Customer Service Data Intelligent Analysis Method and Device

Abstract

The present invention discloses an intelligent analysis method and device for customer service data. The method includes: collecting initial customer service data corresponding to a customer service business from a customer service data source system associated with a data analysis platform according to a pre-determined customer service business; inputting the initial customer service data into a data analysis model corresponding to the data analysis platform for analysis to obtain customer service index data corresponding to the customer service business, and the customer service index data is used to be output to the front end of the data analysis platform so that the front end displays the customer service index data. It can be seen that implementing the present invention can directly import the initial customer service data in the customer service data source system into the data analysis model of the data analysis platform for analysis to obtain customer service index data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. In addition, by providing digital support for the collection and analysis of customer service data, it is beneficial to realize the closed-loop control and real-time control of customer service business.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to an intelligent analysis method and device for customer service data. Background Art

[0002] In real life, customer service business is an important part of the marketing system of an enterprise's products or services. In order to improve the level of customer service business, it is necessary to collect customer service data of each business team of the customer service business offline, so as to analyze the business handling situation and business operation situation of each business team. However, it is found in practice that the existing method for collecting and analyzing customer service data has low efficiency and increases the daily workload of the customer service business team. Therefore, it is particularly important to improve the collection efficiency and analysis efficiency of customer service data and reduce the daily workload of the customer service business team. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent analysis method and device for customer service data, which can improve the efficiency and accuracy of collecting and analyzing customer service data and reduce the daily workload of the customer service business team.

[0004] To solve the above technical problem, in the first aspect of the present invention, an intelligent analysis method for customer service data is disclosed, and the method includes:

[0005] Collect initial customer service data corresponding to the customer service business from a customer service data source system associated with a data analysis platform according to a pre-determined customer service business;

[0006] Input the initial customer service data into a data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service index data corresponding to the customer service business, and the customer service index data is used to be output to the front end of the data analysis platform so that the front end displays the customer service index data.

[0007] As an optional implementation manner, in the first aspect of the present invention, the data analysis model analyzes the initial customer service data to obtain customer service index data corresponding to the customer service business, including:

[0008] The data analysis model determines characteristic data corresponding to one or more data indexes of the customer service business according to the initial customer service data;

[0009] The data analysis model analyzes the characteristic data corresponding to each data index according to the index type of each data index to obtain customer service index data corresponding to the customer service business;

[0010] Among them, the data analysis model determines characteristic data corresponding to one or more data indicators of the customer service business according to the initial customer service data, including:

[0011] The data analysis model extracts underlying data corresponding to one or more data indicators of the customer service business from the initial customer service data;

[0012] For each of the data indicators, the data analysis model determines characteristic data corresponding to the data indicator according to the underlying data corresponding to the data indicator.

[0013] As an alternative implementation manner, in the first aspect of the present invention, for each of the data indicators, the data analysis model determines characteristic data corresponding to the data indicator according to the underlying data corresponding to the data indicator, including:

[0014] The data analysis model determines whether the underlying data corresponding to the data indicator satisfies the dimensional condition of the data indicator;

[0015] When the judgment result is yes, the data analysis model determines the underlying data corresponding to the data indicator as the characteristic data corresponding to the data indicator;

[0016] When the judgment result is no, the data analysis model performs a feature extraction operation on the underlying data corresponding to the data indicator according to the data dimension corresponding to the data indicator to obtain the characteristic data corresponding to the data indicator;

[0017] Among them, for each of the data indicators, the data analysis model determines whether the underlying data corresponding to the data indicator satisfies the dimensional condition of the data indicator, including:

[0018] The data analysis model determines whether the underlying data corresponding to the data indicator includes all data dimensions corresponding to the data indicator. When the judgment result is yes, it is determined that the underlying data corresponding to the data indicator satisfies the dimensional condition of the data indicator.

[0019] As an alternative implementation manner, in the first aspect of the present invention, the initial customer service data includes one or more data combinations;

[0020] The data analysis model determines the underlying data corresponding to one or more data indicators of the customer service business from the initial customer service data, including:

[0021] The data analysis model screens all the data combinations of the initial customer service data according to the screening keywords corresponding to one or more data indicators of the customer service business to obtain target data combinations matching each data indicator as the underlying data corresponding to the data indicator; and / or,

[0022] The data analysis model matches all the data metrics and all the data combinations according to the metric identifiers corresponding to one or more data metrics of the customer service service and the data identifiers corresponding to all the data combinations of the initial customer service data, and obtains the target data combination matched with each data metric as the underlying data corresponding to the data metric.

[0023] As an optional implementation manner, in the first aspect of the present invention, the data analysis model analyzes the characteristic data corresponding to each data metric according to the metric type of each data metric, and obtains the customer service metric data corresponding to the customer service service, including:

[0024] For each data metric with the metric type being the first preset type, the data analysis model determines the characteristic data corresponding to the data metric as the customer service metric data corresponding to the customer service service;

[0025] For each data metric with the metric type being the second preset type, the data analysis model analyzes the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service service.

[0026] As an optional implementation manner, in the first aspect of the present invention, for each data metric with the metric type being the second preset type, the data analysis model analyzes the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service service, including:

[0027] The data analysis model operates on the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service service; or,

[0028] The data analysis model determines at least one associated data metric in all the data metrics that matches the data metric according to the calculation algorithm corresponding to the data metric, and operates on the characteristic data corresponding to the data metric and the characteristic data corresponding to at least one associated data metric that matches the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service service.

[0029] As an optional implementation manner, in the first aspect of the present invention, the method further includes:

[0030] Generating a visualization page corresponding to the customer service service according to the customer service metric data, where the visualization page is used to be output to the front end so that the front end displays the customer service metric data based on the visualization page;

[0031] Among them, the customer service metric data includes the analysis results corresponding to one or more data metrics of the customer service business. Generating the visualization page corresponding to the customer service business according to the customer service metric data includes:

[0032] Determine the sub-template corresponding to each data metric in the pre-determined template file;

[0033] For each data metric, generate the visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric;

[0034] Combine the visualization units corresponding to all the data metrics to obtain the visualization page corresponding to the customer service business.

[0035] As an optional implementation manner, in the first aspect of the present invention, for each data metric, generating the visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric includes:

[0036] Perform a keyword replacement operation on the template keywords in the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain the visualization unit corresponding to the data metric; and / or,

[0037] Perform a keyword filling operation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain the visualization unit corresponding to the data metric; and / or,

[0038] Generate the visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the template form of the sub-template corresponding to the data metric; and / or,

[0039] Perform information annotation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain the visualization unit corresponding to the data metric.

[0040] The second aspect of the present invention discloses a customer service data intelligent analysis device, and the device includes:

[0041] An acquisition module, configured to collect the initial customer service data corresponding to the customer service business from the customer service data source system associated with the data analysis platform according to the pre-determined customer service business;

[0042] A data analysis module, which is used to input the initial customer service data into a data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service index data corresponding to the customer service business, and the customer service index data is used to be output to the front end of the data analysis platform, so that the front end displays the customer service index data.

[0043] As an alternative implementation manner, in the second aspect of the present invention, the specific manner in which the data analysis model analyzes the initial customer service data to obtain the customer service index data corresponding to the customer service business includes:

[0044] According to the initial customer service data, determine the characteristic data corresponding to one or more data indicators of the customer service business;

[0045] According to the index type of each data indicator, analyze the characteristic data corresponding to each data indicator to obtain the customer service index data corresponding to the customer service business;

[0046] Among them, the specific manner in which the data analysis model determines the characteristic data corresponding to one or more data indicators of the customer service business according to the initial customer service data includes:

[0047] Extract the underlying data corresponding to one or more data indicators of the customer service business from the initial customer service data;

[0048] For each data indicator, determine the characteristic data corresponding to the data indicator according to the underlying data corresponding to the data indicator.

[0049] As an alternative implementation manner, in the second aspect of the present invention, for each data indicator, the specific manner in which the data analysis model determines the characteristic data corresponding to the data indicator according to the underlying data corresponding to the data indicator includes:

[0050] Judge whether the underlying data corresponding to the data indicator meets the dimensional conditions of the data indicator;

[0051] When the judgment result is yes, determine the underlying data corresponding to the data indicator as the characteristic data corresponding to the data indicator;

[0052] When the judgment result is no, perform a feature extraction operation on the underlying data corresponding to the data indicator according to the data dimension corresponding to the data indicator to obtain the characteristic data corresponding to the data indicator;

[0053] Among them, for each data indicator, the specific manner in which the data analysis model judges whether the underlying data corresponding to the data indicator meets the dimensional conditions of the data indicator includes:

[0054] Determine whether the underlying data corresponding to the data metric includes all the data dimensions corresponding to the data metric. When the determination result is yes, it is determined that the underlying data corresponding to the data metric meets the dimension condition of the data metric.

[0055] As an optional implementation manner, in the second aspect of the present invention, the initial customer service data includes one or more data combinations;

[0056] The specific manner in which the data analysis model determines the underlying data corresponding to one or more data metrics of the customer service business from the initial customer service data includes:

[0057] Screen all the data combinations of the initial customer service data according to the screening keywords corresponding to one or more data metrics of the customer service business, and obtain the target data combinations matching each data metric as the underlying data corresponding to the data metric; and / or,

[0058] Match all the data metrics and all the data combinations according to the metric identifiers corresponding to one or more data metrics of the customer service business and the data identifiers corresponding to all the data combinations of the initial customer service data, and obtain the target data combinations matching each data metric as the underlying data corresponding to the data metric.

[0059] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the data analysis model analyzes the characteristic data corresponding to each data metric according to the metric type of each data metric to obtain the customer service metric data corresponding to the customer service business includes:

[0060] For each data metric with the metric type being the first preset type, determine the characteristic data corresponding to the data metric as the customer service metric data corresponding to the customer service business;

[0061] For each data metric with the metric type being the second preset type, analyze the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business.

[0062] As an optional implementation manner, in the second aspect of the present invention, for each data metric with the metric type being the second preset type, the specific manner in which the data analysis model analyzes the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business includes:

[0063] Perform an operation on the characteristic data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business; or,

[0064] According to the calculation algorithm corresponding to the data metric, determine at least one associated data metric that matches the data metric among all the data metrics, and perform an operation on the characteristic data corresponding to the data metric and the characteristic data corresponding to at least one of the associated data metrics that matches the data metric according to the calculation algorithm corresponding to the data metric, to obtain the customer service metric data corresponding to the customer service business.

[0065] As an alternative implementation manner, in the second aspect of the present invention, the device further includes:

[0066] A generation module, configured to generate a visualization page corresponding to the customer service business according to the customer service metric data, where the visualization page is used to be output to the front end, so that the front end displays the customer service metric data based on the visualization page;

[0067] Wherein, the customer service metric data includes analysis results corresponding to one or more data metrics of the customer service business, and the specific manner for the generation module to generate a visualization page corresponding to the customer service business according to the customer service metric data includes:

[0068] Determine a sub-template corresponding to each data metric in a pre-determined template file;

[0069] For each data metric, generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric;

[0070] Combine the visualization units corresponding to all the data metrics to obtain a visualization page corresponding to the customer service business.

[0071] As an alternative implementation manner, in the second aspect of the present invention, for each data metric, the specific manner for the generation module to generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric includes:

[0072] Perform a keyword replacement operation on the template keywords in the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric, to obtain a visualization unit corresponding to the data metric; and / or,

[0073] Perform a keyword filling operation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric, to obtain a visualization unit corresponding to the data metric; and / or,

[0074] Generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the template form of the sub-template corresponding to the data metric; and / or,

[0075] According to the analysis result corresponding to the data index, information annotation is performed on the sub-template corresponding to the data index to obtain the visualization unit corresponding to the data index.

[0076] The third aspect of the present invention discloses another intelligent customer service data analysis device, and the device includes:

[0077] A memory storing executable program code;

[0078] A processor coupled to the memory;

[0079] The processor calls the executable program code stored in the memory to execute the intelligent customer service data analysis method disclosed in the first aspect of the present invention.

[0080] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute the intelligent customer service data analysis method disclosed in the first aspect of the present invention when called.

[0081] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0082] In the embodiments of the present invention, according to the pre-determined customer service business, initial customer service data corresponding to the customer service business is collected from the customer service data source system associated with the data analysis platform; the initial customer service data is input into the data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service index data, and the customer service index data is used to be output to the front end of the data analysis platform, so that the front end displays the customer service index data. It can be seen that implementing the present invention can directly import the initial customer service data in the customer service data source system into the data analysis platform, and analyze the initial customer service data based on the data analysis model of the data analysis platform to obtain customer service index data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. In addition, by providing digital support for the collection and analysis of customer service data, it is beneficial to realize the closed-loop control and real-time control of the customer service business, thereby facilitating the promotion of the transparent and flat management of the customer service business and improving the quality of the customer service business. Description of the Drawings

[0083] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0084] Figure 1It is a schematic flowchart of a method for intelligent analysis of customer service data disclosed in an embodiment of the present invention;

[0085] Figure 2 It is a schematic flowchart of another method for intelligent analysis of customer service data disclosed in an embodiment of the present invention;

[0086] Figure 3 It is a schematic structural diagram of a device for intelligent analysis of customer service data disclosed in an embodiment of the present invention;

[0087] Figure 4 It is a schematic structural diagram of another device for intelligent analysis of customer service data disclosed in an embodiment of the present invention;

[0088] Figure 5 It is a schematic structural diagram of yet another device for intelligent analysis of customer service data disclosed in an embodiment of the present invention. Detailed implementation manners

[0089] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0090] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or terminal that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or terminals.

[0091] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0092] The present invention discloses an intelligent analysis method and device for customer service data, which can directly import the initial customer service data in the customer service data source system into the data analysis platform, and analyze the initial customer service data based on the data analysis model of the data analysis platform to obtain customer service index data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. In addition, by providing digital support for the collection and analysis of customer service data, it is beneficial to realize the closed-loop control and real-time control of the customer service business, thus facilitating the promotion of the transparent and flat management of the customer service business and improving the quality of the customer service business. The following will be described in detail respectively.

[0093] Embodiment 1

[0094] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an intelligent analysis method for customer service data disclosed in an embodiment of the present invention. Among them, Figure 1 the described intelligent analysis method for customer service data can be applied to the process of collecting and analyzing customer service data, and the embodiments of the present invention do not make limitations. As Figure 1 shown, the intelligent analysis method for customer service data can include the following operations:

[0095] 101. Collect the initial customer service data corresponding to the customer service business from the customer service data source system associated with the data analysis platform according to the pre-determined customer service business.

[0096] In an embodiment of the present invention, optionally, the customer service business may include one or more of user demand business, service commitment business, AI customer service business, customer service quality inspection business, and Internet operation business. Among them, the initial customer service data corresponding to the user demand business may include data representing the user demands received by the customer service center, the initial customer service data corresponding to the service commitment business may include data representing the completion of the external service commitments of the customer service center, the initial customer service data corresponding to the AI customer service business may include data representing the working conditions of the AI customer service in the customer service center, the customer service quality inspection data may include data related to the business quality inspection of the customer service center, and the initial customer service data corresponding to the Internet operation business may include data representing the Internet business operation conditions of the customer service center. It can be seen that this is beneficial to improving the comprehensiveness and diversity of customer service data analysis, and thus beneficial to improving the quality and breadth of customer service operations.

[0097] The customer service data source system associated with the data analysis platform may include one or more of a marketing system, an intelligent interaction system, an intelligent quality inspection system, and an online system. Further optionally, initial customer service data corresponding to at least one of user demand services, service commitment services, and customer service Internet operation services can be collected from the marketing system; initial customer service data corresponding to at least one of AI customer service services, user demand services, and customer service quality inspection services can be collected from the intelligent interaction system; initial customer service data corresponding to at least one of customer service quality inspection services and service commitment services can be collected from the intelligent quality inspection system; and initial customer service data corresponding to at least one of Internet operation services and user demand services can be collected from the online system. Further optionally, the intelligent interaction system may include an intelligent voice interaction system and / or an intelligent online interaction system, and the intelligent voice interaction system may be an intelligent IVR (Interactive Voice Response) system. It can be seen that this can improve the richness of the sources of initial customer service data by associating multiple customer service data source systems with the data analysis platform, thereby facilitating the improvement of the comprehensiveness of customer service data collection.

[0098] In an embodiment of the present invention, optionally, the initial customer service data may include one or more data combinations. Further optionally, each data combination may include one or more of the data collection time, service execution time, service execution method, service recipient, service provider, service content, and the business type to which it belongs corresponding to the data combination. It can be seen that this can improve the richness of each piece of initial customer service data, and thus facilitate providing data support for the analysis of multiple data indicators simultaneously and reducing the amount of data redundancy.

[0099] In an embodiment of the present invention, optionally, collecting the initial customer service data corresponding to the customer service business from the customer service data source system associated with the data analysis platform according to the pre-determined customer service business may include: capturing, based on the data capture technology, data that meets the preset business type conditions from the database of the customer service data source system associated with the data analysis platform according to the pre-determined customer service business, as the initial customer service data corresponding to the customer service business. Preferably, the data capture technology may be the OGG (Oracle GoldenGate) technology. It can be seen that implementing this optional implementation method can further improve the accuracy and efficiency of data collection.

[0100] 102. Input the initial customer service data into the data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain the customer service index data corresponding to the customer service business.

[0101] In an embodiment of the present invention, optionally, the customer service metric data can be output to the front end of the data analysis platform so that the front end can display the customer service metric data. Optionally, the front end has a dashboard function and can display the customer service metric data in forms such as text and charts.

[0102] As an optional implementation manner, the data analysis model analyzes the initial customer service data to obtain the customer service metric data corresponding to the customer service business, which may include:

[0103] The data analysis model determines the characteristic data corresponding to one or more data metrics of the customer service business according to the initial customer service data;

[0104] The data analysis model analyzes the characteristic data corresponding to each data metric according to the metric type of each data metric to obtain the customer service metric data corresponding to the customer service business.

[0105] It can be seen that implementing this optional implementation manner can analyze the characteristic data based on the type of data metrics, improve the matching degree between the analysis method of the characteristic data and the metric type, and thus improve the accuracy of the characteristic data analysis.

[0106] In this optional implementation manner, optionally, the data metrics of the user demand service may include the total customer service demand metric and / or the customer service demand metric corresponding to each demand channel. The total customer service demand metric and the customer service demand metric corresponding to each demand channel may each include one or more of the number of demands, the number of repeated complaints, the number of repeated complaints, the number of unhandled complaints, the number of handled complaints, the number of unreasonable demands, the repeated complaint rate, the repeated complaint rate, the unhandled complaint rate, the handled complaint rate, the unreasonable demand rate, etc. It can be seen that this is beneficial to a more comprehensive understanding of user demands, so as to provide a better customer service experience for users.

[0107] In this optional implementation manner, optionally, the data metrics of the service commitment service are used to represent the completion status corresponding to the service commitment service. Taking the power grid customer service center as an example, the data metrics of the service commitment service may include one or more of the qualified rate of residential voltage, the power supply reliability rate, the average arrival time of fault repair personnel at the scene, the average power restoration time, the timely rate of restoring power for overdue payments, the duration of business expansion and installation, the duration of electricity application and installation, the duration of electricity query, the connection rate within 20 seconds, the timely rate of replying to users, etc. It can be seen that this is beneficial to improving the control degree of the completion status of the service commitment, thereby being beneficial to further improving the service level, improving user satisfaction and thus improving user stickiness.

[0108] In this optional implementation, optionally, the data metrics of the AI customer service business may include the customer service metrics corresponding to the comprehensive intelligent customer service and the customer service metrics corresponding to each type of intelligent customer service. Among them, the intelligent customer service may include intelligent voice customer service and intelligent online customer service. Further optionally, the customer service metrics corresponding to the comprehensive intelligent customer service and each type of intelligent customer service may each include one or more of the call volume and regional distribution corresponding to the intelligent customer service, the current-day real-time call volume, the service proportion, the scenario coverage rate, the translation accuracy rate, the user question recognition rate, the accuracy rate of self-service filling of intelligent work orders, the service satisfaction rate, the number of quality inspection work orders, the quality inspection work order rate, the number of quality inspection work orders in a specific language, the quality inspection work order rate in a specific language, the top ten high-frequency user questions, the accuracy rate of key items of user experience, etc. Among them, the number of quality inspection work orders includes the number of work orders that meet the preset rule conditions among all the work orders of the intelligent customer service. The quality inspection work order rate in a specific language includes the proportion of work orders that meet the preset rule conditions among all the work orders in a specific language among all the work orders. For example, the proportion of work orders that meet the preset rule conditions (such as the chat content involves mall points) among all the incoming calls in Mandarin among all the incoming calls in Mandarin. The accuracy rate of key items of user experience = (1 - the number of work orders with key item errors) / the total number of randomly inspected work orders of the intelligent customer service. The number of work orders with key item errors includes the number of work orders with key item errors (such as unsolved problems, bad attitude, unclear communication) that lead to defects in user experience. It can be seen that this can improve the control degree of the service situation of the intelligent customer service business, and thus is conducive to improving the intelligent customer service business, increasing the scenario coverage rate of the intelligent customer service, and reducing the daily workload of customer service personnel.

[0109] In the embodiments of the present invention, optionally, the data metrics of the customer service quality inspection business may include one or more of the quality inspection metrics of the customer service hotline, the quality inspection metrics of the AI customer service, and the quality inspection metrics of customer service training. Further optionally, the customer service hotline includes incoming calls and / or outgoing calls of the customer service hotline. The quality inspection metrics of the customer service hotline and the quality inspection metrics of the AI customer service may each include one or more of the quality inspection cancellation rate, the quality inspection accuracy rate, the accuracy rate of business key items, and the accuracy rate of compliance key items. Among them, the quality inspection cancellation rate = the number of work orders with closed-loop processed errors / the total number of error work orders, the quality inspection accuracy rate = the number of qualified quality inspection work orders / the total number of quality inspection work orders, the accuracy rate of compliance key items = (1 - the number of work orders with compliance key item errors) / the total number of randomly inspected work orders. The number of work orders with compliance key item errors includes the number of work orders with violations. The accuracy rate of business key items = (1 - the number of work orders with business key item errors) / the total number of randomly inspected work orders. The number of work orders with business key item errors includes the number of work orders with key item errors that lead to defects in the business. The customer service training metrics may include the passing rate of customer service training assessment and the passing rate of assessment during the on-the-job observation period. It can be seen that this is conducive to improving the overall control degree of the service situation of manual customer service and intelligent customer service, and thus is conducive to improving the customer service business and is conducive to avoiding service risks in advance.

[0110] In an embodiment of the present invention, optionally, the data metrics of the Internet operation service may include one or more of tweet metrics, Internet mall metrics, and Internet service handling metrics. Among them, the tweet metrics may include one or more of the number of tweets, the number of tweet reads, the number of likes obtained for tweets, the number of tweets with a read volume greater than a first threshold, the number of tweets with a like volume greater than a second threshold, etc. The Internet mall metrics may include one or more of the number of users of the Internet mall, the number of users who obtain markers based on their first login, the number of users who obtain markers based on their first account binding, the number of users who obtain markers based on bill checking, the number of lottery orders based on markers, the number of winning lottery orders based on markers, the number of commodity exchange orders based on markers, etc. Among them, the markers may include virtual objects with transaction functions, such as points, electronic currency, etc. The Internet service handling metrics may include one or more of the Internet service handling volume, the Internet service handling ratio, etc. It can be seen that this can improve the overall control degree of the Internet operation service, facilitate accurately grasping user hotspots and interest points, so as to provide better Internet operation services for users.

[0111] In this optional embodiment, optionally, the data analysis model determines the characteristic data corresponding to one or more data metrics of the customer service business according to the initial customer service data, which may include:

[0112] The data analysis model extracts the underlying data corresponding to one or more data metrics of the customer service business from the initial customer service data;

[0113] For each data metric, the data analysis model determines the characteristic data corresponding to the data metric according to the underlying data corresponding to the data metric.

[0114] For example, if the data metric is the number of unprocessed complaints, all unprocessed complaint work orders need to be extracted from the initial customer service data as the underlying data, and then all unprocessed complaint work orders are counted to determine the number of unprocessed complaints as the characteristic data.

[0115] It can be seen that implementing this optional embodiment can also extract the underlying data from the initial customer service data and then determine the characteristic data from the underlying data, which is beneficial to gradually reduce the unnecessary interference information in the customer service data and improve the efficiency and accuracy of customer service data analysis.

[0116] In this optional embodiment, further optionally, for each data metric, the data analysis model determines the characteristic data corresponding to the data metric according to the underlying data corresponding to the data metric, which may include:

[0117] The data analysis model determines whether the underlying data corresponding to the data metric meets the dimensional conditions of the data metric;

[0118] When the judgment result is yes, the data analysis model determines the underlying data corresponding to the data index as the characteristic data corresponding to the data index;

[0119] When the judgment result is no, the data analysis model performs a feature extraction operation on the underlying data corresponding to the data index according to the data dimension corresponding to the data index, and obtains the characteristic data corresponding to the data index.

[0120] In this optional implementation manner, optionally, the feature extraction operation may include one or more of classification, counting, sorting, and filtering.

[0121] It can be seen that implementing this optional implementation manner can also perform a feature extraction operation on the underlying data to obtain characteristic data only when the underlying data does not meet the dimension conditions of the data index, reducing unnecessary operations, and being beneficial to improving the coincidence degree between the data dimension of the characteristic data and the data dimension of the data index, thereby improving the accuracy and reliability of the characteristic data extraction.

[0122] In this optional implementation manner, further optionally, for each data index, the data analysis model determines whether the underlying data corresponding to the data index meets the dimension conditions of the data index, which may include:

[0123] The data analysis model determines whether the underlying data corresponding to the data index includes all the data dimensions corresponding to the data index. When the judgment result is yes, it is determined that the underlying data corresponding to the data index meets the dimension conditions of the data index.

[0124] For example, if the underlying data is all user problems on the current day, when the data index is all user problems on the current day, the underlying data includes all the data dimensions corresponding to the data index. When the data index is the top three high-frequency user problems on the current day, the underlying data does not include all the data dimensions corresponding to the data index (the occurrence frequency of each user problem and the sorting determined based on the occurrence frequency of each user problem).

[0125] It can be seen that implementing this optional implementation manner can also determine that it meets the dimension conditions when the underlying data includes all the data dimensions corresponding to the data index, which is beneficial to improving the comprehensiveness of the data dimension of the customer service data, and thus beneficial to improving the comprehensiveness and accuracy of the customer service data analysis.

[0126] In this optional implementation manner, further optionally, the data analysis model determines the underlying data corresponding to one or more data indexes of the customer service business from the initial customer service data, which may include:

[0127] The data analysis model filters all data combinations of the initial customer service data according to the screening keywords corresponding to one or more data indicators of the customer service service, and obtains the target data combinations matching each data indicator as the underlying data corresponding to the data indicator; and / or,

[0128] The data analysis model matches all data indicators and all data combinations according to the indicator identifiers corresponding to one or more data indicators of the customer service service and the data identifiers corresponding to all data combinations of the initial customer service data, and obtains the target data combinations matching each data indicator as the underlying data corresponding to the data indicator.

[0129] It can be seen that implementing this optional implementation manner can also filter the corresponding underlying data from the initial customer service data according to the screening keywords or data identifiers corresponding to the data indicators, which is beneficial to improving the accuracy and efficiency of underlying data filtering and reducing the possibility of incomplete underlying data.

[0130] In this optional implementation manner, further optionally, the data analysis model analyzes the characteristic data corresponding to each data indicator according to the indicator type of each data indicator, and obtains the customer service indicator data corresponding to the customer service service, which may include:

[0131] For each data indicator with the indicator type being the first preset type, the data analysis model determines the characteristic data corresponding to the data indicator as the customer service indicator data corresponding to the customer service service;

[0132] For each data indicator with the indicator type being the second preset type, the data analysis model analyzes the characteristic data corresponding to the data indicator according to the calculation algorithm corresponding to the data indicator, and obtains the customer service indicator data corresponding to the customer service service.

[0133] For example, if the underlying data is all intelligent voice work orders on the same day and the data indicator is the number of all intelligent voice work orders on the same day, the characteristic data obtained after counting the underlying data, that is, the number of all intelligent voice work orders on the same day, is the customer service indicator data corresponding to the customer service service. If the data indicator is the average duration of intelligent voice work orders on the same day, the characteristic data (the duration of all intelligent voice work orders on the same day) is extracted from the underlying data, and the characteristic data is calculated to obtain the average duration of intelligent voice work orders on the same day as the customer service indicator data corresponding to the customer service service.

[0134] It can be seen that implementing this optional implementation manner can also adopt different methods for different types of data indicators to determine customer service indicator data according to the feature data, improving the flexibility and diversity of customer service data analysis. Moreover, directly determining the feature data of the data indicators of the first preset type as the customer service indicator data improves the analysis efficiency of customer service data, and uses the corresponding algorithm to analyze the feature data of the data indicators of the second preset type, improving the accuracy and reliability of customer service data analysis.

[0135] In this optional implementation manner, further optionally, for each data indicator whose indicator type is the second preset type, the data analysis model analyzes the feature data corresponding to the data indicator according to the calculation algorithm corresponding to the data indicator, and the obtained customer service indicator data corresponding to the customer service service may include:

[0136] The data analysis model performs an operation on the feature data corresponding to the data indicator according to the calculation algorithm corresponding to the data indicator to obtain the customer service indicator data corresponding to the customer service service; or,

[0137] The data analysis model determines at least one associated data indicator that matches the data indicator among all data indicators according to the calculation algorithm corresponding to the data indicator, and performs an operation on the feature data corresponding to the data indicator and the feature data corresponding to at least one associated data indicator that matches the data indicator according to the calculation algorithm corresponding to the data indicator to obtain the customer service indicator data corresponding to the customer service service.

[0138] For example, if the data indicator is the average duration of intelligent voice work orders, then only by performing an operation on the feature data corresponding to the data indicator (the duration of all intelligent voice work orders) according to the calculation algorithm corresponding to the data indicator, the customer service indicator data corresponding to the customer service service can be obtained; if the data indicator is the qualified rate of intelligent voice quality inspection, then it is necessary to perform an operation on the feature data corresponding to the data indicator (the number of qualified intelligent voice quality inspection work orders) and the feature data corresponding to at least one associated data indicator that matches the data indicator (the total number of intelligent voice quality inspection work orders) according to the calculation algorithm corresponding to the data indicator to obtain the customer service indicator data corresponding to the customer service service.

[0139] It can be seen that implementing this optional implementation manner can also determine whether it is necessary to call the feature data of other associated data indicators to participate in the operation of the feature data corresponding to the current data indicator according to the calculation algorithm corresponding to the data indicator, reducing data redundancy caused by setting judgment rules for each data indicator, and being beneficial to improving the flexibility, diversity, and accuracy of customer service data analysis.

[0140] It can be seen that implementing the embodiments of the present invention can directly import the initial customer service data in the customer service data source system into the data analysis platform, and analyze the initial customer service data based on the data analysis model of the data analysis platform to obtain customer service index data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. In addition, by providing digital support for the collection and analysis of customer service data, it is conducive to realizing the closed-loop control and real-time control of the customer service business, thereby facilitating the promotion of the transparent and flat management of the customer service business and improving the quality of the customer service business.

[0141] In an optional embodiment, the method may further include:

[0142] Based on the customer service index data, determine whether there are any abnormal data indicators among all data indicators whose corresponding analysis results do not meet the preset conditions;

[0143] When the judgment result is yes, determine the abnormal cause of the abnormal data indicator according to the target data corresponding to the abnormal data indicator and / or the target data corresponding to the associated data indicator that matches the abnormal data indicator, where the target data includes one or more of underlying data, feature data, and analysis results;

[0144] Generate a warning message for the abnormal data indicator according to the abnormal cause, and the warning message is used to be output to the user terminal of the customer service personnel corresponding to the abnormal data indicator.

[0145] It can be seen that implementing this optional embodiment can also monitor the customer service index data, timely detect abnormal data indicators and notify the customer service personnel, thereby facilitating the realization of the real-time control of the customer service business and improving the quality of the customer service business.

[0146] Embodiment 2

[0147] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of another intelligent customer service data analysis method disclosed in the embodiments of the present invention. Among them, Figure 2 The described intelligent customer service data analysis method can be applied to the collection and analysis process of customer service data, and the embodiments of the present invention do not make limitations. As Figure 2 shown, the intelligent customer service data analysis method may include the following operations:

[0148] 201. According to the pre-determined customer service business, collect the initial customer service data corresponding to the customer service business from the customer service data source system associated with the data analysis platform.

[0149] 202. Input the initial customer service data into the data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain the customer service index data corresponding to the customer service business.

[0150] 203. Generate a visualization page corresponding to the customer service business based on the customer service metric data.

[0151] In an embodiment of the present invention, the visualization page is used to be output to the front end, so that the front end displays the customer service metric data based on the visualization page.

[0152] In an embodiment of the present invention, optionally, the customer service metric data includes the analysis results corresponding to one or more data metrics of the customer service business.

[0153] As an optional implementation manner, generating a visualization page corresponding to the customer service business according to the customer service metric data may include:

[0154] Determine the sub-template corresponding to each data metric in the pre-determined template file.

[0155] For each data metric, generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric.

[0156] Combine the visualization units corresponding to all data metrics to obtain a visualization page corresponding to the customer service business.

[0157] It can be seen that implementing this optional implementation manner can generate visualization units by importing the analysis results corresponding to the data metrics into the sub-templates corresponding to the data metrics, which is beneficial to improving the generation efficiency of the visualization page, and obtaining the visualization page by combining the visualization units, which is beneficial to improving the flexibility of generating the visualization page, and reducing data redundancy and costs caused by designing and storing multiple visualization templates.

[0158] In this optional implementation manner, optionally, for each data metric, generating a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric may include:

[0159] Perform a keyword replacement operation on the template keywords in the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain a visualization unit corresponding to the data metric; and / or,

[0160] Perform a keyword filling operation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain a visualization unit corresponding to the data metric; and / or,

[0161] Generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the template form of the sub-template corresponding to the data metric; and / or,

[0162] According to the analysis result corresponding to the data indicator, perform information annotation on the sub-template corresponding to the data indicator to obtain the visualization unit corresponding to the data indicator.

[0163] It can be seen that implementing this optional implementation method can generate the visualization unit corresponding to the data indicator by performing operations such as keyword replacement, keyword filling, and information annotation on the sub-template corresponding to the data indicator, or generating the visualization unit corresponding to the data indicator according to the template form, improving the flexibility and diversity of the generation of the visualization unit.

[0164] In this optional implementation method, optionally, combine the visualization units corresponding to all data indicators to obtain the visualization page corresponding to the customer service business, which may include:

[0165] Determine the attribute parameters corresponding to each data indicator;

[0166] According to the attribute parameters corresponding to each data indicator, determine the position of the visualization unit corresponding to the data indicator on the pre-set simulated front-end dashboard. Among them, the interval distance between the positions of the visualization units corresponding to every two data indicators on the simulated front-end dashboard is not less than the preset distance threshold;

[0167] According to the positions of the visualization units corresponding to all data indicators on the simulated front-end dashboard, combine the visualization units corresponding to all indicators to obtain the visualization page corresponding to the customer service business.

[0168] In this optional implementation method, optionally, the attribute parameters corresponding to each data indicator may include one or more of the display priority of the data indicator, the analysis situation corresponding to the data indicator, the indicator type of the data indicator, the customer service business to which the data indicator belongs, the unit size of the visualization unit corresponding to the data indicator, and the unit type of the visualization unit corresponding to the data indicator. Among them, the analysis situation corresponding to each data indicator is used to indicate whether the analysis result corresponding to the data indicator exceeds the rated normal range.

[0169] It can be seen that implementing this optional implementation method can also determine the position of its visualization unit on the simulated front-end dashboard according to the attribute parameters corresponding to the data indicator, and then combine all the visualization units to obtain the visualization page, which is beneficial to improving the distribution position and rationality of the customer service indicator data on the visualization page, and improving the aesthetics of the visualization page, thereby improving the comfort level of the customer service business personnel when viewing the visualization page and the convenience and accuracy of finding the customer service indicator data.

[0170] It can be seen that implementing the embodiments of the present invention can directly import the initial customer service data in the customer service data source system into the data analysis platform, and analyze the initial customer service data based on the data analysis model of the data analysis platform to obtain customer service metric data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. Moreover, by providing digital support for the collection and analysis of customer service data, it is conducive to realizing the closed-loop control and real-time control of customer service operations, thereby facilitating the promotion of the transparent and flat management of customer service operations and improving the quality of customer service. In addition, visual business will be generated according to the customer service metric data and output to the front end of the data analysis platform, enriching the functions of the data analysis platform, improving the visualization level of customer service data and the support ability of the data analysis platform for customer service operations, and facilitating the timely reflection of customer service business problems, so that customer service business personnel can timely discover the current situation of customer service, thus being conducive to improving the quality of customer service operations.

[0171] Embodiment III

[0172] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of an intelligent customer service data analysis device disclosed in the embodiments of the present invention. Among them, Figure 3 the described intelligent customer service data analysis device can be applied to the process of collecting and analyzing customer service data, and the embodiments of the present invention do not make limitations. As Figure 3 shown, the intelligent customer service data analysis device may include:

[0173] A collection module 301, configured to collect initial customer service data corresponding to the customer service business from the customer service data source system associated with the data analysis platform according to the pre-determined customer service business;

[0174] A data analysis module 302, configured to input the initial customer service data into the data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service metric data corresponding to the customer service business, and the customer service metric data is used to be output to the front end of the data analysis platform, so that the front end displays the customer service metric data.

[0175] It can be seen that implementing Figure 3 the described device can directly import the initial customer service data in the customer service data source system into the data analysis platform, and analyze the initial customer service data based on the data analysis model of the data analysis platform to obtain customer service metric data, improving the efficiency and accuracy of the collection and analysis of customer service data, reducing the daily workload of the customer service business team. Moreover, by providing digital support for the collection and analysis of customer service data, it is conducive to realizing the closed-loop control and real-time control of customer service operations, thereby facilitating the promotion of the transparent and flat management of customer service operations and improving the quality of customer service.

[0176] In an alternative embodiment, as Figure 3 shown, the specific manner in which the data analysis model analyzes the initial customer service data to obtain the customer service metric data corresponding to the customer service business may include:

[0177] Determine the characteristic data corresponding to one or more data metrics of the customer service business according to the initial customer service data;

[0178] Analyze the characteristic data corresponding to each data metric according to the metric type of each data metric to obtain the customer service metric data corresponding to the customer service business;

[0179] Among them, the specific manner in which the data analysis model determines the characteristic data corresponding to one or more data metrics of the customer service business according to the initial customer service data may include:

[0180] Extract the underlying data corresponding to one or more data metrics of the customer service business from the initial customer service data;

[0181] For each data metric, determine the characteristic data corresponding to the data metric according to the underlying data corresponding to the data metric.

[0182] It can be seen that implementing Figure 3 the described device can also analyze the characteristic data based on the type of data metrics, improving the matching degree between the analysis method of the characteristic data and the metric type, and further improving the accuracy of the characteristic data analysis. In addition, by extracting the underlying data from the initial customer service data and then determining the characteristic data from the underlying data, it is beneficial to gradually reduce the unnecessary interference information in the customer service data and improve the efficiency and accuracy of the customer service data analysis.

[0183] In another alternative embodiment, as Figure 3 shown, for each data metric, the specific manner in which the data analysis model determines the characteristic data corresponding to the data metric according to the underlying data corresponding to the data metric may include:

[0184] Judge whether the underlying data corresponding to the data metric meets the dimensional condition of the data metric;

[0185] When the judgment result is yes, determine the underlying data corresponding to the data metric as the characteristic data corresponding to the data metric;

[0186] When the judgment result is no, perform a feature extraction operation on the underlying data corresponding to the data metric according to the data dimension corresponding to the data metric to obtain the characteristic data corresponding to the data metric;

[0187] Among them, for each data metric, the specific manner in which the data analysis model judges whether the underlying data corresponding to the data metric meets the dimensional condition of the data metric may include:

[0188] Determine whether all data dimensions corresponding to the data metric are included in the underlying data corresponding to the data metric. When the determination result is yes, determine that the underlying data corresponding to the data metric meets the dimensional condition of the data metric.

[0189] It can be seen that implementing Figure 3 the described device can also perform feature extraction operations on the underlying data to obtain feature data only when the underlying data does not meet the dimensional condition of the data metric, reducing unnecessary operations and facilitating improving the coincidence degree between the data dimension of the feature data and the data dimension of the data metric, thereby improving the accuracy and reliability of feature data extraction. In addition, determining that it meets the dimensional condition when the underlying data includes all data dimensions corresponding to the data metric is conducive to improving the comprehensiveness of the data dimension of customer service data, and thus conducive to improving the comprehensiveness and accuracy of customer service data analysis.

[0190] In another alternative embodiment, as Figure 3 shown, the initial customer service data includes one or more data combinations;

[0191] The specific ways for the data analysis model to determine the underlying data corresponding to one or more data metrics of the customer service business from the initial customer service data may include:

[0192] Filter all data combinations of the initial customer service data according to the screening keywords corresponding to one or more data metrics of the customer service business to obtain the target data combinations matching each data metric as the underlying data corresponding to the data metric; and / or,

[0193] Match all data metrics and all data combinations according to the metric identifiers corresponding to one or more data metrics of the customer service business and the data identifiers corresponding to all data combinations of the initial customer service data to obtain the target data combinations matching each data metric as the underlying data corresponding to the data metric.

[0194] It can be seen that implementing Figure 3 the described device can also screen the corresponding underlying data from the initial customer service data according to the screening keywords or data identifiers corresponding to the data metrics, which is conducive to improving the accuracy and efficiency of underlying data screening and reducing the possibility of incomplete underlying data.

[0195] In another alternative embodiment, as Figure 3 shown, the specific ways for the data analysis model to analyze the feature data corresponding to each data metric to obtain the customer service metric data corresponding to the customer service business may include:

[0196] For each data metric with the first preset type of metric type, determine the feature data corresponding to the data metric as the customer service metric data corresponding to the customer service business;

[0197] For each data metric with the second preset type of metric type, analyze the feature data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business.

[0198] It can be seen that implementing Figure 3 the described device can also adopt different methods for different types of data metrics to determine the customer service metric data according to the feature data, improving the flexibility and diversity of customer service data analysis. Moreover, directly determining the feature data of the data metrics of the first preset type as the customer service metric data improves the analysis efficiency of customer service data, and analyzing the feature data of the data metrics of the second preset type using the corresponding algorithm improves the accuracy and reliability of customer service data analysis.

[0199] In yet another alternative embodiment, as Figure 3 shown, for each data metric with the second preset type of metric type, the specific ways in which the data analysis model analyzes the feature data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business may include:

[0200] Perform operations on the feature data corresponding to the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business; or,

[0201] According to the calculation algorithm corresponding to the data metric, determine at least one associated data metric that matches the data metric among all data metrics, and perform operations on the feature data corresponding to the data metric and the feature data corresponding to at least one associated data metric that matches the data metric according to the calculation algorithm corresponding to the data metric to obtain the customer service metric data corresponding to the customer service business.

[0202] It can be seen that implementing Figure 3 the described device can also determine whether to call the feature data of other associated data metrics to participate in the operation of the feature data corresponding to the current data metric according to the calculation algorithm corresponding to the data metric, reducing the system redundancy caused by setting judgment rules for each data metric, and being beneficial to improving the flexibility, diversity, and accuracy of customer service data analysis.

[0203] In yet another alternative embodiment, as Figure 4 shown, the device may further include:

[0204] A generation module 303 is configured to generate a visualization page corresponding to the customer service service according to the customer service metric data. The visualization page is used to be output to the front end so that the front end can display the customer service metric data based on the visualization page.

[0205] Among them, the customer service metric data includes the analysis results corresponding to one or more data metrics of the customer service service. The specific manner in which the generation module generates a visualization page corresponding to the customer service service may include:

[0206] Determine the sub-template corresponding to each data metric in the pre-determined template file;

[0207] For each data metric, generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric;

[0208] Combine the visualization units corresponding to all data metrics to obtain a visualization page corresponding to the customer service service.

[0209] It can be seen that implementing Figure 4 The described device can generate a visualization service according to the customer service metric data and output it to the front end of the data analysis platform, enriching the functions of the data analysis platform, improving the visualization level of customer service data and the support ability of the data analysis platform for customer service services, and being conducive to timely reflecting customer service business problems so that customer service business personnel can timely discover the current situation of customer service, thereby being conducive to improving the quality of customer service operations. In addition, by importing the analysis results corresponding to the data metrics into the sub-templates corresponding to the data metrics to generate visualization units, it is conducive to improving the generation efficiency of the visualization page, and by combining the visualization units to obtain the visualization page, it is conducive to improving the generation flexibility of the visualization page and reducing system redundancy and costs caused by designing and storing multiple visualization templates.

[0210] In another optional embodiment, as Figure 4 shown, for each data metric, the specific manner in which the generation module generates a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric may include:

[0211] Perform a keyword replacement operation on the template keywords in the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain a visualization unit corresponding to the data metric; and / or,

[0212] Perform a keyword filling operation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain a visualization unit corresponding to the data metric; and / or,

[0213] Generate a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the template form of the sub-template corresponding to the data metric; and / or,

[0214] Perform information annotation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric to obtain a visualization unit corresponding to the data metric.

[0215] It can be seen that implementing Figure 4 the described device can generate a visualization unit corresponding to the data metric by performing operations such as keyword replacement, keyword filling, information annotation on the sub-template corresponding to the data metric or according to the template form, improving the flexibility and diversity of generating the visualization unit.

[0216] Embodiment Four

[0217] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of another customer service data intelligent analysis device disclosed in the embodiments of the present invention. As Figure 5 shown, the customer service data intelligent analysis device may include:

[0218] A memory 401 storing executable program code;

[0219] A processor 402 coupled to the memory 401;

[0220] The processor 402 calls the executable program code stored in the memory 401 and executes the steps in the customer service data intelligent analysis method described in Embodiment One or Embodiment Two of the present invention.

[0221] Embodiment Five

[0222] The embodiments of the present invention disclose a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the customer service data intelligent analysis method described in Embodiment One or Embodiment Two of the present invention.

[0223] Embodiment Six

[0224] The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the customer service data intelligent analysis method described in Embodiment One or Embodiment Two.

[0225] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0226] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium capable of carrying or storing data.

[0227] Finally, it should be noted that the intelligent analysis method and device for customer service data disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent analysis of customer service data, characterized in that The method includes: Collecting initial customer service data corresponding to the customer service business from a customer service data source system associated with a data analysis platform according to a pre-determined customer service business; Inputting the initial customer service data into a data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service index data corresponding to the customer service business, and the customer service index data is used to be output to the front end of the data analysis platform, so that the front end displays the customer service index data; Wherein, the data analysis model analyzes the initial customer service data to obtain customer service index data corresponding to the customer service business, including: The data analysis model extracts underlying data corresponding to one or more data indicators of the customer service business from the initial customer service data; For each of the data indicators, the data analysis model determines whether all data dimensions corresponding to the data indicator are included in the underlying data corresponding to the data indicator; if so, the underlying data corresponding to the data indicator is determined as the characteristic data corresponding to the data indicator; if not, according to the data dimensions corresponding to the data indicator, a feature extraction operation is performed on the underlying data corresponding to the data indicator to obtain the characteristic data corresponding to the data indicator; The data analysis model analyzes the characteristic data corresponding to each data indicator according to the indicator type of each data indicator to obtain customer service index data corresponding to the customer service business.

2. The intelligent analysis method for customer service data according to claim 1, characterized in that The initial customer service data includes one or more data combinations; The data analysis model determines underlying data corresponding to one or more data indicators of the customer service business from the initial customer service data, including: The data analysis model filters all the data combinations of the initial customer service data according to filtering keywords corresponding to one or more data indicators of the customer service business to obtain target data combinations matching each data indicator as the underlying data corresponding to the data indicator; and / or, The data analysis model matches all the data indicators and all the data combinations according to the indicator identifiers corresponding to one or more data indicators of the customer service business and the data identifiers corresponding to all the data combinations of the initial customer service data to obtain target data combinations matching each data indicator as the underlying data corresponding to the data indicator.

3. The intelligent analysis method for customer service data according to claim 1 or 2, characterized in that, The data analysis model analyzes the characteristic data corresponding to each data indicator according to the indicator type of each data indicator to obtain customer service index data corresponding to the customer service business, including: For each data indicator with an indicator type of a first preset type, the data analysis model determines the characteristic data corresponding to the data indicator as the customer service index data corresponding to the customer service business; For each data indicator with an indicator type of a second preset type, the data analysis model analyzes the characteristic data corresponding to the data indicator according to the calculation algorithm corresponding to the data indicator to obtain customer service index data corresponding to the customer service business.

4. The intelligent analysis method for customer service data according to claim 3, wherein, For each of the data metrics whose metric type is the second preset type, the data analysis model analyzes the feature data corresponding to the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service business, including: The data analysis model operates on the feature data corresponding to the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service business; or, The data analysis model determines at least one associated data metric that matches the data metric among all the data metrics according to the calculation algorithm corresponding to the data metric, and operates on the feature data corresponding to the data metric and the feature data corresponding to at least one associated data metric that matches the data metric according to the calculation algorithm corresponding to the data metric, and obtains the customer service metric data corresponding to the customer service business.

5. The intelligent analysis method for customer service data according to any one of claims 1, 2, and 4, characterized in that The method further includes: Generating a visualization page corresponding to the customer service business according to the customer service metric data, where the visualization page is used to be output to the front end, so that the front end displays the customer service metric data based on the visualization page; Wherein, the customer service metric data includes analysis results corresponding to one or more data metrics of the customer service business, and generating a visualization page corresponding to the customer service business according to the customer service metric data includes: Determining a sub-template corresponding to each data metric in a pre-determined template file; For each data metric, generating a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric; Combining the visualization units corresponding to all the data metrics to obtain a visualization page corresponding to the customer service business.

6. The intelligent analysis method for customer service data according to claim 5, wherein, For each data metric, generating a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the sub-template corresponding to the data metric includes: Performing a keyword replacement operation on the template keywords in the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric, to obtain a visualization unit corresponding to the data metric; and / or, Performing a keyword filling operation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric, to obtain a visualization unit corresponding to the data metric; and / or, Generating a visualization unit corresponding to the data metric according to the analysis result corresponding to the data metric and the template form of the sub-template corresponding to the data metric; and / or, Performing information annotation on the sub-template corresponding to the data metric according to the analysis result corresponding to the data metric, to obtain a visualization unit corresponding to the data metric.

7. An intelligent customer service data analysis device, characterized in that, The apparatus includes: An acquisition module, configured to acquire initial customer service data corresponding to the customer service business from a customer service data source system associated with a data analysis platform according to a pre-determined customer service business; A data analysis module, configured to input the initial customer service data into a data analysis model corresponding to the data analysis platform, so that the data analysis model analyzes the initial customer service data to obtain customer service metric data corresponding to the customer service business, and the customer service metric data is used to be output to the front end of the data analysis platform, so that the front end displays the customer service metric data; Wherein, the manner in which the data analysis model analyzes the initial customer service data to obtain the customer service metric data corresponding to the customer service business specifically includes: extracting underlying data corresponding to one or more data metrics of the customer service business from the initial customer service data; For each of the data metrics, determining whether the underlying data corresponding to the data metric includes all data dimensions corresponding to the data metric; if so, determining the underlying data corresponding to the data metric as the feature data corresponding to the data metric; if not, performing a feature extraction operation on the underlying data corresponding to the data metric according to the data dimensions corresponding to the data metric to obtain the feature data corresponding to the data metric; analyzing the feature data corresponding to each data metric according to the metric type of each data metric to obtain the customer service metric data corresponding to the customer service business.

8. An intelligent customer service data analysis device, characterized in that, The device includes: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the intelligent analysis method for customer service data according to any one of claims 1-6.

Images