User perception improvement method, system and equipment based on terminal and storage medium
By collecting and modeling data of 5G terminal users, evaluating cell quality poorness, positioning the root cause, and adjusting network parameters, the problem of poor perception of 5G terminal users is solved, and the perception improvement of terminal access network is achieved.
Patent Information
- Application Number
- CN202411052804.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-01
AI Technical Summary
In the prior art, the signal strength of 5G terminals receive large differences, resulting in poor user perception, and the unified configuration of network parameters cannot be effectively switched to a 4G network with better coverage, affecting the user experience.
Through the terminal-based user perception improvement method, basic information of users and cells is collected, data processing and portrait modeling is carried out, poor quality is evaluated, root causes are located, and optimization measures are matched, such as adjusting the switching threshold, and improving the perceived quality of terminal access network .
For specific end users, analyze and optimize the cell network, improve the perceived quality of terminal access network, ensure the network quality of all terminals, and improve user experience.
Smart Images

Figure CN118890643A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of communication networks, and in particular to a terminal-based user perception enhancement method, a terminal-based user perception enhancement system, an electronic device, and a computer-readable storage medium. Background Art
[0002] With the upgrading of mobile communication networks, more frequency resources and network resources are used in the development of 5G and 4G mobile communication networks. Due to different 5G terminals, the signal strength of 5G network reception varies greatly. For example, if the signal strength of a certain terminal user group is lower than that of other terminals, the user perception will be poor if they are located in the weak coverage area at the edge of 5G.
[0003] The 5G and 4G network parameter configurations are uniformly configured with reference to the base station opening parameters, and are applicable to all 5G terminals accessing the network. For terminals with low received signal strength, it is easy for them to stay on the 5G network, resulting in a weak signal, and they cannot switch to the 4G network with better coverage, resulting in poor user perception. Summary of the invention
[0004] In order to at least solve the problem in the prior art that unified configuration of network parameters has a significant impact on specific terminals, resulting in poor user perception, the present disclosure provides a terminal-based user perception improvement method, a terminal-based user perception improvement system, an electronic device, and a computer-readable storage medium, which score based on cell portraits, classify problem types according to the scoring results, and output corresponding optimization measures to meet the terminal access network perception guarantee.
[0005] In a first aspect, the present disclosure provides a method for improving user perception based on a terminal, the method comprising:
[0006] Collect data to obtain basic information about users, cells and permanent locations related to specific terminals;
[0007] Process the collected data, merge and clean the data based on common features, and define labels to output sample data of the community;
[0008] Conduct portrait modeling on sample data of the community;
[0009] Evaluate quality and locate root causes based on the results of portrait modeling;
[0010] Match optimization measures for the cell based on root cause location.
[0011] Furthermore, the basic information includes:
[0012] User-level and cell-level MR (Measurement Report) data, KPI (Key Performance Indicator) data, KQI (Key Quality Indicators) data, basic engineering parameter data, user complaint information data, user billing data, user package data and user resident data.
[0013] Furthermore, the image modeling of the sample data of the cell includes:
[0014] For the clustering areas of specific terminals, data analysis is performed from the three dimensions of users, networks, and markets. The indicators of each dimension of the cells in the clustering areas are scored according to preset rules, and the final scores of each cell are summarized to obtain the resident cell portrait of the specific terminal;
[0015] User dimension indicators include user complaints and user weak coverage;
[0016] Network dimension indicators include poor voice quality, poor data quality, weak cell coverage, ultra-long cell coverage, video services, page response and page delay;
[0017] Market dimension indicators include the development and changes in the number of users.
[0018] Furthermore, the quality evaluation and root cause location based on the portrait modeling results include:
[0019] For resident communities whose final scores are lower than the preset scores, the communities are classified and their root causes are located based on four dimensions: parameter problems, coverage problems, construction problems, and other problems.
[0020] Parameter issues include: 4G coverage is better than 5G, 5G coverage is better than 4G, coverage is satisfactory but there are complaints, service is stuck and 4G coverage is better than 5G;
[0021] Coverage issues include: weak 4G coverage, ultra-long cell coverage;
[0022] Construction issues include: 4. Weak 5G coverage;
[0023] Other issues include: market development issues.
[0024] Furthermore, the cell matching optimization measures according to the root cause positioning include:
[0025] For the parameter problem in which 4G coverage is better than 5G, the 5G residence threshold is raised;
[0026] Regarding the parameter problem where 5G coverage is better than 4G, the switching threshold for voice services from 5G to 4G is raised;
[0027] For the coverage complaints in the parameter problem, the reselection threshold from 5G to 4G is raised;
[0028] For the service jams in the parameter problem and 4G coverage is better than 5G, increase the switching threshold for data services from 5G to 4G.
[0029] Furthermore, the method further comprises:
[0030] A list of cells with poor image quality is issued, and based on the feedback on the implementation results of matching optimization measures, the cells are profiled to determine whether they are closed-loop, and the root cause location is iteratively optimized.
[0031] In a second aspect, the present disclosure provides a terminal-based user perception improvement system, the system comprising:
[0032] A data collection module, which is configured to collect data and obtain basic information about users, cells and permanent locations related to a specific terminal;
[0033] A data processing module is configured to process the collected data, merge and clean the data by common features, and define labels to output sample data of the cell;
[0034] A portrait module, which is configured to perform portrait modeling on sample data of a community;
[0035] An analysis module, which is configured to assess poor quality and locate root causes based on the results of the portrait modeling;
[0036] An optimization module is configured to match optimization measures for the cell based on root cause location.
[0037] Furthermore, the system also includes an implementation feedback module;
[0038] The implementation feedback module is configured to issue a list of poor-quality images of the cell, and based on the feedback of the matching optimization measures implementation results, profile the processed cell to determine whether it is closed-loop, and iteratively optimize the root cause location.
[0039] In a third aspect, the present disclosure provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the terminal-based user perception enhancement method as described in any one of the first aspects.
[0040] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the terminal-based user perception enhancement method described in any one of the above-mentioned first aspects is implemented.
[0041] Beneficial effects:
[0042] The terminal-based user perception improvement method, terminal-based user perception improvement system, electronic device and storage medium provided by the present invention perform data analysis and portrait modeling for specific terminal users, output specific terminal focus and user complaint area cells, conduct quality assessment and root cause location for the cells, optimize operational measures for output cell matching, improve terminal access network perception, and ensure network quality for all terminals. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 A schematic diagram of a process of improving user perception based on a terminal provided in the first embodiment of the present disclosure;
[0044] Figure 2 A specific flow chart of a method for improving user perception based on a terminal provided in the second embodiment of the present disclosure;
[0045] Figure 3 A schematic diagram of a user terminal perception analysis dimension provided in the second embodiment of the present disclosure;
[0046] Figure 4 This is an architecture diagram of a terminal-based user perception enhancement system provided in Embodiment 3 of the present disclosure;
[0047] Figure 5 This is an architecture diagram of an electronic device provided in Embodiment 4 of the present disclosure. DETAILED DESCRIPTION
[0048] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the drawings and embodiments. It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention, rather than to limit the present invention.
[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence; and, in the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other.
[0050] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms of "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings.
[0051] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present disclosure, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.
[0052] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems existing in the prior art are described in detail below with specific embodiments. It is understandable that in the embodiments of the present application, the execution subject can perform some or all of the steps in the embodiments of the present application, and these steps or operations are only examples. The embodiments of the present application can also perform other operations or deformations of various operations. In addition, each step can be performed in a different order presented in the embodiments of the present application, and it is possible not to perform all the operations in the embodiments of the present application. And, the following several specific embodiments can be combined with each other, and may not be repeated in some embodiments for the same or similar concepts or processes.
[0053] Figure 1 A method for improving user perception based on a terminal is provided in the first embodiment of the present disclosure, such as Figure 1 As shown, the method includes:
[0054] Step S101: collect data to obtain basic information about users, cells and permanent locations related to a specific terminal;
[0055] Step S102: Process the collected data, merge and clean the data based on common features, and define labels to output sample data of the cell;
[0056] Step S103: Performing image modeling on sample data of the community;
[0057] Step S104: evaluating poor quality and locating root causes based on the portrait modeling results;
[0058] Step S105: Matching optimization measures for the cell according to the root cause positioning.
[0059] Due to the differences in 5G terminals, the strength of received 5G network signals varies greatly. For example, the received signal strength of some terminal user groups is lower than that of other terminals. For these terminals, their gathering areas or certain cells, according to the current parameter configuration, may cause poor user perception.
[0060] To solve this problem, the disclosed embodiment obtains basic information about users, cells and permanent locations related to specific terminals from the network side, service side and account side. The specific terminal is a terminal that receives a certain network signal with relatively weak signal strength; and through common features such as user number and permanent cell, data of different dimensions are associated, merged and cleaned, and then labels are defined for key indicators of the portrait model to determine whether there is a problem in the cell represented by the data, so as to facilitate the subsequent quality assessment of the cell; and sample data of each cell is obtained. Then AI portrait modeling is performed, and portrait assessment and scoring are performed through weight allocation of key indicators and specified algorithm rules. According to the portrait judgment result, it is determined whether the cell has poor image quality. If there is no poor image quality, the loop can be closed. If the cell has poor image quality for this type of terminal, the quality assessment and root cause location are performed to find out the reasons for poor user perception and match the corresponding optimization measures for the cell, such as adjusting the switching parameters. It should be noted that the disclosed embodiment can not only be used to address the problem of receiving weak 5G network signal strength, but also can be applied to other networks.
[0061] The disclosed embodiment performs data analysis and portrait modeling for specific terminal users, outputs cells where specific terminals are focused and where users complain, conducts quality assessment and root cause location for the cells, optimizes operational measures for output cell matching, improves terminal access network perception, and ensures network quality for all terminals.
[0062] Furthermore, the basic information includes:
[0063] User-level and cell-level MR data, KPI data, KQI data, basic engineering parameter data, user complaint information data, user billing data, user package data and user resident data.
[0064] By collecting data on the network side (MR data (user level, cell level), KPI, KQI data, basic engineering parameter data), the service side (user complaint information data) and the operating and accounting side (user billing, package, resident, etc. data), the basic information of a specific type of terminal can be obtained; through this basic information, the network status of this type of terminal can be fully obtained, such as the user's uplink and downlink speeds, voice, telephone, data services, etc., so as to better and more comprehensively profile the cell.
[0065] Furthermore, the image modeling of the sample data of the cell includes:
[0066] For the clustering areas of specific terminals, data analysis is performed from the three dimensions of users, networks, and markets. The indicators of each dimension of the cells in the clustering areas are scored according to preset rules, and the final scores of each cell are summarized to obtain the resident cell portrait of the specific terminal;
[0067] User dimension indicators include user complaints and user weak coverage;
[0068] Network dimension indicators include poor voice quality, poor data quality, weak cell coverage, ultra-long cell coverage, video services, page response and page delay;
[0069] Market dimension indicators include the development and changes in the number of users.
[0070] For the clustered areas, according to the 100-point mechanism, refer to the algorithm rules in the table below to deduct points from each evaluation dimension, and summarize the final scores of the cells to profile the specific terminal resident cells.
[0071] Table 1: Portrait reference scoring table
[0072]
[0073]
[0074] Note: User / cell weak coverage: User / cell MR RSRP (Reference Signal Receiving Power)>=-105 ratio <90%; Cell ultra-long coverage: User access Tadv (Time Advance) distance, 600 meters in urban areas and 1000 meters in rural areas.
[0075] According to the rules in Table 1 above, a comprehensive scoring profile is made from the indicators of each dimension. In this way, the poor quality cells can be determined, and the clustering and user complaint area base station cell list can be output to the terminal. Problem analysis can also be carried out according to the specific situation of each indicator.
[0076] Furthermore, the quality evaluation and root cause location based on the portrait modeling results include:
[0077] For resident communities whose final scores are lower than the preset scores, the communities are classified and their root causes are located based on four dimensions: parameter problems, coverage problems, construction problems, and other problems.
[0078] Parameter issues include: 4G coverage is better than 5G, 5G coverage is better than 4G, coverage is satisfactory but there are complaints, service is stuck and 4G coverage is better than 5G;
[0079] Coverage issues include: weak 4G coverage, ultra-long cell coverage;
[0080] Construction issues include: 4. Weak 5G coverage;
[0081] Other issues include: market development issues.
[0082] The preset score is set according to the actual situation. For example, the full score is 100 points, which can be set to 60, 70, 80, etc., and the cells with final scores lower than the set score are set as poor quality cells. Priority, if there are many problem cells, these cells can also be sorted from low to high by score, and the top problem cells with high rankings can be screened; the top cells can be classified and matched with differentiated optimization measures based on the four dimensions of parameter problems, coverage problems, construction problems, and other problems.
[0083] The determination and classification of each problem can be determined according to the determination methods in the following tables:
[0084] Table 2: Parameter problem determination
[0085]
[0086]
[0087] Table 3: Coverage problem determination
[0088]
[0089] Table 4: Construction problem determination
[0090]
[0091] Table 5: Market development issues determination
[0092]
[0093] Through the portrait evaluation and scoring, the types and dimensions of the problems and the specific situations are classified according to the scoring results, so as to achieve the matching of corresponding optimization measures for the poor quality communities.
[0094] Furthermore, the cell matching optimization measures according to the root cause positioning include:
[0095] For the parameter problem in which 4G coverage is better than 5G, the 5G residence threshold is raised;
[0096] Regarding the parameter problem where 5G coverage is better than 4G, the switching threshold for voice services from 5G to 4G is raised;
[0097] For the coverage complaints in the parameter problem, the reselection threshold from 5G to 4G is raised;
[0098] For the service jams in the parameter problem and 4G coverage is better than 5G, increase the switching threshold for data services from 5G to 4G.
[0099] For specific problem types, corresponding optimization measures are matched through the following Table 6.
[0100] Table 6: Problem types and corresponding optimization measures
[0101]
[0102]
[0103] Note: Definition of over-coverage: The proportion of TA greater than 600 meters in urban areas is greater than 30%, and the proportion of TA greater than 1km in rural areas is greater than 30%.
[0104] Through profiling, we can identify the poor quality cells for specific terminals and analyze the root causes of the poor cell quality. If it is a parameter problem, we can adjust the 5G&4G interoperability threshold. This is suitable for 5G terminal users to switch to the 4G network with better coverage as soon as possible in the 5G edge coverage area.
[0105] When multiple problems exist at the same time, they can be processed according to the pre-set optimization level, such as optimizing and adjusting the parameters first, and then determining whether all the problems are solved. If they cannot be solved, base station enhancement or construction can be performed. Of course, in order to ensure better results, optimization can be performed simultaneously.
[0106] Furthermore, the method further comprises:
[0107] A list of cells with poor image quality is issued, and based on the feedback on the implementation results of matching optimization measures, the cells are profiled to determine whether they are closed-loop, and the root cause location is iteratively optimized.
[0108] After obtaining the optimization measures for each poor-quality community, the provincial company issued a list of poor-quality images, and the prefecture-level cities fed back the implementation results to the provincial company every week or month. The provincial company profiled the processed communities to determine whether they were closed-loop and iterated to optimize the root cause location, thus ensuring that the problem was fundamentally solved.
[0109] This embodiment performs data analysis modeling for specific terminal users, outputs cells that are focused on specific terminals and user complaint areas, assesses poor quality and locates root causes of the cells, optimizes operational measures for root cause matching of the output cells, and checks the implementation of the optimization measures to ensure that poor quality cells are improved, enhance terminal access network perception, and guarantee network quality for all terminals.
[0110] The second embodiment of the present disclosure also provides a method for improving user perception based on a terminal, such as Figure 2 As shown, including:
[0111] ① Data collection: Apple terminal-associated user, community, resident and other basic information acquisition, including network-side data, such as MR data (user level, community level), KPI, KQI data, basic engineering parameter data, service-side data, such as user complaint information data and business-account data, such as user billing, package, resident and other data;
[0112] ②Data processing: Merge and clean data based on common features, such as user number and residential area, and define labels for key indicator information to output data samples;
[0113] ③ AI modeling: Modeling the image algorithm for sample data (scoring the image through the weight allocation of key indicators and the formulated algorithm rules), quality assessment (determining whether there is poor image quality based on the image judgment results), root cause location and matching optimization measures;
[0114] Take Apple terminal perception analysis as an example. Figure 3 As shown, the analysis is conducted from the user dimension, network dimension and market dimension respectively. The user dimension includes complaints (complaints about Apple terminals and non-Apple terminals are counted separately) and weak user coverage (proportion of user weak coverage); the network dimension includes voice perception (low access / high disconnection / high packet loss), data perception (low access / high disconnection / high packet loss), video service (video freeze), page browsing (low page response rate, high page latency), and cell coverage (proportion of cell weak coverage and proportion of cell ultra-long coverage); the market dimension includes a large decline in the number of users and a large number of reduced users.
[0115] Score each dimension indicator separately to obtain a cell portrait. According to the portrait results, determine the list of poor quality cells, locate the root causes of these cells, and optimize the operation measures for the root causes of the output cells.
[0116] ④ Implementation feedback: The provincial company issues a list of poor-quality portraits, and the cities and prefectures provide feedback on the implementation results to the provincial company on a weekly / monthly basis. The provincial company profiles the processed communities to determine whether they are closed-loop and iterates to optimize the root cause location.
[0117] The third embodiment of the present disclosure also provides a terminal-based user perception improvement system, such as Figure 4 As shown, the system comprises:
[0118] A data collection module 11 is configured to collect data and obtain basic information about users, cells and permanent locations related to a specific terminal;
[0119] A data processing module 12 is configured to process the collected data, merge and clean the data by common features, and define labels to output sample data of the cell;
[0120] A portrait module 13, which is configured to perform portrait modeling on sample data of a community;
[0121] An analysis module 14, which is configured to perform quality assessment and root cause location based on the portrait modeling results;
[0122] The optimization module 15 is configured to match optimization measures for the cell according to the root cause location.
[0123] Furthermore, the basic information includes:
[0124] User-level and cell-level MR data, KPI data, KQI data, basic engineering parameter data, user complaint information data, user billing data, user package data and user resident data.
[0125] Furthermore, the portrait module 13 is specifically configured as follows:
[0126] For the clustering areas of specific terminals, data analysis is performed from the three dimensions of users, networks, and markets. The indicators of each dimension of the cells in the clustering areas are scored according to preset rules, and the final scores of each cell are summarized to obtain the resident cell portrait of the specific terminal;
[0127] User dimension indicators include user complaints and user weak coverage;
[0128] Network dimension indicators include poor voice quality, poor data quality, weak cell coverage, ultra-long cell coverage, video services, page response and page delay;
[0129] Market dimension indicators include the development and changes in the number of users.
[0130] Furthermore, the analysis module 14 is specifically configured as follows:
[0131] For resident communities whose final scores are lower than the preset scores, the communities are classified and their root causes are located based on four dimensions: parameter problems, coverage problems, construction problems, and other problems.
[0132] Parameter issues include: 4G coverage is better than 5G, 5G coverage is better than 4G, coverage is satisfactory but there are complaints, service is stuck and 4G coverage is better than 5G;
[0133] Coverage issues include: weak 4G coverage, ultra-long cell coverage;
[0134] Construction issues include: 4. Weak 5G coverage;
[0135] Other issues include: market development issues.
[0136] Furthermore, the optimization module 15 is specifically configured as follows:
[0137] For the parameter problem in which 4G coverage is better than 5G, the 5G residence threshold is raised;
[0138] Regarding the parameter problem where 5G coverage is better than 4G, the switching threshold for voice services from 5G to 4G is raised;
[0139] For the coverage complaints in the parameter problem, the reselection threshold from 5G to 4G is raised;
[0140] For the service jams in the parameter problem and 4G coverage is better than 5G, increase the switching threshold for data services from 5G to 4G.
[0141] Furthermore, the system also includes an implementation feedback module 16;
[0142] The implementation feedback module is configured to issue a list of poor-quality images of the cell, and based on the feedback of the matching optimization measures implementation results, profile the processed cell to determine whether it is closed-loop, and iteratively optimize the root cause location.
[0143] The terminal-based user perception enhancement system of the disclosed embodiment is used to implement the terminal-based user perception enhancement method in method embodiment 1 and embodiment 2, so the description is relatively simple. For details, please refer to the relevant description in the previous method embodiment, which will not be repeated here.
[0144] In addition, if Figure 5 As shown, the fourth embodiment of the present disclosure further provides an electronic device, including a memory 100 and a processor 200, wherein the memory 100 stores a computer program, and when the processor 200 runs the computer program stored in the memory 100, the processor 200 executes the above-mentioned various possible methods.
[0145] The memory 100 is connected to the processor 200. The memory 100 may be a flash memory, a read-only memory or other memory, and the processor 200 may be a central processing unit or a single-chip microcomputer.
[0146] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to perform the above-mentioned various possible methods.
[0147] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), Digital Video Disc (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.
[0148] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.
Claims
1. A method for improving user perception based on a terminal, characterized in that: The method comprises: Collect data to obtain basic information about users, cells and permanent locations related to specific terminals; Process the collected data, merge and clean the data based on common features, and define labels to output sample data of the community; Conduct portrait modeling on sample data of the community; Evaluate quality and locate root causes based on the results of portrait modeling; Match optimization measures for the cell based on root cause location.
2. The method according to claim 1, characterized in that The basic information includes: User-level and cell-level measurement report MR data, key performance indicator KPI data, key quality indicator KQI data, basic engineering parameter data, user complaint information data, user billing data, user package data and user resident data.
3. The method according to claim 1, characterized in that The image modeling of the sample data of the cell includes: For the clustering areas of specific terminals, data analysis is performed from the three dimensions of users, networks, and markets. The indicators of each dimension of the cells in the clustering areas are scored according to preset rules, and the final scores of each cell are summarized to obtain the resident cell portrait of the specific terminal; User dimension indicators include user complaints and user weak coverage; Network dimension indicators include poor voice quality, poor data quality, weak cell coverage, ultra-long cell coverage, video services, page response and page delay; Market dimension indicators include the development and changes in the number of users.
4. The method according to claim 3, characterized in that: The quality evaluation and root cause location based on the portrait modeling results include: For resident communities whose final scores are lower than the preset scores, the communities are classified and their root causes are located based on four dimensions: parameter problems, coverage problems, construction problems, and other problems. Parameter issues include: 4G coverage is better than 5G, 5G coverage is better than 4G, coverage is satisfactory but there are complaints, service is stuck and 4G coverage is better than 5G; Coverage issues include: weak 4G coverage, ultra-long cell coverage; Construction issues include:
4. Weak 5G coverage; Other issues include: market development issues.
5. The method according to claim 1, characterized in that: The cell matching optimization measures according to the root cause positioning include: For the parameter problem in which 4G coverage is better than 5G, the 5G residence threshold is raised; Regarding the parameter problem where 5G coverage is better than 4G, the switching threshold for voice services from 5G to 4G is raised; For the coverage complaints in the parameter problem, the reselection threshold from 5G to 4G is raised; For the service jams in the parameter problem and 4G coverage is better than 5G, increase the switching threshold for data services from 5G to 4G.
6. The method according to claim 1, characterized in that The method further comprises: A list of cells with poor image quality is issued, and based on the feedback on the implementation results of matching optimization measures, the cells are profiled to determine whether they are closed-loop, and the root cause location is iteratively optimized.
7. A terminal-based user perception enhancement system, characterized in that: The system comprises: A data collection module, which is configured to collect data and obtain basic information about users, cells and permanent locations related to a specific terminal; A data processing module is configured to process the collected data, merge and clean the data by common features, and define labels to output sample data of the cell; A portrait module, which is configured to perform portrait modeling on sample data of a community; An analysis module, which is configured to assess poor quality and locate root causes based on the results of the portrait modeling; An optimization module is configured to match optimization measures for a cell based on root cause location.
8. The system according to claim 7, characterized in that The system also includes an implementation feedback module; The implementation feedback module is configured to issue a list of poor-quality images of the cell, and based on the feedback of the matching optimization measures implementation results, profile the processed cell to determine whether it is closed-loop, and iteratively optimize the root cause location.
9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the terminal-based user perception improvement method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the terminal-based user perception improvement method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Cell state sensing method and device and related equipment
CN119383646A
