Telephone service data processing method, apparatus and electronic device

Abstract

An embodiment of the present application provides a method, device and electronic device for processing telephone service data, belonging to the technical field of data processing. The method includes: retrieving the processing progress data corresponding to the legacy service data and the basic emotion score of the user; determining the second dynamic emotion score and the rolling emotion score; when it is detected that the first real-time emotion score reaches the first preset emotion threshold, obtaining the customer service agent status information; determining the access seat position of the user according to the customer service agent status information, the first real-time emotion score and the pre-stored user access seat waiting queue information; connecting the user terminal of the user to the corresponding target idle seat according to the access seat position of the user, and obtaining the current demand information of the user; sending the historical service process data and the current demand information to the target idle seat. This method is used to achieve the effect of serving more users while taking into account the service quality of special users in the scenario of limited and dynamically changing service resources.

Description

Technical Field

[0001] This application relates to the technical field of data processing, specifically to the technical field of telephone service data, and particularly to a method, device, and electronic device for processing telephone service data. Background Art

[0002] With the popularization of telephone services, users have higher requirements for the quality of telephone services and the interactive experience of telephone services. Generally, telephone services support intelligent voice and key navigation. When intelligent voice interaction and key navigation cannot meet the needs of users, it is necessary to connect to a live customer service agent.

[0003] However, in the existing telephone service process, there is still a problem of low utilization rate of service resources in the scenario of dynamic change of service resources, which leads to a low solution rate of user demands. Summary of the Invention

[0004] Embodiments of this application provide a method, device, and electronic device for processing telephone service data, aiming to serve more users in the scenario of limited and dynamically changing service resources while taking into account the service quality effect of special users.

[0005] In a first aspect, embodiments of this application provide a method for processing telephone service data, including:

[0006] Obtain historical service process data of users using telephone services within a preset historical time period, where the historical service process data is obtained in response to the authorization operation of the users;

[0007] When it is detected that there is legacy service data in the historical service process data, the corresponding processing progress data and the basic emotion score of the user are retrieved, and the processing progress data is broadcast to the user to obtain user feedback data;

[0008] According to the user feedback data, determine a first dynamic emotion score, and according to the historical service process data and a preset reduction coefficient, determine a second dynamic emotion score and a rolling emotion score;

[0009] According to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score, determine a first real-time emotion score, and when it is detected that the first real-time emotion score reaches a first preset emotion threshold, obtain the status information of the customer service agent;

[0010] According to the status information of the customer service agent, the first real-time emotion score, and the pre-stored information of the user accessing the agent waiting queue, determine the access seat position of the user;

[0011] Connect the user's client to the corresponding target idle seat according to the access seat position of the user, and obtain the current demand information of the user;

[0012] Send the historical service process data and the current demand information to the target idle seat to obtain demand processing information, where the demand processing information is generated after the demand interaction operation between the target idle seat and the user ends.

[0013] In a possible implementation manner, the historical service process data includes the number of access telephone service times of the user for each date and the multiple service emotion scores of the user for each date; correspondingly, the determining the second dynamic emotion score and the rolling emotion score according to the historical service process data and the preset reduction coefficient includes: determining the real-time influence degree of each date and the number of access telephone service times of the current date according to the number of access telephone service times of each date; performing a comparison and scoring process on the number of access telephone service times of the current date and the preset access number threshold to determine the second dynamic emotion score; performing a score comparison process on the multiple service emotion scores of each date, and determining the service emotion score with the largest value among the multiple service emotion scores as the rolling emotion reference value of the date; determining the initial rolling emotion value of the date according to the rolling emotion reference value and the real-time influence degree of each date; determining the daily rolling emotion target value according to the rolling emotion value of each date and the preset reduction coefficient, and determining all the rolling emotion target values as the rolling emotion score, where the rolling emotion target value is a value greater than 0.

[0014] In a possible implementation manner, the formula for determining the real-time influence degree of each date according to the number of access telephone service times of each date is:

[0015] Deg i =

[0016] In the formula, Deg i is the real-time influence degree of the i-th date, cn i is the number of access telephone service times of the i-th date, where i is an integer less than or equal to 0;

[0017] The formula for determining the initial rolling emotion value of the date according to the rolling emotion reference value and the real-time influence degree of each date is:

[0018] D i = Deg i ×D max(i)

[0019] In the formula, D i is the rolling emotion score of the i-th date, Dmax(i) is the rolling emotion benchmark value for the i-th date, where i is an integer less than or equal to 0, and i = 0 represents the date corresponding to the acquisition of the user feedback data.

[0020] In a possible implementation manner, the determining the first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score includes: performing a summation process on the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score to obtain the first real-time emotion score.

[0021] In a possible implementation manner, the pre-storing the user access agent waiting queue information includes the access agent queues of all users to be served and the waiting priorities of each user to be served; correspondingly, the determining the access agent seat position of the user according to the customer service agent status information, the first real-time emotion score, and the access agent waiting sequence of existing users includes: detecting the number of idle agent seats according to the customer service agent status information, and when it is detected that the number of idle agent seats is zero, then performing a priority calculation process according to the first real-time emotion score to obtain the waiting priority of the user; comparing and matching the waiting priority of the user with the waiting priorities of each user to be served in turn to determine the access agent seat position of the user in the access agent queue.

[0022] In a possible implementation manner, it further includes: when it is detected that the first real-time emotion score is lower than the first preset emotion threshold, then acquiring the actual demand information of the user; performing identification and analysis processing on the actual demand information of the user to obtain the service task information to be served; calling the customer service agent status information according to the service task information to be served, and jumping to the step of determining the access agent seat position of the user according to the customer service agent status information, the first real-time emotion score, and the pre-stored user access agent waiting queue information.

[0023] In a possible implementation manner, before connecting the user terminal of the user to the corresponding target idle agent seat according to the access agent seat position of the user, it further includes: acquiring the user terminal connection status information of the user, and when it is detected that the user terminal connection status is the active hang-up state, then generating a second real-time emotion score; determining the emotion score to be apologized according to the first real-time emotion score and the second real-time emotion score; when it is detected that the emotion score to be apologized reaches the second preset emotion threshold, then generating an apology message and sending the apology message to the user terminal of the user.

[0024] In a possible implementation manner, when identifying, analyzing, and processing according to the actual demand information of the user to obtain the to-be-served task information, it further includes: performing voice analysis and processing on the actual demand information of the user to obtain the third real-time emotion score of the user; the demand processing information includes user satisfaction evaluation information; correspondingly, after obtaining the demand processing information, it further includes: performing analysis and processing according to the user satisfaction evaluation information to obtain the fourth real-time emotion score; determining the service emotion score of the user for this time according to the first real-time emotion score, the second real-time emotion score, the third real-time emotion score, and the fourth real-time emotion score.

[0025] In a second aspect, an embodiment of the present application provides a telephone service data processing device, including:

[0026] A voice interaction module, configured to obtain historical service process data of a user using a telephone service within a preset historical time period, where the historical service process data is obtained in response to the authorization operation of the user;

[0027] The voice interaction module is further configured to, when detecting that there is legacy service data in the historical service process data, retrieve the processing progress data corresponding to the legacy service data and the basic emotion score of the user, and perform a broadcast process on the processing progress data to the user to obtain user feedback data;

[0028] A dynamic emotion scoring processing module, configured to determine a first dynamic emotion score according to the user feedback data, and determine a second dynamic emotion score and a rolling emotion score according to the historical service process data and a preset reduction coefficient;

[0029] The dynamic emotion scoring processing is further configured to determine a first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score, and when detecting that the first real-time emotion score reaches a first preset emotion threshold, obtain the customer service agent seat status information;

[0030] A service resource scheduling module, configured to determine the access seat position of the user according to the customer service agent seat status information, the first real-time emotion score, and the pre-stored user access seat waiting queue information;

[0031] The service resource scheduling module is further configured to connect the user terminal of the user to the corresponding target idle seat according to the access seat position of the user, and obtain the current demand information of the user;

[0032] The service resource scheduling module is further configured to send the historical service process data and the current demand information to the target idle agent to obtain demand processing information, where the demand processing information is generated after the demand interaction operation between the target idle agent and the user ends.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0036] The telephone service data processing method, device and electronic device provided by the embodiments of the present application, after a user using a telephone service accesses the telephone service, first detect whether there is legacy service data, select and call the corresponding telephone service resources to perform a broadcast process on the processing progress data to obtain user feedback information, then perform real-time dynamic scoring according to the user feedback information to determine the first dynamic emotion score, then determine the second dynamic emotion score and the rolling emotion score according to the historical service process data and the preset reduction coefficient, and further determine the first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, and when it is detected that the first real-time emotion score reaches the first preset emotion threshold, obtain the status information of the customer service agent, so as to subsequently connect the user to the target idle agent, and then send the historical service process data and the current demand information to the target idle agent to obtain demand processing information. Dynamically call the service resources of the telephone service for the user, and provide service reference information for the customer service agent, so that the customer service agent can better solve the user's demand information. To achieve serving more users while taking into account the service quality of special users and improving the user service quality and service experience in the scenario of limited and dynamically changing service resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0038] Figure 1 It is a schematic diagram of the application scenario of the telephone service data processing method provided by the embodiment of the present application;

[0039] Figure 2 It is a schematic flowchart of the telephone service data processing method provided by the embodiment of the present application;

[0040] Figure 3Schematic structural diagram of the telephone service data processing device provided by the embodiment of the present application;

[0041] Figure 4 Schematic structural diagram of the electronic device provided by the embodiment of the present application.

[0042] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be given later. These drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0043] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0044] In the technical solution of the present application, the processing of collection, storage, use, processing, transmission, provision, and disclosure of user data and other information involved has been authorized by the user and complies with the provisions of relevant laws and regulations, and does not violate public order and good customs. It should be noted that in the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be regarded as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0045] In the prior art, the inventor found that in the existing telephone service process, since it is impossible to dynamically evaluate the user's emotion and tolerance level throughout the process and call the corresponding telephone service resources according to the evaluation results, there is a lack of reasonable call of service resources in the dynamic change scenarios of sufficient service resources and tight service resources. Therefore, how to serve more users with limited service resources while taking into account the service quality of special users is an urgent problem to be solved by the present invention.

[0046] In response to the above technical problems, the inventor proposed the following inventive concept: by increasing the dynamic analysis of the service data generated during the user's telephone service process, obtaining a service dynamic score for the user, and calling the corresponding service resources for the user according to the real-time service dynamic score, so as to complete the user service more efficiently, so as to serve more users in the scenario of limited and dynamically changing service resources while taking into account the service quality of special users and improving the user service quality and service experience.

[0047] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be elaborated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0048] Figure 1 It is a schematic diagram of the application scenario of the telephone service data processing method provided by the embodiment of this application. As Figure 1 shown, this application scenario includes: a server 101, a user terminal 102, and an agent terminal 103.

[0049] Among them, the server 101 is a service background for providing telephone services. The user terminal 102 can be the terminal device of a user who intends to use telephone services. The agent terminal 103 is the terminal device of an artificial customer service agent uniformly managed and scheduled by the server 101. After establishing a communication connection between the server 101 and the user terminal 102, it provides intelligent voice interaction and keypad navigation for the user, processes the historical service process data of this user, executes each step of the telephone service data processing method, allocates a suitable artificial customer service agent seat for the user, and transfers the telephone service to the agent terminal 103 of the corresponding artificial customer service agent seat, so that the artificial customer service agent can provide higher-quality telephone services for the user, thereby realizing serving more users in the scenario of limited and dynamically changing service resources while taking into account the service quality of special users and improving the user service quality and service experience.

[0050] Figure 2 It is a schematic flowchart of the telephone service data processing method provided by the embodiment of this application. As Figure 2 shown, this method includes:

[0051] S201: Obtain the historical service process data of the user using the telephone service within a preset historical time period, where the historical service process data is obtained after the user authorizes.

[0052] In this embodiment, the preset historical time period can be a time period preset in the server, for example, within one week or three days before the user using the telephone service this time. The historical service process data can be the data generated during the user's use of the telephone service within the preset historical time period, such as: user demand information, a solution record or an unsolved solution record generated after the telephone service ends.

[0053] S202: When it is detected that there is legacy service data in the historical service process data, retrieve the processing progress data corresponding to the legacy service data and the user's basic emotion score, and broadcast the processing progress data to the user to obtain user feedback data.

[0054] In this embodiment, the detection of whether there is legacy service data in the historical service process data can be performed by calling software or automated tools with a retrieval function to perform a retrieval operation on the historical service process data to obtain the processing progress data corresponding to the unresolved telephone service of the user. The legacy service data can be the user demand information recorded when the customer service agent previously connected cannot provide a specific solution on the spot, or it can be the user demand information collected by the server when the user suddenly hangs up the phone when making a demand. The processing progress data can be the demand processing progress description information related to the user's most recent unresolved demand information in the legacy service data, for example: the current demand information of question A is in the verification step after the background approval, and the current processing progress is 80%.

[0055] In this embodiment, retrieving the legacy service data may be a process of retrieving the user's most recent unresolved demand information and the processing progress related to the demand information from the historical service process data for subsequent use.

[0056] In this embodiment, the processing progress data is broadcasted to the user by the server sending the processing progress data to the user's terminal, and the user is informed of the process of processing the progress data in the form of telephone voice broadcast at the user terminal. The user feedback data may be the operation performed by the user at the user terminal with respect to the broadcasted processing progress data, for example, the user feedback data may indicate a signal that the user interrupted the broadcast process at the user terminal or a signal that the broadcast process was not interrupted.

[0057] S203: Determine a first dynamic emotion score according to the user feedback data, and determine a second dynamic emotion score and a rolling emotion score according to the historical service process data and a preset reduction coefficient.

[0058] In this embodiment, if the user feedback data is a signal indicating that the user interrupted the broadcast process, it means that the user has a more urgent demand or is in a bad mood. At this time, the user feedback data can be identified and analyzed to perform a scoring operation to determine the first dynamic emotion score, which can be based on a preset user portrait and score correspondence. When the user feedback data is a signal indicating that the user did not interrupt the broadcast, the first dynamic emotion score can be directly 0, or the first dynamic emotion score is not generated.

[0059] Specifically, in an optional embodiment of the present application, the historical service process data includes the number of access telephone services of the user on each date and the multiple service emotion scores of the user on each date; accordingly, in step S203, the second dynamic emotion score and the rolling emotion score are determined according to the historical service process data and the preset reduction coefficient, including:

[0060] S203a: Determine the real-time impact level for each date and the number of incoming call service times for the current date based on the number of incoming call service times for each date.

[0061] In this embodiment, determining the real-time impact level for each date can be the result obtained by inputting the number of incoming call service times for each date into pre-stored calculation software for numerical calculation.

[0062] In an alternative embodiment of the present application, the calculation formula for determining the real-time impact level for each date based on the number of incoming call service times for each date is:

[0063] Deg i =

[0064] In the formula, Deg i is the real-time impact level for the i-th date, and cn i is the number of incoming call service times for the i-th date, where i is an integer less than or equal to 0.

[0065] In this embodiment, when i = 0, it represents the current date when step S201 is executed. When i = -1, it refers to the date of the day before the current date. When i = -2, it refers to the date of the two days before the current date, and so on. Generally, considering that the user's emotional calm duration is generally 3 days, in this embodiment, i is less than or equal to 3. cn i can be any integer value. For example, when cn i = 4, it means that the number of times the call service is connected on the i-th date is 4 times, and the corresponding real-time impact level Deg i is 2.

[0066] S203ab: Compare and score the number of incoming call service times for the current date with a preset access number threshold to determine the second dynamic emotion score.

[0067] In this embodiment, the comparison and scoring process can be to compare the numerical values of the number of incoming call service times for the current date with the preset access number threshold. When the preset access number threshold is larger, the second dynamic emotion score is counted as 0. Otherwise, the second dynamic emotion score is counted as a preset score, such as 10 points, 20 points, etc. In this embodiment, the preset access number threshold can be a preset fixed value. For example, the preset access number threshold is 3 times.

[0068] S203c: Perform a score comparison process based on the multiple service emotion scores for each date, and determine the rolling emotion benchmark value for the date as the service emotion score with the largest numerical value among the multiple service emotion scores.

[0069] In this embodiment, the score comparison process may be to compare the numerical magnitudes of the multiple service emotion scores for each date in sequence for sorting, or to retain the larger service emotion value after each comparison until all service emotion scores have been compared. The remaining service emotion score is the service emotion score with the largest value, and this service emotion score with the largest value is the rolling emotion baseline value for that date. For example, if the 4 service emotion scores for the date of the day before the execution of step S201 are 65 points, 70 points, 68 points, and 60 points respectively, then after step S203c, the rolling emotion baseline value for the date of the day before is 70 points.

[0070] S203d: Determine the initial rolling emotion value for each date based on the rolling emotion baseline value and the real-time influence degree of each date.

[0071] In this embodiment, determining the initial rolling emotion value for a date may be a process of calculating scores by using a preset score calculation software, tool, or algorithm for the input rolling emotion baseline value and real-time influence degree of each date.

[0072] In an alternative embodiment of the present application, the calculation formula for step S203d is:

[0073] D i = Deg i ×D max(i)

[0074] In the formula, D i is the rolling emotion score for the i-th date, D max(i) is the rolling emotion baseline value for the i-th date, where i is an integer less than or equal to 0, and i = 0 represents the date corresponding to obtaining the user feedback data.

[0075] In this embodiment, D0 represents the rolling emotion score for the current date when step S201 is executed. D -1 represents the rolling emotion score for the date of the day before the current date, D -2 represents the rolling emotion score for the date of two days before the current date, and so on. Generally, the absolute value of i is taken as an integer less than or equal to 3.

[0076] S203e: Determine the daily rolling emotion target value based on the rolling emotion value of each date and a preset reduction coefficient, and determine all the rolling emotion target values as the rolling emotion scores, where the rolling emotion target value is a value greater than 0.

[0077] In this embodiment, the preset reduction coefficient may be a fixed proportional value preset according to the date. For example, the reduction period of the rolling emotion score is 3 days, that is, the emotion influence degree decreases according to the 3-day ratio. The preset reduction coefficient for the current date D0 is a, and the D for the date of the day before-1 The preset reduction coefficient is b, and D of the dates of the first two days -2 The preset reduction coefficient is c, and the preset reduction coefficient of the date one day further back can be set to 0, where 1≥a>b>c>0.

[0078] In an optional embodiment of the present application, the calculation formula of step S203e is:

[0079] D sum = D0×a + D -1 ×b + D -2 ×c

[0080] In the formula, D sum represents the rolling emotion score, D0×a represents the rolling emotion target value of the current date when step S203e is executed, D -1 ×b represents the rolling emotion target value of the date one day before the current date, D -2 ×c represents the rolling emotion target value of the dates of the two days before the current date, and a, b, and c represent preset reduction coefficients with a numerical range of 0 to 1. For example: assuming that the reduction period of the rolling emotion score is 3 days, that is, the emotional impact degree decreases according to a 3-day ratio, the preset reduction coefficient of the current date D0 is 1, and D -1 of the previous day has a preset reduction coefficient of 0.7, and D -2 of the two days before has a preset reduction coefficient of 0.3.

[0081] S204: Determine the first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score, and when it is detected that the first real-time emotion score reaches the first preset emotion threshold, obtain the customer service agent status information.

[0082] In this embodiment, the process of determining the first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score can be a process of calculating the score using a score calculation software, tool, or algorithm.

[0083] In an optional embodiment of the present application, in step S204, determining the first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score includes: performing a summation process on the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score to obtain the first real-time emotion score.

[0084] For example: The first real-time emotion score = rolling emotion score + first dynamic emotion score + second dynamic emotion score + basic emotion score.

[0085] In this embodiment, when it is detected that the first real-time emotion score reaches the first preset emotion threshold, it indicates that the user's current emotion is poor, and it is necessary to quickly call the telephone service resources to solve the user's appeal information. At this time, it is necessary to obtain the customer service agent status information by calling the working status of each agent terminal communicatively connected thereto through the server.

[0086] S205: Determine the user's access seat order according to the customer service agent status information, the first real-time emotion score, and the pre-stored user access seat waiting queue information.

[0087] In this embodiment, determining the user's access seat order may be a process of arranging the user into the pre-stored user access seat waiting queue information according to the first real-time emotion score of the user to obtain the user's access seat order.

[0088] In an alternative embodiment of the present application, the pre-stored user access seat waiting queue information includes the waiting access seat queue of all users to be served and the waiting priority of each user to be served; correspondingly, in step S205, determining the user's access seat order according to the customer service agent status information, the first real-time emotion score, and the access seat waiting sequence of existing users includes:

[0089] S205a: Detect the number of idle seats according to the customer service agent status information, and when it is detected that the number of idle seats is zero, perform priority calculation processing according to the first real-time emotion score to obtain the user's waiting priority.

[0090] In this embodiment, the customer service agent status information includes information on whether each customer service is idle, and the customer service agent status information is retrieved to obtain the number of customer service seats in the idle state. When it is detected that the number of idle seats is zero, it indicates that there is no idle seat currently, and it is necessary to schedule appropriate telephone service resources for the user.

[0091] In this embodiment, performing priority calculation processing may be inputting the first real-time emotion score into an existing priority matching tool to output the corresponding waiting priority. The corresponding relationship between the emotion score and the waiting priority may be pre-stored in the priority matching tool, and the corresponding relationship may be a table. Generally, the higher the first real-time emotion score, the higher the waiting priority.

[0092] In an alternative embodiment of the present application, the service level of the user also needs to be considered, and the waiting priority of the user is determined by combining the service level and the first real-time emotion score. For example, if the first real-time emotion scores of two users are the same, and user A's service level is a four-star user (important user), while user B's service level is a two-star user (ordinary user), then the waiting priority corresponding to user A is higher than that of user B.

[0093] S205b: Compare and match the waiting priority of the user with the waiting priority of each user to be served in turn, so as to determine the access seat order of the user in the queue of seats to be accessed.

[0094] In this embodiment, the matching process refers to comparing the waiting priority of the user with the waiting priority of each user to be served, finding the user to be served with the same or similar waiting priority, and determining the access seat order of the user in the queue of seats to be accessed accordingly.

[0095] S206: Connect the user terminal of the user to the corresponding target idle seat according to the access seat order of the user, and obtain the current demand information of the user.

[0096] In this embodiment, when there is an idle customer service seat, the corresponding idle customer service seat is matched as the target idle seat according to the access seat order of the user, and the server transfers the telephone service to the corresponding target idle seat, so that the customer service of the idle seat provides telephone service for the user, and at the same time obtains the demand information of the user to send to the target idle seat.

[0097] S207: Send the historical service process data and the current demand information to the target idle seat to obtain demand processing information, where the demand processing information is generated after the demand interaction operation between the target idle seat and the user ends.

[0098] In this embodiment, when the server transfers the telephone service of the user to the seat end of the target idle seat, the corresponding historical service process data and the current demand information are sent to the seat end together for display at the seat end, facilitating access by the target idle seat. The historical service process data here may include the basic user information of the user, the telephone service process data within a week, and potential service demands before transferring to the target idle seat, etc., which are background information helpful for the target idle seat to answer the user's questions.

[0099] In this embodiment, the demand processing information may be the satisfaction evaluation result of the user.

[0100] Based on the above embodiment, in an optional embodiment of the present application, the telephone service data processing method further includes:

[0101] Step A: When it is detected that the first real-time emotion score is lower than the preset emotion threshold, obtain the actual demand information of the user.

[0102] In this embodiment, when it is detected that the first real-time emotion score is lower than the preset emotion threshold, it means that common service resources such as intelligent voice interaction or button customer service can still be provided to the user without connecting to a human operator seat. At this time, only the actual demand information of the user needs to be obtained. The process of obtaining the actual demand information of the user may include asking the user about the service demand through a telephone service. The user speaks the specific content of the service demand through the telephone service, and this specific content is returned to the server as the actual demand information of the user.

[0103] Step B: Perform identification and analysis processing on the actual demand information of the user to obtain the to-be-served task information.

[0104] In this embodiment, the identification and analysis processing can be to use the existing semantic analysis large model, intention recognition neural network or software in the server to perform identification and analysis processing on the input actual demand information of the user, so as to output more accurate to-be-served task information.

[0105] Step C: Call the customer service seat status information according to the to-be-served task information, and jump to the step of determining the access seat position of the user according to the customer service seat status information, the first real-time emotion score and the pre-stored user access seat waiting queue information.

[0106] In this embodiment, call the customer service seat status information to confirm the number of idle customer service seats, and jump to step S205.

[0107] Based on the above embodiment, in an optional embodiment of the present application, the telephone service data processing method further includes before step S2206:

[0108] Step D: Obtain the user terminal connection status information of the user. When it is detected that the user terminal connection status is the active hang-up state, a second real-time emotion score is generated.

[0109] In this embodiment, the user terminal connection status information of the user refers to whether the server and the user's user terminal maintain a call connection state directly. When it is detected that the user terminal connection status is the active hang-up state, it means that the user may be dissatisfied with this telephone service. At this time, according to the pre-specified scoring rules, a second real-time emotion score can be generated.

[0110] Step E: Determine the to-be-apologized emotion score according to the first real-time emotion score and the second real-time emotion score.

[0111] In this embodiment, by performing a summation calculation on the first real-time emotion score and the second real-time emotion score, the to-be-apologized emotion score can be obtained.

[0112] Step F: When it is detected that the to-be-apologized emotion score reaches the second preset emotion threshold, an apology message is generated and sent to the user's user terminal.

[0113] In an alternative embodiment of the present application, when it is detected that the to-be-apologized emotion score does not reach the second preset emotion threshold, it indicates that there is no need to send the previous text message to the user, saving the service resources for sending text messages. At this time, this telephone service can be directly ended.

[0114] In this embodiment, the second preset emotion threshold can be a fixed emotion score reflecting that the user's emotion is relatively poor. For example, the second preset emotion threshold is 80 points. The apology text message can be automatically generated according to a pre-specified information template in combination with the user information of the current user. The apology text message can be sent from the server to the user's client through the communication network.

[0115] Based on the above embodiment, in the telephone service data processing method provided as an alternative embodiment of the present application, when identifying and analyzing the actual demand information of the user to obtain the to-be-served task information, it further includes:

[0116] Step G: Perform voice analysis processing on the actual demand information of the user to obtain the third real-time emotion score of the user.

[0117] In this embodiment, the pre-trained large voice recognition model can be called to perform voice analysis processing on the actual demand information of the user. Specifically, after analyzing the user's speech rate, tone, and other voice information that can reflect the user's emotion, the analysis result can be obtained. Based on this analysis result, the third real-time emotion score of the user can be generated.

[0118] In this embodiment, the demand processing information includes user satisfaction evaluation information.

[0119] Correspondingly, after obtaining the demand processing information, it further includes:

[0120] Step H: Perform analysis processing on the user satisfaction evaluation information to obtain the fourth real-time emotion score.

[0121] In this embodiment, the analysis processing of the user satisfaction evaluation information can be that the user directly presses a key to score the current telephone service process. For example: press 1 for very satisfied, press 0 for dissatisfied. The fourth real-time emotion score can be a score automatically generated by the scoring software.

[0122] Step J: Determine the emotion score of the user for this service according to the first real-time emotion score, the second real-time emotion score, the third real-time emotion score, and the fourth real-time emotion score. Then this telephone service can be ended.

[0123] In this embodiment, determining the service emotion score of the user this time can be to sum up the first real-time emotion score, the second real-time emotion score, the third real-time emotion score and the fourth real-time emotion score, or corresponding weights can be preset and calculated to obtain the service emotion score this time. For example: the service emotion score this time = y1 × the first real-time emotion score + y2 × the second real-time emotion score + y3 × the third real-time emotion score + y4 × the fourth real-time emotion score, where y1 + y2 + y3 + y4 = 1, and y1, y2, y3, and y4 are all positive numbers less than 1 and greater than 0.

[0124] In summary, the telephone service processing method provided by the embodiment of the present application, after the user using the telephone service accesses the telephone service, first detects whether there is legacy service data and selects to call the corresponding telephone service resources to perform a broadcast process on the processing progress data to obtain user feedback information, then performs real-time dynamic scoring according to the user feedback information to determine the first dynamic emotion score, and then determines the second dynamic emotion score and the rolling emotion score according to the historical service process data and the preset reduction coefficient. Furthermore, according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, the first real-time emotion score is determined, and when it is detected that the first real-time emotion score reaches the first preset emotion threshold, the status information of the customer service seat is obtained, so as to subsequently connect the user to the target idle seat, and then send the historical service process data and the current request information to the target idle seat to obtain the request processing information. Dynamically call the service resources of the telephone service for the user, and provide service reference information for the customer service seat, so that the customer service seat can better solve the user's request information. In order to achieve serving more users while taking into account the service quality of special users in the scenario of limited and dynamically changing service resources, and improving the user service quality and service experience.

[0125] Figure 3 It is a structural schematic diagram of a telephone service data processing device provided by an embodiment of the present application, as Figure 3 shown, the telephone service data processing device provided in this embodiment includes: a voice interaction module 31, a dynamic emotion scoring processing module 32 and a service resource scheduling module 33.

[0126] Among them, the voice interaction module 31 is used to obtain the historical service process data of the user using the telephone service within a preset historical time period, where the historical service process data is obtained in response to the user's authorization operation.

[0127] The voice interaction module 31 is further used to, when it is detected that there is legacy service data in the historical service process data, retrieve the processing progress data corresponding to the legacy service data and the basic emotion score of the user, and perform a broadcast process on the processing progress data to the user to obtain user feedback data;

[0128] The dynamic emotion score processing module 32 is used to determine a first dynamic emotion score according to user feedback data, and determine a second dynamic emotion score and a rolling emotion score according to historical service process data and a preset reduction coefficient.

[0129] The dynamic emotion score processing module 32 is further used to determine a first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score, and when it is detected that the first real-time emotion score reaches a first preset emotion threshold, obtain the customer service agent status information.

[0130] The service resource scheduling module 33 is used to determine the access seat position of the user according to the customer service agent status information, the first real-time emotion score, and the pre-stored user access seat waiting queue information.

[0131] The service resource scheduling module 33 is further used to connect the user's client to the corresponding target idle seat according to the user's access seat position and obtain the current demand information of the user.

[0132] The service resource scheduling module is further used to send the historical service process data and the current demand information to the target idle seat to obtain demand processing information, where the demand processing information is generated after the demand interaction operation between the target idle seat and the user ends.

[0133] In an optional embodiment of the present application, the historical service process data includes the number of access to telephone services per day of the user and the multiple service emotion scores per day of the user; correspondingly, the dynamic emotion score processing module 32 is specifically used to: determine the real-time influence degree of each date and the number of access to telephone services on the current date according to the number of access to telephone services per day; perform a comparison and scoring process on the number of access to telephone services on the current date and a preset access number threshold to determine the second dynamic emotion score; perform a score comparison process on the multiple service emotion scores per day, and determine the service emotion score with the largest value among the multiple service emotion scores as the rolling emotion benchmark value of the date; determine the initial rolling emotion value of the date according to the rolling emotion benchmark value and the real-time influence degree of each date; determine the daily rolling emotion target value according to the rolling emotion value of each date and a preset reduction coefficient, and determine all the rolling emotion target values as the rolling emotion score, where the rolling emotion target value is a value greater than 0.

[0134] In an optional embodiment of the present application, the dynamic emotion score processing module 32 is specifically used to: the formula for determining the real-time influence degree of each date according to the number of access to telephone services per day is:

[0135] Deg i =

[0136] Wherein, Deg i is the real-time influence degree on the i-th date, and cn i is the number of incoming call service times on the i-th date, where i is an integer less than or equal to 0;

[0137] According to the rolling emotion benchmark value and the real-time influence degree of each date, the calculation formula for determining the initial value of the rolling emotion of the date is:

[0138] D i = Deg i ×D max(i)

[0139] Wherein, D i is the rolling emotion score of the i-th date, and D max(i) is the rolling emotion benchmark value of the i-th date, where i is an integer less than or equal to 0, and i = 0 represents the date corresponding to obtaining the user feedback data.

[0140] In an optional embodiment of the present application, the dynamic emotion scoring process 32 is specifically used for: performing a summation process based on the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score, and the basic emotion score to obtain the first real-time emotion score.

[0141] In an optional embodiment of the present application, the pre-stored user access to the agent waiting queue information includes the waiting access agent queue of all users to be served and the waiting priority of each user to be served; correspondingly, the service resource scheduling module 33 is specifically used for: detecting the number of idle agent seats according to the agent seat status information, and when the detected number of idle agent seats is zero, then performing a priority calculation process according to the first real-time emotion score to obtain the waiting priority of the user; comparing and matching the waiting priority of the user with the waiting priority of each user to be served in turn to determine the access seat order of the user in the waiting access agent queue.

[0142] In an optional embodiment of the present application, the voice interaction module 31 is further used for: when it is detected that the first real-time emotion score is lower than the first preset emotion threshold, then obtaining the actual appeal information of the user; performing identification and analysis processing according to the actual appeal information of the user to obtain the to-be-served task information; calling the agent seat status information according to the to-be-served task information, and jumping to the step of determining the access seat order of the user according to the agent seat status information, the first real-time emotion score, and the pre-stored user access to the agent waiting queue information.

[0143] In an optional embodiment of the present application, the voice interaction module 31 is further configured to: obtain the user's client connection status information, and when it detects that the client connection status is the active hang-up state, generate a second real-time emotion score; determine the emotion score to be apologized according to the first real-time emotion score and the second real-time emotion score; when it detects that the emotion score to be apologized reaches the second preset emotion threshold, generate an apology message and send the apology message to the user's client.

[0144] In an optional embodiment of the present application, the voice interaction module 31 is further configured to: perform voice analysis and processing according to the user's actual demand information to obtain the user's third real-time emotion score; the demand processing information includes user satisfaction evaluation information; correspondingly, after obtaining the demand processing information, the voice interaction module 31 is further configured to: perform analysis and processing according to the user satisfaction evaluation information to obtain a fourth real-time emotion score; determine the user's service emotion score for this time according to the first real-time emotion score, the second real-time emotion score, the third real-time emotion score and the fourth real-time emotion score.

[0145] The telephone service data processing method provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0146] Figure 4 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 4 shown, the electronic device provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the device further includes a communication component 403. Among them, the processor 401, the memory 402 and the communication component 403 are connected through a bus.

[0147] In a specific implementation process, at least one processor 401 executes the computer execution instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0148] The specific implementation process of the processor 401 can refer to the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0149] An embodiment of the present application further provides a computer-readable storage medium, in which computer execution instructions are stored, and when the processor executes the computer execution instructions, the above telephone service data processing method is implemented.

[0150] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above telephone service data processing method is implemented.

[0151] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU for short), or may also be other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0152] The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0153] The bus may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0154] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0155] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above method is implemented.

[0156] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0157] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0158] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed between each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can be in electrical, mechanical, or other forms.

[0159] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0161] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0162] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the aforementioned storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0163] Finally, it should be noted that: after considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present invention. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed by the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A telephone service data processing method, characterized in that: include: Acquire historical service process data of a user using telephone services within a preset historical time period, wherein the historical service process data is acquired in response to an authorization operation of the user; When it is detected that there is legacy service data in the historical service process data, the processing progress data corresponding to the legacy service data and the basic emotion score of the user are retrieved, and the processing progress data is broadcasted to the user to obtain user feedback data; Determine a first dynamic emotion score according to the user feedback data, and determine a second dynamic emotion score and a rolling emotion score according to the historical service process data and a preset reduction coefficient; Determine a first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, and obtain customer service agent status information when it is detected that the first real-time emotion score reaches a first preset emotion threshold; Determine the access seat order of the user according to the customer service agent status information, the first real-time emotion score and the pre-stored user access seat waiting queue information; Connecting the user terminal of the user to the corresponding target idle seat according to the access seat order of the user, and obtaining the current demand information of the user; The historical service process data and the current demand information are sent to the target idle seat to obtain demand processing information, wherein the demand processing information is generated after the demand interaction operation between the target idle seat and the user is completed.

2. The method according to claim 1, characterized in that The historical service process data includes the number of telephone service accesses of the user on each date and the multiple service emotion scores of the user on each date; Accordingly, determining the second dynamic emotion score and the rolling emotion score according to the historical service process data and the preset reduction coefficient includes: According to the number of access telephone services on each date, determine the real-time impact of each date and the number of access telephone services on the current date; Compare and score the number of access telephone services on the current date with a preset access number threshold to determine a second dynamic emotion score; Perform score comparison processing based on multiple service emotion scores of each date, and determine the service emotion score with the largest value among the multiple service emotion scores as the rolling emotion benchmark value of the date; Determine the rolling sentiment initial value of each date according to the rolling sentiment baseline value and the real-time impact of the date; According to the rolling emotion value of each date and the preset reduction coefficient, the daily rolling emotion target value is determined, and all rolling emotion target values ​​are determined as rolling emotion scores, wherein the rolling emotion target value is a value greater than 0.

3. The method according to claim 2, characterized in that The calculation formula for determining the real-time impact of each date based on the number of access telephone services on each date is: You i = In the formula, Deg i is the real-time impact of the ith date, cn i is the number of access telephone services on the i-th date, where i is an integer less than or equal to 0; The calculation formula for determining the rolling emotion initial value of each date based on the rolling emotion baseline value and the real-time influence of each date is: D i = You i ×D max(i) Where D i is the rolling sentiment score for the i-th date, D max(i) is the rolling sentiment baseline value of the i-th date, where i is an integer less than or equal to 0, and i=0 represents the date corresponding to when the user feedback data is obtained.

4. The method according to claim 3, characterized in that The determining a first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score includes: A first real-time emotion score is obtained by summing the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score.

5. The method according to claim 1, characterized in that The pre-stored user access seat waiting queue information includes the access seat queues of all users to be served and the waiting priority of each user to be served; Accordingly, determining the access seat order of the user according to the customer service agent status information, the first real-time emotion score and the access seat waiting sequence of the existing users includes: Detecting the number of idle seats according to the customer service seat status information, and when the number of idle seats is zero, performing priority calculation processing according to the first real-time emotion score to obtain the waiting priority of the user; The waiting priority of the user is compared and matched with the waiting priority of each user to be served in turn, so as to determine the access seat order of the user in the queue of seats to be accessed.

6. The method according to claim 1, characterized in that Also includes: When it is detected that the first real-time emotion score is lower than the first preset emotion threshold, obtaining the actual demand information of the user; Identify, analyze and process the actual demand information of the user to obtain information on the tasks to be served; The customer service agent status information is called according to the to-be-serviced task information, and the step of jumping to the step of determining the user's access seat order according to the customer service agent status information, the first real-time emotion score and the pre-stored user access agent waiting queue information.

7. The method according to any one of claims 1 to 6, characterized in that Before connecting the user terminal of the user to the corresponding target idle seat according to the access seat order of the user, the method further includes: Acquire the user terminal connection state information of the user, and when it is detected that the user terminal connection state is in an active hang-up state, generate a second real-time emotion score; Determining an emotion score to be apologized according to the first real-time emotion score and the second real-time emotion score; When it is detected that the emotion score to be apologized reaches a second preset emotion threshold, an apology message is generated and sent to the user terminal of the user.

8. The method according to claim 7, characterized in that When the identification and analysis are performed according to the actual demand information of the user to obtain the task information to be served, the process further includes: Performing speech analysis and processing according to the actual demand information of the user to obtain a third real-time emotion score of the user; The appeal processing information includes user satisfaction evaluation information; Accordingly, after obtaining the appeal processing information, the method further includes: Analyze and process the user satisfaction evaluation information to obtain a fourth real-time emotion score; The current service emotion score of the user is determined according to the first real-time emotion score, the second real-time emotion score, the third real-time emotion score and the fourth real-time emotion score.

9. A telephone service data processing device, characterized in that: include: A voice interaction module, used to obtain historical service process data of a user using a telephone service within a preset historical time period, wherein the historical service process data is obtained in response to an authorization operation of the user; The voice interaction module is further configured to retrieve processing progress data corresponding to the legacy service data and the basic emotion score of the user when detecting that there is legacy service data in the historical service process data, and broadcast the processing progress data to the user to obtain user feedback data; A dynamic emotion scoring processing module, used to determine a first dynamic emotion score according to the user feedback data, and to determine a second dynamic emotion score and a rolling emotion score according to the historical service process data and a preset reduction coefficient; The dynamic emotion scoring process is further used to determine a first real-time emotion score according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, and obtain customer service agent status information when it is detected that the first real-time emotion score reaches a first preset emotion threshold; A service resource scheduling module, configured to determine the access seat order of the user according to the customer service agent status information, the first real-time emotion score and pre-stored user access seat waiting queue information; The service resource scheduling module is further used to connect the user terminal of the user to the corresponding target idle seat according to the access seat order of the user, and obtain the current demand information of the user; The service resource scheduling module is further used to send the historical service process data and the current demand information to the target idle seat to obtain demand processing information, wherein the demand processing information is generated after the demand interaction operation between the target idle seat and the user is completed.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

Images