38results about How to "Reduce conflict" patented technology

The invention relates to the field of material chemistry on-line detection, in particular to a 1, 2, 4-trichlorobenzene on-line detection material and a preparation method thereof, and provides a film-forming sensitive layer material capable of being coated on the surface of a transducer, and the film-forming sensitive layer material comprises chitosan, a crosslinking component with the content of 0.1-5wt% in terms of glutaraldehyde and magnetic core-shell molecularly imprinted particles after being dried, the magnetic core-shell molecularly imprinted particle contains a ferroferric oxide magnetic inner core, a silicon dioxide middle layer and a molecularly imprinted polymer shell layer, and the shell layer is a cyclodextrin methacrylate and ethylene glycol dimethacrylate copolymer network and takes 1, 2, 4-trichlorobenzene as a template. The material keeps the membrane integrity and long-term stability under the working conditions of circulation and regeneration and also gives consideration to quick response, and the residual 1, 2, 4-trichlorobenzene is controlled to be not greater than 0.10 wt% and the residual glutaraldehyde is controlled to be not greater than 0.5 wt%. The method is used for relieving structural mass transfer contradiction and processing and coating coupling contradiction caused by high filler load, and has online detection application value.

The application relates to the technical field of aerial video analysis, and discloses a large-scene multi-modal analysis system and method based on a UAV. The method acquires an original video frame sequence from aerial equipment, extracts a scene change period and an object motion trend by calculating an inter-frame motion feature vector, and judges whether a scene is in a stable or dynamic state by means of a state classification model. In the dynamic state, a tracking target position is calculated according to preset parameters, and an analysis target area is adjusted in combination with the motion trend; a camera parameter adjustment instruction is generated according to a deviation amount of the analysis target area from an actual object position, and is output to an executing mechanism; a complexity value is acquired through a scene complexity feedback signal, and when the complexity value exceeds a preset range, an adaptive algorithm is used to update an analysis strategy and output an adjustment signal; the output timing of control and strategy adjustment signals is optimized, the frame sequence and analysis parameter change trend are monitored in real time, preset parameters are dynamically updated to match user requirements, and efficient video analysis processing is realized.

The application provides a seven-day period factory cyclic Megalobrama amblycephala fry behavior domestication method and system, relates to the Megalobrama amblycephala breeding technical field, and includes: domesticating the fry into a domestication pond on the first day; starting vertical water flow impact before feeding fresh bait fish according to a preset first feeding frequency on the second day; feeding electric shock disabled live bait according to a preset second feeding frequency on the third day; feeding mixed live bait according to a preset third feeding frequency on the fourth day; feeding mosaic bait according to a preset fourth feeding frequency on the fifth day; feeding pure artificial compound feed using a composite feeding mode and starting water flow impact on the sixth day; feeding pure artificial compound feed on the seventh day, and screening domestication successful individuals based on behavior indexes after the period ends, so that the Megalobrama amblycephala is rapidly domesticated from feeding live bait to feeding artificial compound feed.

The invention relates to the technical field of network communication equipment, in particular to a distributed network signal convergence concentrator, which comprises a main control module, and a power supply module supplies power to each module; the distributed signal acquisition unit is used for acquiring multi-path distributed network signals and transmitting the multi-path distributed network signals to the signal convergence processing module; the signal convergence processing module is used for carrying out integration, protocol conversion and bandwidth optimization processing on multiple paths of network signals; the network interface module is used for outputting processed convergence signals to superior network equipment; one side of the main control module is also provided with an extensible interface module; for some specific areas, the main control module is inconvenient to move or a connecting line is short, the mobile interface is arranged, so that butt joint with an external interface is facilitated, the whole equipment does not need to be moved, and a complex scene is adapted; and multiple types of wired and wireless signals are compatible, multi-protocol unified convergence is realized through protocol conversion, and the equipment compatibility is improved.

This invention relates to the fields of data analysis and intelligent marketing technology. Specifically, it relates to a method and system for intelligently generating marketing strategies based on high-dimensional customer profiles. This invention combines event-driven and time-sliding window approaches to obtain category-differentiated decay functions. It updates demand intensity values ​​by setting dynamic decay rates based on product lifecycles and customer stickiness. Through cross-cycle behavior matching and spatiotemporal alignment of demand intensity waveforms, it identifies demand transfer logic chains and labels core demand tags. It aggregates tag strength and commercial factors to generate a list, triggers marketing resource migration with dual thresholds, collects response data, and compares conversion rate deviations to optimize parameters and complete self-calibration. The system includes a demand intensity calculation unit, a demand transfer path analysis unit, a strategy dynamic optimization unit, and a decay calibration feedback unit. This invention solves the problems of strategy lag and resource mismatch, improves marketing accuracy and resource utilization, and adapts to changing demand scenarios in the maternal and infant and home appliance industries.

The invention relates to the technical field of hemostasis management, in particular to a multi-robot hemostasis management system based on task scheduling, which comprises a hemostasis physiological monitoring module, a compression state time sequence module, a hemostasis task scheduling module, a release path planning module and a multi-robot collaboration module. Multi-type physiological monitoring, identity labels, position changes and operation nodes are subjected to linkage collection, the whole-process tracking ability of the sick and wounded is enhanced through time and space identification, the compression period and operation allocation are optimized through interaction judgment of physiological monitoring and path information, intelligent response of task sorting and execution subject selection is achieved, and the system is high in practicability and easy to popularize. Space nodes and passing tracks are dynamically updated, the avoiding and resource utilization efficiency during hemostasis robot cooperation is improved, task linkage parameters are synchronized, the scheduling sequence and execution stability of the sick and wounded in batches are improved, the splitting and conflict phenomena are reduced, an information chain penetrates through the front line and the rear line, and the efficiency is improved. Time sequence management, risk prevention and control and group cooperation capability of hemostasis management are enhanced.

The present disclosure provides a data interaction method and device, equipment and storage medium, relates to the technical field of network communication, and particularly relates to the field of cloud computing technology. The specific implementation scheme is as follows: a plurality of communication links are determined for each preset data interaction requirement detection, wherein the source device and the target device of the data interaction requirement are connected through different exchange devices; for each data interaction requirement, a communication link for realizing the data interaction requirement is selected from the communication link corresponding to the data interaction requirement; the exchange device directly connected with the source device of each data interaction requirement is informed to perform link information configuration according to the communication link selected for each data interaction requirement, so that each source device performs data interaction with the target device according to the configured information. The scheme provided by the embodiment of the present disclosure can realize smooth data interaction.

The invention relates to a bill element intelligent extraction and verification method and system, and relates to the field of artificial intelligence, and the method comprises the steps: collecting bill image information; extracting bill element information based on the bill image information; obtaining a current information filling format according to the bill image information and the bill element information; obtaining bill code information according to the bill element information; matching a standard information filling format through the bill coding information; if the current information filling format is inconsistent with the standard information filling format, combining the current information filling format with the standard information filling format to generate a format difference condition; and determining a difference processing method based on the format difference condition, and performing prompt processing according to the difference processing method. The method and the device have the effect of improving the bill information processing efficiency.

This invention provides a dynamic unloading method and system for bulk cargo ships based on multi-site collaboration, comprising: Step S1: constructing a terminal operation knowledge base and a yard stockpile knowledge base; Step S2: collecting operation data in real time; Step S3: generating a multi-site list based on the yard stockpile knowledge base, yard inventory and inbound / outbound information, and material usage plan, wherein the multi-site list includes product name and available time for each site; Step S4: generating a multi-site selection sequence scheme for each simultaneously operating conveyor belt system based on the multi-site list and a dynamic site selection model; Step S5: generating an optimal unloading scheme based on the terminal knowledge base, ship information, equipment tracking status information, ship compartment volume, and multi-site selection sequence scheme through a ship unloading model; Step S6: guiding the unloading operation according to the unloading scheme, dynamically analyzing the deviation between planned and actual volume based on real-time collected operation data and unloading conveyor belt volume, and repeating steps S3-S5 when the deviation exceeds a threshold or a major event is detected.

The invention provides a fault injection parameter processing method and device based on a test process context, and the method comprises the steps: obtaining process context information containing a multi-step logic relation through analyzing a test process described by an ATML (Automatic Test Markup Language); according to the process context information and the real-time resource state of the current test system, collaborative analysis and dynamic decision making are carried out, and adaptive fault injection parameters are intelligently generated; and finally executing fault injection according to the generated parameters. According to the method, the defects of fixed fault parameters and lack of process adaptability in a comprehensive test in the prior art are overcome, the conversion from static parameter table lookup to dynamic context sensing decision is realized, and the automation level, test precision and adaptability to complex test scenes of aviation tests and tests are remarkably improved.

The application provides a cloud edge collaborative method based on multi-source heterogeneous information fusion, comprising image processing, Faster R-CNN network construction, basic belief distribution output, multi-view basic belief distribution fusion through supervised and unsupervised methods, target state feature extraction, reinforcement learning model reasoning update, cloud side classification head migration and edge side model fusion, and edge reasoning update under multi-view image input. The application extracts and efficiently integrates the multi-modal data collected by different sensors, introduces an evidence fusion strategy to ensure the reliability of the evidence, introduces an evidence correction strategy for the high conflict problem that may exist in the multiple edge side fused evidence, combines the conflict identification and dynamic management mechanism to effectively avoid the generation of counter-intuitive conclusions, globally optimizes through reinforcement learning, realizes the dynamic interaction and intelligent feedback between the cloud and the edge, and ensures the low conflict and high reliability of the system in a complex environment.

This application discloses a steel structure roof, relating to the technical field of steel structure buildings. It includes a frame, tiles, and connectors connecting the frame and tiles, all mounted on the roof. Each tile includes symmetrically arranged rain-proof portions and connecting portions, each with an arc-shaped protrusion. The connecting portion is located between two rain-proof portions, and its radius is larger than that of the rain-proof portions. The rain-proof portions of adjacent tiles are interlocked. The connector includes a mounting sleeve sliding on the frame and symmetrically hinged abutment plates to the mounting sleeve. Connecting plates are symmetrically arranged on the inner wall of the connecting portion. The mounting sleeve is equipped with a control component that controls the abutment plates to flip and abut against the connecting plates. When the tiles move away from the frame after the abutment plates flip, the connecting plates abut against the abutment plates. Clamping plates slide symmetrically on the abutment plates, and a driving component is provided on the abutment plates. When the abutment plates abut against the connecting plates, the driving component drives the two clamping plates to clamp the connecting plates. This application addresses the possibility of water leakage in steel structure roofs.

The application discloses an upgrade control method and device of a safety switch, computer equipment and a storage medium, wherein the safety switch comprises a target controller and at least one non-target controller connected to the same bus. The target controller enters an upgrade state in response to an upgrade instruction broadcast by an upper computer and sends an upgrade ready identifier, receives an upgrade frame broadcast by the upper computer and performs receiving verification, and when the verification is passed, sends an upgrade feedback identifier, so that the upper computer continues to broadcast the next frame of the upgrade frame until an end frame is received, and then based on the received upgrade frame, the upgrade processing is completed. The upgrade frame is also used to be received by the non-target controller to perform the upgrade processing, and the upgrade feedback identifier is also used for the non-target controller to listen to, so as to keep the upgrade timing synchronization with the target controller, thereby being capable of improving the synchronous upgrade efficiency and reliability of the multi-controller safety switch.

The disclosure relates to a differential gear assembly (20) comprising a ring-shaped gear (26) being rotatable around an axis (A) and a bevel gear unit (44) with four bevel gears (48a, 48b, 48c, 48d) being supported on a bevel gear carrier (46). Two bevel gears (48a, 48b, 48c, 48d) are additionally supported on a cross shaft (60). The ring-shaped gear (26) comprises at least two primary contact surfaces (38a, 38b) having a spherical shape and the bevel gear carrier (46) comprises at least two secondary contact surfaces (56a, 56b) having a spherical shape. Each of the secondary contact surfaces (56a, 56b) contacts an associated primary contact surface (38a, 38b). Moreover, two reception slots (40a, 40b) are arranged on the ring-shaped gear (26) and an end (62a, 62b) of the cross shaft (60) is received in each of the two reception slots (40a, 40b) such that the ends (62a, 62b) and the reception slots (40a, 40b) form a positive locking being effective in a circumferential direction of the ring-shaped gear (26). Additionally, a drivetrain for a vehicle comprising such a differential gear assembly (20), a method for assembling a differential gear assembly (20), and a method for disassembling a differential gear assembly (20) are explained.

The throttling fluid working condition parameter calculation method based on teacher-student architecture and law constraint neural network belongs to the field of computational fluid dynamics. First, the calculation coordinate system, input parameters and predicted output parameters are determined, and the input parameters and predicted output parameters are expressed as input vectors and predicted output vectors respectively, and a teacher network loss function is constructed in combination with the physical laws satisfied by the throttling fluid. Second, the teacher network is constructed based on the teacher network loss function and the teacher network is trained using the teacher network training data set to obtain the trained teacher network, and a student network loss function is constructed using the teacher network output and the real label vector as double benchmarks. Finally, the student network is constructed and trained using the student network training data set to obtain the student network for outputting the throttling fluid working condition parameters. The present application can realize the decoupling of physical law learning and parameter regularization, and give consideration to calculation accuracy, real-time performance, explainability and physical consistency.

This application discloses a multi-task reinforcement learning method, apparatus, electronic device, and medium for a language model, relating to the field of AI technology. The method includes: dividing multiple types of tasks to be learned into at least one task group, each task group corresponding to a reinforcement learning stage of the language model; within the reinforcement learning stage corresponding to each task group, dynamically adjusting the gradients corresponding to the tasks in each task group based on first information corresponding to each task in that task group, the first information including at least one of the following: sample advantage information of the task in the current training step, and learning progress information of the task in the current training step; and updating the model parameters of the language model based on the adjusted gradients.

The invention relates to a terminal self-judgment fast random access method, which is applied to a terminal and comprises the following steps of: after random selection of an access opportunity is completed and before a random access preamble message is sent, transmitting an own IMEI Z sequence on an access declaration resource corresponding to the selected access opportunity, simultaneously and synchronously receiving signals on the noise measurement resource and the access declaration resource corresponding to the access opportunity; measuring the reference noise power according to the signal on the noise measurement resource, and calculating the own signal power according to the signal on the access declaration resource; performing access conflict judgment according to the reference noise power and the self signal power; and selecting a proper random access flow according to a conflict judgment result. According to the invention, the access speed of the terminal can be accelerated.

This utility model discloses a composite foundation and its installation structure. The composite foundation includes: a pile foundation, inserted into the soil downwards along the ground level, with the end of the pile foundation sunk below the ground level; and a shallow pit concrete foundation, constructed around the pile foundation at a predetermined depth below the end of the pile foundation, used to fix the pile foundation. This utility model reduces the amount of earthwork excavation, the horizontal excavation area, and the vertical excavation depth, effectively reducing conflicts with surrounding underground pipelines and the risk of damage to them. Simultaneously, the shallow pit concrete foundation reduces the amount of concrete poured, shortens the construction period, and improves the overall construction efficiency of the composite foundation.

The invention particularly relates to a dynamic congestion sensing hierarchical scheduling method and device based on reconfigurable computing, and the method comprises the steps: constructing a hierarchical tree-shaped scheduling structure, and mapping a node scheduling algorithm and a congestion algorithm to a reconfigurable computing module; performing congestion identification on the dequeued and enqueued queues based on a mapping congestion algorithm; when an enqueue application is received, the messages are classified according to a congestion detection result; calculating priority and sending time information of the dequeued application queue elements; queue elements are pushed into the scheduling sub-lists according to the priorities, ordered insertion of the priorities and sending time of the queue elements is completed in the sub-lists, the elements which meet the sending time and have the highest priorities are extracted, and the scheduling sub-lists and information of corresponding pointers are updated during pushing and extraction. According to the invention, dynamic adjustment of the scheduling strategy is supported, dynamic and efficient sharing of intelligent differential congestion control and computing resources is realized, and the scheduling efficiency of complex multi-service traffic in high-speed network equipment is improved.

The invention relates to a block chain data synchronization method and device, equipment, a storage medium and a product, and relates to the technical field of block chains. The method comprises the steps of obtaining prediction data related to a network state of a block chain network; predicting the network load of the block chain network based on the prediction data through the hybrid prediction model to obtain a network load prediction value; the hybrid prediction model is constructed based on a time sequence model and a graph neural network model; based on the network load prediction value and the network topology structure information, performing preliminary slicing on the to-be-synchronized data to obtain a preliminary slicing result; performing resource consumption assessment and synchronous risk assessment on each block chain node to obtain a resource consumption score and a synchronous risk score of each block chain node; and generating a data synchronization strategy based on the resource consumption score and the synchronization risk score of each block chain node and the preliminary slicing result, so as to perform block chain data synchronization based on the data synchronization strategy.

The invention discloses a data processing system and method based on a vehicle-mounted CAN / LIN bus hybrid application layer, and the system comprises a data collection layer which is used for receiving and transmitting a CAN message, and receiving and transmitting an LIN message; the cache management layer comprises a cache strategy and cache partitions, the cache strategy comprises cache according to a matrix table and cache index counting, and the cache partitions comprise a CAN channel partition and an LIN channel partition; the network transmission layer comprises a communication protocol and frame header filling, the communication protocol comprises a UDP (User Datagram Protocol) and CAN / LIN (Controller Area Network / Local Interconnect Network) packaging and reassembling, the frame header filling comprises a filling format and filling content, and the method further comprises a CAN / LIN message circular cache management method, a dynamic template CAN data acquisition method and a timestamp synchronous calibration method. The method has the advantages that the CAN message processing efficiency is improved, the memory occupation is reduced, the timestamp synchronization precision is enhanced, dynamic configuration and template switching are supported, and CAN / LIN bus unified management is realized.

The application provides a path planning method based on a DYPIBT algorithm, which can effectively solve path conflicts between agents in narrow and busy terrain, and reduce invalid movement and chain congestion of the agents. The method fuses four-dimensional dynamic calculation priorities of task urgency, remaining distance, local congestion coefficient and unique ID, so as to ensure that each agent has different priorities at the same time step. For each position in the map, a pre-judgment backtracking judgment is performed, the next congestion risk is pre-judged before the agent moves, backtracking is triggered in advance, and invalid movement of the agent is reduced. A high-priority priority rule and a priority inheritance rule are designed for the path conflict problem of the agent. After a high-priority agent occupies a target position, a low-priority agent inherits the priority of the high-priority agent, so that the agent that has given way can have an opportunity to obtain road right in the next path selection, and a single agent can reduce invalid movement.

The application relates to the technical field of bearing retainers, in particular to a tapered roller retainer which comprises a first ring body, a second ring body and a plurality of connecting beams connecting the first ring body and the second ring body, a pocket is formed around the first ring body, the second ring body and any two adjacent connecting beams; one end of the connecting beam towards the center of the circle is provided with a limiting part in the form of a protrusion, at least one limiting protrusion is arranged on the limiting part; at the same height, the minimum distance between the two adjacent limiting protrusions is smaller than the diameter of the tapered roller, and the distance between the limiting protrusion and the retainer shaft center is smaller than the distance between the shaft center of the tapered roller and the retainer shaft center, so that the application has the advantage of reducing the assembly difficulty of the roller.

The application relates to the technical field of Internet of Things warehouse management, and discloses a warehouse data comprehensive management system, method, equipment and medium based on the Internet of Things, which is characterized in that: firstly, warehouse basic environment and main body modeling are carried out, including establishing a warehouse grid map, an AGV cluster and a task set model; a global space-time occupation ST(v, t) table is constructed according to AGV empty running rate, conflicts, delays and energy consumption, and a multi-objective optimization function is constructed; the generated AGV carrying tasks are sorted according to priority and deadline, and the tasks are auctioned according to task application values, the tasks with larger application values obtain the tasks, and space-time resources are locked; lower local re-planning is carried out, the AGV obtaining the tasks travels along a pre-planned space-time path, and periodic detection is carried out during path execution, whether obstacles / conflicts / lockups or task changes appear is judged, and a new path is generated in combination with the global ST(v, t) table and real-time obstacles. The application solves the contradiction of multi-AGV collaborative task conflicts, and avoids the problem that traditional algorithms can only stop or invalidly bypass when encountering lockups, so that the overall efficiency is low.

The invention relates to a multi-modal data correction method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining target multi-modal data, and generating a corresponding initial text based on the target multi-modal data, the target multi-modal data at least comprising voice data; sending the initial text to a plurality of terminals, so that the plurality of terminals perform real-time labeling operation based on the initial text to obtain collaborative labeling data; receiving collaborative annotation data sent by the plurality of terminals, and generating a collaborative annotation result according to the collaborative annotation data; and based on the collaborative labeling result, correcting the initial text to generate a corrected text. Therefore, a multi-user real-time collaborative labeling and dynamic correction mechanism is introduced in a multi-mode voice transcription process, and adaptive optimization and elastic computing power scheduling are combined, so that real-time editability, collaborative consistency and high accuracy of a transcription text are realized, and meanwhile, stable operation of a system in a high-concurrency scene is guaranteed.

This invention provides a problem analysis and processing method, apparatus, electronic device, medium, and program product, applicable to the field of artificial intelligence technology. The method includes: acquiring target problem text to be analyzed; performing type identification and text extraction on the target problem text based on a preset set of problem type tags to obtain a first text fragment and a second text fragment; selecting target knowledge resources from different types of knowledge resources based on the first and second text fragments and performing retrieval to obtain corresponding first and second candidate information; and performing dynamic balancing calculations on the first and second candidate information to obtain processing suggestions. By integrating philosophical analysis methods with an artificial intelligence problem parsing framework, different problem types in mixed inputs can be accurately separated, and appropriate retrieval strategies and generation logics can be adopted for each, thereby avoiding knowledge mismatch and improving the accuracy and persuasiveness of the response.

The invention discloses a micro-grid scheduling method and device, computer equipment and a storage medium, which can be applied to various scenes such as power system operation and power resource management, and the method comprises the following steps: constructing a plurality of reward functions of a micro-grid; based on the plurality of reward functions, constructing an initial reinforcement learning model of the micro-grid; optimizing the initial reinforcement learning model by using a preset multi-target optimization algorithm to obtain a target reinforcement learning model; and inputting the micro-grid data into the target reinforcement learning model, outputting a scheduling strategy, and executing micro-grid scheduling based on the scheduling strategy. The key performance indexes in the operation process of the micro-grid are effectively integrated, the corresponding reward function is configured for each key performance index, conflicts among the multiple reward functions are reduced through the multi-target optimization algorithm, the method can be suitable for micro-grid scheduling of a multi-target scene, the robustness and adaptability of the model are enhanced, and the scheduling efficiency of the micro-grid is improved. And the operation efficiency and reliability of the micro-grid are also improved.

The present application relates to automatic loading and unloading technical field, especially to a kind of automatic loading and unloading unmanned vehicle loading and unloading method and system, method includes: according to loading and unloading task and operating area map, initial global shortest path and path point sequence are obtained by A algorithm;With any unmanned vehicle as target vehicle, the rest is matching vehicle, risk characteristic value of path point is quantified by DTW algorithm interactive analysis, adaptability score is obtained by combining direction deviation, and screening point is local target point;Based on the risk characteristic value and local target point of dynamic updating, the path is adjusted in real time using improved artificial potential field method, and the loading and unloading task is completed by cyclic iteration.The present application combines A algorithm and improved artificial potential field method, determines global path by A algorithm, quantifies risk characteristic value by DTW algorithm and dynamically updates local target point, adjusts potential field intensity to avoid dynamic obstacles, guarantees path optimization and driving stability, and reduces conflict congestion.

The invention relates to a multi-mechanical-arm motion intelligent partitioning and avoiding method, a storage medium and detection equipment, and the multi-mechanical-arm motion intelligent partitioning method comprises the following steps that target point coordinates in a mechanical arm operation area are obtained; determining candidate segmentation lines in all the segmentation directions according to the coordinate distribution characteristics of the target points in the plurality of preset segmentation directions and preset window parameters, so that the number of the target points in the areas on the two sides of the candidate segmentation lines tends to be balanced; delimiting a dangerous area according to the candidate segmentation line and a preset collision risk parameter, wherein a target point in the dangerous area is a dangerous point; and counting the number of dangerous points in the dangerous area corresponding to each segmentation direction, selecting a candidate segmentation line with a small number of dangerous points as a target segmentation line, dividing the operation area into a plurality of sub-areas through the target segmentation line, and allocating one mechanical arm to each sub-area. Intelligent, efficient and risk-free cooperative avoidance of the multiple mechanical arms is achieved.

Embodiments of the present application provide a network parameter planning method and device, the method comprises: determining the coordinate sequence of the coverage area block of the cell of the 5G base station according to the spatial topology distribution of the 5G base station in the network, determining the adjacent area block sequence of the coverage area block of the cell of the current 5G base station according to the coordinate sequence, determining the 5G base station adjacent cell sequence according to the adjacent area block sequence, and processing the PCI sequence configured for the 5G base station adjacent cell sequence to determine the target processing result from the processing result sequence, determining the target cell sequence from the 5G base station adjacent cell sequence according to the target processing result, and determining the shortest path sequence between the cell of the current 5G base station and the target cell sequence, determining the shortest distance sequence according to the shortest path sequence, determining the target shortest distance from the shortest distance sequence, and planning the PCI of the current 5G base station, which realizes the planning of the PCI parameter in the 5G base station.