A data processing method, device and product

Abstract

This disclosure provides a data processing method, device, and product. The method includes: acquiring multi-source sensing data for a first user, wherein the multi-source sensing data includes at least one of user-level sensing data for the first user, network quality deterioration data corresponding to the first user, and regional-level sensing data of the area to which the first user belongs; fusing the multi-source sensing data based on the weights corresponding to the multi-source sensing data to obtain fused sensing data; and generating an anomaly prompt message for the first user in response to the fused sensing data and / or the change in the fused sensing data satisfying a set condition, wherein the anomaly prompt message is used to characterize communication network quality anomalies. This disclosure realizes communication network quality anomaly analysis and prompting for a single user.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a data processing method, apparatus and product. Background Technology

[0002] With the full commercialization of 5G networks and the large-scale popularization of high-bandwidth, low-latency services such as cloud gaming, high-definition live streaming, and real-time interaction, the operation and maintenance mode of mobile communication networks is gradually shifting from traditional network indicator control to refined operation and maintenance centered on the actual user experience.

[0003] Currently, network quality is generally evaluated based on regional macro-aggregate indicators such as regional average speed and call drop rate. This can easily lead to situations where regional indicators are good, but the user experience is poor, and the network quality for individual users cannot be guaranteed. Summary of the Invention

[0004] This disclosure provides a data processing method, device, and product to perform data analysis on multi-source sensing data for a single user and provide anomaly alerts for communication network quality.

[0005] According to one aspect of this disclosure, a data processing method is provided, comprising: Acquire multi-source sensing data for the first user, wherein the multi-source sensing data includes at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and region-level sensing data of the area to which the first user belongs. Based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data. In response to the fusion sensing data and / or the change in the fusion sensing data meeting a set condition, an abnormal prompt message is generated for the first user, the abnormal prompt message being used to characterize an abnormality in the communication network quality.

[0006] According to another aspect of this disclosure, a data processing apparatus is provided, comprising: The data acquisition module is used to acquire multi-source sensing data for the first user. The multi-source sensing data includes at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and regional-level sensing data of the area to which the first user belongs. The data fusion module is used to perform fusion processing on the multi-source sensing data based on the weights corresponding to each of the multi-source sensing data to obtain fused sensing data; An anomaly alert module is used to generate an anomaly alert message for the first user in response to the fusion sensing data and / or the change in the fusion sensing data meeting a set condition. The anomaly alert message is used to characterize an anomaly in the communication network quality.

[0007] According to another aspect of this disclosure, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data processing method described in any embodiment of this disclosure.

[0008] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions for causing a processor to execute and implement the data processing method described in any embodiment of this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is provided, which, when executed by a processor, implements the data processing method as described in any of the embodiments of this disclosure.

[0010] The technical solution provided in this embodiment acquires multi-source sensing data from a first user and fuses it to obtain fused sensing data. This fused sensing data comprehensively represents the first user's perception of the communication network. The quality of the communication network is determined based on the fused sensing data or its changes. When preset conditions are met, an anomaly in communication network quality is identified, and an anomaly alert is generated for the first user. This achieves communication network quality anomaly analysis and alerts for a single user.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a data processing method according to an embodiment of this disclosure; Figure 2 This is a flowchart of a data processing method according to an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of a data processing device according to an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] Figure 1 This is a flowchart illustrating a data processing method provided in this embodiment. This embodiment is applicable to situations involving data analysis and communication network quality anomaly alerts for multi-source sensing data from a single user. The method can be executed by the data processing device in this embodiment, which can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps: S110, acquire multi-source sensing data for the first user, the multi-source sensing data including at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and regional-level sensing data of the area to which the first user belongs.

[0018] S120, based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data.

[0019] S130, in response to the fused sensing data and / or the change in the fused sensing data meeting a set condition, an abnormal prompt message is generated for the first user, the abnormal prompt message being used to characterize an abnormality in the communication network quality.

[0020] The first user can be one of a large number of telecommunications service users. A telecommunications service user can be understood as a single-terminal user who has entered into a service agreement with a telecommunications operator, uses network services such as mobile communications and fixed communications, and is assigned a unique identity by the telecommunications network.

[0021] Multi-source sensing data can be understood as multi-source data related to the first user, statistically analyzed from the perspective of a single user's perception. The first user's user-level sensing data can be understood as sensing data reported by the first user's associated terminals, which may include, but is not limited to, at least one of the following: single-user service rate, sensing evaluation data, and service type. Single-user service rate includes upload rate and download rate, and service type may include, but is not limited to, video, voice, and download. Poor network quality data can be understood as monitoring indicators of poor network communication quality, representing a quantitative manifestation of network quality degradation. The poor network quality data corresponding to the first user can characterize monitoring indicators of poor network communication quality of the first user's associated terminals, and can be obtained through the terminal logs and core network monitoring data of the first user's associated terminals. The poor network quality data corresponding to the first user may include, but is not limited to, at least one of the following: single-user packet loss rate, latency, and signal interference. The area to which the first user belongs can be understood as the coverage area of ​​a base station where the first user is located. Area-level sensing data can be understood as the overall sensing data of the aforementioned coverage area, including, but not limited to, at least one of the following: area throughput, wireless signal coverage strength, and area call drop rate.

[0022] In some embodiments of this disclosure, the multi-source sensing data is preprocessed. The preprocessing includes at least one of outlier removal and missing value imputation. Outlier removal can be performed using the 3σ principle, and missing value imputation can be performed using linear interpolation. This preprocessing ensures the effectiveness of the multi-source sensing data.

[0023] Obtain the weights corresponding to the multi-source sensing data. These weights can be preset or dynamically determined according to the analytic hierarchy process.

[0024] In the multi-source sensing data, the weights of user-level sensing data, network quality poor data, and regional sensing data are summed to 1. For example, the weights of user-level sensing data, network quality poor data, and regional sensing data are 55%, 25%, and 10%, respectively. For instance, user-level sensing data includes single-user service rate and sensing evaluation data, with weights of 30% and 25%, respectively; network quality poor data includes latency and packet loss rate, with weights of 20% and 15%, respectively; and regional sensing data includes wireless signal coverage strength and regional call drop rate, with weights of 8% and 2%, respectively.

[0025] The fusion processing of multi-source sensing data includes: weighting the multi-source sensing data according to their respective weights. The fused sensing data can be represented by the following formula: ,in, Let be the weight of the i-th indicator in the multi-source sensing data. Let be the value of the i-th indicator in the multi-source sensing data, and n be the total number of indicators in the multi-source sensing data. Preprocessing of multi-source sensing data can also include standardization and normalization. This transforms the value of each indicator in the multi-source sensing data to the range of 0-1.

[0026] The value range of the fused perception data is 0-1. The closer the fused perception data is to 1, the better the user's perception experience.

[0027] In some embodiments of this disclosure, the fused perception data corresponding to multiple first users are associated with regional-level indicators of the regions to which the multiple first users belong, to generate a two-dimensional perception matrix of region-user.

[0028] For the first user, fused sensing data at different times is obtained according to the set subscription frequency. Optionally, the communication network quality is judged based on the fused sensing data at the current time to determine whether the communication network quality is abnormal. An abnormal communication network quality can lead to abnormal user perception. If so, an abnormal prompt message is generated for the first user. Specifically, in response to the fused sensing data at the current time meeting the set conditions, it is determined that the communication network quality is abnormal. The set conditions include the fused sensing data being less than a first threshold, for example, the first threshold could be 0.3.

[0029] Optionally, communication network quality can be assessed based on the changing trends of fused sensing data at multiple time points to determine if the communication network quality is abnormal. If so, an abnormality alert message for the first user is generated. The changing trend of the fused sensing data can include the amount of change in the fused sensing data, i.e., the difference between the fused sensing data at a second time point and the fused sensing data at a first time point. The second time point is after the first time point; for example, the second time point could be the current time point, and the first time point could be the time point preceding the current time point. If the amount of change in the fused sensing data meets a set condition, an abnormal communication network quality is determined. This set condition includes the fused sensing data becoming smaller and the amount of change in the fused sensing data being greater than a second threshold. That is, the fused sensing data at the second time point is smaller than the fused sensing data at the first time point, and the amount of change is greater than the second threshold, which can be 0.3.

[0030] Understandably, different first-users have different perceived needs for communication network quality. Based on these needs, first-users can be categorized into two types: Type 1 and Type 2. Type 1 users have higher network quality requirements than Type 2 users. In other words, Type 1 users are considered to have high perceived network quality requirements, while Type 2 users are considered to have low perceived network quality requirements.

[0031] Optionally, different subscription frequencies can be set for different types of first users. For example, the subscription frequency for the first type is higher than the event interval for the second type, so as to obtain fused perception data according to different subscription frequencies and meet the data processing needs of different types of users.

[0032] Optionally, the subscription frequency is dynamically determined based on the change in the fused sensing data of the first user, and the subscription frequency is positively correlated with the change in the fused sensing data. For example, the correspondence between the subscription frequency and the change in the fused sensing data is shown in Table 1.

[0033] Table 1 Optionally, different setting conditions can be set for different types of first users, and the values ​​of the first threshold and the second threshold can be different in different setting conditions. For example, the value of the first threshold in the setting conditions corresponding to the first type is higher than the value of the first threshold in the setting conditions corresponding to the second type, and the value of the second threshold in the setting conditions corresponding to the first type is lower than the value of the second threshold in the setting conditions corresponding to the second type.

[0034] Based on the above embodiments, when an abnormality in communication network quality is determined, an abnormality prompt message for the first user is generated. This abnormality prompt message can be understood as a prompt message indicating an abnormality in communication network quality, which leads to the first user perceiving the abnormality. The specific form of the abnormality prompt message is not limited here; for example, it can be in text form or alarm icon form. By generating the abnormality prompt message for the first user and promptly handling the communication network abnormality for the first user, the impact of the communication network quality abnormality on the first user's communication services is reduced.

[0035] In some embodiments, an operation and maintenance work order is generated based on the anomaly notification information from the first user, and the work order is transmitted to the operation and maintenance equipment, or to the anomaly handling module. The operation and maintenance equipment can be understood as the associated equipment of the anomaly handling personnel, who perform anomaly handling based on the received work order. The anomaly handling module can be understood as an automatic processing module in an electronic device, possessing anomaly functionality and capable of automatically handling anomalies in response to operation and maintenance work orders. Optionally, the anomaly handling module may store an anomaly handling algorithm.

[0036] The technical solution provided in this embodiment acquires multi-source sensing data from a first user and fuses it to obtain fused sensing data. This fused sensing data comprehensively represents the first user's perception of the communication network. The quality of the communication network is determined based on the fused sensing data or its changes. When preset conditions are met, an anomaly in communication network quality is identified, and an anomaly alert is generated for the first user. This achieves communication network quality anomaly analysis and alerts for a single user.

[0037] Figure 2 This is a flowchart of a data processing method provided in an embodiment of this disclosure, which is optimized based on the above embodiment. The method specifically includes: S210, acquire multi-source sensing data for the first user, the multi-source sensing data including at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and regional-level sensing data of the area to which the first user belongs.

[0038] S220, based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data.

[0039] S230, in response to the set trigger event, obtain the demand type of the first user, the demand type includes a first type and a second type, the network quality demand corresponding to the first type is higher than the network quality demand corresponding to the second type; if the demand type of the first user is the first type, set a first tag for the first user.

[0040] S240, for a first user with a first tag, in response to the fused sensing data and / or the change in the fused sensing data meeting a set condition, an abnormal prompt message is generated for the first user, the abnormal prompt message being used to characterize an abnormality in the communication network quality.

[0041] Setting a trigger event can be understood as an event that can trigger the demand type of acquiring the first user. For example, setting a trigger event can include a periodic update event of the demand type and a new user registration event.

[0042] Optionally, obtaining the demand type of the first user includes: obtaining user-level features of a first historical time period, network quality defects of a second historical time period, and fused perception data of the first user; classifying the user-level features of the first historical time period, network quality defects of the second historical time period, and fused perception data of the first user using a pre-trained demand classification model to obtain the probability that the first user belongs to each demand type; and determining the probability that the first user belongs to each demand type based on a dynamic threshold to obtain the demand type of the first user.

[0043] The first historical time period and the second historical time period can be the same or different. For example, the first historical time period can be 7 days before the current time, and the second historical time period can be 24 hours before the current time. User-level characteristics include at least one of the following: service usage frequency, service type ratio, and number of historical request feedbacks. Poor network quality characteristics include the number of times latency exceeds the standard and the duration of packet loss rate exceeding the third threshold.

[0044] Feature encoding is performed on user-level features, network quality deterioration features, and fused sensing data. Specifically, one-hot encoding is used for categorical features such as service type, and Min-Max normalization is used for continuous features such as service usage frequency. The encoded features are integrated into a feature vector, which is then input into a pre-trained demand classification model to obtain the probability that the first user belongs to each demand type. The sum of the probabilities of the first user inputting the first type and the second type is 1. This demand classification model can be a machine learning model, such as the XGBoost model.

[0045] The training process of this demand classification model includes: acquiring a sample dataset, optimizing model parameters using 5-fold cross-validation (learning rate 0.1, tree depth 5, iterations 100), and outputting the probability that a user belongs to each demand type. The sample dataset includes positive and negative samples. Positive samples include association features of historical users of the first demand type, and negative samples include association features of historical users of the second demand type. These association features include historical user-level features from the first historical time period, historical network quality poor features from the second historical time period, and historical fusion perception data of the historical users. The sample dataset is updated periodically, and the demand classification model is periodically optimized based on the updated sample dataset.

[0046] The probability of the first user belonging to each demand type is determined based on a dynamic threshold, including: if the probability of the first user belonging to the first type is greater than or equal to the dynamic threshold, the first user is determined to belong to the first type; if the probability of the first user belonging to the first type is less than the dynamic threshold, the first user is determined to belong to the second type.

[0047] The dynamic threshold is dynamically determined based on the real-time network load of the area to which the first user belongs. Specifically, the real-time network load of the area to which the first user belongs is obtained; based on the correspondence between network load range and threshold, the dynamic threshold corresponding to the real-time network load is determined. The area to which the first user belongs is the coverage area of ​​a base station where the first user is located. Real-time network load can be understood as the ratio of the number of users within the base station's coverage area to the area's capacity. The correspondence between network load range and threshold is that different network load ranges correspond to different thresholds. For example, if the network load range is (0, 60%), the threshold is 0.6; if the network load range is (60%, 80%), the threshold is 0.7; and if the network load range is (80%, 100%), the threshold is 0.8. The real-time network load of the area to which the first user belongs is matched within the above network load ranges, and the threshold corresponding to the successfully determined network load range is used as the dynamic threshold.

[0048] In some embodiments of this disclosure, a first tag is set for a first user of a first type, the first tag representing that the first user's demand type is the first type. Optionally, the user identifier of the first user, the network quality characteristics of the first user, and the demand type of the first user (or the probability that the first user belongs to each demand type) are transmitted to a tag processing module, which sets the first tag for the first user. The tag processing module is also used to record the setting timestamp of the first tag, and generate a setting trigger event for updating the demand type and tag based on the tag validity period and the setting timestamp of the first tag.

[0049] For the second user, which includes the first user with a first tag, the fused perception data of the second user is obtained according to the subscription frequency, and anomalies in communication network quality are determined based on the fused perception data. The first tag distinguishes between first users who require communication network quality anomaly determination and those who do not, allowing for anomaly determination only for the first user with the first tag, thus reducing the amount of data required for anomaly determination.

[0050] It is understandable that network quality poor indicators include various types of indicators, and different first users may have different network quality poor indicators. In order to reduce the number of indicators to be monitored, the priority of multiple network quality poor indicators is determined, and the target network quality poor indicator is selected from multiple network quality poor indicators. The indicator data of the target network quality poor indicator for the second user is obtained to update the fusion perception data of the second user. Anomalies in the communication network quality of the second user are then determined based on the fusion perception data of the second user.

[0051] Based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data, including: obtaining a set of network quality poor indicators for a second user, the second user including a first user with a first label; filtering target network quality poor indicators based on the entropy values ​​corresponding to each network quality poor indicator in the set of network quality poor indicators for the second user; obtaining fused sensing data based on at least one of the user-level sensing data of the second user, the target network quality poor data corresponding to the second user, and the regional-level sensing data of the region to which the second user belongs, wherein the target network quality poor data is the indicator data corresponding to the target network quality poor indicator.

[0052] The network quality indicators for different second users can be the same, different, or partially the same. The set of network quality indicators for a second user can be understood as the union of the network quality indicators for multiple second users, after removing duplicates. This set includes multiple network quality indicators, such as, but not limited to, packet loss rate, latency, and signal interference.

[0053] In some embodiments, target network quality indicators are filtered by the entropy value corresponding to each network quality indicator. In some embodiments, priority representation data corresponding to each network quality indicator is determined by the entropy value corresponding to each network quality indicator, and target network quality indicators are filtered by the priority representation data corresponding to the network quality indicators.

[0054] Optionally, the entropy value corresponding to each poor network quality indicator is determined by: for the j-th poor network quality indicator, obtaining the indicator values ​​of multiple second users for the j-th poor network quality indicator, and determining the proportion of the indicator value of the k-th second user for the j-th poor network quality indicator in the data of the j-th poor network quality indicator. j and k are positive numbers greater than or equal to 1. The entropy value of the j-th network quality poorness index is determined based on the data proportions corresponding to multiple second users. This entropy value can be expressed by the following formula: m represents the total number of second-level users.

[0055] The entropy value corresponding to the poor network quality index represents the dispersion of index values ​​of multiple second users for this poor network quality index. The lower the entropy value, the more dispersed the index values ​​of multiple second users for this poor network quality index are, and the greater the data difference. The higher the entropy value, the more concentrated the index values ​​of multiple second users for this poor network quality index are, and the smaller the data difference is. This has a smaller impact on distinguishing the quality of communication networks, and therefore the difference in perceived experience between different second users is not significant.

[0056] Optionally, network quality poor indicators with entropy values ​​less than the fourth threshold are used as target network quality poor indicators. Optionally, network quality poor indicators are sorted based on entropy values, and the first number of network quality poor indicators are selected as target network quality poor indicators based on the sorting. Optionally, priority representation data for network quality poor indicators is determined based on their entropy values, and the priority representation data is negatively correlated with the entropy value of the network quality poor indicator. For example, the priority representation data for the j-th network quality poor indicator could be... =1- The network quality indicators are sorted based on priority, and the highest number of these indicators are selected as the target network quality indicators. The highest number can be 5.

[0057] The target network quality metric is bound to the second user's first tag. When the first tag is valid, the metric value of the target network quality metric is obtained based on the subscription frequency. When the first tag expires, the subscription to the metric value of the target network quality metric is stopped.

[0058] Based on the subscription frequency, at least one of the following is obtained: user-level perception data of the second user, target network quality poor data corresponding to the second user, and regional perception data of the area to which the second user belongs. Based on the above user-level perception data, target network quality poor data, and regional perception data, fusion processing is performed to obtain fused perception data. Based on the fused perception data or the change in the fused perception data, anomaly determination of communication network quality is made.

[0059] The technical solution provided in this embodiment determines the demand type of a first user, sets a first tag for the first user of the first type, and marks the first user with the first tag as a second user. Indicator subscriptions are only performed for the second user, reducing the amount of data for indicator subscription and thus reducing resource consumption. The fused perception data of the second user is acquired, and anomalies in communication network quality are determined, with timely alerts provided for any communication network quality anomalies in the second user.

[0060] Based on the above embodiments, upon receiving an anomaly alert from a first user, compensation is provided to the first user. Specifically, the compensation strategy for the first user is obtained; compensation alert information is generated, which includes the quality defect characteristics of the first user and a description of the compensation strategy.

[0061] Optionally, multiple compensation strategies can be pre-set, and the compensation strategy for the first user can be randomly selected from multiple strategies. Compensation strategies can include resource compensation strategies, and different compensation strategies can include resource compensation strategies for different network services. For example, network services can include video, games, and voice calls. The resources here can be virtual resources, such as bandwidth resources.

[0062] Optionally, obtaining the compensation strategy for the first user includes: determining at least one target network service based on the interaction frequency of the first user for different network services; and generating a compensation strategy for the at least one target network service.

[0063] The frequency of interaction of a first user with different network services can characterize the degree of demand for those services. The network service with the highest interaction frequency can be selected as the target network service; alternatively, network services can be ranked based on interaction frequency, and a second number of network services can be selected as the target network service based on this ranking. A compensation strategy related to the target network service is selected from multiple compensation strategies and adopted as the first user's compensation strategy. Compensation prompt information is generated based on the first user's compensation strategy and transmitted to the first user's terminal device.

[0064] The compensation prompt information includes the poor quality characteristics of the first user and the description information of the compensation strategy. For example, the poor quality characteristics of the first user may include latency over-edge, and the description information of the compensation strategy may include at least one of the following: resource packet push information related to the target network service and resource compensation information.

[0065] Optionally, a compensation prompt template can be obtained, and the quality improvement characteristics and compensation strategy of the first user can be added to the compensation prompt template to obtain compensation prompt information. For example, the compensation prompt template can be in the form of "quality improvement characteristics, description of compensation strategy".

[0066] The technical solution of this embodiment compensates for the resources of a single user by means of a supplementary strategy when the terminal device of a single user has abnormal communication network quality, thereby reducing the impact of poor user experience caused by abnormal communication network quality.

[0067] Figure 3 This is a schematic diagram of a data processing device provided in an embodiment of the present disclosure. The device specifically includes: a data acquisition module 310, a data fusion module 320, and an anomaly alert module 330.

[0068] The data acquisition module 310 is used to acquire multi-source sensing data for the first user. The multi-source sensing data includes at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and regional-level sensing data of the area to which the first user belongs. The data fusion module 320 is used to perform fusion processing on the multi-source sensing data based on the weights corresponding to the multi-source sensing data respectively, so as to obtain fused sensing data. The anomaly alert module 330 is used to generate an anomaly alert message for the first user in response to the fusion sensing data and / or the change in the fusion sensing data meeting a set condition. The anomaly alert message is used to characterize an anomaly in the communication network quality.

[0069] The technical solution of this embodiment acquires multi-source sensing data from a first user and fuses it to obtain fused sensing data. This fused sensing data comprehensively represents the first user's perception of the communication network. The quality of the communication network is determined based on the fused sensing data or its changes. When preset conditions are met, an anomaly in communication network quality is identified, and an anomaly alert is generated for the first user. This achieves communication network quality anomaly analysis and alerts for a single user.

[0070] Based on the above embodiments, optionally, the setting conditions include at least one of the following: The fused sensing data is less than the first threshold; The fused sensing data becomes smaller, and the amount of change in the fused sensing data is greater than the second threshold.

[0071] Optionally, based on the above embodiments, the device further includes: The tag setting module is used to respond to a set trigger event, obtain the demand type of the first user, the demand type includes a first type and a second type, the network quality demand corresponding to the first type is higher than the network quality demand corresponding to the second type; when the demand type of the first user is the first type, a first tag is set for the first user.

[0072] Optionally, the label setting module is also used to obtain user-level features of the first historical time period, network quality defects of the second historical time period, and fused perception data of the first user; through a pre-trained demand classification model, the user-level features of the first historical time period, network quality defects of the second historical time period, and fused perception data of the first user are classified to obtain the probability that the first user belongs to each demand type; and the probability that the first user belongs to each demand type is determined based on a dynamic threshold to obtain the demand type of the first user.

[0073] Optionally, the tag setting module is also used to obtain the real-time network load of the area to which the first user belongs; and to determine the dynamic threshold corresponding to the real-time network load based on the correspondence between the network load range and the threshold.

[0074] Based on the above embodiments, optionally, the data fusion module 320 is specifically used for: obtaining a set of network quality poor indicators for a second user, the second user including a first user with a first label; filtering target network quality poor indicators based on the entropy values ​​corresponding to each network quality poor indicator in the set of network quality poor indicators for the second user; obtaining fused perception data based on at least one of the user-level perception data of the second user, the target network quality poor data corresponding to the second user, and the regional-level perception data of the area to which the second user belongs, wherein the target network quality poor data is the indicator data corresponding to the target network quality poor indicator.

[0075] Optionally, based on the above embodiments, the device further includes: a compensation module, configured to acquire the compensation strategy of the first user; and generate compensation prompt information, wherein the compensation prompt information includes the quality defect characteristics of the first user and the description information of the compensation strategy.

[0076] Optionally, the compensation module is further configured to determine at least one target network service based on the interaction frequency of the first user for different network services; and generate a compensation strategy for the at least one target network service.

[0077] The above-described products can perform the methods provided in any embodiment of this disclosure, and have the corresponding functional modules and beneficial effects for performing the methods.

[0078] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0079] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0080] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0081] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as data processing methods.

[0082] In some embodiments, the data processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data processing method by any other suitable means (e.g., by means of firmware).

[0083] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] Computer programs used to implement the methods of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0085] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0087] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0088] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0089] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0090] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the data processing method according to any embodiment of this disclosure.

[0091] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data processing method, characterized in that, include: Acquire multi-source sensing data for the first user, wherein the multi-source sensing data includes at least one of user-level sensing data for the first user, network quality poor data corresponding to the first user, and region-level sensing data of the area to which the first user belongs. Based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data. In response to the fusion sensing data and / or the change in the fusion sensing data meeting a set condition, an abnormal prompt message is generated for the first user, the abnormal prompt message being used to characterize an abnormality in the communication network quality.

2. The method according to claim 1, characterized in that, The setting conditions include at least one of the following: The fused sensing data is less than the first threshold; The fused sensing data becomes smaller, and the amount of change in the fused sensing data is greater than the second threshold.

3. The method according to claim 1, characterized in that, The method further includes: In response to a set trigger event, the demand type of the first user is obtained. The demand type includes a first type and a second type, where the network quality demand corresponding to the first type is higher than the network quality demand corresponding to the second type. If the first user's need type is the first type, then set the first user with a first tag.

4. The method according to claim 3, characterized in that, Obtain the demand type of the first user, including: Acquire user-level features for the first historical time period, network quality deterioration features for the second historical time period, and fused perception data of the first user; By using a pre-trained demand classification model, the user-level features of the first historical time period, the network quality poor features of the second historical time period, and the fused perception data of the first user are classified to obtain the probability that the first user belongs to each demand type. The probability of the first user belonging to each demand type is determined based on a dynamic threshold, thus obtaining the demand type of the first user.

5. The method according to claim 4, characterized in that, The method further includes: Obtain the real-time network load of the region to which the first user belongs; Based on the correspondence between network load range and threshold, the dynamic threshold corresponding to the real-time network load is determined.

6. The method according to claim 3, characterized in that, Based on the weights corresponding to the multi-source sensing data, the multi-source sensing data is fused to obtain fused sensing data, including: Obtain a set of poor network quality indicators for the second user, where the second user includes the first user with a first label set. Based on the entropy value corresponding to each network quality poor indicator in the network quality poor indicator set of the second user, the target network quality poor indicators are filtered. Based on at least one of the user-level perception data of the second user, the target network quality difference data corresponding to the second user, and the regional-level perception data of the region to which the second user belongs, fused perception data is obtained, wherein the target network quality difference data is the indicator data corresponding to the target network quality difference index.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the compensation strategy for the first user; Generate compensation prompt information, which includes the poor quality characteristics of the first user and a description of the compensation strategy.

8. The method according to claim 7, characterized in that, Obtaining the compensation strategy for the first user includes: Based on the interaction frequency of the first user with different network services, at least one target network service is determined; Generate a compensation strategy for the at least one target network service.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data processing method according to any one of claims 1-8.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the data processing method according to any one of claims 1-8.

Images