CN116320164A - Method, device, equipment and storage medium for creating call center service summary - Google Patents

Abstract

The specification relates to the field of voice communication data processing, and provides a call center service receipt creation method, a device, equipment and a storage medium, wherein the method comprises the following steps: collecting IVR track of a target user when a telephone traffic platform carries out voice conversation with the target user, and obtaining service state data of the target user; after the telephone traffic platform and the target user finish the voice session, identifying the calling intention of the target user according to the IVR track and the service state data; extracting keywords which can represent the call intention from the call intention; inquiring a mapping relation table of the word segmentation library and the service attendant labels according to the keywords so as to determine the service attendant labels corresponding to the keywords; and generating a service small statement based on the keyword and the corresponding service person label. The embodiment of the specification can improve the creation efficiency and the content accuracy of the call center service receipt, and save the labor cost.

Description

Method, device, equipment and storage medium for creating call center service summary statement

technical field

This description relates to the technical field of voice communication data processing, in particular to a method, device, equipment and storage medium for creating a call center service summary.

Background technique

At present, in the call center (Call Center), the service summary is generally recorded manually by the front-line agent after answering the incoming call. However, since the call center has to handle a large number of incoming calls from users every day. This method of manually creating a service summary is inefficient and prone to problems such as misremembering or omission of call intentions.

Contents of the invention

The purpose of the embodiments of this specification is to provide a method, device, device and storage medium for creating a call center service summary, so as to improve the efficiency and content accuracy of the call center service summary, and save labor costs.

In order to achieve the above purpose, on the one hand, the embodiment of this specification provides a method for creating a call center service summary, including:

Collecting the IVR track of the target user when the traffic platform carries out a voice conversation with the target user, and obtaining the business status data of the target user;

After the voice conversation between the traffic platform and the target user is completed, identify the call intention of the target user according to the IVR track and the service state data;

extracting keywords that can characterize the call intent in the call intent;

Querying the mapping relationship table between the word segmentation database and the service provider label according to the keyword, so as to determine the service provider label corresponding to the keyword;

A service summary is generated based on the keywords and their corresponding service person labels.

In the call center service summary creation method of the embodiment of this specification, after generating the service summary based on the keywords and their corresponding service person labels, it also includes:

The service summary is pushed to the target agent for confirmation or modification; the target agent is an agent participating in the voice conversation in the traffic platform.

In the call center service summary creation method of the embodiment of this specification, identifying the call intention of the target user according to the IVR track and the business status data includes:

Using the IVR trajectory and the business state data as the corresponding user behavior state vector of the target user in this voice session;

Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix, and obtain a similarity set; the user behavior state matrix includes the user behavior state corresponding to the identified call intention of all users vector;

Determine the target vector in the user behavior state matrix according to the similarity set; the target vector is the user behavior state vector with the highest similarity to the user behavior state vector corresponding to the target user in this voice session;

The calling intention corresponding to the target vector is used as the calling intention of the target user in this voice session.

In the method for creating a call center service summary sheet in the embodiment of the present specification, before identifying the call intention of the target user according to the IVR track and the business status data, it also includes:

对所述IVR轨迹进行归一化处理；According to the formula

Carry out normalization processing to described IVR track;

Among them, x _i is the parameter value of the i-th parameter in the IVR trajectory, y _i is the normalized parameter value of the parameter value of the i-th parameter in the IVR trajectory, and x _min is the maximum value of the i-th parameter in the specified data range value, x _max is the maximum value of x _i for the i-th parameter within the specified data range.

In the method for creating a call center service summary sheet in the embodiment of the present specification, before identifying the call intention of the target user according to the IVR track and the business status data, it also includes:

对所述IVR轨迹进行归一化处理；According to the formula

Carry out normalization processing to described IVR track;

Among them, x _i is the parameter value of the i-th parameter in the IVR trajectory, y _i is the normalized parameter value of the parameter value of the i-th parameter in the IVR trajectory, and x _min is the maximum value of the i-th parameter in the specified data range value, x _max is the maximum value of x _i for the i-th parameter within the specified data range, a and b are preset constants, and a and b satisfy

In the method for creating a call center service summary sheet according to an embodiment of the present specification, the querying the word segmentation database and the service person label mapping relationship table according to the keyword to determine the service person label corresponding to the keyword includes:

Taking the keywords as input, query the mapping relationship table between the word segmentation database and service provider tags in a recursive query manner, so as to determine the service provider tags corresponding to the keywords.

On the other hand, the embodiment of this specification also provides a device for creating a call center service summary statement, including:

A data collection module, used to collect the IVR track of the target user when the traffic platform and the target user carry out a voice conversation, and obtain the business status data of the target user;

An intention identification module, configured to identify the calling intention of the target user according to the IVR track and the service status data after the voice conversation between the traffic platform and the target user is ended;

The intent word segmentation module is used to extract keywords that can characterize the call intent in the call intent;

The label mapping module is used to query the word segmentation database and the service provider label mapping relationship table according to the keyword, so as to determine the service provider label corresponding to the keyword;

A summary generating module, configured to generate a service summary based on the keywords and their corresponding service provider labels.

On the other hand, the embodiment of this specification also provides a computer device, including a memory, a processor, and a computer program stored on the memory. When the computer program is run by the processor, instructions for executing the above method .

On the other hand, the embodiment of this specification also provides a computer storage medium, on which a computer program is stored, and when the computer program is run by a processor of a computer device, instructions for executing the above method are executed.

On the other hand, the embodiment of this specification also provides a computer program product, where the computer program product includes a computer program, and when the computer program is run by a processor of a computer device, instructions for executing the above method are executed.

It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification automatically identify the user's call intention based on the IVR trajectory and business status, and based on the keywords in the call intention that can represent the call intention, query the word segmentation database and service responsibility Provider label mapping relationship table, so as to determine the service provider label corresponding to the keyword, and finally automatically generate a service summary based on the keyword and the corresponding service provider label, thereby realizing the automatic creation of the service summary, without the need for a call platform The first-line agents on the side can manually create service summary sheets, thus improving the efficiency and content accuracy of call center service summary sheets, and saving labor costs.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments described in this specification. Those skilled in the art can also obtain other drawings based on these drawings without any creative effort. In the attached picture:

FIG. 1 shows a schematic diagram of an application scenario of a summary server in some embodiments of this specification;

Fig. 2 shows the flow chart of the method for creating a call center service summary sheet in some embodiments of this specification;

FIG. 3 shows a schematic diagram of identifying a target user call according to IVR trajectory and service state data in some embodiments of the present specification;

FIG. 4 shows a flow chart of a method for creating a call center service summary sheet in other embodiments of the specification;

FIG. 5 shows a flow chart of a method for creating a call center service summary sheet in other embodiments of the specification;

Figure 6 shows a structural block diagram of a device for creating a call center service summary sheet in some embodiments of the specification;

Fig. 7 shows a structural block diagram of a computer device in some embodiments of the present specification.

[Description of Reference Signs]

10. Client;

20. Call platform;

30. Summary statement server;

61. Data acquisition module;

62. Intent recognition module;

63. Intention word segmentation module;

64. Label mapping module;

65. Summary generation module;

702. Computer equipment;

704. Processor;

706. memory;

708. Driving mechanism;

710. Input/output interface;

712. Input device;

714. Output device;

716. Presentation equipment;

718. Graphical user interface;

720. Network interface;

722. Communication link;

724. Communication bus.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described The embodiments are only some of the embodiments in this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

The embodiment of this specification relates to the automatic creation technology of the service summary, which can be applied to the creation of the service summary in the scene of the call center of various industries, and is especially suitable for the scene where the call center transfers the incoming call to the agent for processing.

For ease of understanding, before describing the embodiments of this specification, some concepts are explained first.

1. Call center

Call center is also called customer service center. It is a comprehensive information service system based on computer communication technology (mainly including call platform, etc.) to handle voice call inquiries from enterprises and customers. Call centers generally have the ability to handle a large number of It also has the calling number display, which can automatically assign incoming calls to personnel with corresponding skills (such as agents) for processing, and can record and store all incoming call information.

2. Interactive Voice Response (IVR)

IVR is an automatic voice response system, which can provide users with self-service voice response services through communication networks and voice value-added support platforms. IVR is one of the important components of the call center (or call platform), which can answer the user's call and provide corresponding services at any time without interruption (7*24 hours), with voice navigation, information query, voice mail, fax, outbound call and other business functions. For example, when a user dials a specified number through a client (such as a telephone, etc.), he can listen to and click to send the required voice information according to the operation prompts provided by the IVR, or participate in interactive services such as chatting and making friends.

3. Service summary

The service summary is a customer service record form of the call center, which is used to record the service documents for the call center to answer the user's incoming call. The service summary may include information such as the user's call intention (that is, the user's problem), the responsible department that should be transferred, the number of the call, and the time of the call.

In view of the low efficiency of manually creating a service summary and the possibility of misremembering or omission of call intentions, this manual provides a technical solution for automatically creating a service summary to improve the efficiency and content of creating a service summary in a call center Accuracy, save labor cost.

Fig. 1 shows the application scenario of the summary statement server in some embodiments of this specification, the user can carry out voice conversation with the traffic platform 20 based on the client 10, and the summary statement server 30 can carry out the voice conversation between the user and the traffic platform 20 Collect the user's IVR trajectory and obtain the user's service status data at any time. After the voice conversation between the call service platform 20 and the target user is completed, the user's call intention can be identified according to the obtained IVR trajectory and service status data; the call intention can be represented in the extracted call intention. Intended keywords; query the thesaurus and service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword; generate a service summary based on the keyword and its corresponding service provider label.

In some embodiments, the client 10 may be a fixed phone, a mobile phone (such as a smart phone) or other terminal equipment with a voice conversation function (such as a self-service terminal equipment, a desktop computer, a notebook computer, a tablet computer, a digital assistant or a smart phone). wearable devices, etc.). Among them, smart wearable devices may include smart bracelets, smart watches, smart glasses, or smart helmets. Of course, the client 10 is not limited to the above-mentioned electronic device with a certain entity, and it may also be software (such as App, etc.) running in the above-mentioned electronic device. The summary server 30 may be an electronic device with computing and network interaction functions; it may also be software running on the electronic device to provide business logic for data processing and network interaction.

The embodiment of this specification provides a method for creating a call center service summary sheet, which can be applied to the above-mentioned summary sheet server side, as shown in FIG. 2 , in some embodiments, the method for creating a call center service summary sheet may include the following steps :

Step 201: Collect the IVR track of the target user when the traffic platform conducts a voice conversation with the target user, and acquire the service status data of the target user.

Step 202, after the voice conversation between the traffic platform and the target user is ended, identify the call intention of the target user according to the IVR trace and the service state data.

Step 203, extracting keywords that can characterize the calling intention in the calling intention.

Step 204 : Query the mapping relationship table between the word segmentation database and the service provider label according to the keyword, so as to determine the service provider label corresponding to the keyword.

Step 205, generating a service summary based on the keywords and their corresponding service provider tags.

The embodiment of this specification automatically recognizes the user's call intention based on the IVR trajectory and business status, and based on the keywords in the call intention that can represent the call intention, query the mapping relationship table between the word segmentation library and the service provider label, so as to determine the keyword correspondence. Finally, based on the keywords and the corresponding service person tags, the service summary sheet is automatically generated, thereby realizing the automatic creation of the service summary sheet, without the need for the front-line agents on the call platform side to manually create the service summary sheet, thus The creation efficiency and content accuracy of the call center service summary list are improved, and the labor cost is saved.

The voice conversation between the service platform and the user is generally initiated by the user (such as business consultation and complaints initiated by the user), and of course it can also be initiated by the service platform (such as the return visit of the call center for the user's call). Since each voice session is in one-to-one correspondence with the service summary sheet, a corresponding service summary sheet can be created for each voice session. Therefore, the target user may be a user corresponding to a certain voice session.

Collecting the IVR track of the target user when the traffic platform conducts a voice conversation with the target user refers to: collecting the IVR track of the target user when the traffic platform and the corresponding client of the target user connect to the voice conversation channel. During specific implementation, the small statement server can instruct or request the traffic platform (or IVR system) to collect the IVR track of the target user, that is, the small statement server can obtain the IVR track of the target user from the traffic platform (or IVR system).

The IVR track records information such as the user's dialogue nodes (ie, dialogue links), interactive operations (such as selecting buttons), and dwell time (such as the duration of calls under each dialogue node) when the user is communicating with the traffic platform (or IVR system). The call platform (or IVR system) can timely provide the user with operation options according to the interaction with the user for the user to choose.

In the IVR trajectory, user feedback can be divided into two types: positive feedback behavior and negative feedback behavior. Positive feedback behavior refers to the behavior that can directly indicate the user's intention; negative feedback behavior refers to the behavior that does not directly indicate the user's intention (such as the frequency of visiting nodes, the length of stay, the current state, etc.). In actual data collection, the collected positive feedback behaviors of users may be too small. In order to facilitate accurate identification of user intentions, users' negative feedback behaviors can also be referred to.

For example, in an exemplary embodiment, a user enters the line to inquire about a loan issue, the user's current loan status is a successful loan, the system fails to automatically debit the loan on a certain repayment date, and the current bill is overdue. The IVR system first recommends options such as repayment issues and overdue issues for the user, and the user's selection operation preset by the system can be regarded as a positive feedback behavior. Otherwise, other operations are negative feedback behaviors.

For example, in an exemplary embodiment, the call platform (or IVR system) can output "Welcome to call..., please dial the extension number, please press 1 for consultation, and press 2 for after-sales service" when connecting to the user's call. Press 3 for the latest promotional activities, press 9 for complaints and suggestions, press 0" for number checking, etc. At this time, it is a dialogue node. After the user selects one of the operation options, he can enter the next dialogue node.

The IVR track can reflect the user's calling intention to a certain extent; However, relying solely on the IVR track may be difficult to fully and objectively identify the user's calling intention. Therefore, in the embodiments of this description, while collecting the IVR track of the target user, It is also possible to obtain the business status data of the target user. For example, in an exemplary embodiment, taking the loan business as an example, the business status data includes: the status of the user's loan application, loan review, loan disbursement, repayment, and overdue in various channels. In addition, as required, the business status data can also include other information (such as incoming line channels, historical incoming lines, whether to create a work order, etc.)

The service state data reflects the latest state of the user in the service. In different service states, the user's behavior may be different. Therefore, the service state data can also be used to assist in identifying the call intention of the user to a certain extent. For example, in an exemplary embodiment, when the user calls to inquire about repayment matters, if the user's repayment status at this time is that the repayment has failed, it can be recognized that the user's call intention is to consult the cause of repayment failure and corresponding solution.

Referring to Fig. 3, in some embodiments, identifying the call diagram of the target user according to the IVR track and the service state data may include the following steps:

Step 301: Use the IVR trajectory and the service state data as a user behavior state vector corresponding to the target user in this voice session.

The parameter values of the parameters in the IVR trajectory and service state data are generally numerical values or constants, and these parameter values can be arranged in sequence to form a vector. Therefore, the IVR trajectory and service state data under the same voice session can be used as the corresponding user behavior state vector in the voice session.

Step 302: Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix respectively, and obtain a similarity set; the user behavior state matrix includes all users' identified call intentions corresponding to User behavior state vector.

In some embodiments, the identified call intentions of all users may be the identified call intentions of all users within a specified historical period. Wherein, the designated historical period can be preset as required. For example, the specified historical period may be the last half year, one year, the last three years, and so on.

Obviously, in order to facilitate subsequent similarity calculations, the user behavior state vector in the user behavior state matrix should have the same data structure as the user behavior state vector corresponding to the target user in this voice session.

For example, in an exemplary embodiment, the user behavior state vector corresponding to the target user in this voice session is a ₁ , b ₁ , c ₁ , x ₁ , y ₁ , where a ₁ , b ₁ , c ₁ is the parameter value corresponding to the IVR trajectory of the target user in this voice session, and x ₁ , y ₁ is the parameter value corresponding to the business status of the target user in this voice session. Then the i-th user behavior state vector in the user behavior state matrix can represent: a _i , b _i , c _i , x _i , y _i , where a _i , b _i , c _i , x _i , y _i and a ₁ , b ₁ , c ₁ , x ₁ , y ₁ correspond, that is, a _i and a ₁ are two parameter values under the same parameter, b _i and b ₁ are two parameter values under the same parameter, c _i and c ₁ is two parameter values under the same parameter, x _i and x ₁ are two parameter values under the same parameter, y _i and y ₁ are two parameter values under the same parameter.

In some embodiments, the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix can be calculated based on vector similarity algorithms such as Euclidean distance and cosine distance, and these similarities can form a similarity degree collection.

In some other embodiments, considering that in the IVR trajectory and service status data, different parameters have different contributions or influences on identifying call intentions, in order to further improve the progress of calling intention identification, in specific implementation, the IVR trajectory can be used as required. Different weights are set for each parameter in the business status data. For example, in an exemplary embodiment, taking the IVR trajectory as an example, a parameter corresponding to a positive feedback behavior may be given a higher weight, a parameter corresponding to a negative feedback behavior may be given a lower weight, and so on. In this scenario, the user behavior state vector can be a weighted user behavior state vector, for example, a ₁ , b ₁ , c ₁ , x ₁ , y ₁ become λ ₁ a ₁ , λ ₂ b ₁ ,λ ₂ c ₁ ,λ ₄ x ₁ ,λ ₅ y ₁ .

Step 303: Determine the target vector in the user behavior state matrix according to the similarity set; the target vector is the user behavior state with the highest similarity to the user behavior state vector corresponding to the target user in this voice session vector.

By sorting the similarity sets, the user behavior state vector (ie, the target vector) with the highest similarity to the user behavior state vector corresponding to the target user in this voice session can be determined.

Step 304: Use the calling intention corresponding to the target vector as the calling intention of the target user in this voice session.

The highest similarity between the two user behavior state vectors indicates that the corresponding IVR trajectory and service state data are very similar (or even the same), and as mentioned above, both the IVR trajectory and the service state can represent the call intention. Therefore, the target The call intent corresponding to the vector is used as the call intent of the target user in this voice session. Compared with only considering the IVR trace alone, in the embodiment of this specification, the call intention identification method combining the IVR trace and service state data can improve the recognition accuracy of the call intention.

In some embodiments, extracting keywords that can characterize the call intent in the call intent may include: first calling a word segmentation tool (such as jieba, etc.) to segment the call intent, and then calling a keyword recognition tool (such as SurTime, Adwords, etc.) from Keywords are identified in the word segmentation results. For example, in an exemplary embodiment, taking loan repayment as the scenario, if the text corresponding to the call intention is: "repayment process, normal repayment business, settlement process", the keyword "repayment , Normal, Settlement".

The mapping relationship table between the word segmentation database and the service person in charge of labels is pre-configured, and is used to indicate the corresponding relationship between each keyword related to the business and the corresponding service person in charge of the label. Among them, the service person in charge tag is used to uniquely identify a type of service person in charge (that is, the person in charge of the response). For example, "normal repayment" corresponds to "person responsible for normal repayment", "settlement handling" corresponds to "person responsible for settlement handling", and so on. Therefore, the service provider tag corresponding to the keyword can be accurately identified by querying the mapping relation table between the thesaurus and the service provider tag by keywords. In some embodiments, the keyword can be used as an input to query the mapping relationship table between the word segmentation database and the service provider label in a recursive query manner, so as to determine the service provider label corresponding to the keyword.

Generating a service summary based on the keywords and their corresponding service person labels may refer to: filling information such as the keywords and their corresponding service person labels into a preset service summary template, thereby automatically generating Service summary for this voice session.

The embodiment of this specification provides another method for creating a call center service summary sheet, which can be applied to the above-mentioned summary sheet server side, as shown in FIG. 4 , in other embodiments, the method for creating a call center service summary sheet may include The following steps:

Step 401 , collect the IVR track of the target user when the traffic platform conducts a voice conversation with the target user, and obtain the service status data of the target user.

Step 402 , after the voice conversation between the traffic platform and the target user ends, normalize the IVR trajectory.

Step 403, identifying the call intention of the target user according to the IVR track and the service state data.

Step 404, extracting keywords that can characterize the calling intention in the calling intention.

Step 405 : Query the mapping relationship table between the word segmentation database and the service provider label according to the keyword, so as to determine the service provider label corresponding to the keyword.

Step 406, generating a service summary based on the keywords and their corresponding service provider tags.

Compared with the method for creating a call center service summary sheet shown in Figure 2, the method for creating a call center service summary sheet shown in Figure 4 includes normalizing the IVR track after the call platform and the target user end the voice conversation processing steps. Through normalization processing, large values can be mapped to a small range, and the processing efficiency of subsequent vector similarity calculations can be improved. During specific implementation, the normalization algorithm can be selected as required.

For example, in some embodiments, normalizing the IVR trajectory may include:

对所述IVR轨迹进行归一化处理；According to the formula

Carry out normalization processing to described IVR trajectory;

可以将参数值归一到0～1之间。Among them, x _i is the parameter value of the i-th parameter in the IVR trajectory, y _i is the normalized parameter value of the parameter value of the i-th parameter in the IVR trajectory, and x _min is the maximum value of the i-th parameter in the specified data range value, x _max is the maximum value of x _i for the i-th parameter within the specified data range. by formula

The parameter value can be normalized to between 0 and 1.

For example, in other embodiments, normalizing the IVR trajectory may include:

对所述IVR轨迹进行归一化处理；According to the formula

Carry out normalization processing to described IVR trajectory;

通过公式

可以将参数值归一到0.1～0.9之间。Among them, x _i is the parameter value of the i-th parameter in the IVR trajectory, y _i is the normalized parameter value of the parameter value of the i-th parameter in the IVR trajectory, and x _min is the maximum value of the i-th parameter in the specified data range value, x _max is the maximum value of x _i for the i-th parameter within the specified data range, a and b are preset constants, and a and b satisfy

by formula

The parameter value can be normalized to between 0.1 and 0.9.

The embodiment of this specification provides another method for creating a call center service summary sheet, which can be applied to the above-mentioned summary sheet server side, as shown in FIG. 5 , in other embodiments, the method for creating a call center service summary sheet may include The following steps:

Step 501 , collect the IVR track of the target user when the traffic platform conducts a voice conversation with the target user, and obtain the service status data of the target user.

Step 502 , after the voice conversation between the traffic platform and the target user is ended, normalize the IVR trajectory.

Step 503, identifying the call intention of the target user according to the IVR track and the service state data.

Step 504, extracting keywords that can characterize the calling intention in the calling intention.

Step 505 : Query the mapping relationship table between the word segmentation database and the service provider label according to the keyword, so as to determine the service provider label corresponding to the keyword.

Step 506, generating a service summary based on the keywords and their corresponding service person tags.

Step 507 , pushing the service summary to the target agent for confirmation or modification; the target agent is the agent participating in the voice conversation on the call platform.

Compared with the creation method of the call center service summary sheet shown in Figure 4, in the call center service summary sheet creation method shown in Figure 5, the confirmation step of the service summary sheet is added after the service summary sheet is generated; Improve the accuracy of matching service personnel.

Although the process flows described above include multiple operations occurring in a particular order, it should be clearly understood that the processes may include more or fewer operations, which may be performed sequentially or in parallel (e.g., using parallel processors or multi-threaded environment).

Corresponding to the above-mentioned method for creating a call center service summary statement, the embodiment of this specification also provides a device for creating a call center service summary statement, which can be configured on the above-mentioned summary statement server, as shown in FIG. 6 , in some embodiments Among them, the call center service brief creation device may include:

The data collection module 61 is used for collecting the IVR track of the target user when the traffic platform carries out the voice conversation with the target user, and obtaining the service state data of the target user;

Intention identification module 62, is used for identifying the call intention of the target user according to the IVR track and the service state data after the voice conversation between the traffic platform and the target user is ended;

The intent word segmentation module 63 is used to extract keywords that can characterize the call intent in the call intent;

The tag mapping module 64 is used to query the word segmentation database and the service person in charge tag mapping relationship table according to the keyword, so as to determine the service person in charge tag corresponding to the keyword;

A summary generating module 65, configured to generate a service summary based on the keywords and their corresponding service person labels.

For the convenience of description, when describing the above devices, functions are divided into various units and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more pieces of software and/or hardware.

It should be noted that in the embodiments of this specification, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.), are all information and data authorized and agreed by the user and fully authorized by all parties.

The embodiment of this specification also provides a computer device. As shown in FIG. 7, in some embodiments of this specification, the computer device 702 may include one or more processors 704, such as one or more central processing units (CPUs) or graphics processing units (GPUs), each A processing unit may implement one or more hardware threads. The computer device 702 may also include any memory 706 for storing any kind of information such as codes, settings, data, etc. In a specific embodiment, a computer program on the memory 706 and executable on the processor 704, When the computer program is run by the processor 704, it can execute the instructions of the method for creating a call center service summary in any of the above-mentioned embodiments. Non-limiting, for example, the memory 706 may include any one or combination of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, and so on. More generally, any memory can use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of computer device 702 . In one instance, when processor 704 executes the associated instructions stored in any memory or combination of memories, computer device 702 may perform any operation of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708 for interfacing with any memory, such as a hard disk drive, an optical disk drive, or the like.

Computer device 702 may also include input/output interface 710 (I/O) for receiving various inputs (via input device 712 ) and for providing various outputs (via output device 714 ). One particular output mechanism may include a presentation device 716 and an associated graphical user interface 718 (GUI). In other embodiments, the input/output interface 710 (I/O), the input device 712 and the output device 714 may not be included, and it is only used as a computer device in the network. Computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722 . One or more communication buses 724 couple together the components described above.

Communication link 722 can be implemented in any manner, for example, through a local area network, wide area network (eg, the Internet), point-to-point connection, etc., or any combination thereof. Communication link 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name summary servers, etc. governed by any protocol or combination of protocols.

The present application is described with reference to flowcharts and/or block diagrams of methods, devices (systems), computer-readable storage media, and computer program products in some embodiments of the specification. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processor to produce a machine such that the instructions executed by the processor of the computer or other programmable data processor produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processor to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processor, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

In a typical configuration, a computer device includes one or more processors (CPUs), input/output interfaces, network interfaces and memory.

Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by computer equipment. As defined in this specification, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

Those skilled in the art should understand that the embodiments of this specification may be provided as methods, systems or computer program products. Accordingly, the embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Embodiments of the present description may also be practiced in distributed computing environments where tasks are performed by remote processors that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

It should also be understood that in the embodiments of this specification, the term "and/or" is only an association relationship describing associated objects, which means that there may be three relationships. For example, A and/or B may mean that A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiment.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structures, materials or features are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.

The above descriptions are only examples of the present application, and are not intended to limit the present application. For those skilled in the art, various modifications and changes may occur in this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims (10)

1. A call center service receipt creation method, comprising:

collecting IVR track of a target user when a telephone traffic platform carries out voice conversation with the target user, and obtaining service state data of the target user;

after the telephone traffic platform and the target user finish the voice session, identifying the calling intention of the target user according to the IVR track and the service state data;

extracting keywords which can represent the call intention from the call intention;

inquiring a mapping relation table of the word segmentation library and the service attendant labels according to the keywords so as to determine the service attendant labels corresponding to the keywords;

and generating a service small statement based on the keyword and the corresponding service person label.

2. The call center service receipt creation method of claim 1, further comprising, after generating a service receipt based on the keyword and its corresponding service attendant tag:

pushing the service receipt to target seat personnel for confirmation or modification; the target agent personnel are agent personnel participating in the voice conversation in the telephone traffic platform.

3. The call center service placard creation method of claim 1, wherein identifying the call intention of the target user from the IVR trajectory and the business state data comprises:

the IVR track and the service state data are used as corresponding user behavior state vectors of the target user in the voice session;

determining the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix respectively to obtain a similarity set; the user behavior state matrix comprises user behavior state vectors corresponding to the recognized calling intention of the full number of users;

determining a target vector in the user behavior state matrix according to the similarity set; the target vector is a user behavior state vector with highest similarity with a user behavior state vector corresponding to the target user in the voice session;

and taking the calling intention corresponding to the target vector as the calling intention of the target user in the voice conversation.

4. The call center service placard creation method of claim 1, further comprising, prior to identifying the call intent of the target user based on the IVR trajectory and the business state data:

according to the formula

Normalizing the IVR track;

wherein x is _i The parameter value of the ith parameter in the IVR track, y _i Normalized parameter value, x, which is the parameter value of the ith parameter in the IVR trace _min For the maximum value of the ith parameter in the specified data range, x _max X within the specified data range for the ith parameter _i Is a maximum value of (a).

5. The call center service placard creation method of claim 1, further comprising, prior to identifying the call intent of the target user based on the IVR trajectory and the business state data:

according to the formula

Normalizing the IVR track;

wherein x is _i The parameter value of the ith parameter in the IVR track, y _i Normalized parameter value, x, which is the parameter value of the ith parameter in the IVR trace _min For the maximum value of the ith parameter in the specified data range, x _max X within the specified data range for the ith parameter _i A and b are preset constants, and a and b satisfy

6. The call center service nodelet creation method of claim 1, wherein the querying the keyword library and service actor tag mapping table according to the keyword to determine the service actor tag corresponding to the keyword comprises:

and inquiring a mapping relation table of the word bank and the service attendant labels according to a recursive inquiry mode by taking the keywords as input so as to determine the service attendant labels corresponding to the keywords.

7. A call center service receipt creation apparatus, comprising:

the data acquisition module is used for acquiring the IVR track of the target user when the telephone traffic platform carries out voice conversation with the target user and acquiring service state data of the target user;

the intention recognition module is used for recognizing the calling intention of the target user according to the IVR track and the service state data after the telephone traffic platform and the target user finish the voice session;

the intention word segmentation module is used for extracting keywords which can represent the call intention in the call intention;

the label mapping module is used for inquiring the word segmentation library and the service attendant label mapping relation table according to the keywords so as to determine the service attendant label corresponding to the keywords;

and the summary generation module is used for generating a service summary list based on the keywords and the corresponding service person labels.

8. A computer device comprising a memory, a processor, and a computer program stored on the memory, characterized in that the computer program, when being executed by the processor, performs the instructions of the method according to any of claims 1-6.

9. A computer storage medium having stored thereon a computer program, which, when executed by a processor of a computer device, performs the instructions of the method according to any of claims 1-6.

10. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, executes instructions of the method according to any of claims 1-6.

Images