A system and method for identifying spatial clusters of users with degraded user experience within a heterogeneous network.

Abstract

The present disclosure provides a novel solution for network optimization in telecommunication networks, which has traditionally always been driven by measuring and improving key performance indicators (KPIs) of network elements, which facilitates the identification of customers with poor experience and the identification of spatial clusters of these customers to pinpoint the exact location of the problem, thereby enabling more targeted network optimization. The system and method included in the present invention allows the identification of these customers with poor experience and the identification of spatial clusters of these customers to pinpoint the exact location of the problem, thereby enabling more targeted network optimization. The present disclosure provides a solution that allows the user's experience to be benchmarked and tracked and improved accordingly by aggregating multiple metrics related to the user's voice, data and coverage experience, and deriving a single KPI.

Description

Technical Field

[0001] Reservation of Rights A part of the disclosure of this patent document includes, but is not limited to, matters subject to intellectual property rights such as copyrights, designs, trademarks, IC layout designs, and / or trade dress protection belonging to Jio Platforms Limited (JPL) or its related companies (hereinafter referred to as the owner). The owner has no objection to any reproduction of this patent document or this patent disclosure by anyone as it appears in the patent file or records of the Patent and Trademark Office, but in case it is not so, all rights are reserved whatever they may be. All rights to such intellectual property are fully reserved by the owner.

[0002] This disclosure relates to telecommunications, and more particularly, to identifying spatial clusters of users with degraded experiences within a heterogeneous network, and is intended to be used for spatial clustering to identify clusters of users whose experiences within a telecommunications network are not optimally met.

Background Art

[0003] The following description of related technologies is intended to provide background information belonging to the field of this disclosure. This section may include some aspects of the art related to various features of this disclosure. However, it should be understood that this section is not used as an admission of prior art, but is only used to enhance the reader's understanding of this disclosure.

[0004] Today, with the emergence of wireless technologies such as GSM, EDGE, HSPA, and LTE, all communications within wireless networks provide a variety of communication services, including voice, video, data, advertising, content, messaging, and broadcast. One example of such a network is Advanced Universal Terrestrial Radio Access (E-UTRA), a radio access network standard defined in 3GPP® Release 5 and later to replace UMTS and HSDPA / HSUPA technologies. E-UTRA is the air interface for 3GPP's Long-Term Evolution (LTE) upgrade path for mobile networks. Unlike HSPA, LTE's E-UTRA is a completely new air interface system that is unrelated to and incompatible with W-CDMA. E-UTRA enables higher data rates, lower latency, and is optimized for packet data. UMTS, the successor to Global Systems for Mobile Communications (GSM) technology, currently supports various air interface standards such as Wideband Code Division Multiple Access (W-CDMA), Time Division Code Division Multiple Access (TD-CDMA), and Time Division Synchronous Code Division Multiple Access (TD-SCDMA). UMTS also supports enhanced 3G data communication protocols, such as High Speed ​​Packet Access (HSPA), which brings higher data transfer rates and greater capacity to the associated UMTS network. With this increased capacity and higher data transfer rates comes numerous challenges related to cell and cell optimization.

[0005] In 5G cellular deployments, macrocells, along with various small cells, are planned to provide coverage and capacity solutions across target areas. Therefore, site-to-site distances will be shorter for the network. Furthermore, a greater number of sites / enodes will be needed to mitigate the growing data demands in emerging networks, thereby creating high-density to ultra-high-density wireless access networks in large cities.

[0006] Network optimization in telecommunications networks has traditionally been driven by measuring and improving key performance indicators (KPIs) of network elements within heterogeneous networks. This approach ignores the actual location of customers affected by underperforming network elements.

[0007] Currently, existing network optimization methods focus solely on improving the performance of heterogeneous network elements, failing to consider the actual problems faced by customers. The results of network optimization activities do not always directly translate into improvements in the customer experience. The core of the problem lies in the fact that operators cannot identify where these customers with degraded experiences are located, nor can they identify clusters of these users. [Overview of the project] [Problems that the invention aims to solve]

[0008] Therefore, it is necessary to facilitate the identification of customers with a degraded experience and the identification of spatial clusters of these customers in order to precisely pinpoint the location of the problem and thereby enable more targeted network optimization.

[0009] This disclosure enables a solution for directly and accurately identifying specific areas where customers with a degraded experience are concentrated, by identifying customers with a degraded experience within the network, and then identifying clusters enclosed by a concave hull where these users are concentrated within a heterogeneous network.

[0010] One of the primary objectives of this invention is to help organizations shift from network element-driven performance optimization to user-driven performance improvement, thereby enabling them to directly measure, track, and improve the user experience in addition to clustering.

[0011] Another object of the present invention is to provide a solution to the problem that measuring and analyzing the customer experience for each customer does not yield useful results unless the customer experience is aggregated, clustered, and areas that need to be addressed are identified.

[0012] Another objective of the present invention is to provide a solution that enables benchmarking, tracking, and improving the user experience by aggregating numerous metrics related to the user's voice, data, and coverage experience, and by obtaining a single KPI.

[0013] Another object of the present invention is to provide a solution that enables telecommunications service providers to identify the most severely affected locations and to implement targeted solutions. [Means for solving the problem]

[0014] In one embodiment, the Disclosure provides a system for facilitating the identification of degradation of the experience in one or more wireless services by one or more users within a heterogeneous network. The system may include one or more user devices commutably coupled to the heterogeneous network, the heterogeneous network may further include a plurality of nodes and one or more network access points configured to provide wireless services to one or more users. The system may further include an analysis server operably coupled to the heterogeneous network. The analysis server may further include a processor that executes a set of executable instructions stored in memory, the processor causing the analysis server to receive a set of data packets from the plurality of nodes relating to signals associated with one or more wireless services accessed by one or more user devices, the set of data packets to be received over a predefined period of time. The analysis server may extract a first set of attributes from a set of data packets, wherein the first set of attributes relates to parameters associated with signal quality, signal strength, interference, cell throughput, drop, and mute occurrences for one or more wireless services; and then compare the extracted first set of attributes with a predetermined set of parameters stored in the routing server's knowledge base, wherein the predetermined set of parameters includes a threshold set of parameters for signal quality, signal strength, interference, cell throughput, drop, and mute occurrences for one or more wireless services. The analysis server may then categorize the received set of data packets into several predefined categories based on the comparison between the extracted first set of attributes and the predetermined set of parameters; and calculate a Customer Experience (CE) score based on the comparison between the extracted first set of attributes and the predetermined set of parameters.Furthermore, the analysis server can identify one or more users with a degraded experience based on the calculated CE score.

[0015] In one embodiment, the disclosure provides a method for facilitating the identification of degradation of the experience in one or more wireless services by one or more users in a heterogeneous network. The method may include the step of an analysis server receiving a set of data packets relating to signals associated with one or more wireless services accessed by one or more user devices associated with one or more users from a plurality of nodes. The set of data packets may be received over a predefined period of time. The analysis server may be operably coupled to a heterogeneous network comprising a plurality of nodes and one or more network access points configured to provide wireless services to one or more users. The method may further include the step of the analysis server extracting a first set of attributes from the set of data packets, wherein the first set of attributes relates to parameters relating to signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrences for one or more wireless services; and the step of the analysis server comparing the extracted first set of attributes with a predetermined set of parameters stored in a routing server's knowledge base. The predetermined set of parameters includes a threshold set of parameters for signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrences for one or more wireless services. The method may include the step of the analysis server categorizing a set of received data packets into several predefined categories based on a comparison of a first set of extracted attributes with a predetermined set of parameters, and then calculating a customer experience (CE) score based on the comparison of the first set of extracted attributes with the predetermined set of parameters. Furthermore, the method may include the step of the analysis server identifying one or more users with a degraded experience based on the calculated CE score.

[0016] The accompanying drawings incorporated herein and forming part of this disclosure illustrate exemplary embodiments of the methods and systems disclosed, where similar reference numerals throughout the various drawings refer to the same parts. Components in the drawings are not necessarily to scale, and instead, the emphasis is on clearly illustrating the principles of this disclosure. Some drawings may use block diagrams to show components and may not represent the internal circuitry of each component. It will be understood by those skilled in the art that disclosures in such drawings include disclosures of electrical components or circuits commonly used to implement such components. [Brief explanation of the drawing]

[0017] [Figure 1] This figure shows a typical existing heterogeneous telecommunications deployment according to one embodiment of the present disclosure. [Figure 2] This figure shows an exemplary customer experience score calculation and identification of users with a degraded experience, according to one embodiment of the present disclosure. [Figure 3] This figure shows a proposed exemplary spatial clustering of identified grids in a high-density block diagram according to one embodiment of the present disclosure. [Figure 4] This figure shows a degraded cluster of experience within area A of a heterogeneous network, as described in one embodiment of the present disclosure. [Figure 5] This is a proposed exemplary system diagram according to one embodiment of the present disclosure. [Figure 6] This figure shows an exemplary sample KPI classification proposed according to one embodiment of the present disclosure. [Figure 7] This figure shows an exemplary sample score aggregation proposed according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0018] In the following description, for the purpose of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent, however, that embodiments of the present invention may be practiced without these specific details. Some of the features to be described hereinafter may be used independently of each other, or in any combination with other features. Individual features may not address any of the problems discussed above, or may address only some of the problems discussed above. Some of the problems discussed above may not be fully addressed by any of the features described herein. Exemplary embodiments of the present invention will be described below as shown in various drawings, in which like reference numerals refer to the same parts throughout the various drawings.

[0019] In one aspect, the present disclosure relates to identifying customers with degraded experiences and identifying spatial clusters of these customers to accurately pinpoint the exact location of problems, thereby enabling more targeted network optimization within a heterogeneous network in a cost - effective manner. The present disclosure enables a solution for directly and accurately identifying a specific area where customers with degraded experiences concentrate by identifying customers with degraded experiences within the network and then identifying clusters surrounded by depressions where these users concentrate.

[0020] In one aspect, FIG. 1 shows a typical heterogeneous network operating within area A. The telecommunications network is composed of wireless network elements such as macro cells

[0101] , small cells

[0102] , and Wi-Fi access points

[0103] to provide wireless services to users. The network is accessed by a user

[0104] , and the user

[0104] can be a human or a machine. In a typical IP-based telecommunications network, a user connects to the network via a wireless network element and uses IP-based data services or voice services as needed when necessary. Usage instances related to voice or data are captured within geolocated spatial measurement samples collected by a call logs server

[0105] located within the telecommunications core. Other modules can request the collection of measurement samples corresponding to specific time intervals from the centralized entity 105. The geolocated measurement samples can include one or more of the following. IMSI (Customer Identifier) CELL ID (Macro cell / Micro cell / Wi-Fi Identifier instance) Latitude / Longitude (Estimated location of the user) Voice / Data flag Session duration RSRP (Signal strength) RSRQ (Signal quality) SINR (Signal-to-interference-plus-noise ratio) Call Drop Flag (when the voice flag is true) Call Mute Stat (when the voice flag is true)

[0021] In another embodiment, Figure 2 illustrates the identification of users with a degraded experience according to various embodiments of the present invention. This identification begins at

[0201] , where measurement samples are collected over a specified period. The samples are then categorized into buckets for signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrence, as shown at

[0202] . After categorization, the samples are aggregated by customer, as shown at

[0204] , to obtain aggregated values ​​for each customer in the buckets for signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrence. Combining these buckets by customer yields an overall customer experience value for each customer. Finally, as shown at

[0205] , customers with a degraded experience are identified based on a customer experience score such that its score must be below the nth percentile of the customer experience score calculated for each customer.

[0022] In another embodiment, Figure 3 illustrates a process for clustering spatial measurement samples belonging to customers with a degraded experience, which have been identified as being in the lower n percentile of the customer experience score across all customers calculated according to Figure 2. The clustering process begins at

[0301] , where samples belonging to customers identified as having a degraded experience are mapped to spatial grids, each grid having size S. After mapping all applicable samples to their corresponding spatial grids, a set of grids is selected for clustering according to

[0302] , based on the criterion that the number of samples in the selected grids should be below the n percentile of the number of samples per grid across all grids resulting from mapping the spatial measurements of customers with a degraded experience. After selecting the grids for clustering, a grid-based DBSCAN algorithm is executed according to

[0303] to construct grid clusters. Furthermore, two configurable parameters are given to the DBSCAN algorithm, which are the minimum cluster area and the minimum measurement sample density, respectively. Optionally, a concave boundary is also constructed around each cluster to represent each cluster as a spatial hole representing an area of ​​degraded customer experience. After calculating the spatial clusters of customers with degraded experience,

[0304] calculates one or more parameters for each cluster by aggregating various fields / parameters of spatially measured samples mapped to each grid belonging to each cluster.

[0023] In another embodiment, Figure 4 shows a spatial cluster identified inside Area A

[0401] after performing the spatial clustering process described in Figure 3 on a spatial measurement sample of an identified customer with degraded experience, according to various aspects of the present invention.

[0024] In another embodiment, Figure 5 shows a block diagram and key components of an analysis server according to various aspects of the present invention. 501 represents a storage module from which spatial measurement samples corresponding to Area A are fetched from the telecommunications core and stored for analysis. 502 represents a CEC (Customer Experience Calculator) module, which calculates a customer experience score according to various aspects of the present invention and stores the calculated customer experience score in storage module 501 for later use. Module 504 identifies customers with a degraded experience according to various aspects of the present invention and stores the identified customers in storage module 501 for later use. Module 503 represents a geospatial clustering module, which retrieves the collection of spatial measurement samples and the list of customers with a degraded experience stored in 501, filters the collection of samples to select only those samples corresponding to customers with a degraded experience, and calculates spatial clusters of customers with a degraded experience, along with various parameters for each cluster, according to various aspects of the present invention. The calculated cluster of customers with degraded experience is ultimately stored in storage module 501 by 503 for visualization and reporting. 505 and 506 represent the CPU and RAM, respectively, accessed by 501, 502, 503, and 504 for their respective calculation needs.

[0025] The calculation of the CE score for a particular customer is shown in Figures 6 and 7. The CE score calculation comprises a sample classifier

[0603] and a sample score aggregater

[0701] . The CE score calculation begins by classifying the key performance indicators

[0601] for each spatial measurement sample

[0602] belonging to that customer into buckets, with 1 representing the worst and 5 representing the best. The bucket calculated for each KPI is called the score

[0604] for that KPI for the spatial measurement sample

[0602] . This classification is performed through the sample classifier

[0603] , which parses each sample for that customer and identifies the appropriate bucket to which its value should belong.

[0026] In another embodiment, all samples

[0602] belonging to a particular customer and their corresponding KPI scores

[0604] are then supplied to a sample score aggregater

[0701] to calculate a customer experience score

[0702] for that customer over a specific time interval. The formula used by the sample score aggregater to calculate the customer experience score is as follows:

[0027]

number

[0028] Here, S ~ This represents the average score of a certain KPI aggregated across all samples of that customer over a given time interval. This score is calculated for each KPI, and Σw i A normalized weighting factor (w) for that KPI such that w = 1. i It is multiplied by the result. The resulting sum is divided by n, where n is the non-zero S obtained for that user over a specified duration. ~ It is the number of [number].

[0029] While this specification has focused heavily on the embodiments disclosed, it will be understood that many more embodiments can be created, and that many modifications can be made to the embodiments without departing from the principles of the present invention. The above and other modifications to the embodiments of the present invention will be obvious to those skilled in the art. It should be understood that the above-described features implemented are illustrative and not limiting.

[0030] Benefits of this disclosure One of the key advantages is that the present invention helps organizations shift from network element-driven performance optimization to user-driven performance improvement, thereby enabling them to directly measure, track, and improve the user experience in addition to clustering.

[0031] Another advantage of the present invention is that it provides a solution to the problem that measuring and analyzing the customer experience for each customer does not yield useful results unless the customer experience is aggregated, clustered, and areas that need to be addressed are identified.

[0032] Another advantage of the present invention is that it provides a solution that enables benchmarking, tracking, and improving the user experience by aggregating numerous metrics related to the user's voice, data, and coverage experience, and by obtaining a single KPI.

[0033] Another advantage of the present invention is that it provides a solution for telecommunications service providers to identify the most severely affected locations and to implement targeted solutions. [Explanation of symbols]

[0034] 101 Macrocell 102 Small Cells 103 Wi-Fi access points 104 users 105 Call log server, centralized entity 401 Spatial Cluster 501 Storage Module 502 CEC (Customer Experience Calculator) Module 503 Geospatial Clustering Module 504 module 505 CPU 506 RAM 601 Key performance indicators 602 Spatial measurement sample 603 Sample Classifier 604 The score of that KPI, KPI score 701 Sample Score Aggregator 702 Customer Experience Score

Claims

1. A system that facilitates the identification of degradation in the experience of one or more wireless services by one or more users within a heterogeneous network, The heterogeneous network comprises one or more user devices that are communicably coupled to the heterogeneous network, and the heterogeneous network is Multiple nodes, and one or more network access points configured to provide wireless services to one or more users, An analysis server comprising a processor operably coupled to the heterogeneous network and executing a set of executable instructions stored in memory, The processor, when it executes the set of executable instructions, sends the analysis server, Receiving from the plurality of nodes a set of data packets relating to signals associated with one or more wireless services accessed by one or more user devices, wherein the set of data packets is received over a predefined period of time. Extracting a first set of attributes from the set of data packets, wherein the first set of attributes relates to parameters related to the signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrence of the one or more wireless services. Comparing a first set of extracted attributes with a predetermined set of parameters stored in the routing server's knowledge base, wherein the predetermined set of parameters includes a threshold set of parameters for signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrences of the one or more wireless services. Based on the comparison between the first set of extracted attributes and a predetermined set of parameters, the received set of data packets is categorized into several predefined categories. Based on the comparison between the first set of extracted attributes and a predetermined set of parameters, a customer experience (CE) score is calculated, and Based on the calculated CE score, identify one or more users with a degraded experience. A system that enables this to happen.

2. The system according to claim 1, wherein one or more users with a degraded experience are identified based on a CE score that is less than the nth percentile of the customer experience score calculated for each of the users.

3. The aforementioned analysis server, Mapping one or more signal samples belonging to one or more users with a degraded experience to one or more spatial grids, each having a predefined size. Comparing one or more signal samples from each grid to the nth percentile of the number of signal samples per grid across the one or more spatial grids, and After comparison, select a set of grid clusters if one or more signal samples in the set of grids are less than the number of signal samples per grid across the one or more spatial grids. The system according to claim 1, further configured to perform the following:

4. The system according to claim 3, wherein a set of instructions is executed to construct a plurality of grid clusters from the selected set of grids based on the minimum cluster area and the minimum measured sample density.

5. The system according to claim 3, wherein a concave boundary is constructed around each grid cluster to represent each of the grid clusters as a spatial hole representing an area of ​​degraded user experience.

6. The system according to claim 3, wherein the set of grid clusters is stored in a storage module for visualization and reporting.

7. The system according to claim 1, wherein the degraded experience of one or more users is stored in a storage module for visualization and reporting.

8. The system according to claim 1, wherein the analysis server is further configured to directly measure, track, and improve user experience, in addition to clustering.

9. The system according to claim 1, wherein the signal sample includes an aggregate of metrics related to the user's voice, data, and coverage experience.

10. The system according to claim 1, wherein the analysis server is configured to continuously monitor and track the user experience, and the analysis server further identifies any location that has suffered the greatest damage and adopts a targeted solution.

11. A method for facilitating the identification of degradation in the experience of one or more wireless services by one or more users in a heterogeneous network, The steps include: an analysis server receiving a set of data packets relating to signals associated with one or more wireless services accessed by one or more user devices associated with one or more users, wherein the set of data packets is received over a predefined period of time, the analysis server is operably coupled to the heterogeneous network, the heterogeneous network comprising the multiple nodes and one or more network access points, and the one or more access points being configured to provide wireless services to the one or more users; The analysis server extracts a first set of attributes from the set of data packets, wherein the first set of attributes relates to parameters related to the signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrences of one or more wireless services. The steps include: comparing a first set of attributes extracted by the analysis server with a predetermined set of parameters stored in the knowledge base of the routing server, wherein the predetermined set of parameters includes a set of threshold parameters for signal quality, signal strength, interference, cell throughput, disconnection, and mute occurrences of one or more wireless services; Based on the comparison between the first set of extracted attributes and a predetermined set of parameters, the analysis server categorizes the received set of data packets into several predefined categories. The analysis server calculates a customer experience (CE) score based on the comparison between the first set of attributes extracted and a predetermined set of parameters. The analysis server performs the following steps: to identify one or more users with a degraded experience based on the CE score calculated by the analysis server; Methods that include...

12. The analysis server identifies one or more users with a degraded experience based on a CE score that is below the nth percentile of the customer experience score calculated for each of the users. The method according to claim 11, further comprising:

13. The analysis server performs the steps of mapping one or more signal samples belonging to one or more users with a degraded experience to one or more spatial grids, each having a predefined size, The analysis server performs the steps of comparing one or more signal samples from each grid with the nth percentile of the number of signal samples per grid across the one or more spatial grids, After comparison, the analysis server selects a set of grid clusters if one or more signal samples in the set of grids are less than the number of signal samples per grid across the one or more spatial grids. The method according to claim 11, further comprising:

14. From the selected set of grids, the step of executing a set of instructions to construct multiple grid clusters based on the minimum cluster area and minimum measured sample density. The method according to claim 13, further comprising:

15. The step of constructing a concave boundary around each grid cluster, in order to represent each grid cluster as a spatial hole representing an area where the user experience is degraded. The method according to claim 13, further comprising:

16. The step of storing the set of grid clusters in a storage module for visualization and reporting. The method according to claim 13, further comprising:

17. The step of storing in a storage module the names of one or more users whose experience has deteriorated, for visualization and reporting purposes. The method according to claim 11, further comprising:

18. The step of configuring the analytics server, which is further configured to directly measure, track, and improve the user experience in addition to clustering. The method according to claim 11, further comprising:

19. The method according to claim 11, wherein the signal sample includes an aggregate of metrics relating to the user's voice, data, and coverage experience.

20. A step of configuring the analysis server to continuously monitor and track the user experience, wherein the analysis server further identifies any location that has suffered the greatest damage and adopts a targeted solution. The method according to claim 13, further comprising:

Images