Telephone service data processing method and device and electronic equipment

Abstract

The embodiment of the invention provides a telephone service data processing method and device and electronic equipment, and belongs to the technical field of data processing. The method comprises the following steps: calling processing progress data corresponding to legacy service data and a basic emotion score of a user; determining a second dynamic emotion score and a rolling emotion score; when it is detected that the first real-time emotion score reaches a first preset emotion threshold value, customer service seat state information is obtained; determining an access seat of the user according to the customer service seat state information, the first real-time emotion score and pre-stored user access seat waiting queue information; accessing the user side of the user to a corresponding target idle seat according to the access seat of the user, and acquiring current appeal information of the user; and sending the historical service process data and the current appeal information to the target idle seat. The method is used for serving more users under the scene of limited and dynamically changing service resources, and meanwhile, the effect of considering the service quality of special users is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, specifically to the field of telephone service data technology, and more particularly to a telephone service data processing method, device and electronic equipment. Background Art

[0002] With the popularity of telephone services, users have higher requirements for the quality of telephone services and the interactive experience of telephone services. General telephone services support intelligent voice and key navigation, and the telephone service process is that when intelligent voice interaction and key navigation cannot meet the needs of users, manual customer service seats need to be connected.

[0003] However, in the existing telephone service process, users still have low service resource utilization in the scenario where service resources change dynamically, which leads to a low user demand resolution rate. Summary of the invention

[0004] The embodiments of the present application provide a telephone service data processing method, device and electronic device to achieve the service quality effect for special users while serving more users in a scenario with limited and dynamically changing service resources.

[0005] In a first aspect, an embodiment of the present application provides a method for processing telephone service data, comprising:

[0006] 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;

[0007] 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;

[0008] 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;

[0009] 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;

[0010] 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;

[0011] 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;

[0012] 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.

[0013] In a possible implementation, 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, determining the second dynamic emotion score and the rolling emotion score based on the historical service process data and the preset reduction coefficient includes: determining the real-time impact of each date and the number of access telephone services on the current date based on the number of access telephone services on each date; performing a scoring process based on the number of access telephone services on the current date and a preset access number threshold to determine the second dynamic emotion score; performing a score comparison process based 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 baseline value of the date; determining the rolling emotion initial value of the date based on the rolling emotion baseline value and the real-time impact of each date; determining the daily rolling emotion target value based on the rolling emotion value of each date and the preset reduction coefficient, and determining all rolling emotion target values ​​as rolling emotion scores, wherein the rolling emotion target value is a value greater than 0.

[0014] In a possible implementation manner, the calculation formula for determining the real-time impact of each date based on the number of access telephone services on each date is:

[0015] Deg i =

[0016] 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;

[0017] 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:

[0018] D i = Deg i ×D max(i)

[0019] Where D i is the rolling sentiment score for the i-th date, Dmax(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.

[0020] In a possible implementation, 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: summing the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score to obtain a first real-time emotion score.

[0021] In a possible implementation, 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 seat 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 detected to be zero, performing priority calculation processing 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 access seat queue.

[0022] In a possible implementation, the method further 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; performing identification, analysis and processing based on the actual demand information of the user to obtain information on tasks to be served; calling the customer service agent status information based on the information on tasks to be served, and jumping to the step of determining the access seat order of the user based on the customer service agent status information, the first real-time emotion score and pre-stored user access agent waiting queue information.

[0023] In a possible implementation, before connecting the user terminal of the user to the corresponding target idle seat according to the access seat order of the user, it also includes: obtaining the user terminal connection status information of the user, and when it is detected that the user terminal connection status is an active hang-up state, generating 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, generating an apology message, and sending the apology message to the user terminal of the user.

[0024] In a possible implementation, when the identification, analysis and processing are performed based on the actual demand information of the user to obtain the information of the task to be served, the method further includes: performing voice analysis and processing based on the actual demand information of the user to obtain a third real-time emotion score of the user; the demand processing information includes user satisfaction evaluation information; accordingly, after obtaining the demand processing information, the method further includes: performing analysis and processing based on the user satisfaction evaluation information to obtain a fourth real-time emotion score; and determining the user's emotion score for this service based on 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, 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;

[0027] 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;

[0028] 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;

[0029] 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;

[0030] 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;

[0031] 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;

[0032] 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.

[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 implementations of the first aspect.

[0036] The telephone service data processing method, device and electronic device provided in the embodiment of the present application first detect whether there is any legacy service data after the user using the telephone service accesses the telephone service, and then selects to call the corresponding telephone service resource to broadcast the processing progress data to obtain user feedback information, and 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, and then determines 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, the customer service agent status information is obtained so that the user can access the target idle seat in the future, and then the historical service process data and the current demand information are sent to the target idle seat to obtain the demand processing information. The service resources of the telephone service are dynamically called for the user, and the service reference information is provided for the customer service seat, so that the customer service seat can better solve the user's demand information. In this way, while serving more users in the scenario of limited and dynamically changing service resources, the service quality of special users is taken into account, and the user service quality and service experience are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] Figure 1 A schematic diagram of an application scenario of the telephone service data processing method provided in an embodiment of the present application;

[0039] Figure 2 A flowchart of a telephone service data processing method provided in an embodiment of the present application;

[0040] Figure 3A schematic diagram of the structure of a telephone service data processing device provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0042] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope 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 DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, 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 this application, the collection, storage, use, processing, transmission, provision and disclosure of user data and other information involved have all been authorized by the user and comply with the provisions of relevant laws and regulations, and do not violate public order and good morals. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components, models, etc. may be mentioned, and they should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0045] In the prior art, the inventors have discovered that in the existing telephone service process, it is impossible to dynamically evaluate the user's emotions and tolerance throughout the entire process and call the corresponding telephone service resources based on the evaluation results, resulting in a lack of reasonable calling of service resources in such dynamically changing scenarios as 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 a problem that the present invention urgently needs to solve.

[0046] In response to the above technical problems, the inventors proposed the following inventive concept: by adding dynamic analysis of the service data generated during the user's telephone service process, a dynamic service score for the user is obtained, and the corresponding service resources are called for the user based on the real-time dynamic service score, so as to complete the user service more efficiently, so as to achieve serving more users in the scenario of limited and dynamically changing service resources, while taking into account the service quality of special users, thereby improving the user service quality and service experience.

[0047] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0048] Figure 1 A schematic diagram of an application scenario of the telephone service data processing method provided in an embodiment of the present application, such as Figure 1 As shown, the 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 end 102 can be a terminal device of a user who is to use the telephone service, and the agent end 103 is a terminal device of an artificial customer service agent that is uniformly managed and scheduled by the server 101. After the server 101 establishes a communication connection with the user end 102, it provides the user with intelligent voice interaction and button navigation, and processes and executes each step of the telephone service data processing method according to the user's historical service process data, and allocates a suitable artificial customer service agent to the user, and transfers the telephone service to the agent end 103 of the corresponding artificial customer service agent, so that the artificial customer service agent can provide the user with higher quality telephone service, thereby achieving service to more users in the scenario of limited and dynamically changing service resources while taking into account the service quality of special users, thereby improving user service quality and service experience.

[0050] Figure 2 A flowchart of a telephone service data processing method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0051] S201: Acquire historical service process data of a user who uses telephone services within a preset historical time period, wherein the historical service process data is acquired after authorization by the user.

[0052] In this embodiment, the preset historical time period can be pre-set in the time end of the server, such as within a week or three days before the user uses the telephone service this time. The historical service process data can be the data generated by the user during the use of the telephone service within the preset historical time period, such as: user demand information, and the solution or unsolved solution record sheet generated after the telephone service is completed.

[0053] S202: 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.

[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: 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.

[0061] In this embodiment, the real-time impact of each date may be determined by inputting the number of access telephone services on each date into pre-stored calculation software and then performing numerical calculation to obtain the result.

[0062] In an optional embodiment of the present application, the calculation formula for determining the real-time impact of each date is as follows based on the number of access telephone services on each date:

[0063] Deg i =

[0064] 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.

[0065] In this embodiment, when i=0, it indicates the current date when step S201 is executed, i=-1 refers to the date of the day before the current date, i=-2 refers to the date of two days before the current date, and so on. In general, considering that the user's emotional calmness period is generally 3 days, in this embodiment, i is less than or equal to 3. i Can be any integer value, for example, when cn i =4, it means that the number of telephone services connected on the ith day is 4 times, and the corresponding real-time impact degree Deg i is 2.

[0066] S203ab: Performing a comparison and scoring process based on the number of access telephone services on the current date and a preset access number threshold to determine a second dynamic emotion score.

[0067] In this embodiment, the comparison and scoring process may be to compare the number of telephone service accesses on the current date with the preset access number threshold, and when the preset access number threshold is larger, the second dynamic emotion score is scored as 0. Otherwise, the second dynamic emotion score is scored as a preset score, such as 10 points, 20 points, etc. In this embodiment, the preset access number threshold may be a preset fixed value, such as the preset access number threshold is 3 times.

[0068] S203c: 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.

[0069] In this embodiment, the score comparison process can be to compare the numerical values ​​of multiple service emotion scores of each date in turn to sort them or retain the larger service emotion value after each comparison until all service emotion scores are compared. The remaining service emotion score is the service emotion score with the largest numerical value, and the service emotion score with the largest numerical value is the rolling emotion benchmark value of the date. For example: the four service emotion scores of the date of the day before executing step S201 are 65 points, 70 points, 68 points and 60 points respectively, then after step S203c, the rolling emotion benchmark value of the date of the day before is 70 points.

[0070] S203d: Determine the rolling emotion initial value of the date according to the rolling emotion baseline value and the real-time impact of each date.

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

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

[0073] D i = Deg i ×D max(i)

[0074] 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.

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

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

[0077] In this embodiment, the preset reduction coefficient can be a fixed ratio value pre-set according to the date. For example, the reduction period of the rolling emotion score is 3 days, that is, the emotion impact is reduced in proportion to 3 days. The preset reduction coefficient of the current date D0 is a, and the preset reduction coefficient of the previous day D-1 The default reduction factor is b, and the D of the previous two days -2 The preset reduction coefficient is c, and the preset reduction coefficient of the previous day 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] Where D sum represents the rolling emotion score, D0×a represents the rolling emotion target value of the current date when executing step S203e, and D -1 ×b represents the rolling sentiment target value of the day before today’s date, D -2 ×c represents the rolling emotion target value of the two days before the date, and a, b, c represent the preset reduction coefficients ranging from 0 to 1. For example, assuming that the reduction cycle of the rolling emotion score is 3 days, that is, the emotion impact is reduced in proportion to 3 days, the preset reduction coefficient of the current date D0 is 1, and the preset reduction coefficient of the previous day D -1 The default reduction factor is 0.7, and the D -2 The default reduction factor is 0.3.

[0081] S204: 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.

[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 may be a process of performing score calculation using score calculation software, tools or algorithms.

[0083] In an optional embodiment of the present application, in step S204, a first real-time emotion score is determined according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, including: summing 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 means that the user's current emotion is bad, and it is necessary to call the telephone service resource as soon as possible to solve the user's demand information. At this time, the server needs to call the working status of each seat terminal connected to it to obtain the customer service seat status information.

[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 access seat rank of the user may be a process of arranging the user into pre-stored user access seat waiting queue information according to the first real-time emotion score of the user to obtain the access seat rank of the user.

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

[0089] S205a: Detect the number of idle seats according to the customer service agent status information, and when 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 agent is idle, and the customer service agent status information is retrieved to obtain the number of customer service agents in an idle state. When it is detected that the number of idle seats is zero, it means that there are currently no idle seats and appropriate telephone service resources need to be dispatched for the user.

[0091] In this embodiment, the priority calculation process may be to input the first real-time emotion score into an existing priority matching tool to output a corresponding waiting priority, and the priority matching tool may pre-store a correspondence between the emotion score and the waiting priority, and the correspondence may be a table. Generally, the higher the first real-time emotion score, the higher the waiting priority.

[0092] In an optional embodiment of the present application, the user's service level is also considered, and the waiting priority of the user is determined in combination with 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 the service level of user A is a four-star user (important user) and the service level of user B is a two-star user (ordinary user), then the waiting priority corresponding to user A is higher than the waiting priority 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 waiting user, finding the waiting user with the same or similar waiting priority, and determining the access seat order of the user in the access seat queue.

[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 user's access seat order, and the server transfers the telephone service to the corresponding target idle seat, so that the customer service of the idle seat can provide telephone service to the user, and at the same time obtain the user's demand information and send it to the target idle seat.

[0097] S207: Sending historical service process data and 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.

[0098] In this embodiment, when the server transfers the user's telephone service to the agent terminal of the target idle seat, the corresponding historical service process data and current demand information are sent to the agent terminal for display by the agent terminal, so as to facilitate the target idle seat to check. The historical service process data here may include the user's basic information, telephone service process data within a week, and potential service demands before the transfer to the target idle seat, etc., which are background information that helps the target idle agent to answer the user's questions.

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

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

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

[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 key customer service can also be provided to the user without accessing a human agent. At this time, it is only necessary to obtain the user's current actual demand information. The process of obtaining the user's actual demand information may include the telephone service asking the user's service demand, the user speaking the specific content of the service demand through the telephone service, and the specific content returned to the server is the user's actual demand information.

[0103] Step B: Identify, analyze and process the user's actual demand information to obtain information about the tasks to be served.

[0104] In this embodiment, the recognition and analysis processing can be performed by using the existing semantic analysis model, intent recognition neural network or software in the server to recognize and analyze the actual demand information input by the user to output more accurate task information to be served.

[0105] Step C: calling the customer service agent status information according to the task to be served information, and 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.

[0106] In this embodiment, the customer service agent status information is called to confirm the number of idle customer service agents, and then jump to step S205.

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

[0108] Step D: Acquire the user's client connection status information, and when it is detected that the user's client connection status is an active hang-up state, generate a second real-time emotion score.

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

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

[0111] In this embodiment, the first real-time emotion score and the second real-time emotion score are summed to obtain the emotion score to be apologized.

[0112] Step F: 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's terminal.

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

[0114] In this embodiment, the second preset emotion threshold may be a fixed emotion score reflecting a poor user emotion. For example, the second preset emotion threshold is 80 points. The apology message may be automatically generated based on a pre-specified message template combined with the user information of the current user. The apology message may be sent from the server to the user terminal of the user via the communication network.

[0115] On the basis of the above embodiment, in the telephone service data processing method provided as an optional embodiment of the present application, when the identification and analysis processing are performed according to the actual demand information of the user to obtain the task information to be served, the method further includes:

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

[0117] In this embodiment, the pre-trained speech recognition model can be called to perform speech analysis on the user's actual demand information. Specifically, the user's speech speed, intonation and other sound information that can reflect the user's emotions can be analyzed to obtain the analysis result. Based on the analysis result, the user's third real-time emotion score can be generated.

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

[0119] Accordingly, after obtaining the appeal processing information, it also includes:

[0120] Step H: Analyze and process the user satisfaction evaluation information to obtain a fourth real-time emotion score.

[0121] In this embodiment, the analysis and processing of the user satisfaction evaluation information may be that the user directly rates the current telephone service process by pressing a button, for example: if you are very satisfied, press 1; if you are not satisfied, press 0. The fourth real-time emotion score may be a score automatically generated by a rating software.

[0122] Step J: Determine the user's service emotion score based on 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 the telephone service can be terminated.

[0123] In this embodiment, the user's service emotion score can be determined by summing 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 by presetting corresponding weights and calculating to obtain the service emotion score. For example: service emotion score = y1 × first real-time emotion score + y2 × second real-time emotion score + y3 × third real-time emotion score + y4 × fourth real-time emotion score, where y1 + y2 + y3 + y4 = 1, and y1, y2, y3, 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 resource to broadcast the processing progress data to obtain user feedback information, and 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, and then determines 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, the customer service agent status information is obtained, so as to subsequently access the target idle seat for the user, and then the historical service process data and the current demand information are sent to the target idle seat to obtain the demand processing information. The service resources of the telephone service are dynamically called for the user, and the service reference information is provided for the customer service seat, so that the customer service seat can better solve the user's demand information. In order to achieve serving more users in the scenario of limited and dynamically changing service resources, the service quality of special users is taken into account, and the user service quality and service experience are improved.

[0125] Figure 3 A schematic diagram of the structure of a telephone service data processing device provided in an embodiment of the present application, such as Figure 3 As 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] The voice interaction module 31 is used to obtain historical service process data of users who use telephone services within a preset historical time period, wherein the historical service process data is obtained in response to the user's authorization operation.

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

[0128] The dynamic emotion scoring processing module 32 is used to determine a first dynamic emotion score according to user feedback data, and to 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 scoring processing module 32 is also used to determine the first real-time emotion score based on the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score, and obtain the customer service agent status information when it is detected that the first real-time emotion score reaches the first preset emotion threshold.

[0130] The service resource scheduling module 33 is used to 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.

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

[0132] The service resource scheduling module is also used to send historical service process data and 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.

[0133] 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, the dynamic emotion scoring processing module 32 is specifically used to: determine the real-time impact of each date and the number of access telephone services on the current date according to the number of access telephone services on each 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 the 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 baseline value of the date; determine the rolling emotion initial value of the date according to the rolling emotion baseline value and the real-time impact of each date; determine the daily rolling emotion target value according to the rolling emotion value of each date and the preset reduction coefficient, and determine all rolling emotion target values ​​as rolling emotion scores, wherein 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: determine the real-time impact of each date according to the number of access telephone services on each date. The calculation formula is:

[0135] Deg i =

[0136] 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;

[0137] According to the rolling sentiment baseline value and real-time impact of each date, the calculation formula for determining the rolling sentiment initial value of the date is:

[0138] D i = Deg i ×D max(i)

[0139] 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.

[0140] In an optional embodiment of the present application, the dynamic emotion scoring process 32 is specifically used to: perform summing processing according to the rolling emotion score, the first dynamic emotion score, the second dynamic emotion score and the basic emotion score to obtain a first real-time emotion score.

[0141] In an optional embodiment of the present application, 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, the service resource scheduling module 33 is specifically used to: detect the number of idle seats according to the customer service seat status information, and when the number of idle seats is detected to be zero, perform priority calculation processing according to the first real-time emotion score to obtain the user's waiting priority; compare and match the user's waiting priority with the waiting priority of each user to be served in turn to determine the user's access seat order in the access seat queue.

[0142] In an optional embodiment of the present application, the voice interaction module 31 is also used to: when it is detected that the first real-time emotion score is lower than the first preset emotion threshold, obtain the user's actual demand information; perform identification, analysis and processing based on the user's actual demand information to obtain the task information to be served; call the customer service agent status information based on the task information to be served, and jump to the step of determining the user's access seat order based on the customer service agent status information, the first real-time emotion score and the pre-stored user access agent waiting queue information.

[0143] In an optional embodiment of the present application, the voice interaction module 31 is also used to: obtain the user's user terminal connection status information, and when it is detected that the user terminal connection status is an active hang-up state, generate a second real-time emotion score; determine the emotion score to be apologized based on 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, generate an apology message, and send the apology message to the user's user terminal.

[0144] In an optional embodiment of the present application, the voice interaction module 31 is further used to: perform voice analysis and processing based on 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; accordingly, after obtaining the demand processing information, the voice interaction module 31 is further used to: perform analysis and processing based on the user satisfaction evaluation information to obtain a fourth real-time emotion score; determine the user's service emotion score based on 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 embodiments, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0146] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As 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. The processor 401, the memory 402 and the communication component 403 are connected via a bus.

[0147] In a specific implementation process, at least one processor 401 executes the computer-executable 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 be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

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

[0150] The embodiment of the present application also provides a computer program product, including a computer program, which implements the above telephone service data processing method when executed by a processor.

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

[0152] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0153] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or 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 ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

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

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

[0156] The above-mentioned 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, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0157] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium 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 circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0158] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

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

[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into 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, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0162] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned 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, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0163] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. 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 knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only 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