CN114980135A - 5G base station address distribution system and method based on big data - Google Patents

5G base station address distribution system and method based on big data Download PDF

Info

Publication number
CN114980135A
CN114980135A CN202210554190.6A CN202210554190A CN114980135A CN 114980135 A CN114980135 A CN 114980135A CN 202210554190 A CN202210554190 A CN 202210554190A CN 114980135 A CN114980135 A CN 114980135A
Authority
CN
China
Prior art keywords
base station
arrangement
information
interference
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210554190.6A
Other languages
Chinese (zh)
Other versions
CN114980135B (en
Inventor
李超
章韵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nupt Institute Of Big Data Research At Yancheng
Nanjing University of Posts and Telecommunications
Original Assignee
Nupt Institute Of Big Data Research At Yancheng
Nanjing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nupt Institute Of Big Data Research At Yancheng, Nanjing University of Posts and Telecommunications filed Critical Nupt Institute Of Big Data Research At Yancheng
Priority to CN202210554190.6A priority Critical patent/CN114980135B/en
Publication of CN114980135A publication Critical patent/CN114980135A/en
Application granted granted Critical
Publication of CN114980135B publication Critical patent/CN114980135B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/18—Network planning tools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention provides a 5G base station addressing system and method based on big data, wherein the system comprises: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first area information of a first area needing 5G base station address arrangement; a formulating module, configured to formulate a base station arrangement strategy suitable for the first area according to the first area information based on a big data technology; and the execution module is used for scheduling a plurality of first workers to carry out corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the address arrangement of the 5G base station after the base station arrangement is completed. The 5G base station address distribution system and method based on the big data determine an appropriate arrangement strategy based on the first area information needing 5G base station address distribution and the big data technology, and carry out corresponding arrangement, so that the rationality of the arrangement strategy is improved.

Description

5G base station address distribution system and method based on big data
Technical Field
The invention relates to the field of big data analysis, in particular to a 5G base station address distribution system and method based on big data.
Background
At present, 5G communication services develop rapidly, coverage of related communication networks increases rapidly (for example, because more base stations are needed for building a 5G communication network compared with 4G network communication), a 5G base station is used as a key device of the 5G communication network, the layout of the 5G base station directly affects the quality of area signals, the existing base station layout is generally designed by a manual layout strategy (for example, engineering designers carry out targeted design by self experience and field information), in this case, depending on the experience of the designers, the consideration factor is not comprehensive, and the base station layout is not reasonable.
Therefore, a solution is needed.
Disclosure of Invention
One of the objectives of the present invention is to provide a 5G base station address allocation system and method based on big data, which determine an appropriate allocation strategy based on the big data technology and perform corresponding allocation based on the first area information of the 5G base station address allocation, thereby improving the rationality of the allocation strategy.
The embodiment of the invention provides a 5G base station addressing system based on big data, which comprises:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first area information of a first area needing 5G base station address arrangement;
a formulating module, configured to formulate a base station arrangement strategy suitable for the first area according to the first area information based on a big data technology;
and the execution module is used for scheduling a plurality of first workers to perform corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the 5G base station address arrangement after the base station arrangement is completed.
Preferably, the formulation module performs the following operations:
based on a big data technology, acquiring a first arrangement process of a plurality of manual 5G base station addresses;
verifying the availability of the first arrangement process, and taking the verified first arrangement process as a second arrangement process;
based on a preset model training algorithm, carrying out model training according to all the second arrangement processes to obtain a base station arrangement strategy formulation model;
and formulating a base station arrangement strategy suitable for the first area according to the first area information based on the base station arrangement strategy formulation model.
Preferably, verifying the availability of the first placement process comprises:
acquiring second area information of a second area correspondingly arranged in the first arrangement process;
performing feature extraction on the first region information to obtain a plurality of first information features;
performing feature extraction on the second region information to obtain a plurality of second information features;
performing feature matching on the first information features and the second information features to obtain matching values which are matched;
if the matching value is greater than or equal to a preset matching value threshold value, acquiring a first information type corresponding to the first information characteristic or the second information characteristic to be matched, and associating the corresponding matching value with the first information type;
accumulating and calculating the matching values associated with the first information type to obtain a matching value sum;
if the matching value sum is larger than or equal to a preset matching value and a threshold value corresponding to the first information type, taking the corresponding first information type as a second information type;
inquiring a preset information type-criticality library, and determining the criticality of the second information type;
accumulating and calculating the criticality corresponding to each second information type to obtain a criticality sum, and associating the criticality sum with the corresponding first arrangement process;
acquiring at least one 5G base station communication abnormal event which occurs historically in the second area;
analyzing a causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model to obtain a causal value;
if the cause-and-effect value is larger than or equal to a preset cause-and-effect value threshold value, carrying out severity analysis on the communication abnormal event based on a preset severity analysis model, acquiring a severity value, and associating the severity value with the corresponding first arrangement process;
accumulating and calculating the criticality associated with the first arrangement process and the criticality value to obtain a usability;
if the availability is larger than or equal to a preset availability threshold, judging that the corresponding first arrangement process is verified;
otherwise, the verification is determined to be not passed.
Preferably, the 5G base station addressing system based on big data further includes:
and the reminding module is used for acquiring a plurality of first arrangement behaviors generated by a first worker in the first area when the first worker performs corresponding base station arrangement in the first area, judging whether the first arrangement behaviors are standard, and if not, correspondingly reminding the first worker.
Preferably, the reminding module judges whether the first arrangement behavior is normal, and if not, correspondingly reminds the first worker, including:
performing behavior specification judgment on the first arrangement behavior based on a preset behavior specification judgment model to obtain a second arrangement behavior which is judged to be an irregular behavior in the first arrangement behavior, and taking the first worker corresponding to the second arrangement behavior as a second worker;
acquiring the working position and first personnel information of the second worker;
acquiring a preset dynamic display robot distribution diagram;
based on the dynamic display robot distribution diagram, acquiring a dynamic display robot closest to the working position, and controlling the dynamic display robot to move to the working position;
after the dynamic display robot reaches the working position, controlling the dynamic display robot to acquire second personnel information of a third worker within a preset range of the working position;
sequentially traversing the second personnel information, and taking the traversed second personnel information as third personnel information;
matching the first personnel information with the third personnel information, and if the first personnel information is matched with the third personnel information, taking a third worker corresponding to the matched third personnel information as a learner;
controlling the dynamic display robot to dynamically acquire the sight range of the learner;
analyzing the second arrangement behavior corresponding to the learner to obtain a learning item of the learner;
based on a preset display rule, controlling the dynamic display robot to perform dynamic display in the sight line range according to the learning item;
and when the dynamic display robot finishes displaying, finishing reminding.
Preferably, the 5G base station addressing system based on big data further includes:
the simulation module is used for carrying out simulation test on the 5G base station system based on the base station arrangement strategy before the base station arrangement is carried out, and carrying out corresponding optimization on the base station arrangement strategy based on a test result of the simulation test;
the simulation module performs the following operations:
based on a virtual reference station technology, performing simulated base station setting in the first area according to the base station arrangement strategy to obtain a simulated 5G base station system;
acquiring a plurality of simulation test points in the simulation 5G base station system based on a preset test point selection rule;
carrying out analog signal test on the analog test point to obtain the signal intensity of the analog test signal of the analog test point;
determining a test result of the simulation test according to a preset test result judgment rule based on the signal intensity of the simulation test signal;
and performing corresponding optimization based on the test result.
Preferably, based on the simulation test result, performing corresponding optimization, including:
judging whether the 5G base station addressing system needs to be optimized or not based on the test result;
if the map information of the first area is judged to need to be optimized, obtaining the map information of the first area;
based on the map information, making a two-dimensional distribution graph corresponding to the map information;
marking the signal intensity of the analog test signal on the two-dimensional distribution graph;
sending the marked two-dimensional distribution map to a preset expert node, and analyzing the interference reason of the first area by the expert node;
obtaining at least one first interference reason based on the interference reason analysis;
obtaining an interference type of the first interference cause, where the interference type includes: active interference and passive interference;
when the interference type is active interference, inquiring a preset interference reason-active interference optimization scheme library to obtain at least one second interference reason;
extracting a first interference characteristic of the first interference reason, and simultaneously extracting a second interference characteristic of the second interference reason;
performing feature matching on the first interference feature and the second interference feature, and if the matching is in accordance with the second interference feature, acquiring a matching in accordance with a third interference feature;
inquiring a preset interference characteristic-weight value database, determining the weight value of the third interference characteristic, and associating the weight value with the second interference reason;
accumulating and calculating the weight value associated with the second interference reason to obtain a weight value sum;
if the weight value sum is greater than or equal to a preset weight value threshold value, taking the corresponding second interference reason as a third interference reason;
determining a first optimization scheme corresponding to the third interference reason based on the interference reason-active interference optimization scheme library;
acquiring a preset effect analysis model, and analyzing the first processing effect to acquire a first processing effect value of the first optimization scheme;
inquiring a preset weight value and-adjustment degree library, and determining the adjustment degree of a first processing effect value corresponding to the first optimization scheme based on the weight value sum of the first optimization scheme corresponding to a third interference cause;
determining a second processing effect value corresponding to the first optimization scheme based on a first processing effect value corresponding to the first optimization scheme and the adjustment degree;
determining the first optimization scheme with the maximum second processing effect value as a second optimization scheme;
scheduling the first worker to perform corresponding optimization based on the second optimization scheme;
when the interference type is passive interference, acquiring a preset judgment circle, and controlling the judgment circle to perform random displacement on the two-dimensional distribution map;
judging a third area needing to be optimized in the two-dimensional distribution map according to a preset judgment circle judgment rule based on the signal intensity of the simulation test signal;
obtaining a complaint log of the user in the third area;
analyzing the complaint log to obtain a complaint area of the complaint user corresponding to the two-dimensional distribution map;
informing the detection personnel closest to the complaint area to carry detection equipment to go to the complaint area;
when the detection personnel reach the complaint area, detecting interference equipment in a fourth area within a preset range of the complaint area;
performing interference equipment detection on the fourth area based on a preset interference detection rule, and determining interference equipment in the fourth area;
acquiring a device manager of the interference device, and coordinating with the device manager based on a preset coordination rule;
if the coordination is successful, the optimization is completed;
if the coordination fails, acquiring a preset base station adjustment strategy base, and determining a base station adjustment strategy aiming at the interference equipment based on a third interference reason of the interference equipment;
based on the base station adjustment strategy, adjusting the base station arrangement strategy to obtain an adjusted optimized arrangement strategy;
and scheduling the first worker to perform the 5G base station address distribution in the first area based on the optimal arrangement strategy.
The invention provides a 5G base station address distribution method based on big data, which comprises the following steps:
step S1: acquiring first area information of a first area needing 5G base station address arrangement;
step S2: based on big data technology, making a base station arrangement strategy suitable for the area according to the first area information;
step S3: and scheduling a plurality of first workers to perform corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the 5G base station address arrangement after the base station arrangement is completed completely.
Preferably, step S2: based on big data technology, according to the first area information, making a base station arrangement strategy suitable for the area, including:
based on a big data technology, acquiring a plurality of manual first arrangement processes for arranging addresses of the 5G base stations;
verifying the availability of the first arrangement process, and taking the verified first arrangement process as a second arrangement process;
based on a preset model training algorithm, carrying out model training according to the second arrangement process to obtain a base station arrangement strategy formulation model;
and formulating a base station arrangement strategy according to the first area information based on the base station arrangement strategy formulation model.
Preferably, verifying the availability of the first placement process comprises:
acquiring second area information of a second area correspondingly arranged in the first arrangement process;
performing feature extraction on the first region information to obtain a plurality of first information features;
performing feature extraction on the second region information to obtain a plurality of second information features;
performing feature matching on the first information feature and the second information feature to obtain a matching value which matches;
if the matching value is greater than or equal to a preset matching value threshold value, acquiring a first information type corresponding to the first information characteristic or the second information characteristic to be matched, and associating the corresponding matching value with the first information type;
accumulating and calculating the matching values associated with the first information type to obtain a matching value sum;
if the matching value sum is larger than or equal to a preset matching value and a threshold value corresponding to the first information type, taking the corresponding first information type as a second information type;
inquiring a preset information type-criticality library, and determining the criticality of the second information type;
accumulating and calculating the criticality corresponding to each second information type to obtain a criticality sum, and associating the criticality sum with the corresponding first arrangement process;
acquiring at least one 5G base station communication abnormal event which occurs historically in the second area;
analyzing a causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model to obtain a causal value;
if the cause-and-effect value is larger than or equal to a preset cause-and-effect value threshold value, carrying out severity analysis on the communication abnormal event based on a preset severity analysis model, acquiring a severity value, and associating the severity value with the corresponding first arrangement process;
accumulating and calculating the criticality associated with the first arrangement process and the criticality value to obtain a usability;
if the availability is larger than or equal to a preset availability threshold, judging that the first arrangement process is verified;
otherwise, the verification is determined to be not passed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic diagram of a 5G base station addressing method based on big data according to an embodiment of the present invention;
fig. 2 is a flowchart of a 5G base station addressing method based on big data in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
An embodiment of the present invention provides a 5G base station addressing system based on big data, as shown in fig. 1, including:
the system comprises an acquisition module 1, a processing module and a processing module, wherein the acquisition module is used for acquiring first area information of a first area needing 5G base station address arrangement;
a formulating module 2, configured to formulate a base station arrangement strategy suitable for the first area according to the first area information based on a big data technology;
and the execution module 3 is used for scheduling a plurality of first workers to perform corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the 5G base station address arrangement after the base station arrangement is completed.
The working principle and the beneficial effects of the technical scheme are as follows:
acquiring first area information (such as topographic information, cell distribution, population density and the like of the first area) of a first area needing to be subjected to 5G base station address allocation, determining a proper base station arrangement strategy according to the first area information based on a big data technology, performing corresponding base station arrangement in the first area based on the base station arrangement strategy, and finishing base station address allocation after the base station arrangement needing to be arranged is finished;
the embodiment of the invention determines a proper arrangement strategy based on the first area information needing to carry out 5G base station address arrangement and based on the big data technology, and carries out corresponding arrangement, thereby improving the reasonability and comprehensiveness of the arrangement strategy.
In the 5G base station addressing system based on big data provided by the embodiment of the present invention, the formulation module 2 performs the following operations:
based on a big data technology, acquiring a plurality of manual first arrangement processes for arranging addresses of the 5G base stations;
verifying the availability of the first arrangement process, and taking the verified first arrangement process as a second arrangement process;
based on a preset model training algorithm, carrying out model training according to the second arrangement process to obtain a base station arrangement strategy formulation model;
and formulating a base station arrangement strategy according to the first area information based on the base station arrangement strategy formulation model.
The working principle and the beneficial effects of the technical scheme are as follows:
when the base station arrangement strategy formulation model is trained, a plurality of first arrangement processes can be obtained through big data, but not all the first arrangement processes have high referential performance, and if the referential performance of the first arrangement processes is low, the trained base station arrangement strategy formulation model is unreasonable; therefore, a solution is urgently needed;
obtaining a first arrangement process (base station arrangement process of manual record obtained based on big data technology) of a plurality of 5G base station addresses, verifying the availability of the first arrangement process respectively, if the first arrangement process passes the verification, performing model training on a second arrangement process passing the verification, obtaining a base station arrangement strategy formulation model (training a neural network model by taking the second arrangement process as training data, training the neural network model to be convergent), and formulating a base station arrangement strategy according to the first area information;
the embodiment of the invention verifies based on the availability of the first arrangement process to obtain a second arrangement process which passes the verification, performs model training on the second arrangement process to obtain a base station arrangement strategy formulation model, and improves the training rationality of the base station arrangement strategy formulation model.
The 5G base station address arranging system based on big data provided by the embodiment of the invention verifies the availability of the first arranging process, and comprises the following steps:
acquiring second area information of a second area correspondingly arranged in the first arrangement process;
performing feature extraction on the first area information to obtain a plurality of first information features;
performing feature extraction on the second region information to obtain a plurality of second information features;
performing feature matching on the first information features and the second information features to obtain matching values which are matched;
if the matching value is greater than or equal to a preset matching value threshold value, acquiring a first information type corresponding to the first information characteristic or the second information characteristic to be matched, and associating the corresponding matching value with the first information type;
accumulating and calculating the matching values associated with the first information type to obtain a matching value sum;
if the matching value sum is greater than or equal to a preset matching value and a threshold value corresponding to the first information type, taking the corresponding first information type as a second information type;
inquiring a preset information type-criticality library, and determining the criticality of the second information type;
accumulating and calculating the criticality corresponding to each second information type to obtain a criticality sum, and associating the criticality sum with the corresponding first arrangement process;
acquiring at least one 5G base station communication abnormal event which occurs historically in the second area;
analyzing a causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model to obtain a causal value;
if the cause-and-effect value is larger than or equal to a preset cause-and-effect value threshold value, carrying out severity analysis on the communication abnormal event based on a preset severity analysis model, acquiring a severity value, and associating the severity value with the corresponding first arrangement process;
accumulating and calculating the criticality associated with the first arrangement process and the criticality value to obtain a usability;
if the availability is larger than or equal to a preset availability threshold, judging that the corresponding first arrangement process is verified;
otherwise, the verification is determined to be not passed.
The working principle and the beneficial effects of the technical scheme are as follows:
the first arrangement process obtained through the big data is not all available, the area information of different areas is different and corresponds to different information characteristics (such as altitude, user density and distribution of the areas), the corresponding key degrees of different information characteristics are different (such as preferentially ensuring the communication quality of the areas with dense users), and if the verification is not reasonable, the first arrangement process selected is not suitable; therefore, a solution is urgently needed;
obtaining second area information (such as topographic information, cell distribution, population density and the like of a second area) of an arrangement area corresponding to a first arrangement process, performing feature extraction (which can be realized based on a feature extraction technology) on the first area information, obtaining a plurality of first information features (which is realized based on the feature extraction technology), performing feature extraction on the second area information, obtaining a plurality of second information features (the same principle as above), obtaining a matching value of matching coincidence (the larger the matching value is, the more the area information of the first area and the second area is identical), if the matching value is greater than or equal to a preset matching value threshold (such as 85), obtaining an information type (such as topographic information) of the first information features performing matching, associating the matching value with the corresponding first information type, accumulating the matching value associated with the first information type, obtaining the sum of the matching values (the sum of the matching values is larger, indicating that the similarity of the information types corresponding to the first area and the second area is higher), if the sum of the matching values is greater than or equal to a preset matching value and a threshold (for example: 500) using the corresponding first information type as the second information type, querying a preset information type-criticality database (a database, storing information types and corresponding criticalities), and determining the criticality of the second information type (the greater the criticality is, the greater the influence on the arrangement policy is, for example: 80) accumulating and calculating the criticality corresponding to the second information type to obtain a criticality sum;
acquiring at least one 5G base station communication abnormal event (such as the condition that a user telephone cannot be switched on) which occurs in the second area historically, analyzing the causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model (training the neural network model by using a plurality of records for analyzing the causal relationship of the communication abnormal event as training data to be a converged neural network model), acquiring a causal value (the larger the causal value is, the more the communication abnormal event is characterized to be caused by the first arrangement process), training the neural network model based on a preset severity analysis model (training the neural network model by using a plurality of records for manually analyzing the severity of the communication abnormal event as training data to be a converged neural network model) if the causal value is greater than or equal to a preset causal value threshold (such as 90), analyzing the severity of the communication abnormal event, acquiring a severity value (the greater the severity value is, the more serious the influence representing the communication abnormal event is), accumulating and calculating the criticality and the severity value, acquiring the corresponding availability, and if the availability is greater than or equal to a preset availability threshold (for example: 00), judging that the corresponding first arrangement process passes availability verification, otherwise, not passing verification;
the embodiment of the invention determines the matching type with a high matching value based on the matching value of the first information characteristic and the second information characteristic, calculates the criticality sum of the first arrangement process corresponding to the second information type based on the criticality of the second information type matched with the first information characteristic, determines the causal value between the first arrangement process and the communication abnormal event based on the causal analysis model, determines the serious value of the communication abnormal event corresponding to the first arrangement process based on the severity analysis model, determines the availability based on the serious value and the serious value, verifies the availability of the first arrangement process, screens out the second arrangement process passing the verification, and improves the validity of the availability verification.
The 5G base station addressing system based on big data provided by the embodiment of the invention further comprises:
and the reminding module is used for acquiring a plurality of first arrangement behaviors generated by a first worker in the first area when the first worker performs corresponding base station arrangement in the first area, judging whether the first arrangement behaviors are standard, and if not, correspondingly reminding the first worker.
The working principle and the beneficial effects of the technical scheme are as follows:
acquiring a first arrangement behavior (a field working behavior for arranging by a first worker, such as adjusting an antenna angle) when the first worker arranges a corresponding base station in a first area, judging whether the first arrangement behavior is standard, and if not, performing corresponding processing;
according to the embodiment of the invention, based on the acquired first arrangement behaviors of the first workers, the corresponding first workers with irregular arrangement behaviors are processed, so that the management efficiency is improved.
In the 5G base station addressing system based on big data provided by the embodiment of the present invention, the reminding module determines whether the first arrangement behavior is normal, and if not, correspondingly reminds the corresponding first worker, including:
performing behavior specification judgment on the first arrangement behavior based on a preset behavior specification judgment model to obtain a second arrangement behavior which is judged to be an irregular behavior in the first arrangement behavior, and taking the first worker corresponding to the second arrangement behavior as a second worker;
acquiring the working position and first person information of the second worker;
acquiring a preset dynamic display robot distribution diagram;
based on the dynamic display robot distribution diagram, acquiring a dynamic display robot closest to the working position, and controlling the dynamic display robot to move to the working position;
after the dynamic display robot reaches the working position, controlling the dynamic display robot to acquire second personnel information of a third worker within a preset range of the working position;
sequentially traversing the second personnel information, and taking the traversed second personnel information as third personnel information;
matching the first personnel information with the third personnel information, and if the first personnel information is matched with the third personnel information, taking a third worker corresponding to the matched third personnel information as a learner;
controlling the dynamic display robot to dynamically acquire the sight range of the learner;
analyzing the second arrangement behavior corresponding to the learner to obtain a learning item of the learner;
based on a preset display rule, controlling the dynamic display robot to perform dynamic display in the sight line range according to the learning item;
and when the dynamic display robot finishes displaying, finishing reminding.
The working principle and the beneficial effects of the technical scheme are as follows:
when a worker arranges a base station, the base station arrangement is unreasonable if the first arrangement behavior is irregular, and the quality of the whole network is further affected, so that the irregular worker needs to be reminded in time (for example, the base station arrangement is not carried out according to an arrangement strategy), and the reminding worker needing to carry out corresponding treatment needs to be determined; therefore, a solution is urgently needed;
based on a preset behavior specification judging model (training a neural network model by using a plurality of records for artificially judging the normativity of behaviors as training data and training the neural network model to a converged neural network model), performing behavior specification judgment on a first arrangement behavior, determining an irregular second arrangement behavior from the first arrangement behavior, and meanwhile, determining an irregular second worker, and acquiring a working position (the working position can be acquired by an intelligent terminal device carried by the second worker through a GPS positioning technology) and personnel information (such as personnel face information, construction projects and the like) of the second worker;
acquiring a preset dynamic display robot distribution diagram (the dynamic display robot stores standard behavior data of different operation projects, the acquired distribution diagram is the dynamic position of the dynamic display robot in an operation area), acquiring the dynamic display robot closest to the working position, and controlling the dynamic display robot to move to the working position (the position of a second worker);
after the dynamic display robot reaches the working position, controlling the dynamic display robot to acquire second personnel information (such as face information of a third person) of a third person within a preset range (such as within 50 m) of the working position, determining a learner to be displayed from the third person based on a face recognition technology, controlling the dynamic display robot to acquire a sight line range of the learner (the dynamic display robot acquires a visual area of the learner through a configured miniature camera), analyzing a second arrangement behavior corresponding to the learner, acquiring a learning item of the learner (such as an antenna adjustment method), controlling the dynamic display robot to dynamically display within the sight line range based on a preset display rule (a display method, such as the whole process of displaying a construction standard and standard behavior to the first learner through a 3D holographic projection technology), and controlling the dynamic display robot to display in accordance with the learning item, when the dynamic display robot finishes displaying, finishing reminding;
according to the embodiment of the invention, the first second working personnel with irregular arrangement behaviors are determined based on the preset behavior specification judgment model, and the irregular second working personnel are deeply reminded of different learning items to be learned through the preset dynamic display robot based on the 3D projection technology, so that the reminding effectiveness and pertinence are improved.
The 5G base station addressing system based on big data provided by the embodiment of the invention further comprises:
the simulation module is used for carrying out simulation test on the 5G base station system based on the base station arrangement strategy before the base station arrangement is carried out, and carrying out corresponding optimization on the base station arrangement strategy based on a test result of the simulation test;
the simulation module performs the following operations:
based on a virtual reference station technology, performing simulated base station setting in the first area according to the base station arrangement strategy to obtain a simulated 5G base station system;
acquiring a plurality of simulation test points in the simulation 5G base station system based on a preset test point selection rule;
carrying out analog signal test on the analog test point to obtain the signal intensity of the analog test signal of the analog test point;
determining a test result of the simulation test according to a preset test result judgment rule based on the signal intensity of the simulation test signal;
and carrying out corresponding optimization based on the test result.
The working principle and the beneficial effects of the technical scheme are as follows:
because the construction cost of the base station is high and the position adjustment at the later stage is inconvenient, the base station is simulated according to a base station arrangement strategy before the construction to obtain a simulated 5G base station system (realized by a virtual reference station technology), a plurality of simulated test points in the simulated 5G base station system are obtained based on a preset test point selection rule (the selected position and density are, for example, intensive selection in a residential area), a simulated signal test is carried out on the simulated test points to obtain the signal strength (for example, -20dBm) of the simulated test signals of the simulated test points, and the test results of the simulated test are determined according to a preset test result determination rule (for example, the signal strength of the simulated test points lower than-70 dBm is larger than 10, the signal strength of the simulated test points is determined to be weak, and the base station arrangement needs to be adjusted);
the embodiment of the invention performs analog signal test on the 5G base station system before the base station is constructed, obtains the analog test result, provides data support for the effect of base station arrangement, and improves the reliability.
The 5G base station addressing system based on big data provided by the embodiment of the invention is correspondingly optimized based on the simulation test result, and comprises the following steps:
judging whether the 5G base station addressing system needs to be optimized or not based on the test result;
if the map information of the first area is judged to need to be optimized, obtaining the map information of the first area;
based on the map information, making a two-dimensional distribution graph corresponding to the map information;
marking the signal intensity of the analog test signal on the two-dimensional distribution graph;
sending the marked two-dimensional distribution map to a preset expert node, and analyzing the interference reason of the first area by the expert node;
obtaining at least one first interference reason based on the interference reason analysis;
obtaining an interference type of the first interference cause, where the interference type includes: active interference and passive interference;
when the interference type is active interference, inquiring a preset interference reason-active interference optimization scheme library to obtain at least one second interference reason;
extracting a first interference characteristic of the first interference reason, and simultaneously extracting a second interference characteristic of the second interference reason;
performing feature matching on the first interference feature and the second interference feature, and if the first interference feature and the second interference feature are matched, acquiring a third interference feature matched with the first interference feature;
inquiring a preset interference characteristic-weight value database, determining the weight value of the third interference characteristic, and associating the weight value with the second interference reason;
accumulating and calculating the weight value associated with the second interference reason to obtain a weight value sum;
if the weight value sum is greater than or equal to a preset weight value threshold value, taking the corresponding second interference reason as a third interference reason;
determining a first optimization scheme corresponding to the third interference reason based on the interference reason-active interference optimization scheme library;
acquiring a preset effect analysis model, and analyzing the first processing effect to acquire a first processing effect value of the first optimization scheme;
inquiring a preset weight value and-adjustment degree library, and determining the adjustment degree of a first processing effect value corresponding to the first optimization scheme based on the weight value sum of the first optimization scheme corresponding to a third interference cause;
determining a second processing effect value corresponding to the first optimization scheme based on a first processing effect value corresponding to the first optimization scheme and the adjustment degree;
determining the first optimization scheme with the maximum second processing effect value as a second optimization scheme;
scheduling the first worker to perform corresponding optimization based on the second optimization scheme;
when the interference type is passive interference, acquiring a preset judgment circle, and controlling the judgment circle to perform random displacement on the two-dimensional distribution map;
judging a third area needing to be optimized in the two-dimensional distribution map according to a preset judgment circle judgment rule based on the signal intensity of the simulation test signal;
obtaining a complaint log of the user in the third area;
analyzing the complaint log to obtain a complaint area of the complaint user corresponding to the two-dimensional distribution diagram;
informing the detection personnel closest to the complaint parcel to carry the detection equipment to go to the complaint parcel;
when the detection personnel reach the complaint area, detecting interference equipment in a fourth area within a preset range of the complaint area;
performing interference equipment detection on the fourth area based on a preset interference detection rule, and determining interference equipment in the fourth area;
acquiring a device manager of the interference device, and coordinating with the device manager based on a preset coordination rule;
if the coordination is successful, the optimization is completed;
if the coordination fails, acquiring a preset base station adjustment strategy base, and determining a base station adjustment strategy aiming at the interference equipment based on a third interference reason of the interference equipment;
based on the base station adjustment strategy, adjusting the base station arrangement strategy to obtain an adjusted optimized arrangement strategy;
and scheduling the first worker to perform the 5G base station address distribution in the first area based on the optimal arrangement strategy.
The working principle and the beneficial effects of the technical scheme are as follows:
when a simulated 5G base station system is subjected to system test, different signal interference reasons are determined according to a test result, and different optimization modes of the interference reasons are different; therefore, a solution is urgently needed;
judging whether optimization is needed or not based on the test result, if so, obtaining map information (such as the distribution of buildings and roads) in a preset range of a first area, obtaining a two-dimensional distribution diagram corresponding to the map information based on the map information, marking the simulation test result on the two-dimensional distribution diagram, sending the two-dimensional distribution diagram to a preset expert node (such as XX wireless communication company technical department), analyzing the interference reasons of the first area by the expert node, obtaining at least one first interference reason (such as unreasonable base station parameter setting), and obtaining the interference type of the first interference reason, wherein the interference type comprises: active interference (such as unreasonable base station parameter setting) and passive interference (such as a mobile phone signal amplifier which is installed by a communication coverage area user privately);
when the interference type is active interference, inquiring a local interference cause-active interference optimization scheme library (a database for storing active interference and corresponding schemes processed historically by a local team), acquiring at least one second interference cause, extracting a first interference feature of the first interference cause (realized based on a feature extraction technology, such as voice distortion in a call process), simultaneously extracting a second interference feature of the second interference cause (the principle is the same as above), performing feature matching on the first interference feature and the second interference feature, if the first interference feature and the second interference feature are matched, acquiring a matching conforming third interference feature, inquiring a preset interference feature-weight value library (the database for storing the interference features and weight values thereof), determining the weight value of the third interference feature, wherein the larger the weight value represents that the larger the influence of the third interference feature, and accumulating and calculating the weight value associated with the second interference cause, obtaining a weighted value sum, if the weighted value sum is greater than or equal to a preset weighted value threshold (for example, 0.8), using the corresponding second interference cause as a third interference cause (interference feature with high similarity), determining a first optimization scheme (historically, an optimization scheme adopted by the third interference feature, for example, user parameter adjustment) corresponding to the third interference cause based on an interference cause-active interference optimization scheme library, obtaining a preset effect analysis model (training a neural network model by using a plurality of records of artificially analyzed optimization scheme effects as training data, training the neural network model to a converged neural network model), analyzing a first processing effect, obtaining a first processing effect value of the first optimization scheme (the first optimization scheme corresponds to the effect of the interference corresponding to the third interference cause), querying a preset weighted value sum-adjustment degree library (database, storing a weight value and an adjustment value for the degree of adjustment of the first processing effect value), and determining the degree of adjustment of the first optimization scheme based on the sum of the weight values of the first optimization scheme corresponding to the third interference cause (for example: 0.9), determining a second treatment effect value corresponding to the first optimization scheme (the higher the second treatment effect value is, the more appropriate the corresponding first optimization scheme is), determining the first optimization scheme with the maximum second treatment effect value as a second optimization scheme (screening out the most appropriate optimization scheme), and performing corresponding optimization by the first worker (for example: readjusting base station parameters, adjusting an antenna pitch angle, and the like), when the interference type is passive interference, acquiring a preset determination circle (a closed area in a preset range), controlling the determination circle to perform random displacement in the two-dimensional distribution diagram, and based on a simulation test result, according to a preset determination circle determination rule (a preset rule for determining a region to be optimized, for example: when the simulation test result data has 10 or more-120 dBm data, determining that the area of the two-dimensional distribution diagram where the current judgment circle is located is mapped in the corresponding area of the first area as an area needing to be optimized, judging a third area needing to be optimized in the two-dimensional distribution diagram, and acquiring a complaint log of a user in the third area (a complaint record of the user, for example: at XX, communication obstacle occurs in a certain cell), the complaint log is analyzed, and a complaint section corresponding to the two-dimensional distribution graph of the complaint user is obtained (for example: XX cell), notifying the inspector closest to the complaint parcel to carry the inspection equipment (for example: handheld NR scanner), go to the complaint patch, and when the inspection staff arrives at the complaint patch, perform interference device inspection in a fourth area within a preset range of the complaint patch, and the preset interference inspection rule (interference inspection mode, for example: determining an interference source according to a gradient of signal attenuation or a gradient of interfered strength), performing interference device detection on the fourth area, and determining an interference device in the fourth area (for example: a video monitoring device in an elevator), a device manager that obtains the interfering device (e.g.: XX corporation), based on a preset coordination rule (coordination manner, for example: coordinating an opposite company to change a frequency band of a remote transmission signal), coordinating with an equipment management party, completing optimization if coordination is successful, and determining an alternative optimization scheme for the interference equipment based on a preset base station adjustment strategy base (storing other base station adjustment strategies obtained from big data) and a third interference reason of the interference equipment if coordination is failed (for example: adding a small base station near the interference equipment);
the embodiment of the invention determines the interference reason of the simulated 5G base station system based on the simulation test result obtained by the monitoring trolley and expert analysis, determines a proper optimization scheme based on the reason type, and improves the optimization efficiency.
The 5G base station address distribution method based on big data further comprises
The system comprises a user verification module, a client side and a server, wherein the user verification module is used for verifying a user when the user inputs a request for uploading a complaint log, and if the user passes the verification, the user is allowed to upload the complaint log;
wherein the user authentication of the user comprises:
acquiring the identity verification information uploaded by the user;
carrying out information splitting on the identity authentication information to obtain a plurality of information items;
obtaining an information type corresponding to the information item, wherein the information type comprises: primary information and secondary information;
when the information type is main information, acquiring a first integrity and a main value corresponding to the information item based on a preset integrity analysis model;
when the information type is auxiliary information, acquiring a second integrity and an auxiliary value corresponding to the information item based on the integrity analysis model;
calculating a verification value of the user based on the first integrity, the primary value, the second integrity and the secondary value;
when the verification value is greater than or equal to a preset verification value threshold value, the user is authenticated;
otherwise, it fails.
The working principle and the beneficial effects of the technical scheme are as follows:
the obtained identity authentication information uploaded by the user comprises (identity information, complaint content and the like of the user), the identity authentication information is split, a plurality of information items (such as name items, number items, address items and the like) are obtained, and the information type corresponding to the information items is obtained, wherein the information type comprises: main information (key information) and auxiliary information (other information for auxiliary verification), when the information type is the main information, based on a preset integrity analysis model (a plurality of records for manually performing integrity analysis on the information are used as training data to train the neural network model and train the neural network model to be converged), acquiring a first integrity and a main value (the key degree of the information item is higher, the more the information item is critical) of the corresponding information item, when the information type is the auxiliary information, based on the integrity analysis model (in principle, the same as above), acquiring a second integrity and an auxiliary value (degree of auxiliary verification) of the corresponding information item, and calculating a verification value of a user based on the first integrity, the main value, the second integrity and the auxiliary value, wherein the calculation formula is as follows:
Figure BDA0003654226440000211
where ρ is the verification value, w i Is the ith said first full value, k i Is the ith main value, n 1 For the total number of information items whose information type is primary information, w j Is the jth of the second complete value, l j Is the jth of said auxiliary value, n 2 For the total number of said information items whose information type is auxiliary information, gamma 1 And gamma 2 Is a preset weight;
when the verification value is greater than or equal to a preset verification value threshold (for example: 100), the user passes the identity verification;
the embodiment of the invention splits the information item of the identity authentication information based on the acquired identity authentication information of the user, determines the authentication value based on the integrity degree and the main degree of the information provided by the user and the auxiliary authentication degree which can help the authentication, authenticates the user applying for complaint, reduces the probability of malicious uploading, and is more favorable for pertinently solving the complaint through real-name authentication.
The invention provides a 5G base station address distribution method based on big data, as shown in fig. 2, comprising:
step S1: acquiring first area information of a first area needing 5G base station address arrangement;
step S2: based on big data technology, according to the first area information, making a base station arrangement strategy suitable for the first area;
step S3: and scheduling a plurality of first workers to perform corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the address arrangement of the 5G base station after the base station arrangement is completed.
The working principle and the beneficial effects of the above technical solution have been explained in the method right, and are not described in detail.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A big data-based 5G base station addressing system is characterized by comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first area information of a first area needing 5G base station address arrangement;
a formulating module, configured to formulate a base station arrangement strategy suitable for the first area according to the first area information based on a big data technology;
and the execution module is used for scheduling a plurality of first workers to carry out corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the address arrangement of the 5G base station after the base station arrangement is completed.
2. The big-data based 5G base station addressing system of claim 1, wherein the formulating module performs the following operations:
based on a big data technology, acquiring a first arrangement process of a plurality of manual 5G base station addresses;
verifying the availability of the first arrangement process, and taking the verified first arrangement process as a second arrangement process;
based on a preset model training algorithm, carrying out model training according to all the second arrangement processes to obtain a base station arrangement strategy formulation model;
and formulating a base station arrangement strategy suitable for the first area according to the first area information based on the base station arrangement strategy formulation model.
3. The big-data-based 5G base station addressing system as claimed in claim 2, wherein said verifying the availability of said first placement process comprises:
acquiring second area information of a second area correspondingly arranged in the first arrangement process;
performing feature extraction on the first region information to obtain a plurality of first information features;
performing feature extraction on the second region information to obtain a plurality of second information features;
performing feature matching on the first information features and the second information features to obtain matching values which are matched;
if the matching value is greater than or equal to a preset matching value threshold value, acquiring a first information type corresponding to the first information characteristic or the second information characteristic to be matched, and associating the corresponding matching value with the first information type;
accumulating and calculating the matching values associated with the first information type to obtain a matching value sum;
if the matching value sum is larger than or equal to a preset matching value and a threshold value corresponding to the first information type, taking the corresponding first information type as a second information type;
inquiring a preset information type-criticality library, and determining the criticality of the second information type;
accumulating and calculating the criticality corresponding to each second information type to obtain a criticality sum, and associating the criticality sum with the corresponding first arrangement process;
acquiring at least one 5G base station communication abnormal event which occurs historically in the second area;
analyzing a causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model to obtain a causal value;
if the cause-and-effect value is larger than or equal to a preset cause-and-effect value threshold value, carrying out severity analysis on the communication abnormal event based on a preset severity analysis model, acquiring a severity value, and associating the severity value with the corresponding first arrangement process;
accumulating and calculating the criticality associated with the first arrangement process and the criticality value to obtain a usability;
if the availability is larger than or equal to a preset availability threshold, judging that the corresponding first arrangement process is verified;
otherwise, the verification is determined to be not passed.
4. The big-data-based 5G base station addressing system of claim 1, further comprising:
and the reminding module is used for acquiring a plurality of first arrangement behaviors generated by a first worker in the first area when the first worker performs corresponding base station arrangement in the first area, judging whether the first arrangement behaviors are standard, and if not, correspondingly reminding the first worker.
5. The big-data-based 5G base station addressing system of claim 4, wherein the reminding module judges whether the first arrangement behavior is normal, and if not, correspondingly reminding the corresponding first worker comprises:
performing behavior specification judgment on the first arrangement behavior based on a preset behavior specification judgment model to obtain a second arrangement behavior which is judged to be an irregular behavior in the first arrangement behavior, and taking the first worker corresponding to the second arrangement behavior as a second worker;
acquiring the working position and first personnel information of the second worker;
acquiring a preset dynamic display robot distribution diagram;
based on the dynamic display robot distribution diagram, acquiring a dynamic display robot closest to the working position, and controlling the dynamic display robot to move to the working position;
after the dynamic display robot reaches the working position, controlling the dynamic display robot to acquire second personnel information of a third worker within a preset range of the working position;
sequentially traversing the second personnel information, and taking the traversed second personnel information as third personnel information;
matching the first personnel information with the third personnel information, and if the first personnel information is matched with the third personnel information, taking a third worker corresponding to the matched third personnel information as a learner;
controlling the dynamic display robot to dynamically acquire the sight range of the learner;
analyzing the second arrangement behavior corresponding to the learner to obtain a learning item of the learner;
controlling the dynamic display robot to perform dynamic display in the sight line range according to the learning items based on preset display rules;
and when the dynamic display robot finishes displaying, finishing reminding.
6. The big-data-based 5G base station addressing system of claim 1, further comprising:
the simulation module is used for carrying out simulation test on the 5G base station system based on the base station arrangement strategy before the base station arrangement is carried out, and carrying out corresponding optimization on the base station arrangement strategy based on a test result of the simulation test;
the simulation module performs the following operations:
based on a virtual reference station technology, performing simulated base station setting in the first area according to the base station arrangement strategy to obtain a simulated 5G base station system;
acquiring a plurality of simulation test points in the simulation 5G base station system based on a preset test point selection rule;
carrying out analog signal test on the analog test point to obtain the signal intensity of the analog test signal of the analog test point;
determining a test result of the simulation test according to a preset test result judgment rule based on the signal intensity of the simulation test signal;
and carrying out corresponding optimization based on the test result.
7. The big-data-based 5G base station addressing system as claimed in claim 6, wherein said performing corresponding optimization based on said simulation test result comprises:
judging whether the 5G base station addressing system needs to be optimized or not based on the test result;
if the map information of the first area is judged to need to be optimized, obtaining the map information of the first area;
based on the map information, making a two-dimensional distribution graph corresponding to the map information;
marking the signal intensity of the analog test signal on the two-dimensional distribution graph;
sending the marked two-dimensional distribution map to a preset expert node, and analyzing the interference reason of the first area by the expert node;
obtaining at least one first interference reason based on the interference reason analysis;
obtaining an interference type of the first interference cause, where the interference type includes: active interference and passive interference;
when the interference type is active interference, inquiring a preset interference reason-active interference optimization scheme library to obtain at least one second interference reason;
extracting a first interference characteristic of the first interference reason, and simultaneously extracting a second interference characteristic of the second interference reason;
performing feature matching on the first interference feature and the second interference feature, and if the matching is in accordance with the second interference feature, acquiring a matching in accordance with a third interference feature;
inquiring a preset interference characteristic-weight value database, determining the weight value of the third interference characteristic, and associating the weight value with the second interference reason;
accumulating and calculating the weight value associated with the second interference reason to obtain a weight value sum;
if the weight value sum is greater than or equal to a preset weight value threshold value, taking the corresponding second interference reason as a third interference reason;
determining a first optimization scheme corresponding to the third interference reason based on the interference reason-active interference optimization scheme library;
acquiring a preset effect analysis model, and analyzing the first processing effect to acquire a first processing effect value of the first optimization scheme;
inquiring a preset weight value and-adjustment degree library, and determining the adjustment degree of a first processing effect value corresponding to the first optimization scheme based on the weight value sum of the first optimization scheme corresponding to a third interference cause;
determining a second processing effect value corresponding to the first optimization scheme based on a first processing effect value corresponding to the first optimization scheme and the adjustment degree;
determining a first optimization scheme with the maximum second processing effect value as a second optimization scheme;
scheduling the first worker to perform corresponding optimization based on the second optimization scheme;
when the interference type is passive interference, acquiring a preset judgment circle, and controlling the judgment circle to perform random displacement on the two-dimensional distribution map;
judging a third area needing to be optimized in the two-dimensional distribution map according to a preset judgment circle judgment rule based on the signal intensity of the simulation test signal;
obtaining a complaint log of the user in the third area;
analyzing the complaint log to obtain a complaint area of the complaint user corresponding to the two-dimensional distribution map;
informing the detection personnel closest to the complaint parcel to carry the detection equipment to go to the complaint parcel;
when the detection personnel reach the complaint area, detecting interference equipment in a fourth area within a preset range of the complaint area;
performing interference equipment detection on the fourth area based on a preset interference detection rule, and determining interference equipment in the fourth area;
acquiring a device manager of the interference device, and coordinating with the device manager based on a preset coordination rule;
if the coordination is successful, the optimization is completed;
if the coordination fails, acquiring a preset base station adjustment strategy base, and determining a base station adjustment strategy aiming at the interference equipment based on a third interference reason of the interference equipment;
based on the base station adjustment strategy, adjusting the base station arrangement strategy to obtain an adjusted optimized arrangement strategy;
and scheduling the first worker to perform the 5G base station address distribution in the first area based on the optimal arrangement strategy.
8. A5G base station address distribution method based on big data is characterized by comprising the following steps:
step S1: acquiring first area information of a first area needing 5G base station address arrangement;
step S2: based on big data technology, according to the first area information, making a base station arrangement strategy suitable for the area;
step S3: and scheduling a plurality of first workers to perform corresponding base station arrangement in the first area according to the base station arrangement strategy, and completing the address arrangement of the 5G base station after the base station arrangement is completed.
9. The big-data-based 5G base station addressing method of claim 7, wherein the step S2 is: based on big data technology, according to the first area information, making a base station arrangement strategy suitable for the area, including:
based on a big data technology, acquiring a plurality of manual first arrangement processes for arranging addresses of the 5G base stations;
verifying the availability of the first arrangement process, and taking the verified first arrangement process as a second arrangement process;
based on a preset model training algorithm, performing model training according to the second arrangement process to obtain a base station arrangement strategy formulation model;
and formulating a base station arrangement strategy according to the first area information based on the base station arrangement strategy formulation model.
10. The big-data-based 5G base station addressing method of claim 7, wherein the verifying the availability of the first placement process comprises:
acquiring second area information of a second area correspondingly arranged in the first arrangement process;
performing feature extraction on the first region information to obtain a plurality of first information features;
performing feature extraction on the second region information to obtain a plurality of second information features;
performing feature matching on the first information features and the second information features to obtain matching values which are matched;
if the matching value is greater than or equal to a preset matching value threshold value, acquiring a first information type corresponding to the first information characteristic or the second information characteristic to be matched, and associating the corresponding matching value with the first information type;
accumulating and calculating the matching values associated with the first information type to obtain a matching value sum;
if the matching value sum is larger than or equal to a preset matching value and a threshold value corresponding to the first information type, taking the corresponding first information type as a second information type;
inquiring a preset information type-criticality library, and determining the criticality of the second information type;
accumulating and calculating the criticality corresponding to each second information type to obtain a criticality sum, and associating the criticality sum with the corresponding first arrangement process;
acquiring at least one 5G base station communication abnormal event which occurs historically in the second area;
analyzing a causal relationship between the first arrangement process and the communication abnormal event based on a preset causal analysis model to obtain a causal value;
if the cause-and-effect value is larger than or equal to a preset cause-and-effect value threshold value, carrying out severity analysis on the communication abnormal event based on a preset severity analysis model, acquiring a severity value, and associating the severity value with the corresponding first arrangement process;
accumulating and calculating the criticality associated with the first arrangement process and the criticality value to obtain a usability;
if the availability is larger than or equal to a preset availability threshold, judging that the corresponding first arrangement process is verified;
otherwise, the verification is determined to be not passed.
CN202210554190.6A 2022-05-20 2022-05-20 5G base station site distribution system and method based on big data Active CN114980135B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210554190.6A CN114980135B (en) 2022-05-20 2022-05-20 5G base station site distribution system and method based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210554190.6A CN114980135B (en) 2022-05-20 2022-05-20 5G base station site distribution system and method based on big data

Publications (2)

Publication Number Publication Date
CN114980135A true CN114980135A (en) 2022-08-30
CN114980135B CN114980135B (en) 2023-05-12

Family

ID=82984966

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210554190.6A Active CN114980135B (en) 2022-05-20 2022-05-20 5G base station site distribution system and method based on big data

Country Status (1)

Country Link
CN (1) CN114980135B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116193455A (en) * 2022-12-26 2023-05-30 中国联合网络通信集团有限公司 Base station site selection method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001285923A (en) * 2000-03-31 2001-10-12 Mitsubishi Electric Corp Method for deciding base station arrangement pattern
CN110972152A (en) * 2019-12-18 2020-04-07 武汉大学 Urban space 5G base station site selection optimization method considering signal blocking effect
CN111866896A (en) * 2020-07-17 2020-10-30 中国联合网络通信集团有限公司 Base station position determining method, device, equipment and storage medium
US20210398054A1 (en) * 2020-05-20 2021-12-23 XOEye Technologies, Inc. Automated generation of condition state information for one or more machines, devices, or systems associated with service or repair events
CN113988898A (en) * 2021-09-18 2022-01-28 安徽电信规划设计有限责任公司 5G planning site recommendation method based on big data
CN114257957A (en) * 2021-12-09 2022-03-29 北京东土拓明科技有限公司 Network planning method and device, computing equipment and computer readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001285923A (en) * 2000-03-31 2001-10-12 Mitsubishi Electric Corp Method for deciding base station arrangement pattern
CN110972152A (en) * 2019-12-18 2020-04-07 武汉大学 Urban space 5G base station site selection optimization method considering signal blocking effect
US20210398054A1 (en) * 2020-05-20 2021-12-23 XOEye Technologies, Inc. Automated generation of condition state information for one or more machines, devices, or systems associated with service or repair events
CN111866896A (en) * 2020-07-17 2020-10-30 中国联合网络通信集团有限公司 Base station position determining method, device, equipment and storage medium
CN113988898A (en) * 2021-09-18 2022-01-28 安徽电信规划设计有限责任公司 5G planning site recommendation method based on big data
CN114257957A (en) * 2021-12-09 2022-03-29 北京东土拓明科技有限公司 Network planning method and device, computing equipment and computer readable storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116193455A (en) * 2022-12-26 2023-05-30 中国联合网络通信集团有限公司 Base station site selection method and device
CN116193455B (en) * 2022-12-26 2024-03-29 中国联合网络通信集团有限公司 Base station site selection method and device

Also Published As

Publication number Publication date
CN114980135B (en) 2023-05-12

Similar Documents

Publication Publication Date Title
CN107679818A (en) Software project management method, terminal and computer-readable recording medium
CN107888574A (en) Method, server and the storage medium of Test database risk
CN101951617B (en) Mobile network communication quality evaluation method based on analytic hierarchy process
CN114491623B (en) Asynchronous federation learning method and system based on blockchain
US11762396B2 (en) Positioning system and positioning method based on WI-FI fingerprints
CN110324779A (en) Location data monitoring method and relevant device based on information security
CN104869019A (en) Feedback method and apparatus for positioning faults, and server
CN105933328B (en) A kind for the treatment of method and apparatus of user access activity
Ferreira et al. Witness-based location proofs for mobile devices
CN109522166A (en) A kind of automatic assessment method and system of equal guarantors' assessment
CN111294730A (en) Method and device for processing network problem complaint information
CN114980135A (en) 5G base station address distribution system and method based on big data
CN110267268A (en) The recognition methods of pseudo-base station, apparatus and system
CN107248995A (en) Account verification method and device
CN108764369A (en) Character recognition method, device based on data fusion and computer storage media
CN113159638B (en) Intelligent substation layered health degree index evaluation method and device
CN112800098A (en) Education management information maintenance system of education platform
CN109068329A (en) Dummy location recognition methods, device, equipment and computer readable storage medium
CN108460854A (en) The attendance punch card method and system of mobile terminal based on wireless network
CN110337118B (en) Method and device for quickly processing user complaints
CN116402458A (en) Existing building reconstruction fire-fighting inspection system
CN111314926B (en) Coverage relation determination method and device and computer readable storage medium
CN115829209A (en) Environment-friendly intelligent warehouse environment-friendly quality analysis method and device based on carbon path
CN113240824B (en) Attendance checking method and device, computer equipment and storage medium
CN110839257B (en) Network quality evaluation method, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant