A network quality data processing method, device, equipment, storage medium and product

Abstract

Embodiments of the present application disclose a network quality data processing method, device, equipment, storage medium and product. The method comprises: obtaining M measurement reports based on Internet applications, wherein each measurement report of an Internet application contains description information of at least one main area, and the description information of any main area comprises network quality data corresponding to the main area and environmental characteristics; mining neighboring areas of a first main area through the M measurement reports based on Internet applications; and predicting network quality data of a base station of a neighboring area in a target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring area, wherein the target area is included in an area covered by the first main area. It can be seen that the network quality data of the base station of the neighboring area in the target area can be conveniently obtained by mining the neighboring areas of each main area based on the measurement reports based on Internet applications, and combining the network quality data corresponding to the main area and the environmental characteristics of the corresponding neighboring area.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a network quality data processing method, a network quality data processing device, a computer device, a computer-readable storage medium, and a network quality data processing product. Background Technology

[0002] With advancements in scientific research, mobile communication technology has developed rapidly. In the field of mobile communication, base station signals are frequently interfered with by various factors; for example, interference from building obstructions and reflections, and uneven base station signal coverage leading to decreased communication quality. Ensuring network (signal) quality is an ongoing challenge, requiring network operators (or service providers) to collect vast amounts of network data to assess network quality in various areas.

[0003] Research has found that network quality assessment in each region depends on network quality data corresponding to the primary region, as well as network quality data from neighboring base stations in the target region (which is included in the coverage area of ​​the primary region). Network quality data corresponding to the primary region can be directly collected by acquisition equipment, while network quality data from neighboring base stations in the target region is difficult to collect and report directly. Summary of the Invention

[0004] This application provides a network quality data processing method, apparatus, device, computer-readable storage medium, and product that can conveniently obtain network quality data of neighboring base stations in a target area.

[0005] On one hand, embodiments of this application provide a network quality data processing method, including:

[0006] Obtain M measurement reports based on Internet applications. Each measurement report for an Internet application contains description information of at least one main area. The description information of each main area includes the network quality data and environmental characteristics corresponding to that main area. M is an integer greater than 1.

[0007] By using M measurement reports based on Internet applications, the neighboring cells of the first primary region are mined, and the descriptive information of the first primary region is contained in at least one measurement report based on Internet applications.

[0008] Based on the network quality data corresponding to the first main area and the environmental characteristics of neighboring areas, the network quality data of the base stations in the neighboring areas in the target area is predicted. The target area is included in the area covered by the first main area.

[0009] On one hand, embodiments of this application provide a network quality data processing apparatus, which includes:

[0010] The acquisition unit is used to acquire M measurement reports based on Internet applications. Each measurement report of an Internet application contains description information of at least one main area. The description information of each main area includes network quality data and environmental characteristics corresponding to the main area. M is an integer greater than 1.

[0011] The processing unit is used to mine the neighboring cells of the first main region through M measurement reports based on Internet applications, wherein the descriptive information of the first main region is contained in at least one measurement report based on Internet applications.

[0012] And for predicting the network quality data of the base stations in the target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas, the target area being included in the area covered by the first main area.

[0013] In one implementation, the processing unit is configured to mine neighboring cells of the first primary region using M measurement reports from Internet applications, specifically for:

[0014] Neighbor pair mining is performed on M measurement reports based on Internet applications from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighboring cells of the first main region.

[0015] In one implementation, the description information of any primary region also includes the collection location of the network quality data corresponding to that primary region; the processing unit is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0016] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0017] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0018] Count the number of co-occurrences of each main region pair in each sub-region. Any main region pair consists of any two main regions associated with M measurement reports based on Internet applications.

[0019] The neighboring cells of the first primary region are determined based on the number of co-occurrences of each primary region pair.

[0020] In one implementation, the process by which the processing unit counts the co-occurrence counts of each main region pair in each sub-region includes:

[0021] If the same acquisition device acquires network quality data corresponding to the first main area and network quality data corresponding to the second main area in the first sub-region, and the acquisition time interval between the two network quality data is less than the duration threshold, then the number of co-occurrences of the target main area in the first sub-region is increased.

[0022] If different acquisition devices acquire network quality data corresponding to the first main area and network quality data corresponding to the second main area respectively in the first sub-region, then increase the number of times the target main area co-occurs in the first sub-region;

[0023] The target main region consists of a first main region and a second main region, and the first sub-region is any one of the at least two sub-regions.

[0024] In one implementation, the processing unit is configured to determine the neighboring regions of the first primary region based on the co-occurrence count of each primary region pair, specifically configured to:

[0025] If the co-occurrence frequency of the target sub-region pair in the first sub-region is greater than the frequency threshold, then the second main region is determined as a neighboring region of the first main region, and the target sub-region pair consists of the first main region and the second main region; or,

[0026] The network quality data corresponding to the first main region and the network quality data corresponding to the second main region are counted the number of times they are collected in the first sub-region. Based on the number of times the network quality data corresponding to the first main region and the network quality data corresponding to the second main region are collected in the first sub-region, as well as the number of times the target sub-region pair co-occurs in the first sub-region, the spatial neighbor probability is calculated. If the spatial neighbor probability is greater than the spatial probability threshold, the second main region is determined as a neighbor of the first main region. The target sub-region pair consists of the first main region and the second main region.

[0027] In one implementation, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processing unit is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0028] If any measurement report based on an Internet application indicates that the time interval between the collection of network quality data corresponding to the first primary area and the collection of network quality data corresponding to the second primary area is less than the duration threshold, and the collection distance of network quality data is less than the distance threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0029] The network quality data collection distance is calculated based on the collection location of the network quality data corresponding to the first primary area and the collection location of the network quality data corresponding to the second primary area.

[0030] In one implementation, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processing unit is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0031] The temporal correlation score and spatial correlation score of the first and second main regions are obtained. The temporal correlation score is determined based on the time interval between the collection of network quality data corresponding to the first and second main regions, as well as the collection distance of the network quality data. The spatial correlation score is determined based on the number of times the first and second main regions co-occur in the first sub-region. The first sub-region is obtained by dividing the regions corresponding to M Internet application-based measurement reports according to a preset regional division rule.

[0032] The time-related dimension score and the spatial-related dimension score are weighted and summed to obtain the correlation score of the first and second main regions.

[0033] If the correlation score is greater than the score threshold, the second primary region will be identified as a neighboring region of the first primary region.

[0034] In one implementation, the description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected; the processing unit is used to mine the neighboring regions of the first primary region through M measurement reports based on Internet applications, specifically for:

[0035] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0036] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0037] If the number of times the network quality data corresponding to the first primary area is collected in the first sub-area is greater than the first threshold, and the number of times the network quality data corresponding to the second primary area is collected in the second sub-area is greater than the second threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0038] The second sub-region is the adjacent sub-region of the first sub-region.

[0039] In one implementation, the processing unit is configured to predict the network quality data of the neighboring cells at the target location based on the network quality data corresponding to the first primary cell and the environmental characteristics of the neighboring cells, specifically configured to:

[0040] The network quality data prediction model is invoked to predict the network quality data of the first primary area and the environmental characteristics of neighboring areas, thereby obtaining the network quality data of the neighboring base stations in the target area; or...

[0041] The impact of different environmental features on network quality is obtained. Based on the impact of each environmental feature on network quality, the environmental features of neighboring cells are filtered. Based on the filtered environmental features of neighboring cells and the network quality data corresponding to the first primary area, the network quality data of the base stations in the neighboring cells in the target area is predicted.

[0042] In one embodiment, the processing unit is further configured to:

[0043] Based on the network quality data corresponding to the first primary area and the network quality data of the base stations in the neighboring areas in the target area, a network quality assessment result for the target area is generated.

[0044] In one implementation, the network quality data includes wireless signal quality indicators; the processing unit is configured to generate a network quality assessment result for the target area based on the network quality data corresponding to the first primary area and the network quality data of base stations in neighboring areas within the target area, specifically for:

[0045] The signal strength of the target area is determined based on the signal quality indicators of the base station in the first main area and the signal quality indicators of the base stations in the neighboring areas.

[0046] Display the area map, with the target area included in the area map;

[0047] The target area is displayed in the area map in a color that corresponds to the signal strength of the target area.

[0048] Accordingly, this application provides a computer device comprising:

[0049] Memory, which stores computer programs;

[0050] The processor is used to load computer programs to implement the aforementioned network quality data processing method.

[0051] Accordingly, this application provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed by the above-described network quality data processing method.

[0052] Accordingly, this application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned network quality data processing method.

[0053] In this embodiment, M measurement reports based on Internet applications are obtained. Each Internet application measurement report contains descriptive information of at least one main region. The descriptive information of each main region includes network quality data and environmental characteristics corresponding to that main region. Using the M Internet application measurement reports, neighboring regions of the first main region are mined. Based on the network quality data corresponding to the first main region and the environmental characteristics of the neighboring regions, the network quality data of the base stations in the neighboring regions in the target region is predicted. The target region is included in the area covered by the first main region. Therefore, by mining neighboring regions of each main region using Internet application measurement reports and combining the network quality data corresponding to the main region with the environmental characteristics of the corresponding neighboring regions, the network quality data of the base stations in the neighboring regions in the target region can be easily obtained. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0055] Figure 1a A schematic diagram illustrating the relationship between a primary region and neighboring regions is provided for an embodiment of this application.

[0056] Figure 1b A network quality data processing scenario diagram provided in this application embodiment;

[0057] Figure 2 A flowchart illustrating a network quality data processing method provided in this application embodiment;

[0058] Figure 3a A spatial association diagram provided for an embodiment of this application;

[0059] Figure 3b A time correlation diagram provided for an embodiment of this application;

[0060] Figure 3c A multi-dimensional association diagram provided for an embodiment of this application;

[0061] Figure 3dA location association diagram provided for an embodiment of this application;

[0062] Figure 3e Another location association diagram provided for an embodiment of this application;

[0063] Figure 4 A flowchart illustrating another network quality data processing method provided in this application embodiment;

[0064] Figure 5a A network quality data processing architecture diagram provided for embodiments of this application;

[0065] Figure 5b A schematic diagram of a map display provided in an embodiment of this application;

[0066] Figure 6 A schematic diagram of the structure of a network quality data processing device provided in an embodiment of this application;

[0067] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0068] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0069] This application relates to technologies related to mobile network communication. A brief introduction to these technologies is provided below:

[0070] Over-the-Top (OTT) technology: This refers to providing content and services via the internet, rather than through traditional telecommunications operators or broadcast service providers. In the mobile communications field, OTT typically refers to video, audio, or other media services provided through data services (such as 4G and 5G networks).

[0071] Over-The-Top Measurement Report (OTT-MR): This can be understood as measurement report data obtained through OTT technology. OTT-MR includes data on the behavior and performance of the target device within the network. The data in OTT-MR can be further precisely located using high-precision positioning technology, enabling network service providers to more accurately analyze network quality in various regions.

[0072] Serving Cell: This is the base station cell currently providing network services to the target device.

[0073] Neighbor Cells: These are cells surrounding the primary cell, typically geographically adjacent or within the same radio coverage area. Network quality data from neighboring cells is crucial for seamless handover between mobile terminals. Figure 1a This is a schematic diagram illustrating the relationship between a primary region and neighboring regions, provided as an embodiment of this application. Figure 1a As shown, when the UE is in area A, the cell with physical cell identifier "A" acts as the primary cell providing network service to the UE. At this time, cells with physical cell identifiers "B", "C", "D", and "E" are all neighboring cells of the cell with physical cell identifier "A". Typically, the network service quality (e.g., signal strength) of the primary cell in area A is better than that of the neighboring cells. When the UE moves to area D (or moves to area D), the network service for the UE will be switched, and the cell with physical cell identifier "D" (acting as the primary cell) will provide network service to the UE. At this time, the cell with physical cell identifier "A" becomes a neighboring cell of the cell with physical cell identifier "D".

[0074] Reference Signal Received Power (RSRP) is an indicator that measures the downlink signal strength in a cell and is used to evaluate the communication quality between the target device and the base station.

[0075] Reference Signal Received Quality (RSRQ) is a metric that measures the quality of received signals, taking into account signal power, noise, and interference.

[0076] Signal to Interference plus Noise Ratio (SINR) is an indicator that describes the current signal quality, reflecting the ratio of signal strength to background noise and interference.

[0077] Based on the aforementioned technologies related to mobile network communication, this application provides a network quality data processing scheme that can conveniently obtain network quality data of neighboring base stations in the target area. Figure 1b A network quality data processing scenario diagram is provided for an embodiment of this application, such as... Figure 1bAs shown, the network quality data processing scenario provided in this application includes a terminal device 101 and a server 102. The network quality data processing solution provided in this application can be executed by the server 102. The terminal device may include, but is not limited to: smartphones (such as Android phones, iOS phones, etc.), tablet computers, portable personal computers, mobile internet devices (MIDs), smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, wearable devices, etc., and this application embodiment does not limit this. The server may be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It may also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, and this application embodiment does not limit this.

[0078] It should be noted that, Figure 1b The number of terminal devices and servers is for illustrative purposes only and does not constitute an actual limitation of this application. Terminal device 101 and server 102 can be connected via wired or wireless means, and this application does not impose any restrictions on this.

[0079] The general flow of the network quality data processing solution provided in this application is as follows:

[0080] (1) Server 102 acquires M measurement reports based on Internet applications. Each measurement report based on Internet applications is collected by a terminal device 101. A terminal device 101 can collect multiple measurement reports based on Internet applications. For example, when terminal device 101 uses networks provided by different network service providers at different times, terminal device 101 can collect the reports separately to obtain measurement reports based on Internet applications corresponding to each network service provider. Each measurement report for any Internet application contains description information of at least one main area. The description information of any main area includes network quality data (such as signal strength, latency, etc.) and environmental characteristics (such as altitude, whether it is indoors, etc.) corresponding to the main area, where M is an integer greater than 1.

[0081] (2) Server 102 mines neighboring regions of the first primary region using M measurement reports based on Internet applications; wherein the descriptive information of the first primary region is contained in at least one measurement report based on Internet applications. The neighboring regions of each primary region can be mined based on location information. In one embodiment, server 102 can perform neighbor pair mining on the M measurement reports based on Internet applications from at least one dimension of spatial association and temporal association to obtain the neighboring regions of the first primary region.

[0082] (3) Server 102 predicts the network quality data of the neighboring base stations in the target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas; wherein the target area is included in the area covered by the first main area. In one embodiment, server 102 can call a network quality data prediction model to predict the network quality data of the neighboring base stations in the target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas.

[0083] In this embodiment, M measurement reports based on Internet applications are obtained. Each Internet application measurement report contains descriptive information of at least one main region. The descriptive information of each main region includes network quality data and environmental characteristics corresponding to that main region. Using the M Internet application measurement reports, neighboring regions of the first main region are mined. Based on the network quality data corresponding to the first main region and the environmental characteristics of the neighboring regions, the network quality data of the base stations in the neighboring regions in the target region is predicted. The target region is included in the area covered by the first main region. Therefore, by mining neighboring regions of each main region using Internet application measurement reports and combining the network quality data corresponding to the main region with the environmental characteristics of the corresponding neighboring regions, the network quality data of the base stations in the neighboring regions in the target region can be easily obtained.

[0084] Based on the above network quality data processing scheme, this application proposes a more detailed network quality data processing method. The network quality data processing method proposed in this application will be described in detail below with reference to the accompanying drawings.

[0085] Please see Figure 2 , Figure 2 A flowchart illustrating a network quality data processing method provided in this application embodiment, which can be executed by a computer device; for example, by... Figure 1b The server 102 shown is executing. (As...) Figure 2 As shown, the network quality data processing method may include the following steps S201-S203:

[0086] S201. Obtain M measurement reports based on Internet applications.

[0087] Internet-based measurement reports are generated using data collected by third-party applications. These applications run on mobile devices and collect information about the main base stations providing network services to the mobile devices; for example, network quality data and environmental characteristics corresponding to the main area. After collecting the relevant information about the main area base stations, the third-party applications can generate descriptive information about the main area based on this information and combine it with high-precision positioning data (including the location of the collected data) to generate an internet-based measurement report.

[0088] In one implementation, a third-party application can report the collected data to a computer device in real time. Upon receiving this data, the computer device cleans and formats it to obtain a measurement report based on an internet application. Table 1 is an example table of fields provided in an embodiment of this application, containing the main fields related to the primary area base station.

[0089] Table 1

[0090]

[0091]

[0092] The fields in Table 1 can be directly collected by third-party applications. It should be noted that the fields in Table 1 are example fields; in actual applications, third-party applications can collect hundreds of fields. Computer devices can then clean and format these fields based on requirements and configurations to obtain the desired fields. Furthermore, based on the collected fields, the computer device can also generate extended fields. In one embodiment, the computer device can determine the corresponding province, city, district, point of interest (POI_info), indoor / outdoor indicator, and building outline based on the latitude and longitude coordinates.

[0093] Understandably, after acquiring M measurement reports based on Internet applications, a computer device can obtain network quality data for each primary region from these M reports. In one embodiment, the network quality data for a primary region can be contained within multiple measurement reports based on Internet applications, which can indicate the network quality data of that primary region at different locations (or at different times). If multiple measurement reports based on Internet applications indicate the network quality data of the same primary region within a target area, and the time interval between the acquisition of this network quality data is less than a duration threshold (e.g., 1 minute), the computer device can calculate the average of the multiple network quality data to obtain the network quality data of the target area of ​​that primary region within a certain time period (which can be determined based on the acquisition time interval).

[0094] S202. Using M measurement reports based on Internet applications, identify the neighboring areas of the first main area.

[0095] The descriptive information of the first primary region is contained in at least one measurement report based on an internet application. In one implementation, a computer device performs neighbor pair mining on M measurement reports based on internet applications from at least one of spatial correlation and temporal correlation dimensions to obtain the neighbor regions of the first primary region.

[0096] In one embodiment, the description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected. The computer device performs neighbor pair mining on the M measurement reports based on Internet applications from a (multi-primary region) spatial correlation dimension to obtain the neighboring regions of the first primary region. In one implementation, the computer device divides the region corresponding to the M measurement reports based on Internet applications into at least two sub-regions according to a preset region division rule. The data used to generate the M measurement reports based on Internet applications are all collected in the regions corresponding to the M measurement reports based on Internet applications; for example, assuming that the network quality data is all collected in city A, then the region corresponding to the M measurement reports based on Internet applications is the region where city A is located. The shape of the sub-regions can be any shape (such as square, honeycomb, etc.), and the shape and size of each sub-region can be the same or different; this application does not impose any restrictions on this. For example, the computer device can divide the region corresponding to the M measurement reports based on Internet applications into several H*H grids according to a predicted length H.

[0097] After completing the area division, the computer equipment maps the network quality data corresponding to each main area to the corresponding sub-area based on the collection location of the network quality data corresponding to each main area in the M Internet-based application measurement reports. For example, assuming that the collection location of network quality data 1 is location A, and location A is contained in grid 3, the computer equipment can map network quality data 1 to grid 3. After mapping each network quality data to the corresponding sub-area, the computer equipment counts the co-occurrence frequency of each main area pair in each sub-area; where any main area pair consists of any two main areas associated with the M Internet-based application measurement reports.

[0098] The following uses a target main region pair consisting of a first main region and a second main region as an example to illustrate the statistical method for the co-occurrence frequency of the main region pair. In one implementation, if the same acquisition device acquires network quality data corresponding to both the first and second main regions within the first sub-region, and the acquisition time interval between the two network quality data is less than a duration threshold, then the computer device increases the co-occurrence frequency of the target main region pair within the first sub-region (e.g., increases the co-occurrence frequency by 1). In another implementation, if different acquisition devices acquire network quality data corresponding to both the first and second main regions within the first sub-region, then the computer device increases the co-occurrence frequency of the target main region pair within the first sub-region (e.g., increases the co-occurrence frequency by 1); wherein, the first sub-region is any one of at least two sub-regions.

[0099] Furthermore, after counting the co-occurrence counts of each primary region pair, the computer device determines the neighboring regions of the first primary region based on these counts. In one implementation, if the co-occurrence count of the target sub-region pair in the first sub-region exceeds a threshold, the computer device determines the second primary region as a neighboring region of the first primary region. In another implementation, the computer device counts the number of times the network quality data corresponding to the first primary region and the network quality data corresponding to the second primary region are collected in the first sub-region, and calculates the spatial neighboring region probability based on the number of times the network quality data corresponding to the first primary region, the number of times the network quality data corresponding to the second primary region, and the co-occurrence count of the target sub-region pair in the first sub-region. The specific formula for calculating the spatial neighboring region probability can be expressed as:

[0100] S spatio (C1,C2)=f(N(C1),N(C2),N(C1,C2))

[0101] Among them, S spatio (C1, C2) represents the spatial neighbor probability, and f(x, y, z) is the function for calculating the spatial neighbor probability; for example, f(x, y, z) = z / (x+y). N(C1) represents the number of times the network quality data corresponding to the first main region was collected in the first sub-region, N(C2) represents the number of times the network quality data corresponding to the second main region was collected in the first sub-region, and N(C1, C2) represents the number of times the target sub-region pair co-occurred in the first sub-region. It can be understood that N(C1), N(C2), and N(C1, C2) are obtained statistically from multiple measurement reports based on Internet applications (i.e., involving data collected by multiple acquisition devices).

[0102] After calculating the spatial neighbor probability, the computer device compares the spatial neighbor probability with a spatial probability threshold. If the spatial neighbor probability is greater than the spatial probability threshold, the computer device determines the second primary region as a neighbor of the first primary region (the first primary region and the second primary region are neighbors); correspondingly, if the spatial neighbor probability is less than or equal to the spatial probability threshold, the computer device determines that the second primary region is not a neighbor of the first primary region (the first primary region and the second primary region are not neighbors).

[0103] Figure 3a This is a spatial association diagram provided for an embodiment of this application. For example... Figure 3a As shown, the areas corresponding to M measurement reports based on internet applications are divided into several grids of equal size. Assume the formula for calculating the spatial neighbor probability is: S spatio(C1,C2)=N(C1,C2) / (N(C1)+N(C2)), with a spatial probability threshold of 0.1. If, in grid G1, the network quality data corresponding to principal region 1 (C1) is collected 450 times, the network quality data corresponding to principal region 2 (C2) is collected 550 times, and the co-occurrence frequency of the principal region pair formed by principal regions 1 and 2 is 300, then S spatio (C1,C2)=300 / (450+550)=0.3>spatial probability threshold, the computer determines that main region 1 and main region 2 are neighboring regions. Similarly, if in grid G1, the network quality data corresponding to main region 1 (C1) is collected 450 times, the network quality data corresponding to main region 2 (C2) is collected 550 times, and the co-occurrence frequency of the main region pair formed by main regions 1 and 2 is 10, then S spatio (C1,C2)=10 / (450+550)=0.01<spatial probability threshold, the computer equipment determines that primary area 1 and primary area 2 are not neighboring areas.

[0104] In another embodiment, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region. The computer device performs neighbor pair mining on M measurement reports based on Internet applications from a (single device) time correlation dimension to obtain the neighboring regions of the first primary region. Specifically, the computer device can calculate the temporal neighbor probability based on the collection time interval and collection distance of the network quality data corresponding to two primary regions collected by a single collection device, and determine whether the two primary regions are neighbors based on the temporal neighbor probability and a temporal probability threshold. The formula for the temporal neighbor probability can be expressed as:

[0105] S time (C1,C2)=M(time(C1,C2),distance(C1,C2))

[0106] Among them, S time (C1,C2) represents the temporal neighbor probability, and M(a,b) is the function for calculating the temporal neighbor probability. time(C1,C2) represents the time interval between the acquisition time of the network quality data corresponding to the first primary region and the acquisition time of the network quality data corresponding to the second primary region (acquired by the same acquisition device); distance(C1,C2) represents the acquisition distance between the acquisition location of the network quality data corresponding to the first primary region and the acquisition location of the network quality data corresponding to the second primary region (acquired by the same acquisition device).

[0107] In one implementation, if any measurement report based on an Internet application (generated from data collected by the same acquisition device) indicates that the time interval between the acquisition of network quality data corresponding to the first primary area and the acquisition distance of network quality data corresponding to the second primary area is less than a duration threshold, and the acquisition distance of network quality data is less than a distance threshold, then the computer device determines the second primary area as a neighboring area of ​​the first primary area (the first primary area and the second primary area are neighboring areas); otherwise, the first primary area and the second primary area are not neighboring areas.

[0108] Figure 3b This is a time-related schematic diagram provided for an embodiment of this application. For example... Figure 3b As shown, the areas corresponding to M measurement reports based on internet applications are divided into several grids of the same size. Assume the data acquisition device moves from G1 to G2, and at time 1 acquires network quality data corresponding to main area 1 (C1), with the acquisition location P1; at time 2, it acquires network quality data corresponding to main area 2 (C2), with the acquisition location P2. If the acquisition time interval between time 1 and time 2 is less than a duration threshold, and the acquisition distance between P1 and P2 is less than a distance threshold, then the computer device determines that main areas 1 and 2 are neighboring areas. Otherwise, the computer device determines that main areas 1 and 2 are not neighboring areas.

[0109] In another embodiment, the computer device performs neighbor pair mining on M measurement reports based on Internet applications from both spatial and temporal correlation dimensions to obtain the neighbors of the first main region. Specifically, the computer device can determine the adjacency probability (or score) of the first main region pair (composed of the first main region and the second main region) based on the aforementioned spatial and temporal neighbor probabilities, and determine whether the first main region and the second main region are neighbors based on the adjacency probability (or score) of the first main region pair and a preset probability threshold (or preset score threshold). The adjacency probability (or score) can be expressed as:

[0110] S spatio_time (C1,C2)=g(S spatio (C1,C2),S time (C 1, C2))

[0111] Among them, S spatio_time (C1, C2) represents the probability (or rating) of C1 and C2 being adjacent, S spatio (C1,C2) represents the spatial neighbor probability of C1 and C2, S time (C 1, C2) represents the temporal neighbor probabilities of C1 and C2, and g(a, b) represents the preset algorithm (such as a weighted formula).

[0112] In one implementation, the computer device acquires the temporal correlation score and spatial correlation score of a first primary region and a second primary region. The temporal correlation score is determined based on the time interval between the collection of network quality data corresponding to the first primary region and the network quality data corresponding to the second primary region, as well as the distance between the collection of network quality data. The spatial correlation score is determined based on the number of times the first and second primary regions co-occur in a first sub-region. The first sub-region is obtained by dividing the regions corresponding to M measurement reports based on Internet applications according to a preset regional division rule. After obtaining the temporal correlation score and spatial correlation score, the computer device performs a weighted summation of the temporal correlation score and the spatial correlation score to obtain the correlation score between the first and second primary regions. If the correlation score is greater than a scoring threshold, the computer device determines the second primary region as a neighboring region of the first primary region.

[0113] Figure 3c This is a schematic diagram illustrating a multi-dimensional relationship as provided in an embodiment of this application. For example... Figure 3c As shown, the areas corresponding to M measurement reports based on internet applications are divided into several grids of equal size. Assume the formula for calculating the spatial neighbor probability is: S spatio (C1,C2)=N(C1,C2) / (N(C1)+N(C2)), with a spatial probability threshold of 0.1. If, in grid G1, the network quality data corresponding to principal region 1 (C1) is collected 450 times, the network quality data corresponding to principal region 2 (C2) is collected 550 times, and the co-occurrence frequency of the principal region pair formed by principal regions 1 and 2 is 300, then S spatio (C1,C2) = 300 / (450+550) = 0.3 > spatial probability threshold. Furthermore, if the acquisition device acquires network quality data corresponding to main region 1 (C1) from location P1 at time 1, and acquires network quality data corresponding to main region 2 (C2) from location P2 at time 2 (after moving from P1 to P2), and the acquisition time interval between time 1 and time 2 is less than the duration threshold, and the acquisition distance between P1 and P2 is less than the distance threshold (i.e., simultaneously satisfying the conditions of both spatial correlation and temporal correlation), then the computer device determines that main regions 1 and 2 are neighboring regions. Otherwise, the computer device determines that main regions 1 and 2 are not neighboring regions. In other words, in this case, the computer device comprehensively considers the results of multiple (acquisition) devices in the spatial correlation dimension and the results of a single (acquisition) device in the temporal correlation dimension, resulting in a higher accuracy in obtaining neighboring region pairs compared to a single dimension.

[0114] In another implementation, the description information of any main region also includes the location where the network quality data corresponding to that main region was collected. The computer device divides the regions corresponding to M Internet-based application measurement reports into at least two sub-regions according to a preset region division rule, and maps the network quality data corresponding to each main region to the corresponding sub-region based on the location where the network quality data corresponding to each main region was collected. If the number of times the network quality data corresponding to the first main region is collected in the first sub-region is greater than a first threshold, and the number of times the network quality data corresponding to the second main region is collected in the second sub-region (one or more) is greater than a second threshold, then the computer device determines the second main region as a neighboring region of the first main region (the first and second main regions are neighboring regions); wherein, the second sub-region is an adjacent sub-region of the first sub-region.

[0115] Figure 3d This is a schematic diagram illustrating a location association provided for an embodiment of this application. For example... Figure 3d As shown, the areas corresponding to M measurement reports based on internet applications are divided into several grids of equal size. Assume the first and second count thresholds are both 300 times. In grid G1, the network quality data corresponding to main area 1 (C1) is collected 450 times, exceeding the first count threshold. In adjacent grids G0, G2, G5, and G6 of G1, the network quality data corresponding to main area 2 (C2) is collected 150, 70, 110, and 230 times respectively, for a total count of 150 + 70 + 110 + 230 = 560 times, exceeding the second count threshold. The computer determines main area 2 (C2) as a neighbor of main area 1 (C1) (main areas 1 and 2 are neighbors).

[0116] Figure 3e This is a schematic diagram illustrating a location association provided for an embodiment of this application. For example... Figure 3e As shown, the areas corresponding to M measurement reports based on internet applications are divided into several grids of equal size. Assume the first threshold is 400 times and the second threshold is 200 times. In grid G1, the network quality data corresponding to main area 1 (C1) is collected 450 times, exceeding the first threshold. In the adjacent grid G2 of G1, the network quality data corresponding to main area 2 (C2) is collected 500 times, exceeding the second threshold. The computer determines main area 2 (C2) as a neighbor of main area 1 (C1) (main areas 1 and 2 are neighbors).

[0117] S203. Based on the network quality data corresponding to the first main area and the environmental characteristics of neighboring areas, predict the network quality data of the base stations in the neighboring areas in the target area.

[0118] The target area is contained within the area covered by the first primary area. In one implementation, the computer device can invoke a network quality data prediction model to predict the network quality data corresponding to the first primary area and the environmental characteristics of neighboring areas (i.e., as input data) to obtain the network quality data of the base stations of the neighboring areas in the target area. Table 2 is an example table of fields related to environmental characteristics provided in an embodiment of this application.

[0119] Table 2

[0120]

[0121]

[0122] Based on the fields in Table 2, by distinguishing between the dial-up card operator field, the data card operator field, and single / dual SIM card fields, network quality analysis can be performed for different operators; the network area identifier / location code field, as well as related location fields (such as province, city, district, etc.), can determine the collection location of network quality data; the logical cell number field, base station operator field, and network base station ID, etc., can determine the main area and base station providing network services; the indoor / outdoor field, altitude field, etc., can analyze environmental characteristics. It should be noted that the above fields and uses are for illustrative purposes only and do not constitute actual limitations of this application. In practical applications, the required fields and their uses can be dynamically configured based on needs, and this application does not impose any restrictions on this. The {rsrp,rsrq,sinr}_as_main field represents the prediction result of the network quality data prediction model.

[0123] In one embodiment, the training process of the network quality data prediction model includes: a computer device acquiring network quality data of a third master region and collecting network quality data of neighboring regions of the third master region within a preset region, where the preset region is the area covered by the third master region (i.e., the third master region is the master region of the preset region). The computer device invokes the model to be trained, based on the network quality data of the third master region and the environmental characteristics of its neighboring regions, to predict the network quality data of the neighboring regions of the third master region within the preset region, and trains the model based on the difference between the collected network quality data of the neighboring regions of the third master region within the preset region and the predicted network quality data of the neighboring regions of the third master region within the preset region. The model to be trained can be constructed based on the distributed gradient boosting library (XGBoost) or based on deep neural networks (DNNs). Table 3 shows the prediction errors of the network quality data prediction model constructed based on XGBoost and the network quality data prediction model constructed based on DNNs.

[0124] Table 3

[0125] RSRP 4.6 3.9 RSRQ 3.2 2.8 SINR 5.9 4.1

[0126] As shown in Table 3, the prediction errors of the network quality data prediction model based on DNN in RSRP, RSRQ and SINR are smaller than those of the network quality data prediction model based on XGBoost in RSRP, RSRQ and SINR.

[0127] In another implementation, the computer device acquires the impact of different environmental features on network quality and filters the environmental features of neighboring cells based on the impact of each environmental feature on network quality; for example, only the top k environmental features of neighboring cells with the greatest impact on network quality are retained. After filtering, the computer device predicts the network quality data of the neighboring cell's base station in the target area based on the filtered environmental features of the neighboring cells and the network quality data corresponding to the first main area; for example, the computer device can construct and transform the filtered environmental features to obtain transformed features, determine the network quality parameters based on the mapping relationship between the features and network quality parameters, and finally calculate the network quality data of the neighboring cell's base station in the target area based on the network quality parameters and the network quality data corresponding to the first main area.

[0128] In this embodiment, M measurement reports based on Internet applications are obtained. Each Internet application measurement report contains descriptive information of at least one main region. The descriptive information of each main region includes network quality data and environmental characteristics corresponding to that main region. Neighboring regions of the first main region are mined using the M Internet application measurement reports. Based on the network quality data corresponding to the first main region and the environmental characteristics of the neighboring regions, the network quality data of the base stations in the neighboring regions in the target region is predicted. The target region is included in the area covered by the first main region. Therefore, this application considers spatial and temporal correlations during the neighboring region mining process. By combining the network quality data corresponding to the main region and the environmental characteristics of the corresponding neighboring regions, the network quality data of the base stations in the neighboring regions in the target region can be easily obtained.

[0129] Please see Figure 4 , Figure 4 A flowchart illustrating another network quality data processing method provided in this application embodiment, which can be executed by a computer device; for example, by... Figure 1b The server 102 shown is executing. (As...) Figure 4 As shown, the network quality data processing method may include the following steps S401-S404:

[0130] S401. Obtain M measurement reports based on Internet applications.

[0131] S402. From at least one of the spatial correlation dimension and the temporal correlation dimension, perform neighbor pair mining on M measurement reports based on Internet applications to obtain the neighboring cells of the first main region.

[0132] S403. Based on the network quality data corresponding to the first main area and the environmental characteristics of neighboring areas, predict the network quality data of the base stations in the neighboring areas in the target area.

[0133] For detailed implementation of steps S401-S403, please refer to [link / reference]. Figure 2 The implementation methods for steps S201-S203 will not be described in detail here.

[0134] Figure 5a This is a diagram illustrating a network quality data processing architecture provided in an embodiment of this application. Figure 5a As shown, the computer equipment first cleans and formats the relevant data (such as base station information, network quality data, etc.) collected by the acquisition equipment, and generates an Internet application-based measurement report based on the processed data, storing it in a detailed database. Next, on one hand, the computer equipment mines the neighboring cells corresponding to each main area from at least one of the spatial and temporal correlation dimensions, and the corresponding data (such as neighboring cell relationship pairs) can be stored in a neighboring cell database. On the other hand, the computer equipment obtains network quality data for each main area based on the Internet application measurement report (such as RSRP, RSRQ, SINR, etc., which can be obtained based on the main area identifier), and this data can be stored separately in the main area network quality database. Then, based on the neighboring cell relationships indicated in the neighboring cell database, the computer equipment determines the neighboring cells (which can be one or more) of the target main area, and inputs the network quality data of the target main area in the target region and the environmental characteristics of the target main area's neighboring cells into the network quality data prediction model to obtain the network quality data of the target main area's neighboring cells in the target region (i.e., the prediction result). The network quality data prediction model can be trained based on the collected real data (sample data), and the specific training process of the model can be found in [reference needed]. Figure 2 The training process in step S203 will not be described in detail here. The target main region can be any main region. Following the method described above, the computer device can determine the network quality data of the neighboring regions of each main region in the corresponding area and continue to execute step S404.

[0135] S404. Based on the network quality data corresponding to the first main area and the network quality data of the base stations in the neighboring areas in the target area, generate the network quality assessment result of the target area.

[0136] Network quality data may include, but is not limited to, latency, network congestion, signal strength, and data transmission speed. In one embodiment, network quality data includes at least one of RSRP, RSRQ, and SINR. Signal strength is used as an example below.

[0137] In one implementation, network quality data includes wireless signal quality indicators. The computer device determines the signal strength of the target area based on the signal quality indicators of the base stations in the first primary area and the base stations in neighboring areas; for example, this can be calculated using weighted summation, with different determination methods for different indicators. Further, the computer device can display a regional map (the target area is included in the regional map) and display the target area in the regional map in the color corresponding to its signal strength; for example, if the target area's signal strength belongs to a first interval, it is displayed as green; if it belongs to a second interval, it is displayed as yellow; and if it belongs to a third interval, it is displayed as red. Additionally, the computer device can also send the signal strength of the target area to a terminal device, enabling the terminal device to display a regional map and display the target area in the regional map in the corresponding color according to its signal strength.

[0138] Figure 5b This is a schematic diagram of a map display provided as an embodiment of this application. For example... Figure 5b As shown, the computer device can display a regional map and divide it into several grids. Then, following steps S401-S404, the computer device can obtain the network quality assessment result for each grid and display the grid as a corresponding color (grayscale) based on the network quality assessment result. Network quality maintenance / service personnel can understand the network quality of each region (grid) in real time based on this regional map and take timely measures to maintain the network when poor network quality is detected in a certain region.

[0139] In this embodiment, M measurement reports based on Internet applications are obtained. Each Internet application measurement report contains descriptive information of at least one main area. The descriptive information of each main area includes network quality data and environmental characteristics corresponding to that main area. Neighboring areas of the first main area are mined using the M Internet application measurement reports. Based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas, the network quality data of the base stations in the neighboring areas in the target area is predicted. The target area is included in the area covered by the first main area. Therefore, by mining the neighboring areas of each main area using the Internet application measurement reports and combining the network quality data corresponding to the main area with the environmental characteristics of the corresponding neighboring areas, the network quality data of the base stations in the neighboring areas in the target area can be easily obtained. Based on the network quality data of the base stations in the neighboring areas in the target area and the network quality data corresponding to the main area, a network quality assessment result for the target area is generated, facilitating network maintenance by network operators / service providers.

[0140] The methods of the embodiments of this application have been described in detail above. In order to facilitate better implementation of the above solutions of the embodiments of this application, the apparatus of the embodiments of this application is provided below.

[0141] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a network quality data processing device provided in an embodiment of this application. Figure 6 The network quality data processing device shown can be mounted in a computer device, which can specifically be a terminal device or a server. Figure 6 The network quality data processing device shown can be used to perform the above. Figure 2 and Figure 4 Some or all of the functionality described in the method embodiments. Please refer to [link / reference]. Figure 6 The network quality data processing device includes:

[0142] The acquisition unit 601 is used to acquire M measurement reports based on Internet applications. Each measurement report of an Internet application contains description information of at least one main area. The description information of each main area includes network quality data and environmental characteristics corresponding to the main area. M is an integer greater than 1.

[0143] Processing unit 602 is used to mine neighboring cells of the first main area through M measurement reports based on Internet applications, wherein the descriptive information of the first main area is contained in at least one measurement report based on Internet applications.

[0144] And for predicting the network quality data of the base stations in the target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas, the target area being included in the area covered by the first main area.

[0145] In one implementation, the processing unit 602 is configured to mine neighboring cells of the first primary region using M measurement reports from Internet applications, specifically for:

[0146] Neighbor pair mining is performed on M measurement reports based on Internet applications from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighboring cells of the first main region.

[0147] In one implementation, the description information of any primary region also includes the collection location of the network quality data corresponding to that primary region; the processing unit 602 is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0148] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0149] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0150] Count the number of co-occurrences of each main region pair in each sub-region. Any main region pair consists of any two main regions associated with M measurement reports based on Internet applications.

[0151] The neighboring cells of the first primary region are determined based on the number of co-occurrences of each primary region pair.

[0152] In one implementation, the process by which processing unit 602 counts the co-occurrence counts of each main region pair in each sub-region includes:

[0153] If the same acquisition device acquires network quality data corresponding to the first main area and network quality data corresponding to the second main area in the first sub-region, and the acquisition time interval between the two network quality data is less than the duration threshold, then the number of co-occurrences of the target main area in the first sub-region is increased.

[0154] If different acquisition devices acquire network quality data corresponding to the first main area and network quality data corresponding to the second main area respectively in the first sub-region, then increase the number of times the target main area co-occurs in the first sub-region;

[0155] The target main region consists of a first main region and a second main region, and the first sub-region is any one of the at least two sub-regions.

[0156] In one implementation, the processing unit 602 is configured to determine the neighboring regions of the first primary region based on the co-occurrence count of each primary region pair, specifically configured to:

[0157] If the co-occurrence frequency of the target sub-region pair in the first sub-region is greater than the frequency threshold, then the second main region is determined as a neighboring region of the first main region, and the target sub-region pair consists of the first main region and the second main region; or,

[0158] The network quality data corresponding to the first main region and the network quality data corresponding to the second main region are counted the number of times they are collected in the first sub-region. Based on the number of times the network quality data corresponding to the first main region and the network quality data corresponding to the second main region are collected in the first sub-region, as well as the number of times the target sub-region pair co-occurs in the first sub-region, the spatial neighbor probability is calculated. If the spatial neighbor probability is greater than the spatial probability threshold, the second main region is determined as a neighbor of the first main region. The target sub-region pair consists of the first main region and the second main region.

[0159] In one implementation, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processing unit 602 is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0160] If any measurement report based on an Internet application indicates that the time interval between the collection of network quality data corresponding to the first primary area and the collection of network quality data corresponding to the second primary area is less than the duration threshold, and the collection distance of network quality data is less than the distance threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0161] The network quality data collection distance is calculated based on the collection location of the network quality data corresponding to the first primary area and the collection location of the network quality data corresponding to the second primary area.

[0162] In one implementation, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processing unit 602 is used to perform neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region, specifically used for:

[0163] The temporal correlation score and spatial correlation score of the first and second main regions are obtained. The temporal correlation score is determined based on the time interval between the collection of network quality data corresponding to the first and second main regions, as well as the collection distance of the network quality data. The spatial correlation score is determined based on the number of times the first and second main regions co-occur in the first sub-region. The first sub-region is obtained by dividing the regions corresponding to M Internet application-based measurement reports according to a preset regional division rule.

[0164] The time-related dimension score and the spatial-related dimension score are weighted and summed to obtain the correlation score of the first and second main regions.

[0165] If the correlation score is greater than the score threshold, the second primary region will be identified as a neighboring region of the first primary region.

[0166] In one implementation, the description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected; the processing unit 602 is used to mine the neighboring regions of the first primary region through M measurement reports based on Internet applications, specifically for:

[0167] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0168] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0169] If the number of times the network quality data corresponding to the first primary area is collected in the first sub-area is greater than the first threshold, and the number of times the network quality data corresponding to the second primary area is collected in the second sub-area is greater than the second threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0170] The second sub-region is the adjacent sub-region of the first sub-region.

[0171] In one embodiment, the processing unit 602 is configured to predict the network quality data of the neighboring cells at the target location based on the network quality data corresponding to the first primary cell and the environmental characteristics of the neighboring cells, specifically configured to:

[0172] The network quality data prediction model is invoked to predict the network quality data of the first primary area and the environmental characteristics of neighboring areas, thereby obtaining the network quality data of the neighboring base stations in the target area; or...

[0173] The impact of different environmental features on network quality is obtained. Based on the impact of each environmental feature on network quality, the environmental features of neighboring cells are filtered. Based on the filtered environmental features of neighboring cells and the network quality data corresponding to the first primary area, the network quality data of the base stations in the neighboring cells in the target area is predicted.

[0174] In one embodiment, the processing unit 602 is further configured to:

[0175] Based on the network quality data corresponding to the first primary area and the network quality data of the base stations in the neighboring areas in the target area, a network quality assessment result for the target area is generated.

[0176] In one implementation, the network quality data includes wireless signal quality indicators; the processing unit 602 is configured to generate a network quality assessment result for the target area based on the network quality data corresponding to the first primary area and the network quality data of base stations in neighboring areas within the target area, specifically for:

[0177] The signal strength of the target area is determined based on the signal quality indicators of the base station in the first main area and the signal quality indicators of the base stations in the neighboring areas.

[0178] Display the area map, with the target area included in the area map;

[0179] The target area is displayed in the area map in a color that corresponds to the signal strength of the target area.

[0180] According to one embodiment of this application, Figure 2 and Figure 4 The network quality data processing method shown may involve some steps by [the following]. Figure 6 The network quality data processing apparatus shown is executed by each unit. For example, Figure 2 Step S201 shown can be performed by Figure 6 The acquisition unit 601 shown is executed, and steps S202 and S203 can be performed by... Figure 6 The processing unit 602 shown executes the operation; Figure 4 Step S401 shown can be performed by Figure 6 The acquisition unit 601 shown is executed, and steps S402-S404 can be performed by... Figure 6 The processing unit 602 shown executes. Figure 6 The network quality data processing apparatus shown can be composed of various units, either individually or entirely, combined into one or more other units. Alternatively, some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The above-mentioned units are based on logical functional division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the network quality data processing apparatus may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0181] According to another embodiment of this application, a general-purpose computing device, such as a computer device including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM), can perform operations such as... Figure 2 and Figure 4 The computer program (including program code) for each step involved in the corresponding method shown, to construct such... Figure 6 The network quality data processing apparatus shown herein, and the network quality data processing method for implementing the embodiments of this application, are described. A computer program may be recorded on, for example, a computer-readable recording medium, loaded onto the aforementioned computing device via the computer-readable recording medium, and executed therein.

[0182] Based on the same inventive concept, the principle and beneficial effects of the network quality data processing device provided in the embodiments of this application are similar to the principle and beneficial effects of the network quality data processing method in the embodiments of this application. For details, please refer to the principle and beneficial effects of the method implementation. For the sake of brevity, these will not be repeated here.

[0183] Please see Figure 7 , Figure 7This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device may be a terminal device or a server. Figure 7 As shown, the computer device includes at least a processor 701, a communication interface 702, and a memory 703. The processor 701, communication interface 702, and memory 703 can be connected via a bus or other means. The processor 701 (or Central Processing Unit, CPU) is the computing and control core of the computer device. It can parse various instructions within the computer device and process various data. For example, the CPU can parse power-on / off commands issued by objects to the computer device and control the computer device to perform power-on / off operations; it can also transmit various interactive data between internal structures of the computer device, and so on. The communication interface 702 may optionally include standard wired interfaces or wireless interfaces (such as Wi-Fi, mobile communication interfaces, etc.), and can be used to send and receive data under the control of the processor 701; the communication interface 702 can also be used for data transmission and interaction within the computer device. The memory 703 is the storage device in the computer device, used to store programs and data. It can be understood that the memory 703 here can include the computer device's built-in memory, or it can include extended memory supported by the computer device. The memory 703 provides storage space for storing the operating system of the computer device, which may include, but is not limited to, Android, iOS, Windows Phone, etc. This application does not limit this.

[0184] This application embodiment also provides a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the processing system of the computer device. Furthermore, the storage space also stores computer programs suitable for loading and execution by the processor 701. It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0185] In one embodiment, processor 701 performs the following operations by running a computer program stored in memory 703:

[0186] Obtain M measurement reports based on Internet applications. Each measurement report for an Internet application contains description information of at least one main area. The description information of each main area includes the network quality data and environmental characteristics corresponding to that main area. M is an integer greater than 1.

[0187] By using M measurement reports based on Internet applications, the neighboring cells of the first primary region are mined, and the descriptive information of the first primary region is contained in at least one measurement report based on Internet applications.

[0188] Based on the network quality data corresponding to the first main area and the environmental characteristics of neighboring areas, the network quality data of the base stations in the neighboring areas in the target area is predicted. The target area is included in the area covered by the first main area.

[0189] As an optional embodiment, the processor 701 mines the neighboring cells of the first primary region through M measurement reports based on Internet applications. A specific implementation of this method is as follows:

[0190] Neighbor pair mining is performed on M measurement reports based on Internet applications from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighboring cells of the first main region.

[0191] As an optional embodiment, the description information of any primary region also includes the collection location of the network quality data corresponding to that primary region; the processor 701 performs neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region. A specific embodiment is as follows:

[0192] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0193] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0194] Count the number of co-occurrences of each main region pair in each sub-region. Any main region pair consists of any two main regions associated with M measurement reports based on Internet applications.

[0195] The neighboring cells of the first primary region are determined based on the number of co-occurrences of each primary region pair.

[0196] As an optional embodiment, the process by which processor 701 counts the co-occurrence counts of each primary region pair in each sub-region includes:

[0197] If the same acquisition device acquires network quality data corresponding to the first main area and network quality data corresponding to the second main area in the first sub-region, and the acquisition time interval between the two network quality data is less than the duration threshold, then the number of co-occurrences of the target main area in the first sub-region is increased.

[0198] If different acquisition devices acquire network quality data corresponding to the first main area and network quality data corresponding to the second main area respectively in the first sub-region, then increase the number of times the target main area co-occurs in the first sub-region;

[0199] The target main region consists of a first main region and a second main region, and the first sub-region is any one of the at least two sub-regions.

[0200] As an optional embodiment, the processor 701 determines the neighboring regions of the first primary region based on the co-occurrence count of each primary region pair. A specific embodiment of this is as follows:

[0201] If the co-occurrence frequency of the target sub-region pair in the first sub-region is greater than the frequency threshold, then the second main region is determined as a neighboring region of the first main region, and the target sub-region pair consists of the first main region and the second main region; or,

[0202] The network quality data corresponding to the first main region and the network quality data corresponding to the second main region are counted the number of times they are collected in the first sub-region. Based on the number of times the network quality data corresponding to the first main region and the network quality data corresponding to the second main region are collected in the first sub-region, as well as the number of times the target sub-region pair co-occurs in the first sub-region, the spatial neighbor probability is calculated. If the spatial neighbor probability is greater than the spatial probability threshold, the second main region is determined as a neighbor of the first main region. The target sub-region pair consists of the first main region and the second main region.

[0203] As an optional embodiment, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processor 701 performs neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region. A specific embodiment is as follows:

[0204] If any measurement report based on an Internet application indicates that the time interval between the collection of network quality data corresponding to the first primary area and the collection of network quality data corresponding to the second primary area is less than the duration threshold, and the collection distance of network quality data is less than the distance threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0205] The network quality data collection distance is calculated based on the collection location of the network quality data corresponding to the first primary area and the collection location of the network quality data corresponding to the second primary area.

[0206] As an optional embodiment, the description information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the processor 701 performs neighbor pair mining on M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region. A specific embodiment is as follows:

[0207] The temporal correlation score and spatial correlation score of the first and second main regions are obtained. The temporal correlation score is determined based on the time interval between the collection of network quality data corresponding to the first and second main regions, as well as the collection distance of the network quality data. The spatial correlation score is determined based on the number of times the first and second main regions co-occur in the first sub-region. The first sub-region is obtained by dividing the regions corresponding to M Internet application-based measurement reports according to a preset regional division rule.

[0208] The time-related dimension score and the spatial-related dimension score are weighted and summed to obtain the correlation score of the first and second main regions.

[0209] If the correlation score is greater than the score threshold, the second primary region will be identified as a neighboring region of the first primary region.

[0210] As an optional embodiment, the description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected; the specific embodiment of the processor 701 mining the neighboring regions of the first primary region through M measurement reports based on Internet applications is as follows:

[0211] According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions;

[0212] Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area;

[0213] If the number of times the network quality data corresponding to the first primary area is collected in the first sub-area is greater than the first threshold, and the number of times the network quality data corresponding to the second primary area is collected in the second sub-area is greater than the second threshold, then the second primary area is determined as a neighboring area of ​​the first primary area.

[0214] The second sub-region is the adjacent sub-region of the first sub-region.

[0215] As an optional embodiment, the processor 701 predicts the network quality data of the neighboring cell at the target location based on the network quality data corresponding to the first primary cell and the environmental characteristics of the neighboring cells. A specific embodiment of this is as follows:

[0216] The network quality data prediction model is invoked to predict the network quality data of the first primary area and the environmental characteristics of neighboring areas, thereby obtaining the network quality data of the neighboring base stations in the target area; or...

[0217] The impact of different environmental features on network quality is obtained. Based on the impact of each environmental feature on network quality, the environmental features of neighboring cells are filtered. Based on the filtered environmental features of neighboring cells and the network quality data corresponding to the first primary area, the network quality data of the base stations in the neighboring cells in the target area is predicted.

[0218] As an optional embodiment, the processor 701, by running a computer program in the memory 703, also performs the following operations:

[0219] Based on the network quality data corresponding to the first primary area and the network quality data of the base stations in the neighboring areas in the target area, a network quality assessment result for the target area is generated.

[0220] As an optional embodiment, the network quality data includes wireless signal quality indicators; the processor 701 generates a network quality assessment result for the target area based on the network quality data corresponding to the first main area and the network quality data of the base stations in neighboring areas in the target area. A specific embodiment of this is as follows:

[0221] The signal strength of the target area is determined based on the signal quality indicators of the base station in the first main area and the signal quality indicators of the base stations in the neighboring areas.

[0222] Display the area map, with the target area included in the area map;

[0223] The target area is displayed in the area map in a color that corresponds to the signal strength of the target area.

[0224] Based on the same inventive concept, the principle and beneficial effects of the computer device provided in the embodiments of this application in solving the problem are similar to the principle and beneficial effects of the network quality data processing method in the embodiments of this application in solving the problem. Please refer to the principle and beneficial effects of the method implementation. For the sake of brevity, they will not be repeated here.

[0225] This application also provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and to execute the network quality data processing method of the above-described method embodiments.

[0226] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the network quality data processing method described above.

[0227] The steps in the method of this application embodiment can be adjusted, combined, or deleted according to actual needs.

[0228] The modules in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0229] In the embodiments of this application, the term "module" or "unit" refers to a computer program or part of a computer program with a predetermined function, which works together with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0230] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0231] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Those skilled in the art will understand that all or part of the processes for implementing the above embodiments and equivalent variations made in accordance with the claims of this application are still within the scope of this application.

Claims

1. A network quality data processing method characterized by, The method includes: Obtain M measurement reports based on Internet applications. Each measurement report for an Internet application contains description information of at least one main area. The description information of each main area includes the network quality data and environmental characteristics corresponding to that main area. M is an integer greater than 1. The neighboring areas of the first main area are mined using the M measurement reports based on Internet applications, and the descriptive information of the first main area is contained in at least one measurement report based on Internet applications. Based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring areas, the network quality data of the base stations in the neighboring areas in the target area is predicted, and the target area is included in the area covered by the first main area.

2. The method of claim 1, wherein, The process of mining neighboring cells of the first primary region using the M measurement reports based on internet applications includes: Neighbor pair mining is performed on the M measurement reports based on Internet applications from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighboring cells of the first main region.

3. The method of claim 2, wherein, The description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected; the process of mining neighbor pairs from the M Internet application-based measurement reports from at least one of the spatial correlation and temporal correlation dimensions to obtain the neighboring regions of the first primary region includes: According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions; Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area; Count the number of co-occurrences of each main region pair in each sub-region. Any main region pair consists of any two main regions associated with the M measurement reports based on Internet applications. The neighboring cells of the first primary region are determined based on the number of co-occurrences of each primary region pair.

4. The method of claim 3, wherein, The process of counting the co-occurrence frequency of each principal pair in each sub-region includes: If the same acquisition device acquires network quality data corresponding to the first main area and network quality data corresponding to the second main area in the first sub-region, and the acquisition time interval between the two network quality data is less than the duration threshold, then the number of co-occurrences of the target main area pair in the first sub-region is increased. If different acquisition devices acquire network quality data corresponding to the first main area and network quality data corresponding to the second main area respectively in the first sub-region, then increase the number of times the target main area pair co-occurs in the first sub-region; The target main region is composed of the first main region and the second main region, and the first sub-region is any one of the at least two sub-regions.

5. The method as described in claim 3, characterized in that, The determination of neighboring cells of the first primary region based on the co-occurrence frequency of each primary region pair includes: If the co-occurrence frequency of the target sub-region pair in the first sub-region is greater than a threshold, then the second main region is determined as a neighboring region of the first main region, and the target sub-region pair consists of the first main region and the second main region; or, The network quality data corresponding to the first main region and the network quality data corresponding to the second main region are collected the most frequently in the first sub-region. Based on the number of times the network quality data corresponding to the first main region is collected in the first sub-region, the number of times the network quality data corresponding to the second main region is collected in the first sub-region, and the number of times the target sub-region pair co-occurs in the first sub-region, the spatial neighbor probability is calculated. If the spatial neighbor probability is greater than the spatial probability threshold, the second main region is determined as a neighbor of the first main region. The target sub-region pair consists of the first main region and the second main region.

6. The method as described in claim 2, characterized in that, The descriptive information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the neighbor pair mining of the M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region includes: If any measurement report based on an Internet application indicates that the time interval between the collection of network quality data corresponding to the first primary area and the collection distance of network quality data corresponding to the second primary area is less than the duration threshold and the collection distance of network quality data is less than the distance threshold, then the second primary area is determined as a neighboring area of ​​the first primary area. The network quality data acquisition distance is calculated based on the acquisition location of the network quality data corresponding to the first main area and the acquisition location of the network quality data corresponding to the second main area.

7. The method as described in claim 2, characterized in that, The descriptive information of any primary region also includes the collection location and collection time of the network quality data corresponding to that primary region; the neighbor pair mining of the M Internet application-based measurement reports from at least one of the spatial correlation dimension and the temporal correlation dimension to obtain the neighbor regions of the first primary region includes: The temporal correlation dimension score and spatial correlation dimension score of the first main region and the second main region are obtained. The temporal correlation dimension score is determined based on the time interval between the collection of network quality data corresponding to the first main region and the network quality data corresponding to the second main region, as well as the collection distance of the network quality data. The spatial correlation dimension score is determined based on the number of times the first main region and the second main region co-occur in a first sub-region. The first sub-region is obtained by dividing the regions corresponding to the M Internet application-based measurement reports according to a preset region division rule. The time-related dimension score and the spatial-related dimension score are weighted and summed to obtain the correlation score between the first main region and the second main region. If the associated score is greater than the score threshold, then the second main region is determined as a neighboring region of the first main region.

8. The method as described in claim 1, characterized in that, The description information of any primary region also includes the location where the network quality data corresponding to that primary region was collected; the step of mining neighboring regions of the first primary region through the M measurement reports based on Internet applications includes: According to the preset regional division rules, the regions corresponding to the M Internet-based measurement reports are divided into at least two sub-regions; Based on the collection location of the network quality data corresponding to each main area, the network quality data corresponding to each main area is mapped to the corresponding sub-area; If the number of times the network quality data corresponding to the first main area is collected in the first sub-area is greater than the first threshold, and the number of times the network quality data corresponding to the second main area is collected in the second sub-area is greater than the second threshold, then the second main area is determined as a neighboring area of ​​the first main area. The second sub-region is the adjacent sub-region of the first sub-region.

9. The method as described in claim 1, characterized in that, The step of predicting the network quality data of the neighboring cells at the target location based on the network quality data corresponding to the first primary cell and the environmental characteristics of the neighboring cells includes: The network quality data prediction model is invoked to predict the network quality data corresponding to the first primary area and the environmental characteristics of the neighboring areas, thereby obtaining the network quality data of the base stations in the neighboring areas within the target area; or... The influence of different environmental features on network quality is obtained. Based on the influence of each environmental feature on network quality, the environmental features of the neighboring cells are filtered. Based on the filtered environmental features of the neighboring cells and the network quality data corresponding to the first main area, the network quality data of the base station of the neighboring cell in the target area is predicted.

10. The method as described in claim 1, characterized in that, The method further includes: Based on the network quality data corresponding to the first main area and the network quality data of the base stations in the neighboring areas in the target area, a network quality assessment result for the target area is generated.

11. The method as described in claim 10, characterized in that, The network quality data includes wireless signal quality indicators; the generation of network quality assessment results for the target area based on the network quality data corresponding to the first primary area and the network quality data of the base stations in the neighboring areas in the target area includes: The signal strength of the target area is determined based on the signal quality index of the base station in the first main area and the signal quality index of the base station in the neighboring area in the target area. Display a region map, wherein the target region is contained within the region map; The target area is displayed in the area map in a color that corresponds to the signal strength of the target area.

12. A network quality data processing device, characterized in that, The network quality data processing device includes: The acquisition unit is used to acquire M measurement reports based on Internet applications. Each measurement report of an Internet application contains description information of at least one main area. The description information of each main area includes network quality data and environmental characteristics corresponding to the main area. M is an integer greater than 1. The processing unit is configured to mine neighboring areas of the first main area through the M measurement reports based on Internet applications, wherein the descriptive information of the first main area is contained in at least one measurement report based on Internet applications. And for predicting the network quality data of the base stations of the neighboring cells in the target area based on the network quality data corresponding to the first main area and the environmental characteristics of the neighboring cells, wherein the target area is included in the area covered by the first main area.

13. A computer device, characterized in that, include: A memory, wherein a computer program is stored; A processor for loading the computer program to implement the network quality data processing method as described in any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1-11.

15. A computer program product, characterized in that, The computer program product includes a computer program adapted to be loaded by a processor and execute the network quality data processing method as described in any one of claims 1-11.

Images