting different operation permissions for users with different roles (such as commanders, equipment managers, and police officers) to ensure system security and data confidentiality. Data collection and training were also conducted.
[0029] A comprehensive inventory of existing police equipment was conducted, and each piece of equipment was assigned a unique RFID tag and sensor. Detailed information about the equipment was recorded, including equipment name, model, specifications, manufacturer, production date, purchase date, department using the equipment, and personnel using the equipment. This information was then entered into the equipment management database.
[0030] The data acquisition program is initiated to collect real-time data on equipment location, status, usage records, and police data obtained through interfaces. A data acquisition log mechanism is established to record detailed information such as the time, source, and status of data acquisition for subsequent data quality monitoring and problem investigation. Simultaneously, data acquisition anomaly alarm rules are set up. When anomalies such as data acquisition failure, data transmission interruption, or data format errors occur, the system automatically sends alarm information to maintenance personnel and records anomaly details for rapid problem location and resolution.
[0031] Data cleaning algorithms are used to process the collected raw data, removing duplicate data, missing values, and outliers. For missing values, methods such as mean imputation, median imputation, and regression prediction imputation are used, depending on the data type and business requirements. For outliers, statistical methods such as box plots and the 3σ principle are used to identify them, and corrections or deletions are made as needed.
[0032] Data standardization and normalization processes convert data of different types and ranges into a unified format and scale to facilitate subsequent data analysis and model training. For example, for numerical data, Z-score standardization is used to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1; for categorical data, one-hot encoding or label encoding methods are used for conversion.
[0033] Feature extraction and selection are performed on the data. Principal component analysis (PCA) and feature correlation analysis are used to extract key features, remove redundant features, reduce data dimensionality, and improve data processing efficiency and model training effectiveness. Simultaneously, by combining business knowledge and experience, features that have a significant impact on equipment management and scheduling decisions are selected to construct a feature engineering dataset.
[0034] Equipment Fault Prediction Model Training: Preprocessed equipment status data and fault record data are divided into training, validation, and test sets in a 7:2:1 ratio. During training, cross-validation is used to adjust the hyperparameters of the LSTM and CNN hybrid model, such as learning rate, number of hidden layer neurons, and number of iterations. The model's prediction accuracy, recall, and F1 score are evaluated using the validation set to select the optimal model parameters. The model is trained using the training set, and training is stopped when the model's performance on the validation set no longer improves or reaches the preset number of training iterations. Finally, the trained model is evaluated using the test set to verify its generalization ability and prediction accuracy.
[0035] Intelligent scheduling algorithm model training: By constructing simulated task scenarios and equipment scheduling environments, a large amount of training data is generated, including optimal scheduling schemes under different task types, task scales, equipment configurations, and police force distributions. This data is used as training samples, and a reinforcement learning algorithm is employed for training. A reward function and penalty mechanism are set to encourage the algorithm to generate better scheduling schemes. During training, the algorithm's parameters and strategies are continuously adjusted. Through repeated iterations and optimizations, the algorithm can quickly generate near-optimal equipment scheduling schemes under different task and environmental conditions. Simultaneously, the trained algorithm is periodically evaluated and optimized to ensure its effectiveness and reliability in practical applications.
[0036] Intelligent Recommendation Model Training: Historical task data, equipment usage data, and officer information data are collected to construct a three-dimensional dataset of user-task-equipment. Collaborative filtering algorithms are used to calculate the similarity between tasks and between equipment. Based on user history and preferences, commonly used equipment for similar tasks and usage scenarios for similar equipment are recommended. Combining content—based on the recommendation algorithm—semantic analysis and feature extraction are performed on textual data such as task descriptions and equipment attributes to recommend equipment combinations that meet task requirements and equipment performance. By continuously updating and optimizing training data and adjusting the parameters of the recommendation algorithm, the accuracy and personalization of recommendations are improved.
[0037] After the system is officially put into operation, the modules at each layer work collaboratively according to the predetermined processes and mechanisms. The data acquisition layer continuously collects equipment and police data in real time and transmits the data to the data processing and storage layer; the data processing and storage layer processes and stores the data and provides data support for the artificial intelligence analysis layer; the artificial intelligence analysis layer uses various algorithms and models to analyze and predict the data, and transmits the analysis results to the command and decision-making layer; the command and decision-making layer generates equipment management and dispatch decision-making plans based on the analysis results, displays them to users through a human-computer interaction interface, and receives user operation commands, feeding them back to the relevant modules for processing.
[0038] Establish a system operation monitoring platform to monitor various system performance indicators in real time, such as data acquisition frequency, data processing speed, system response time, and server resource utilization. The system's operating status is displayed through a visual interface. When performance indicators exceed preset thresholds, the system automatically issues warning messages and generates performance analysis reports to help operations and maintenance personnel understand the system's operational status and identify potential problems.
[0039] Establish system operation and management procedures, clearly defining the responsibilities and operating standards for each position, including equipment management personnel, command personnel, and system maintenance personnel. Regularly train system operators to improve their operational skills and professional competence, ensuring the correct use and safe operation of the system. Simultaneously, establish a system operation log recording mechanism to record detailed information on system operations, data changes, and fault events, facilitating subsequent auditing and traceability.
[0040] Data optimization: Regularly clean and archive data, deleting expired and invalid data to free up storage resources. Evaluate and optimize the data models in the data warehouse, adjusting their structure and dimensions based on changes in business needs and data analysis feedback to improve the efficiency of data querying and analysis. Simultaneously, strengthen data quality monitoring, establish a data quality assessment indicator system, and regularly check and evaluate the accuracy, completeness, and consistency of data to promptly identify and resolve data quality issues.
[0041] Algorithm optimization: As the amount of data increases and business scenarios change during system operation, the algorithms and models of the artificial intelligence analysis layer are continuously optimized. This is achieved by introducing new algorithmic technologies, improving existing algorithmic structures, and adjusting algorithmic parameters to enhance algorithm performance and accuracy. For example, for equipment fault prediction models, new fault data is continuously collected, the model's training data is updated, and the model is retrained to improve fault prediction accuracy. For intelligent scheduling algorithms, the objective function and constraints are optimized based on actual scheduling results and user feedback to improve the rationality and feasibility of scheduling schemes.
[0042] Functionality Optimization: Based on user feedback and business development needs, the system's functionality will be optimized and expanded. New functional modules will be added, such as an equipment lifecycle cost analysis module and a police officer equipment usage performance evaluation module, to meet diverse user needs. Existing functional modules will be improved and refined, and the human-computer interface design will be optimized to enhance system usability and user experience. Simultaneously, system security and stability will be strengthened, with regular security vulnerability scans and patching, and improved backup and recovery mechanisms to ensure the system can operate normally in the face of various security threats and failures.
Claims
1. A system and method integrating Internet of Things, big data, and artificial intelligence technologies, providing a technical solution for a police equipment command center system and method with functions of full life-cycle equipment management, intelligent scheduling, and emergency command, thereby protecting the information management and intelligent command and dispatch of police equipment.
