A building network quality evaluation method and device, electronic equipment and medium

Abstract

Embodiments of the present application provide a building network quality evaluation method and device, electronic equipment and medium, the method comprises: obtaining the historical connection number of each base station in the base station list of the target building; determining the permanent user of the target building according to the historical connection number; when detecting that the permanent user enters the target building, obtaining the real-time signaling data of the permanent user; and evaluating the network quality of the target building according to the real-time signaling data. Through the embodiments of the present application, the building network quality is accurately evaluated based on the real-time signaling data of the permanent user.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and medium for assessing the quality of building networks. Background Technology

[0002] In the past, such applications have primarily used two methods: user-level profiling and region-level profiling.

[0003] User-level profiling, where operators use DPI (Distributed Product Index) systems to create profiles of all users, can be based on factors such as network quality, user preferences, and duration of time spent in shopping malls, extracting user tags to support subsequent marketing campaigns. However, this type of profiling often has a time lag, requiring the accumulation of a large amount of user behavior data to extract user interests or quality information. Furthermore, this type of profiling is often based on the individual, making it difficult to incorporate specific location attributes or handle users whose travel patterns are not clearly defined.

[0004] Regional profiling involves creating user profiles for specific areas, such as business districts and buildings, analyzing user characteristics and extracting regional tags. However, after extracting these tags, personalization is often difficult. A uniform strategy is typically used to recommend or tag all users within the area, making it hard to distinguish between resident and temporary users. Furthermore, for buildings with no or partial indoor coverage, it's difficult to determine whether a user is actually inside, as users often occupy external base stations near windows, making it challenging to directly evaluate building quality using regional site data. Summary of the Invention

[0005] In view of the above problems, a method, apparatus, electronic device, and storage medium for building network quality assessment are proposed to overcome or at least partially solve the above problems, including:

[0006] A method for assessing the quality of a building network, the method comprising:

[0007] Retrieve the historical connection count of each base station in the base station list of the target building;

[0008] Determine the resident users of the target building based on historical connection counts;

[0009] When a resident user is detected entering the target building, the real-time signaling data of the resident user is obtained;

[0010] Assess the network quality of the target building based on real-time signaling data.

[0011] Optionally, the number of resident users in the target building can be determined based on historical connection counts, including:

[0012] Determine the target peak hours for the target building based on historical connection counts;

[0013] Obtain historical signaling data of candidate users within a preset time period;

[0014] Based on the target busy time period and historical signaling data, determine the resident users of the target building from the candidate users.

[0015] Optionally, based on the target busy period and historical signaling data, the resident users of the target building are determined from the candidate users, including:

[0016] Determine the base station information and time information in historical signaling data;

[0017] Based on the time information, determine the number of time periods during which the candidate user appears in each base station information during the target busy period;

[0018] Determine the associated base stations of candidate users based on the number of time periods;

[0019] Based on the base station list of the target building and the associated base stations of the candidate users, determine the resident users of the target building from the candidate users.

[0020] Optionally, detecting a resident user entering the target building includes:

[0021] Obtain real-time signaling data of the target user;

[0022] Determine the base station change data of the target user based on real-time signaling data;

[0023] When the base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building.

[0024] Optionally, when base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building, including:

[0025] When matching the target user with the target resident user of the base station change data, the source base station and target base station of the base station change data are determined;

[0026] If the source base station is not in the base station list, but the target base station is in the base station list, it is determined that a resident user has been detected entering the target building.

[0027] Optionally, the network quality of the target building can be assessed based on real-time signaling data, including:

[0028] Determine the call detail record (CDR) type for real-time signaling data;

[0029] Calculate the preset user perception index scoring information according to the call detail record type;

[0030] The network quality of a building is determined based on the scoring information.

[0031] Optionally, the scoring information of preset user perception indicators is calculated according to the call detail record type, including:

[0032] Based on the call detail record (CDR) type, determine the CDR data included in the preset user perception indicators;

[0033] Obtain the weight information of user-perceived command metrics;

[0034] The weighted information and call detail record data are weighted and calculated to obtain the user perception index score information.

[0035] An apparatus for assessing the quality of a building network, the apparatus comprising:

[0036] The historical connection count acquisition module is used to obtain the historical connection count of each base station in the base station list of the target building;

[0037] The resident user identification module is used to identify resident users in a target building based on historical connection counts.

[0038] The real-time signaling data acquisition module is used to acquire the real-time signaling data of a resident user when the resident user is detected entering the target building.

[0039] The building network quality assessment module is used to assess the network quality of a target building based on real-time signaling data.

[0040] An electronic device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above-described method for assessing building network quality.

[0041] A computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the above-mentioned method for building network quality assessment.

[0042] The embodiments of the present invention have the following advantages:

[0043] This invention achieves accurate evaluation of building network quality based on real-time signaling data of resident users by obtaining the historical connection count of each base station in the base station list of the target building; determining the resident users of the target building based on the historical connection count; obtaining the real-time signaling data of the resident users when the resident users are detected entering the target building; and evaluating the network quality of the target building based on the real-time signaling data. Attached Figure Description

[0044] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of the steps of a method for assessing the quality of a building network according to an embodiment of the present invention;

[0046] Figure 2a This is a flowchart of another method for assessing building network quality provided in an embodiment of the present invention;

[0047] Figure 2b This is a flowchart of a building resident user identification algorithm provided in an embodiment of the present invention;

[0048] Figure 2c This is a flowchart of a real-time building user identification algorithm provided in an embodiment of the present invention;

[0049] Figure 3 This is a flowchart of another method for assessing building network quality provided in an embodiment of the present invention;

[0050] Figure 4a This is a detailed flowchart of a building resident user identification algorithm system provided in an embodiment of the present invention;

[0051] Figure 4b This is a detailed flowchart of a real-time building user identification algorithm system provided in an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the structure of a building network quality assessment device provided in an embodiment of the present invention. Detailed Implementation

[0053] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0054] Reference Figure 1 The diagram illustrates a flowchart of a method for assessing building network quality according to an embodiment of the present invention, which may specifically include the following steps:

[0055] Step 101: Obtain the historical connection count of each base station in the base station list of the target building;

[0056] For the network wireless service of the target building, one or more base stations can be pre-configured. The network built by multiple base stations covers the entire target building. In order to determine the resident users of the target building, the historical connection count of each base station in the past preset time can be obtained to analyze the resident users.

[0057] Step 102: Determine the resident users of the target building based on the historical connection count;

[0058] After determining the number of historical connections, the historical connection data reflects the user's wireless connection status, which in turn can help identify the resident users in the target building.

[0059] Step 103: When a resident user is detected entering the target building, obtain the real-time signaling data of the resident user;

[0060] Once a resident user is detected entering the target building, their real-time signaling data can be monitored and tracked to assess the network quality of the target building. The longer a resident user stays in the target building, the more valuable the assessment of the network quality becomes.

[0061] Step 104: Assess the network quality of the target building based on real-time signaling data.

[0062] Among them, real-time signaling data is data directly related to network quality, and can therefore be used to assess the network quality of the target building, such as 4G CHR and 5G N1N2 signaling data.

[0063] After acquiring real-time signaling data, it can be processed through classification, weighted calculation, and other methods. By analyzing the real-time signaling data of resident users, the network quality of the target building can be evaluated.

[0064] This invention achieves accurate evaluation of building network quality based on real-time signaling data of resident users by obtaining the historical connection count of each base station in the base station list of the target building; determining the resident users of the target building based on the historical connection count; obtaining the real-time signaling data of the resident users when the resident users are detected entering the target building; and evaluating the network quality of the target building based on the real-time signaling data.

[0065] Reference Figure 2a The diagram illustrates a flowchart of another method for assessing building network quality according to an embodiment of the present invention, which may specifically include the following steps:

[0066] Step 201: Obtain the historical connection count of each base station in the base station list of the target building;

[0067] For example, to get the total number of wireless connections within a month.

[0068] like Figure 2b The diagram shows a flowchart of a "building resident user identification algorithm", where wireless KPI data is the historical connection count and building indoor distribution sites are the base station list of the target building.

[0069] Step 202: Determine the target busy time period for the target building based on historical connection counts;

[0070] After determining the historical connection count, holiday data can be removed, retaining only weekday data. The maximum RRC connection count for each hour can then be calculated by time period. From step 3) removing holiday data and retaining only weekday data, a preset number of target time periods can be selected based on the maximum RRC connection count calculated for each hour. For example, the time period with the highest RRC connection count in the morning, afternoon, and midnight can be selected as the target busy time period for the building (a total of 3 time periods).

[0071] Step 203: Obtain historical signaling data of candidate users within a preset time period;

[0072] Step 204: Based on the target busy period and historical signaling data, determine the resident users of the target building from the candidate users.

[0073] In one embodiment of the present invention, step 204 includes the following sub-steps:

[0074] Sub-step S11: Determine the base station information and time information in the historical signaling data;

[0075] In practical applications, historical signaling data includes base station information and time information. The time information can be the time when the user starts sending the first call detail record (CDR) data after accessing the wireless network, or other time information can be stored as needed.

[0076] Sub-step S12: Based on the time information, determine the number of time periods during which the candidate user appears in each base station information during the target busy period;

[0077] Based on the time information of each candidate user, the base station corresponding to the target busy period is determined, and the number of time periods for each base station is determined.

[0078] Sub-step S13: Determine the associated base stations of candidate users based on the number of time periods;

[0079] After determining the number of time periods, the data can be sorted from highest to lowest according to the number of time periods, and the top N (N is a positive integer greater than 0) associated base stations of each candidate user can be determined, thereby eliminating pseudo-permanent users.

[0080] For example, to filter each user's top 10 base stations (10 during the day and 10 at night), the number of times each daytime and nighttime occurrences occur must be greater than 5 times, meaning the user must have visited the base station for at least 5 half-days or stayed for at least 5 nights during the day within 2 weeks. This algorithm can eliminate the following types of pseudo-permanent users:

[0081] i. Temporary visitors; ii. Food delivery personnel; iii. Passengers; iv. Overtime workers.

[0082] Sub-step S14: Based on the base station list of the target building and the associated base stations of the candidate users, determine the resident users of the target building from the candidate users.

[0083] Step 205: When a resident user is detected entering the target building, obtain the real-time signaling data of the resident user;

[0084] In one embodiment of the present invention, step 205 includes:

[0085] Sub-step S21: Obtain real-time signaling data of the target user;

[0086] The real-time signaling data for the target user can be 4G CHR and 5G N1N2 signaling data. The real-time signaling data includes base station information and time information.

[0087] Sub-step S22: Determine the base station change data of the target user based on real-time signaling data;

[0088] After determining the real-time signaling data, the real-time location of the target user can be determined based on the base station information in the real-time signaling data. When new real-time signaling data exists, the base station in the new real-time signaling is determined, and it is determined whether there is a change between the new real-time signaling and the base station cached last time. If there is a change, the base station change data is determined. The base station change data includes the target user's original base station and the updated base station.

[0089] For example, such as Figure 2c The diagram shows a flowchart of a "real-time building user identification algorithm". The 4G CHR and 5G N1N2 signaling are extracted through Flume and sent to the Kafka message queue. The real-time location processing module consumes the signaling data in Kafka and processes the data in 10-second windows.

[0090] a) Obtain the base station where each candidate user is located in the last call detail record (i.e., real-time signaling data);

[0091] b) Compare the base stations of candidate users in the cache;

[0092] i. If the base station has not changed, update the user's last appearance time in the cache;

[0093] ii. If the base station changes, update the user's base station and time, and write the user's original base station and the changed base station information into the location change topic in Kafka.

[0094] Sub-step S23: When the base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building.

[0095] After determining the base station change data, the base station change data is matched with the resident user and the base station list respectively to determine whether the resident user has entered the target building. In the event of the resident user entering the target building, the base station change data of the resident user is updated from the base station not in the base station list to the base station in the base station list.

[0096] In one example, when identifying building users, the building's station list can be appropriately broadened. Other resident cells (within 500 meters in latitude and longitude) where the signal of a resident user falls during the working period can also be included as the building's coverage cells. When a resident user appears in these cells, it is considered that the user has entered the building.

[0097] In another embodiment of the present invention, sub-step S23 includes: when the target user of the base station change data matches the target resident user, determining the source base station and the target base station of the base station change data; when the source base station is not in the base station list and the target base station is in the base station list, determining that a resident user has been detected entering the target building.

[0098] The source base station is the base station before the update, and the target base station is the base station after the update.

[0099] For example, the location change subscription processing module can read the base station list and resident user list of the building it is interested in, and broadcast the list to each executor in Flink for matching and judgment.

[0100] The location change subscription processing module consumes location change topic data from Kafka and matches it with the list of buildings to be followed (i.e., the list of base stations in the target building) and the list of resident users.

[0101] a) If the changed data does not match the list of resident users, it will be discarded.

[0102] b) If the changed data matches the list of resident users.

[0103] i. If both the source base station and the target base station of the changed data match the list of buildings of interest, then discard the data.

[0104] ii. If the source base station of the changed data matches the list of buildings of interest, but the target base station does not match the list of buildings of interest, it is assumed that the resident user has left the building of interest, and the sensing processing module is notified to stop calculating the user's building sensing data.

[0105] iii. If the source base station of the changed data does not match the list of buildings of interest, but the target base station matches the list of buildings of interest, it is considered that the resident user has entered the building of interest, and the perception processing module is notified to start calculating the user's building perception data.

[0106] Step 206: Assess the network quality of the target building based on real-time signaling data.

[0107] In one embodiment of the present invention, step 206 may include the following sub-steps:

[0108] Sub-step S31: Determine the call detail record (CDR) type of the real-time signaling data;

[0109] In practical applications, once a resident user enters the target building, their real-time signaling data is tracked to determine the call detail record (CDR) types of that resident user. CDR types are used to distinguish different dimensions of user perception metrics.

[0110] Sub-step S32: Calculate the preset user perception index scoring information according to the call detail record type;

[0111] In this process, the various call detail records (CDRs) included in each category of perception indicators can be determined according to the definition of perception indicators. By obtaining the specific perception indicators for resident users, the scoring information for each category of perception indicators and the total score for that resident user can be calculated for network quality assessment.

[0112] The specific definitions of perception indicators are as follows:

[0113] i. User Wireless Dimension Score: The user wireless dimension score is used to identify the impact of abnormal events in user wireless signaling on users. It mainly includes statistics on abnormal events such as network disconnection, paging timeout, 800M ratio, S1 failure, TAU failure, and Service request timeout.

[0114] ii. User Business Dimension Score: The user business dimension score is used to identify the impact of abnormal events generated in user data service on users. It mainly includes statistics on abnormal events such as instant messaging, video, games, web pages, RTT uplink and downlink latency, QR code payment RTT latency, 4G service waiting timeout, and TCP connection failure.

[0115] iii. User Voice Dimension Score: The user voice dimension score is used to identify the impact of abnormal events generated in the user's voice call service on the user. It mainly includes statistics on abnormal events such as dropped calls, missed calls, paging failures in 2G voice services, dropped calls, missed calls, call connection timeouts, IMS re-registration, registration, EPS Fallback, MOS, jitter, and RTP packet latency in VoLTE voice services.

[0116] iv. User Coverage Dimension Score: The user coverage dimension score is used to identify the impact of weak wireless coverage on users, mainly by counting the number of times weak wireless signal coverage occurs and the proportion of weak coverage.

[0117] Overall User Score Evaluation: This evaluation comprehensively assesses several aspects of user experience, including wireless connectivity, services, voice communication, and coverage. A weighted algorithm across different dimensions is used to assess the overall user perception score. The weights and thresholds for each sub-item are determined by comparing complaint and feedback users using big data analysis at a sampling ratio of 1:40 (other sampling ratios can be used in practice as needed). A worst-case threshold is set for each type of abnormal event, and linear scoring is applied. The maximum cumulative percentage difference between the scores of ordinary users and feedback users is used as a benchmark. The resulting overall score generally reflects the user's actual perception.

[0118] It should be noted that the division of user perception indicators is not limited to the above examples. In this embodiment of the invention, the division of user perception indicators is not subject to many restrictions.

[0119] In one embodiment of the present invention, sub-step S32 may include:

[0120] Sub-step S41: Determine the call detail record (CDR) data included in the preset user perception indicators according to the CDR type;

[0121] Sub-step S42: Obtain the weight information of the user-perceived instruction indicators;

[0122] Sub-step S43 involves weighting the weight information and call detail record data to obtain the user perception index score.

[0123] For example: User total score evaluation formula:

[0124] (I) Total score for perception evaluation:

[0125] SCOREuser=MIN(SCOREwire-service,SCOREvoice)

[0126] (II) Perception Evaluation of Wireless and Service Scores:

[0127] SCOREwire-service=(SCOREwire*WEIGHTwire+

[0128] SCOREservice*WEIGHTservice) / (WEIGHT wire+WEIGHTservice)

[0129] (III) Perception Evaluation Wireless Score:

[0130]

[0131] (iv) Perception Evaluation Business Score:

[0132]

[0133] (V) Perceptual evaluation of speech score:

[0134]

[0135] Among them, the coverage dimension can be included as a field in the wireless score.

[0136] When a message is received from the building user real-time identification module indicating that a resident user has entered the target building, the user signaling real-time tracking module is activated to analyze user perception in real time. The optical splitting acquisition module tracks the target user's call detail records (CDRs) in real time, adds a target building field, and outputs it to the building perception stream processing module. The stream processing module calculates user perception indicators based on the CDR type. Specifically, the stream processing module can use a sliding window to calculate every 10 seconds, aggregating the user perception indicator data from the previous minute for each building and outputting the building perception indicators. When a message is received from the building user real-time identification module indicating that a resident user has left the target building, the user signaling real-time tracking module is deactivated, and the optical splitting acquisition module stops tracking the target user's CDRs.

[0137] Sub-step S33: Determine the network quality of the building based on the scoring information.

[0138] After determining the scoring information, the network quality of a building can be determined based on the scoring information. For example, if the score is greater than a preset threshold, the network quality of the target building is determined to be high; if the score is not greater than the preset threshold, the network quality of the target building is determined to be low. In practical applications, the network quality of the target building can be further granularized as needed.

[0139] In this embodiment of the invention, the following can be achieved: obtaining the historical connection count of each base station in the base station list of the target building; determining the target busy period of the target building based on the historical connection count; obtaining the historical signaling data of candidate users within a preset period; determining the resident users of the target building from the candidate users based on the target busy period and the historical signaling data; obtaining the real-time signaling data of the resident users when they are detected entering the target building; and evaluating the network quality of the target building based on the real-time signaling data of the resident users.

[0140] Reference Figure 3 The diagram illustrates a flowchart of another method for assessing building network quality according to an embodiment of the present invention, which may specifically include the following steps:

[0141] Step 301: Obtain the historical connection count of each base station in the base station list of the target building;

[0142] Step 302: Determine the resident users of the target building based on the historical connection count;

[0143] Step 303: Obtain real-time signaling data of the target user;

[0144] The real-time signaling data for the target user can be 4G CHR and 5G N1N2 signaling data. The real-time signaling data includes base station information and time information.

[0145] Step 304: Determine the base station change data of the target user based on real-time signaling data;

[0146] After determining the real-time signaling data, the real-time location of the target user can be determined based on the base station information in the real-time signaling data. When new real-time signaling data exists, the base station in the new real-time signaling is determined, and it is determined whether there is a change between the new real-time signaling and the base station cached last time. If there is a change, the base station change data is determined. The base station change data includes the target user's original base station and the updated base station.

[0147] Step 305: When the base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building.

[0148] After determining the base station change data, the base station change data is matched with the resident user and the base station list respectively to determine whether the resident user has entered the target building. In the event of the resident user entering the target building, the base station change data of the resident user is updated from the base station not in the base station list to the base station in the base station list.

[0149] Step 306: Obtain real-time signaling data of resident users;

[0150] Step 307: Assess the network quality of the target building based on real-time signaling data.

[0151] This invention, in its embodiments, obtains the historical connection count of each base station in the base station list of a target building; determines the resident users of the target building based on the historical connection count; obtains the real-time signaling data of the target users; determines the base station change data of the target users based on the real-time signaling data; when the base station change data matches the resident users and base station list of the target building, it is determined that a resident user has been detected entering the target building, and the real-time signaling data of the resident user is obtained; the network quality of the target building is evaluated based on the real-time signaling data of the resident users, thus achieving accurate evaluation of building network quality based on the real-time signaling data of resident users.

[0152] The following combination Figures 4a to 4b The above embodiments of the present invention are described by way of example:

[0153] like Figure 4aThe diagram shown is a detailed flowchart of a "Building Permanent Resident User Identification Algorithm" system, which includes the following permanent resident user identification process:

[0154] 1) Obtain the list of indoor distributed antenna system (DAS) base stations related to the building.

[0155] 2) Obtain all wireless metrics for these sites within one month.

[0156] 3) Remove holiday data and retain only weekday data.

[0157] 4) Calculate the maximum number of RRC connections per hour by time period.

[0158] 5) Take the time period with the highest RRC connection count in the morning, afternoon and midnight as the building's self-busy time (a total of 3 time periods).

[0159] 6) Obtain 4 / 5G CHR and N1N2 call detail records for all users within 2 weeks (taking into account the situation of users' 4 / 5G mobile phones).

[0160] 7) Filter out weekday busy time data (3 time periods of building busy time).

[0161] 8) Count the number of times users appear at each base station across the entire network. First, sort them by the number of event segments from most to least. If they are the same, then sort them by the amount of signaling data from most to least.

[0162] 9) Filter the 10 base stations that appear most frequently during each time period for each user (10 during the day and 10 at night).

[0163] i. If the number of times the information occurs during the day and at night is less than 5, then this persistent information will be removed.

[0164] ii. In other cases, the site will be recorded as the user's permanent base station.

[0165] 10) Extract the day and night resident personnel of the buildings of interest based on the building station list.

[0166] like Figure 4b The diagram shown is a detailed flowchart of the "Real-time Building User Identification Algorithm" system, which includes the following real-time identification process:

[0167] 1) Use Flume to obtain 4G CHR and 5G N1N2 signaling call detail records in real time.

[0168] 2) Configure Flume's Kafka sink to send data to the Kafka message queue.

[0169] 3) Use Flink to consume signaling data from Kafka in real time, process data in 10-second windows, and extract the last call detail record (CDR) data of the user within 10 seconds.

[0170] 4) Obtain base station information from call detail records (CDRs).

[0171] 5) Obtain the user's base station from the cache.

[0172] 6) Compare the call details form with the user base station in the cache.

[0173] a) If the base station information is consistent, update the last appearance time of the user in the cache and return to step 3 to continue consuming data.

[0174] b) If the base station changes, update the user's base station and time, and jump to step 7.

[0175] 7) Write the user's original base station and the changed base station information into the location change topic in Kafka.

[0176] 8) The stream processing program reads the list of base stations for the buildings of interest.

[0177] 9) The stream processing program reads the list of resident users in the building.

[0178] 10) Broadcast the data of the buildings under interest and the resident users of those buildings to the various executors in Flink.

[0179] 11) The stream processing program consumes the position change data written in step 7 in a 10-second window.

[0180] 12) Use change data to match the list of buildings to watch and the list of regular users.

[0181] a) If the changed data does not match the list of resident users, discard the data and return to step 11 to continue consuming subsequent messages.

[0182] b) If the changed data matches the list of resident users.

[0183] i. If both the source base station and the target base station of the changed data match the list of buildings of interest, discard the data and return to step 11 to continue consuming subsequent messages.

[0184] ii. If the source base station of the changed data matches the list of buildings of interest, but the target base station does not match the list of buildings of interest, it is assumed that the resident user has left the building of interest. The sensing and processing module is then notified to stop calculating the user's building sensing data and return to step 11 to continue consuming subsequent messages.

[0185] iii. If the source base station of the changed data does not match the list of buildings of interest, but the target base station matches the list of buildings of interest, it is considered that the resident user has entered the building of interest. The sensing and processing module is then notified to start calculating the user's building sensing data and return to step 11 to continue consuming subsequent messages.

[0186] The real-time processing module for building perception may include the following steps:

[0187] 1) Received a message from the building user real-time identification module that a resident user has entered the target building.

[0188] a) The spectral acquisition module tracks the call detail records (CDRs) of the target user in real time and adds the target building field to the building perception stream processing module.

[0189] b) The stream processing module calculates user perception metrics based on call detail record (CDR) type.

[0190] The system calculates user scores in the following dimensions: wireless, service, voice, and coverage, and then calculates the user's total score.

[0191] c) Use a sliding window to calculate every 10 seconds, aggregate the user perception index data of each building for the previous minute, and output the building perception index.

[0192] 2) Upon receiving a message from the building user real-time identification module that a resident user has left the target building, the spectral acquisition module stops tracking the target user's call detail records.

[0193] In this embodiment of the invention, by leveraging big data technology, resident users of buildings are extracted from massive amounts of mobile network data. Real-time big data stream computing technology is used to capture the entry and exit events of resident users in the buildings of interest in real time, and to extract the perception and signaling data of the buildings of interest in real time. This effectively characterizes building perception and abnormal events, providing an effective technical means for real-time building operation and maintenance. By extracting time in real time and correlating the start and end times of user perception computing, a building quality profile is created from the user perspective.

[0194] This invention provides a real-time building user identification and tagging algorithm. This algorithm considers both the exclusion of temporary visitors and the differences in commuting times among permanent users, effectively filtering out network call detail records (CDRs) that require attention for analysis, improving the time complexity of subsequent calculations, saving computing resources, and enhancing the accuracy of building tags.

[0195] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0196] Reference Figure 5The diagram shows a structural schematic of a building network quality assessment device according to an embodiment of the present invention, which may specifically include the following modules:

[0197] The historical connection count acquisition module 501 is used to acquire the historical connection count of each base station in the base station list of the target building;

[0198] The resident user determination module 502 is used to determine the resident users of the target building based on the historical connection count;

[0199] The real-time signaling data acquisition module 503 is used to acquire the real-time signaling data of a resident user when the resident user is detected to have entered the target building.

[0200] The building network quality assessment module 504 is used to assess the network quality of a target building based on real-time signaling data.

[0201] In one embodiment of the present invention, the resident user determination module 502 may include:

[0202] The Target Busy Period Submodule is used to determine the target busy period for a target building based on historical connection counts.

[0203] The historical signaling acquisition submodule is used to acquire historical signaling data of candidate users within a preset time period;

[0204] The resident user determination submodule is used to determine the resident users of the target building from the candidate users based on the target busy period and historical signaling data.

[0205] In one embodiment of the present invention, the resident user determination submodule includes:

[0206] The historical signaling data parsing unit is used to determine the base station information and time information in the historical signaling data;

[0207] The time period data determination unit is used to determine, based on time information, the number of time periods during which a candidate user appears in each base station information during the target busy period;

[0208] The base station determination unit is used to determine the associated base stations of candidate users based on the number of time periods.

[0209] The resident user determination unit is used to determine the resident users of the target building from the candidate users according to the base station list of the target building and the associated base stations of the candidate users.

[0210] In one embodiment of the present invention, the real-time signaling data acquisition module 503 includes:

[0211] The signaling acquisition submodule is used to acquire real-time signaling data of the target user;

[0212] The base station change submodule is used to determine the base station change data of the target user based on real-time signaling data;

[0213] The event determination submodule is used to determine whether a resident user has entered the target building when the base station change data matches the list of resident users and base stations of the target building.

[0214] In one embodiment of the present invention, the entry event determination submodule includes:

[0215] The base station determination unit is used to determine the source base station and the target base station of the base station change data when the target user of the base station change data is matched with the target resident user;

[0216] The base station matching unit is used to determine whether a resident user has entered the target building when the source base station is not in the base station list and the target base station is in the base station list.

[0217] In one embodiment of the present invention, the building network quality assessment module 504 includes:

[0218] The Call Detail Record (CDR) type determination submodule is used to determine the CDR type of real-time signaling data;

[0219] The scoring submodule is used to calculate the scoring information of preset user perception indicators according to the call detail record type;

[0220] The evaluation submodule is used to determine the network quality of a building based on the scoring information.

[0221] In one embodiment of the present invention, the scoring submodule may include:

[0222] The call detail record (CDR) data determination unit is used to determine the CDR data included in the preset user perception indicators according to the CDR type.

[0223] The weight information acquisition unit is used to acquire the weight information of user-perceived command indicators;

[0224] The scoring calculation unit is used to perform weighted calculations on the weight information and call detail record data to obtain the scoring information of user perception indicators.

[0225] An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above-mentioned method for building network quality assessment.

[0226] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-described method for building network quality assessment.

[0227] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0228] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0229] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0230] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0231] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0232] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0233] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0234] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the element.

[0235] The above provides a detailed description of the method, apparatus, electronic equipment, and medium for assessing building network quality. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for assessing the quality of a building network, characterized in that, The methods include: Retrieve the historical connection count of each base station in the base station list of the target building; Determine the resident users of the target building based on historical connection counts; When a resident user is detected entering the target building, the real-time signaling data of the resident user is obtained; Assess the network quality of the target building based on real-time signaling data; Among these, assessing the network quality of the target building based on real-time signaling data includes: Determine the call detail record (CDR) type for real-time signaling data; Calculate the preset user perception index scoring information according to the call detail record type; Determine the network quality of a building based on scoring information; The scoring information for pre-defined user perception indicators, calculated according to call detail record (CDR) type, includes: Based on the call detail record (CDR) type, determine the CDR data included in the preset user perception indicators; Obtain the weight information of user-perceived command metrics; The weighted information and call detail record data are weighted and calculated to obtain the user perception index score information.

2. The method according to claim 1, characterized in that, The resident users of the target building are determined based on historical connection counts, including: Determine the target peak hours for the target building based on historical connection counts; Obtain historical signaling data of candidate users within a preset time period; Based on the target busy time period and historical signaling data, determine the resident users of the target building from the candidate users.

3. The method according to claim 2, characterized in that, Based on the target peak hours and historical signaling data, identify the resident users of the target building from the candidate users, including: Determine the base station information and time information in historical signaling data; Based on the time information, determine the number of time periods during which the candidate user appears in each base station information during the target busy period; Determine the associated base stations of candidate users based on the number of time periods; Based on the base station list of the target building and the associated base stations of the candidate users, determine the resident users of the target building from the candidate users.

4. The method according to claim 1, characterized in that, A resident user was detected entering the target building, including: Obtain real-time signaling data of the target user; Determine the base station change data of the target user based on real-time signaling data; When the base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building.

5. The method according to claim 4, characterized in that, When base station change data matches the list of resident users and base stations of the target building, it is determined that a resident user has been detected entering the target building, including: When matching the target user with the target resident user of the base station change data, the source base station and target base station of the base station change data are determined; If the source base station is not in the base station list, but the target base station is in the base station list, it is determined that a resident user has been detected entering the target building.

6. A device for assessing the quality of a building network, characterized in that, The device includes: The historical connection count acquisition module is used to obtain the historical connection count of each base station in the base station list of the target building; The resident user identification module is used to identify resident users in a target building based on historical connection counts. The real-time signaling data acquisition module is used to acquire the real-time signaling data of a resident user when the resident user is detected to have entered the target building. The building network quality assessment module is used to assess the network quality of a target building based on real-time signaling data. The building network quality assessment module includes: The Call Detail Record (CDR) type determination submodule is used to determine the CDR type of real-time signaling data; The scoring submodule is used to calculate the scoring information of preset user perception indicators according to the call detail record type; The evaluation submodule is used to determine the network quality of a building based on the scoring information. The scoring submodule includes: The call detail record (CDR) data determination unit is used to determine the CDR data included in the preset user perception indicators according to the CDR type. The weight information acquisition unit is used to acquire the weight information of user-perceived command indicators; The scoring calculation unit is used to perform weighted calculations on the weight information and call detail record data to obtain the scoring information of user perception indicators.

7. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, it implements the method for building network quality assessment as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A computer program is stored on a computer-readable storage medium, which, when executed by a processor, implements the method for assessing building network quality as claimed in any one of claims 1 to 5.

Images