Method, device and electronic device for positioning poor quality services of customer acquisition services

Abstract

The embodiments of the present application provide a method, device and electronic device for locating poor-quality services of a customer acquisition service, including: obtaining target data corresponding to the customer acquisition service, the target data including first target data corresponding to the customer acquisition service extracted from Internet DPI data and second target data from multiple service systems; associating the first target data and the second target data to obtain associated data; based on the associated data, establishing an indicator set from multiple dimensions with indicator features corresponding to the associated data; respectively calculating the weight value of each original indicator in the indicator set; selecting an indicator whose weight value exceeds a poor-quality threshold as a poor-quality indicator, and locating the customer acquisition service corresponding to the poor-quality indicator as a poor-quality service.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device and electronic device for locating poor-quality services of a customer acquisition service. Background Art

[0002] With the continuous growth of customer acquisition business, the Internet and voice dedicated lines have become key businesses for customer acquisition. By collecting data sources from different business systems, an indicator system for customer acquisition is established. By performing statistical calculations on the indicators, poor-quality businesses are discovered and alarms are issued to dispatch orders.

[0003] In some scenarios, various indicators in the indicator system come from data sources of multiple different business systems. When locating poor-quality businesses, the positioning of poor-quality businesses is done after statistical analysis of data from business systems such as the dialing system, transmission network system, and complaint system. However, each business system is independent of each other and has poor linkage. In addition, statistical analysis of data from each business system from a single dimension results in inaccurate positioning of poor-quality businesses, which is not conducive to the development of customer acquisition business. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and electronic equipment for positioning poor-quality services for customer acquisition services, thereby improving the accuracy of positioning poor-quality services and facilitating the development of customer acquisition services.

[0005] In order to solve the above technical problems, the embodiments of the present application are implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for locating a poor-quality service of a customer acquisition service, including:

[0007] Obtain target data corresponding to a customer acquisition business, the target data comprising first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from a plurality of business systems; associate the first target data with the second target data to obtain associated data; based on the associated data, establish an indicator set from a plurality of dimensions with indicator features corresponding to the associated data; respectively calculate a weight value of each original indicator in the indicator set; select an indicator whose weight value exceeds a quality difference threshold as a quality difference indicator, and locate the customer acquisition business corresponding to the quality difference indicator as a quality difference business.

[0008] In a second aspect, an embodiment of the present application provides a device for locating poor-quality services for attracting customers, the device comprising:

[0009] Obtain target data corresponding to a customer acquisition business, the target data comprising first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from a plurality of business systems; associate the first target data with the second target data to obtain associated data; based on the associated data, establish an indicator set from a plurality of dimensions with indicator features corresponding to the associated data; respectively calculate a weight value of each original indicator in the indicator set; select an indicator whose weight value exceeds a quality difference threshold as a quality difference indicator, and locate the customer acquisition business corresponding to the quality difference indicator as a quality difference business.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the steps of the method for locating poor quality services for the customer acquisition service as in the first aspect.

[0011] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for locating poor-quality services for a customer acquisition service as described in the first aspect are implemented.

[0012] The technical solution provided by the embodiment of the present application includes: obtaining target data corresponding to the customer acquisition business, the target data includes first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; associating the first target data and the second target data to obtain associated data; based on the associated data, establishing an indicator set from multiple dimensions with the indicator characteristics corresponding to the associated data; respectively calculating the weight value of each original indicator in the indicator set; selecting the indicator whose weight value exceeds the quality difference threshold as the quality difference indicator, and locating the customer acquisition business corresponding to the quality difference indicator as the quality difference business. Therefore, the indicators in the embodiment of the present application are determined from the associated data after the first target data and the second target data are associated, the data have a high linkage, and the indicator value is established from multiple dimensions with the indicator characteristics corresponding to the associated data, which improves the accuracy of locating the quality difference business and is beneficial to the development of the customer acquisition business. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1A first flow chart of a method for locating poor-quality services for attracting customers provided by an embodiment of the present application is shown;

[0015] Figure 2 A second flow chart of a method for locating poor-quality services for attracting customers provided by an embodiment of the present application is shown;

[0016] Figure 3 A third flow chart of a method for locating poor-quality services for attracting customers provided by an embodiment of the present application is shown;

[0017] Figure 4 A schematic diagram showing the module composition of a device for locating poor-quality services for attracting customers provided by an embodiment of the present application is shown;

[0018] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown; DETAILED DESCRIPTION

[0019] The embodiments of the present application provide a method, device and electronic device for positioning poor-quality services for a customer acquisition service, which improves the accuracy of positioning poor-quality services and is beneficial to the development of the customer acquisition service.

[0020] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] The technical solution provided in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 As shown, the embodiment of the present application provides a method for locating a poor-quality service for a customer acquisition service. The execution subject of the method may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers, and the server may be a server capable of locating a poor-quality service for a customer acquisition service. The method for locating a poor-quality service for a customer acquisition service may specifically include the following steps S101 to S104:

[0023] In S101, target data corresponding to the customer acquisition business is obtained.

[0024] Specifically, the target data of the customer acquisition service of the embodiment of the present application expands the data source of the customer acquisition service quality positioning. The target data of the customer acquisition service includes first target data corresponding to the customer acquisition service and second target data of multiple business systems extracted from Internet DPI data.

[0025] The second target data from multiple business systems includes business data from systems such as a dialing system, a transmission network system, and a complaint system.

[0026] Extracting the first target data corresponding to the customer acquisition business from the Internet DPI data includes: filtering and extracting the original call records and dialing data related to the customer acquisition business from the Internet DPI data (Internet DPI call records). The filtering and extraction is completed by matching the static table of the Internet Protocol (IP) network segment and the number segment of the customer acquisition business.

[0027] For Internet DPI call records, they include information such as field name, type, length, and default value.

[0028] For example: For the field named "App Type Code", the type is "byte", the length is 1, and the default value is "all F", which indicates the service type code. For the field named "Procedure Start Time", the type is "byte", the length is 8, and the default value is "all F", which indicates the start time of the Transmission Control Protocol (TCP) or User Datagram Protocol (UDP) stream, Coordinated Universal Time (UTC) time, from 1970 / 1 / 100:00:00 to the current number of microseconds. For the field named "Procedure End Time", the type is "byte", the length is 8, and the default value is "all F", which indicates the end time of the TCP / UDP stream, UTC time), from 1970 / 1 / 1 00:00:00 to the current number of microseconds.

[0029] For a field named "longitude", type "empty", length 8, and default value "full F", it represents the longitude of the Global Positioning System (GPS) position. The longitude and latitude fields in this specification follow the storage format of Double type data specified by the IEEE (Institute of Electrical and Electronics Engineers) 754 standard.

[0030] For the field name "latitude", the type is "empty", the length is 8, and the default value is "all F", it indicates the latitude of the GPS location. For the field name "Protocol Type", the type is "byte", the length is 2, and the default value is "all F", it indicates the protocol type. The protocol identification classification specified by the group refers to the "DPI Equipment Protocol Identification Capability Requirements" in the "China Mobile Data Traffic DPI Identification Capability Specification".

[0031] For the field named "App Type", the type is "byte", the length is 2, and the default value is "all F", it indicates the application category. For the field named "App Sub-type", the type is "byte", the length is 2, and the default value is "all F", it indicates the application subcategory. For the field named "App Content", the type is "byte", the length is 1, and the default value is "all F", it indicates the content segmentation of the application subcategory, such as WeChat text, WeChat voice, etc. The following sequence number is an example of WeChat content segmentation. If there are other application subcategory segments, you can define them yourself. Among them, 2 represents the text chat function, 3 represents the voice intercom function, 4 represents the picture transmission function, 5 represents the video transmission function, 6 represents the video call function, 7 represents the real-time intercom function, 8 represents the friend circle function, and 9 represents the heartbeat. If there is none, fill in F. Add the following definition of Sina Weibo content segmentation: 1 represents the Weibo browsing function, 2 represents the Weibo posting, forwarding and commenting function, if there is none, fill in F.

[0032] For the field named "App Status", the type is "byte", the length is 1, and the default value is "all F", it indicates whether the session is successful. Among them, 0 means success, indicating that the TCP / UDP session process starts and ends normally, and all data transmission is completed. 1 means the server link timeout. After the client sends the first syn, it does not receive the synack message from the server. 2 means the client link timeout. After the server sends the synack message, it does not receive the ack message from the client. 3 means the transmission timeout. After the TCP three-step handshake is successful, if the TCP session does not end with RST / FIN / FIN ACK, it is judged to be timed out. 4 means that the service is rejected by the server, and the application layer protocol gets the response code representing the server's refusal of service. 5 means that the service is rejected by the client, and the application layer protocol gets the response code representing the client's refusal of service. 6 means the server is terminated, and the server sends RST to terminate the session. 7 means the client is terminated, and the client sends RST to terminate the session.

[0033] For the field name "IP address type", the type is "byte", the length is 1, and the default value is "all F", where 0 represents IPv4 and 1 represents IPv6. For the field name "USER_IPv4", the type is "byte", the length is 4, and the default value is "all F", which represents the terminal user's Internet Protocol Version 4 (IPv4) address. If it does not exist, fill in all F. For the field name "USER_IPv6", the type is "byte", the length is 16, and the default value is "all F", which represents the terminal user's Internet Protocol Version 46 (IPv6) address. If it does not exist, fill in all F. For the field name "User Port", the type is "byte", the length is 2, and the default value is "all F", which represents the user's Layer 4 port number. For the field name "L4protocal", the type is "byte", the length is 1, and the default value is "all F", which represents the L4 protocol type, where 0 represents TCP and 1 represents UDP.

[0034] For the field name "App Server IP_IPv4", the type is "byte", the length is 4, and the default value is "all F", which indicates the IPv4 address of the access server. If it is missing, fill in all F. For the field name "App Server IP_IPv6", the type is "byte", the length is 16, and the default value is "all F", which indicates the IPv6 address of the access server. If it is missing, fill in all F. For the field name "App Server Port", the type is "byte", the length is 2, and the default value is "all F", which indicates the port of the accessed server.

[0035] For the field name "UL Data", the type is "byte", the length is 4, and the default value is "0", it indicates that the unit of upstream traffic is byte. For scenario 1, it is defined as the sum of the data packet sizes calculated from the inner IP header; for other scenarios, it is defined as the sum of the data packet sizes calculated from the link layer encapsulation. For the field name "DL Data", the type is "byte", the length is 4, and the default value is "0", it indicates that the unit of downstream traffic is byte. For scenario 2, it is defined as the sum of the data packet sizes calculated from the inner IP header; for other scenarios, it is defined as the sum of the data packet sizes calculated from the link layer encapsulation. For the field name "UL IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates that the number of upstream IP packets is the number of inner IP packets. For the field name "DL IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates that the number of downstream IP packets is the number of inner IP packets. For the field name "updura", the type is "unsigned int", the length is 16, and the default value is "all F", it means the uplink duration, in microseconds, from the first uplink message to the last uplink message. If there is only one message, this field is meaningless and 0 is filled in. For the field name "downdura", the type is "unsigned int", the length is 16, and the default value is "all F", it means the downlink duration, in microseconds, from the first downlink message to the last downlink message. If there is only one message, this field is meaningless and 0 is filled in.

[0036] For the field named "UL Disorder IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates the number of upstream TCP disordered packets. When the L4 protocol is not TCP transmission, this field is filled with 0. For the field named "DL Disorder IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates the number of downstream TCP disordered packets. When it is not TCP transmission, this field is filled with 0. For the field named "UL Retrans IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates the number of upstream TCP retransmission packets. When it is not TCP transmission, this field is filled with 0. For the field named "DL Retrans IP Packet", the type is "byte", the length is 4, and the default value is "0", it indicates the number of downstream TCP retransmission packets. When it is not TCP transmission, this field is filled with 0. For the field named "TCP Response Time", the type is "byte", the length is 4, and the default value is "0", it indicates the TCP link establishment response delay (microseconds). When it is not TCP transmission, this field is filled with 0. The field name is "TCP ACK Time", the type is "byte", the length is 4, and the default value is "0". It represents the TCP link establishment confirmation delay (microseconds). In non-TCP transmission, this field is filled with 0.

[0037] For the field name "UL_IP_FRAG_PACKETS", the type is "byte", the length is 4, and the default value is "0", it means that the fragmentation of the inner IP packet is used as the basis. For the field name "DL_IP_FRAG_PACKETS", the type is "byte", the length is 4, and the default value is "0", it means that the fragmentation of the inner IP packet is used as the basis.

[0038] For the field named "First Req Time", the type is "byte", the length is 4, and the default value is "0", it indicates the delay (in microseconds) from the successful TCP link establishment to the first transaction request. It can be left blank when there is no transaction. In this case, fill in 0. If the third step handshake is not received for some reason, or the third step handshake is later than the transaction request message, fill in 0. For the field named "First Response Time", the type is "byte", the length is 4, and the default value is "0", it indicates the delay (in microseconds) from the first transaction request to its first response packet. It can be left blank when there is no transaction. In this case, fill in 0. For the field named "window", the type is "byte", the length is 4, and the default value is "0", it indicates the window size, the window after TCP link establishment negotiation. In non-TCP transmission, this field is filled in 0. For the field named "MSS", the type is "byte", the length is 4, and the default value is "0", it indicates the MSS size, the maximum segment size of the TCP layer. In non-TCP transmission, this field is filled in 0.

[0039] For the field named "TCP SYN NUM SS", the type is "byte", the length is 1, and the default value is "0", it indicates the number of TCP SYNs, the value of multiple SYNs in a TCP flow. In non-TCP transmission, this field is filled with 0. For the field named "TCP Status", the type is "byte", the length is 1, and the default value is "all F", it indicates the TCP connection status indication, 0 indicates success, and 1 indicates failure. For the field named "Session End", the type is "byte", the length is 1, and the default value is "all F", it indicates whether this XDR represents a complete data flow. If so, fill in 1; if it is a truncation of an overlong data flow, fill in 2, 1 indicates the end, and 2 indicates not ended.

[0040] For the field named "TCP SYN ACK Num", the type is "byte", the length is 1, and the default value is "0", it indicates the number of TCP SYN ACKs. When the value of multiple SYN ACKs in a TCP flow is not TCP transmission, this field is filled with 0. For the field named "TCP ACK Num", the type is "byte", the length is 1, and the default value is "0", it indicates the number of ACKs in reply to SYN ACK is not TCP transmission, this field is filled with 0.

[0041] For the field named "TCP1 / 2Handshake Status", the type is "byte", the length is 1, and the default value is "all F", it indicates the TCP1 / 2 handshake connection status indication, 0 indicates success; 1 indicates failure. For the field named "TCP2 / 3Handshake Status", the type is "byte", the length is 1, and the default value is "all F", it indicates the TCP2 / 3 handshake connection status indication, 0 indicates success; 1 indicates failure. For the field named "Repetition", the type is "byte", the length is 1, and the default value is "all F", it indicates whether the session is counted repeatedly, 0 indicates no; 1 indicates yes.

[0042] The static IP network segment table includes: city, IP address, dedicated line name, product instance, customer name, customer industry, and dedicated line bandwidth, etc.

[0043] By matching the IP addresses and number segments in the static table of IP segments with the data in the Internet DPI bill, the name of the dedicated line, product instance, customer name, bandwidth and other information are filled back into the detailed return form. Then, the data corresponding to the customer collection business is filtered out from the Internet DPI bill, and the data in each business system is associated with the data filtered out from the Internet DPI bill (such as the original bill, broadband table, indicators, etc.) to complete the data synthesis. The data in each business system includes but is not limited to basic accounts, SPIP, USERIP, etc.

[0044] In S102, the first target data and the second target data are associated to obtain associated data, and based on the associated data, an indicator set is established from multiple dimensions with indicator features corresponding to the associated data.

[0045] Specifically, the first target data and the second target data are matched and associated with the data in the Internet DPI call record through the IP address and number segment in the IP network segment static table to obtain the associated data. Then, the associated data is modeled in multiple dimensions through three-dimensional six-part analysis, clustering, and associated synthesis.

[0046] The wide table structure of the associated data after association is shown in Table 1.

[0047] Table 1 Wide table structure

[0048] Fields illustrate time1 time msisdn account ueip User IP city City linename Line Name instance Product Examples customer Customer Name industry Customer Industry host domain name bandwith bandwidth reqcnt Number of requests succcnt Number of successes upflow Upstream traffic dnflow Downstream traffic totalflow Total flow customercnt Number of customers httpwarncnt HTTP success rate alarm number flowwarncnt Traffic alarm number bwwarncnt Bandwidth alarm count

[0049] By extracting the indicator features of related data, data modeling is performed from multiple dimensions. This includes dimensions such as province, city, industry, and business, and calculations are performed on multiple dimensions to generate detailed and full-dimensional data. The combined dimensions generated after modeling include: provincial and municipal business dimension groupings, including but not limited to province, city, and customer industry; customer object dimension groupings, including but not limited to account number, customer name, product strength, dedicated line name, and customer industry; network dimension groupings, including but not limited to customer name, dedicated line name, and bandwidth; business dimension groupings, including but not limited to customer name, dedicated line name, industry, domain name, IP, etc.

[0050] In combination with related data, an indicator set is established from the above multiple dimensions. The indicators included in the indicator set include but are not limited to the number of requests, the number of successes, the access success rate, the access latency, the upstream traffic, the downstream traffic, the total traffic, the number of customers, the online time, the download rate and the bandwidth.

[0051] In S104, the weight values ​​of the original indicators in the indicator set are calculated respectively; the indicators whose weight values ​​exceed the poor quality threshold are selected as poor quality indicators, and the customer acquisition business corresponding to the poor quality indicator is positioned as the poor quality business.

[0052] Specifically, after obtaining the indicators in the above indicator set, the poor quality business of the customer service is located based on the above indicators. That is, when the network indicators are found to be poor quality, the potential root causes of poor quality are obtained and analyzed through the calculation of weight values, and the indicator baseline and customer portrait are formed. The root causes that affect the poor quality of network indicators are determined through association cluster analysis. After the poor quality indicators are found, the poor quality of the dedicated line network to which it belongs is located, and a certain dimension object is specifically located to facilitate the optimization of alarm dispatch. Furthermore, the results after dispatching and the changes in bandwidth capacity can be tracked to form a closed loop of business analysis.

[0053] Furthermore, combining big data and weight value methods, a KQI degradation impact measurement model is established. Based on historical data analysis, comprehensive consideration of KQI changes and data business model changes is made to quantify the degree of influence of indicators in each dimension on KQI degradation. Through the weighted comprehensive historical multi-dimensional indicator influencing factor data model, cluster analysis is performed on the changes and deviations of indicators in each dimension of the poor quality line, and the quality difference variance is calculated.

[0054] The weight value can be calculated using the following formula:

[0055]

[0056] Wherein, Wt represents the weight value, Wc1-Wcn represents the weight factor, Std1 to Stdn are the benchmark indicator values, his1 to hisn are the historical indicator values, and Cur1 to Curn represent the current indicator values ​​of the original indicator. Wherein, N and n are the number of indicators, and the values ​​of N and n can be determined according to the number of indicators, which is not limited in the embodiments of the present application. For example, when the number of indicators is 8, N can be taken as 8, and the corresponding weight factors are: Wc1, which represents the download rate; Wc2, which represents the total traffic; Wc3, which represents the peak bandwidth utilization; Wc4, which represents the network access success rate; Wc5, which represents the traffic limit exceeding; Wc6, which represents the call list access volume; Wc7, which represents the first frame buffering time; Wc8, which represents the user activity.

[0057] For the weight factor, a combination of dynamic adjustment and manual tuning is adopted. The values ​​of the weight factors of the same indicator in different ranges are different. For example, when the peak value of the bandwidth is greater than or equal to 70%, the weight factor of the peak bandwidth utilization is Wc=1.2*PeakV. When the peak value of the bandwidth is less than 70%, the weight factor of the peak bandwidth utilization is Wc=0.8*PeakV, where PeakV is the peak value of the bandwidth. Through the weight value of the peak bandwidth utilization, when locating the quality difference, the comprehensive value of the quality difference of each candidate indicator is calculated separately to perform positioning analysis. For example, in one calculation, we get a Wt weight value of 0.5, which means that the network quality is poor. The peak bandwidth utilization indicator accounts for the largest proportion in the indicator formula calculation. We believe that the positioning result of the poor network quality this time is caused by the poor quality of the peak utilization indicator, and the transmission network needs to be optimized.

[0058] Through the technical solution disclosed in the embodiment of the present application, the indicators in the embodiment of the present application are determined from the associated data after the first target data and the second target data are associated. The data are highly linked, and the indicator values ​​are established from multiple dimensions based on the indicator characteristics corresponding to the associated data, which improves the accuracy of positioning of poor quality businesses and is conducive to the development of customer acquisition businesses.

[0059] like Figure 2 As shown, the embodiment of the present application provides a method for locating a poor-quality service of a customer-attracting service, and the execution subject of the method may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers, and the server may be a server capable of locating a poor-quality service of a customer-attracting service. The method for locating a poor-quality service of a customer-attracting service may specifically include the following steps S201 to S204:

[0060] In S201, target data corresponding to the customer acquisition business is obtained.

[0061] In S202, the first target data and the second target data are associated to obtain associated data, and based on the associated data, an indicator set is established from multiple dimensions with indicator features corresponding to the associated data.

[0062] In S203, target indicators that affect network quality are determined based on big data statistics and a complete data-dependent algorithm or a partial data-dependent algorithm; and the target indicators are expanded to an indicator set.

[0063] Specifically, after determining the indicator set in the above step S202, the indicator set may be further expanded to further improve the positioning accuracy of the poor quality service.

[0064] In one possible implementation, S203 includes: determining new indicators that affect network indicators based on big data statistics; determining the dependency relationship between the new indicators and the original indicators in the indicator set using a complete data dependency algorithm or a partial data dependency algorithm; and selecting indicators whose dependency relationships meet the requirements from the new indicators as target indicators.

[0065] And perform data dependency analysis on the original indicators and new indicators in the indicator set to find indicators that have high correlation with the original indicators in the indicator set and have data dependency, and expand these indicators to the indicator set as the final indicator set.

[0066] Specifically, through big data analysis, we found that there are some new indicators related to problem obstacles, and thus introduced data indicators. These indicators include but are not limited to packet loss, video playback delay, video jitter, first frame buffer time, average buffer ratio, playback time, page opening time, page response time, complaint handling timeliness rate, fault handling timeliness rate, inflow average flow rate, inflow peak flow rate, outflow average flow rate, outflow peak flow rate, CPU utilization, memory usage, bandwidth utilization, daily busy hour average flow rate, daily peak flow rate, daily busy hour average bandwidth utilization, daily peak bandwidth utilization, and traffic balance.

[0067] Then, some invalid indicators in the above new indicators are filtered through a partial dependency algorithm or a full dependency algorithm, that is, indicators whose dependency relationships meet the requirements are selected from the new indicators as target indicators.

[0068] Specifically, for some data-dependent algorithms, the details are as follows:

[0069] Among them, the transitive dependency formula of the partial data dependency algorithm is {X->Y,Y->Z}<->{X->Z}.

[0070] The following indicator relationship is obtained through big data statistical analysis and data transmission dependency formula calculation: bandwidth utilization indicator quality difference (X) is a partial subset of download rate indicator quality difference (Y), and download rate quality difference can directly deduce network quality difference (Z), so the following indicator dependency relationship can be obtained: bandwidth utilization (X) -> network quality difference (Z), similarly: the dependency relationship between total traffic and user activity can also be obtained: total traffic -> user activity, thus, the dependency relationship between the original indicator and the new indicator is obtained.

[0071] For algorithms that rely entirely on data, the augmentation law and the transfer law rules are specifically applied, namely:

[0072] A2 (augmenting law): If X->Y holds, and ZU, then XZ->YZ holds.

[0073] A3 (transitive law): If X->Y, Y->Z, Z->A holds, then XA holds.

[0074] For example, we can deduce that traffic exceeds the limit (X) -> insufficient bandwidth (Y); insufficient bandwidth -> decreased download rate / decreased network access success rate (Z); decreased download rate / decreased network access success rate -> decreased network quality (A), and we can get traffic exceeds the limit (X) -> poor network quality (A). Similarly, we can get: traffic and call record access volume -> user activity.

[0075] Through the above dependency relationship, an indicator that meets the dependency requirements is selected from the new indicators as the target indicator, wherein meeting the requirement means having a dependency relationship with the original indicator. When there is no dependency relationship with the original indicator, it can be determined that the new indicator does not meet the dependency relationship with the original indicator.

[0076] In S204, the weight values ​​of the original indicators in the indicator set are calculated respectively; the indicators whose weight values ​​exceed the poor quality threshold are selected as poor quality indicators, and the customer acquisition business corresponding to the poor quality indicator is positioned as the poor quality business.

[0077] It is worth noting that S201, S202 and S204 have the same or similar implementation methods as the above-mentioned S101 to S104, which can refer to each other and will not be described in detail in the embodiments of the present application.

[0078] Through the technical solution disclosed in the embodiment of the present application, the indicators in the embodiment of the present application are determined from the associated data after the first target data and the second target data are associated, the data are highly linked, and the indicator value is established from multiple dimensions based on the indicator characteristics corresponding to the associated data, which improves the accuracy of positioning the poor quality business and is conducive to the development of the customer acquisition business. In addition, the indicators in the indicator set are further expanded, which further improves the accuracy of positioning the poor quality business and is more conducive to the development of the customer acquisition business.

[0079] like Figure 3 As shown, the embodiment of the present application provides a method for locating a poor-quality service for a customer-attracting service. The execution subject of the method may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers, and the server may be a server capable of locating a poor-quality service for a customer-attracting service. The method for locating a poor-quality service for a customer-attracting service may specifically include the following steps S301 to S305:

[0080] In S301, target data corresponding to the customer acquisition business is obtained.

[0081] In S302, the first target data and the second target data are associated to obtain associated data, and based on the associated data, an indicator set is established from multiple dimensions with indicator features corresponding to the associated data.

[0082] In S304, the weight values ​​of the original indicators in the indicator set are calculated respectively; the indicators whose weight values ​​exceed the poor quality threshold are selected as poor quality indicators, and the customer acquisition business corresponding to the poor quality indicator is positioned as the poor quality business.

[0083] In S305, the target object in the dimension corresponding to the quality difference index is located; and an alarm is dispatched to the target object.

[0084] Through the technical solution disclosed in the embodiment of the present application, the indicators in the embodiment of the present application are determined from the associated data after the first target data and the second target data are associated. The data are highly linked, and the indicator value is established from multiple dimensions based on the indicator characteristics corresponding to the associated data, which improves the accuracy of positioning the poor quality business and is conducive to the development of the customer collection business. In addition, the target object in the dimension where the poor quality indicator is located can be specifically located, and the target object can be targeted for alarm dispatch, which is convenient for users to handle in a timely manner, which is conducive to the development of the customer collection business.

[0085] Corresponding to the method for locating poor-quality services for attracting customers provided in the above embodiment, based on the same technical concept, the embodiment of the present application also provides a device for locating poor-quality services for attracting customers. Figure 4 A schematic diagram of the module composition of a poor quality service positioning device for a customer acquisition service provided in an embodiment of the present application, wherein the poor quality service positioning device for a customer acquisition service is used to perform Figures 1 to 3 The poor quality business positioning method of the customer acquisition business described, such as Figure 4 As shown, the poor quality service positioning device of the customer attraction service includes:

[0086] An acquisition module 401 is used to acquire target data corresponding to a customer acquisition business, wherein the target data includes first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; an association module 402 is used to associate the first target data and the second target data to obtain associated data; an establishment module 403 is used to establish an indicator set from multiple dimensions based on the associated data with indicator features corresponding to the associated data; a calculation module 404 is used to respectively calculate the weight value of each original indicator in the indicator set; a selection module 405 is used to select an indicator whose weight value exceeds a quality difference threshold as a quality difference indicator, and locate the customer acquisition business corresponding to the quality difference indicator as a quality difference business.

[0087] It can be seen from the technical solutions provided by the above embodiments of the present application that

[0088] In a possible implementation, it also includes: a determination module (not shown in the figure), which is used to determine the target indicator that affects the network quality based on big data statistics and a complete data-dependent algorithm or a partial data-dependent algorithm; and an addition module (not shown in the figure), which adds the target indicator to the indicator set.

[0089] In one possible implementation, the determination module (not shown in the figure) is also used to determine new indicators that affect network indicators based on big data statistics; determine the dependency relationship between the new indicators and the original indicators in the indicator set using a complete data dependency algorithm or a partial data dependency algorithm; and select indicators from the new indicators whose dependency relationships meet the requirements as target indicators.

[0090] In a possible implementation, the calculation module 404 calculates the weight value of each original indicator in the indicator set by the following formula:

[0091]

[0092] Among them, Wt represents the weight value, Wc1 to Wcn represent the weight factors, Std1 to Stdn represent the benchmark indicator values, his1 to hisn represent the historical indicator values, Cur1 to Curn represent the current indicator values, and N and n represent the number of indicators.

[0093] In a possible implementation, the association module 402 is further used to associate the first target data with the second target data based on the IP address and number segment in the static table of the IP network segment of the customer acquisition service to obtain the associated data.

[0094] In a possible implementation, the method further includes:

[0095] The positioning module is used to locate the target object in the dimension corresponding to the quality difference index; the alarm module is used to send an alarm to the target object.

[0096] The poor quality service positioning device for the customer attraction service provided in the embodiment of the present application can implement each process in the embodiment corresponding to the poor quality service positioning method for the customer attraction service mentioned above, and will not be described again here to avoid repetition.

[0097] It should be noted that the poor quality service positioning device for the customer attraction service provided in the embodiment of the present application and the poor quality service positioning method for the customer attraction service provided in the embodiment of the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the poor quality service positioning method for the customer attraction service mentioned above, and the repeated parts will not be repeated.

[0098] Corresponding to the method for locating the poor quality service of the customer acquisition service provided in the above embodiment, based on the same technical concept, the embodiment of the present application further provides an electronic device, which is used to execute the above method for locating the poor quality service of the customer acquisition service. Figure 5 A schematic diagram of the structure of an electronic device for implementing various embodiments of the present invention is shown in FIG. Figure 5 As shown. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and memory 502, and the memory 502 may store one or more storage applications or data. Among them, the memory 502 can be a temporary storage or a permanent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the electronic device. Furthermore, the processor 501 can be configured to communicate with the memory 502 to execute a series of computer executable instructions in the memory 502 on the electronic device. The electronic device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input and output interfaces 505, and one or more keyboards 506.

[0099] Specifically in this embodiment, the electronic device includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the following method steps:

[0100] Obtain target data corresponding to the customer acquisition business, the target data including first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; associate the first target data and the second target data to obtain associated data; based on the associated data, establish an indicator set from multiple dimensions with indicator features corresponding to the associated data; calculate the weight value of each original indicator in the indicator set respectively; select the indicator whose weight value exceeds the quality difference threshold as the quality difference indicator, and locate the customer acquisition business corresponding to the quality difference indicator as the quality difference business.

[0101] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following method steps are implemented:

[0102] Obtain target data corresponding to the customer acquisition business, the target data including first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; associate the first target data and the second target data to obtain associated data; based on the associated data, establish an indicator set from multiple dimensions with indicator features corresponding to the associated data; calculate the weight value of each original indicator in the indicator set respectively; select the indicator whose weight value exceeds the quality difference threshold as the quality difference indicator, and locate the customer acquisition business corresponding to the quality difference indicator as the quality difference business.

[0103] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0107] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0112] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for locating poor-quality services for attracting customers, characterized in that: The method comprises: Acquire target data corresponding to the customer acquisition business, wherein the target data includes first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; Associating the first target data with the second target data to obtain associated data; Based on the associated data, establishing an indicator set from multiple dimensions with indicator features corresponding to the associated data; Calculate the weight value of each original indicator in the indicator set respectively; Selecting an indicator in the weight value that exceeds the poor quality threshold as a poor quality indicator, and positioning the customer acquisition business corresponding to the poor quality indicator as a poor quality business; The associating the first target data with the second target data comprises: Based on the IP address and number segment in the static table of IP network segments of the customer acquisition service, the first target data and the second target data are associated to obtain associated data; The second target data includes: business data of the dialing test system, the transmission network system and the complaint system.

2. The method according to claim 1, characterized in that: After establishing an indicator set from multiple dimensions based on the associated data and using indicator features corresponding to the associated data, the method further includes: Determine target indicators that affect network quality based on big data statistics and fully data-dependent algorithms or partially data-dependent algorithms; Add the target indicator to the indicator set.

3. The method according to claim 2, characterized in that The target indicators affecting network quality determined based on big data statistics and a complete data-dependent algorithm or a partial data-dependent algorithm include: Determine new indicators that affect network quality based on the big data statistics; Determine the dependency relationship between the new indicator and the original indicator in the indicator set by using the complete data dependency algorithm or the partial data dependency algorithm; An indicator whose dependency relationship meets the requirements is selected from the new indicators as the target indicator.

4. The method according to claim 1, characterized in that: The weight values ​​of the original indicators in the indicator set are calculated respectively by the following formula: Among them, Wt represents the weight value, Wc1 to Wcn represent the weight factors, Std1 to Stdn represent the benchmark indicator values, his1 to hisn represent the historical indicator values, Cur1 to Curn represent the current indicator values ​​of the original indicator, and N and n represent the number of indicators.

5. The method according to claim 1, characterized in that After selecting the indicator exceeding the quality difference threshold in the weight value as the quality difference indicator and locating the customer acquisition business corresponding to the quality difference indicator as the quality difference business, the method further includes: Locating a target object in a dimension corresponding to the quality difference indicator; Send an alarm to the target object.

6. A device for locating poor-quality services for attracting customers, characterized in that: The device comprises: An acquisition module, used to acquire target data corresponding to the customer acquisition business, wherein the target data includes first target data corresponding to the customer acquisition business extracted from Internet DPI data and second target data from multiple business systems; an associating module, configured to associate the first target data with the second target data to obtain associated data; An establishing module, configured to establish an indicator set from multiple dimensions based on the associated data and with indicator features corresponding to the associated data; A calculation module, used to calculate the weight value of each original indicator in the indicator set respectively; A selection module, used for selecting the index exceeding the quality difference threshold value in the weight value as the quality difference index, and locating the customer acquisition business corresponding to the quality difference index as the quality difference business; The association module is specifically used to associate the first target data with the second target data based on the IP address and number segment in the static table of IP network segments of the customer collection service to obtain the associated data; The second target data includes: business data of the dialing test system, the transmission network system and the complaint system.

7. The device according to claim 6, characterized in that Also includes: A determination module, used to determine target indicators affecting network quality based on big data statistics and a complete data-dependent algorithm or a partial data-dependent algorithm; An adding module is used to add the target indicator to the indicator set.

8. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the steps of the method for locating poor quality services for customer acquisition services as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for locating poor-quality services for a customer acquisition service as described in any one of claims 1 to 5.

Images