Call center service summary creation method, device, equipment and storage medium

Abstract

This specification relates to the field of voice communication data processing, and provides a method, device, equipment, and storage medium for creating a call center service summary. The method includes: collecting the target user's IVR trajectory when a call platform conducts a voice conversation with the target user, and obtaining the target user's business status data; after the call platform and the target user end the voice conversation, identifying the target user's call intention based on the IVR trajectory and the business status data; extracting keywords that can represent the call intention from the call intention; querying the word segmentation library and the service agent label mapping relationship table based on the keyword to determine the service agent label corresponding to the keyword; and generating a service summary based on the keyword and its corresponding service agent label. The embodiments of this specification can improve the efficiency of creating call center service summaries and the accuracy of content, saving labor costs.

Description

Technical Field

[0001] This specification relates to the field of voice communication data processing technology, and in particular to a method, device, equipment, and storage medium for creating a call center service summary. Background Art

[0002] Currently, call center service summary sheets are typically manually recorded by frontline agents after answering calls. However, given the large volume of calls call centers handle daily, this manual service summary process is inefficient and prone to errors or omissions in call intent. Summary of the Invention

[0003] The purpose of the embodiments of this specification is to provide a method, apparatus, device and storage medium for creating a call center service summary, so as to improve the efficiency and content accuracy of creating a call center service summary and save labor costs.

[0004] To achieve the above objectives, on the one hand, an embodiment of this specification provides a method for creating a call center service summary, comprising:

[0005] When the call platform conducts a voice conversation with the target user, it collects the IVR track of the target user and obtains the service status data of the target user;

[0006] After the voice platform and the target user end the voice conversation, identifying the target user's calling intention according to the IVR track and the service status data;

[0007] Extracting keywords that can represent the call intention from the call intention;

[0008] According to the keyword, the word segmentation library and the service agent label mapping relationship table are searched to determine the service agent label corresponding to the keyword;

[0009] A service summary is generated based on the keywords and their corresponding service provider tags.

[0010] In the call center service summary creation method of the embodiment of the present specification, after generating the service summary based on the keyword and its corresponding service agent tag, the method further includes:

[0011] The service summary is pushed to the target agent for confirmation or modification; the target agent is the agent who participates in the voice conversation in the call platform.

[0012] In the call center service summary creation method of the embodiment of this specification, identifying the target user's calling intention based on the IVR track and the service status data includes:

[0013] Using the IVR trajectory and the service status data as the user behavior state vector corresponding to the target user in this voice conversation;

[0014] Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix to obtain a similarity set; the user behavior state matrix includes user behavior state vectors corresponding to the identified call intentions of all users;

[0015] Determining a target vector in the user behavior state matrix based on the similarity set; the target vector is the user behavior state vector having the highest similarity to the user behavior state vector corresponding to the target user in the current voice conversation;

[0016] The calling intention corresponding to the target vector is used as the calling intention of the target user in this voice conversation.

[0017] In the call center service summary creation method of the embodiment of this specification, before identifying the calling intention of the target user according to the IVR track and the service status data, the method further includes:

[0018] According to the formula Normalizing the IVR trajectory;

[0019] 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the x of the i-th parameter within the specified data range i The maximum value of .

[0020] In the call center service summary creation method of the embodiment of this specification, before identifying the calling intention of the target user according to the IVR track and the service status data, the method further includes:

[0021] According to the formula Normalizing the IVR trajectory;

[0022] 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the x of the i-th parameter within the specified data range iThe maximum value of a and b are preset constants, and a and b satisfy

[0023] In the call center service summary creation method of the embodiment of this specification, the querying of the word segmentation library and the service agent label mapping relationship table based on the keyword to determine the service agent label corresponding to the keyword includes:

[0024] The keyword is used as input, and the mapping relationship table between the word segmentation library and the service provider label is queried in a recursive query manner to determine the service provider label corresponding to the keyword.

[0025] On the other hand, the embodiment of this specification also provides a call center service summary creation device, including:

[0026] A data collection module is used to collect the IVR track of the target user when the call platform conducts a voice conversation with the target user, and obtain the service status data of the target user;

[0027] an intention recognition module, configured to identify the target user's calling intention based on the IVR track and the service status data after the voice conversation between the call platform and the target user ends;

[0028] An intention word segmentation module is used to extract keywords that can represent the call intention from the call intention;

[0029] A label mapping module is used to query the word segmentation library and the service agent label mapping relationship table according to the keyword to determine the service agent label corresponding to the keyword;

[0030] The summary generation module is used to generate a service summary based on the keywords and their corresponding service provider tags.

[0031] On the other hand, an embodiment of this specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the computer program executes instructions of the above method when executed by the processor.

[0032] On the other hand, an embodiment of this specification further provides a computer storage medium having a computer program stored thereon, wherein the computer program executes the instructions of the above method when executed by a processor of a computer device.

[0033] On the other hand, an embodiment of this specification further provides a computer program product, which includes a computer program. When the computer program is executed by a processor of a computer device, the computer program executes the instructions of the above method.

[0034] It can be seen from the technical solutions provided in the above embodiments of this specification that the embodiments of this specification automatically identify the user's calling 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 library and the service agent label mapping relationship table to determine the service agent label corresponding to the keyword, and finally automatically generate a service summary based on the keyword and its corresponding service agent label, thereby realizing the automatic creation of the service summary, and eliminating the need for front-line agents on the call platform side to manually create the service summary, thereby improving the creation efficiency and content accuracy of the call center service summary and saving labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some of the embodiments described in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0036] Figure 1 A schematic diagram showing an application scenario of a small statement server in some embodiments of this specification is shown;

[0037] Figure 2 A flowchart of a method for creating a call center service summary in some embodiments of this specification is shown;

[0038] Figure 3 A schematic diagram illustrating identifying target user calls based on IVR traces and service status data in some embodiments of this specification is shown;

[0039] Figure 4 A flowchart showing a method for creating a call center service summary in some other embodiments of this specification is shown;

[0040] Figure 5 A flowchart showing a method for creating a call center service summary in other embodiments of this specification is shown;

[0041] Figure 6 It shows a structural block diagram of a device for creating a call center service summary in some embodiments of this specification;

[0042] Figure 7 It shows a structural block diagram of a computer device in some embodiments of this specification.

[0043] [Description of Reference Numerals]

[0044] 10. Client;

[0045] 20. Call center platform;

[0046] 30. Small statement server;

[0047] 61. Data acquisition module;

[0048] 62. Intent recognition module;

[0049] 63. Intent segmentation module;

[0050] 64. Label mapping module;

[0051] 65. Summary generation module;

[0052] 702. Computer equipment;

[0053] 704, processor;

[0054] 706. Memory;

[0055] 708, driving mechanism;

[0056] 710, input / output interface;

[0057] 712. Input devices;

[0058] 714. Output device;

[0059] 716. Presentation equipment;

[0060] 718. Graphical User Interface;

[0061] 720, network interface;

[0062] 722, communication link;

[0063] 724. Communication bus. DETAILED DESCRIPTION

[0064] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0065] The embodiments of this specification relate to a technology for automatically creating service summaries, which can be applied to the creation of service summaries in call center scenarios in various industries, and are particularly suitable for scenarios where call centers transfer incoming calls to agents for processing.

[0066] To facilitate understanding, some concepts are explained before describing the embodiments of this specification.

[0067] 1. Call Center

[0068] A call center, also known as a customer service center, is an integrated information service system based on computer communication technology (mainly including a call platform, etc.) to handle voice calls and inquiries from businesses and customers. A call center generally has the ability to handle a large number of calls simultaneously, and also has caller ID display, which can automatically assign incoming calls to personnel with corresponding skills (such as agents) to handle them, and can record and store all incoming call information.

[0069] 2. Interactive Voice Response (IVR)

[0070] An IVR is an automated voice response system that provides users with self-service voice response services through communication networks and voice-based value-added support platforms. An essential component of a call center (or call center platform), IVR provides 24 / 7 access to answer user calls and provide relevant services. It offers features such as voice navigation, information query, voicemail, fax, and outbound dialing. For example, when a user dials a designated number through a client (such as a telephone), they can follow the IVR's prompts to listen to and send desired voice messages, or participate in interactive services such as chatting and making friends.

[0071] 3. Service Summary

[0072] A service summary is a form of customer service record used by a call center to document the service process for responding to incoming calls. It can include information such as the user's call intent (i.e., the issue), the responsible department to whom the call should be directed, the call number, and the time of the call.

[0073] Given that manually creating service summaries is inefficient and prone to misremembering or missing call intent, this manual provides a technical solution for automatically creating service summaries to improve the efficiency and content accuracy of call center service summary creation and save labor costs.

[0074] Figure 1The application scenarios of the summary server in some embodiments of this specification are shown. The user can have a voice conversation with the call platform 20 based on the client 10. The summary server 30 can collect the user's IVR trajectory and obtain the user's business status data when the user has a voice conversation with the call platform 20. After the call platform 20 ends the voice conversation with the target user, the user's call intention is identified based on the obtained IVR trajectory and business status data; keywords that can represent the call intention are extracted from the call intention; the word segmentation library and the service agent label mapping relationship table are queried based on the keywords to determine the service agent label corresponding to the keyword; and a service summary is generated based on the keyword and its corresponding service agent label.

[0075] In some embodiments, the client 10 can be a fixed telephone, a mobile phone (such as a smart phone) or other terminal device with a voice conversation function (such as a self-service terminal device, a desktop computer, a laptop computer, a tablet computer, a digital assistant or a smart wearable device, etc.). Among them, smart wearable devices may include smart bracelets, smart watches, smart glasses or smart helmets, etc. Of course, the client 10 is not limited to the above-mentioned electronic devices with a certain entity, it can also be software running in the above-mentioned electronic devices (such as App, etc.). The small statement server 30 can be an electronic device with computing and network interaction functions; it can also be software running in the electronic device to provide business logic for data processing and network interaction.

[0076] This specification embodiment provides a call center service summary creation method, which can be applied to the above-mentioned summary service side, referring to Figure 2 As shown, in some embodiments, the call center service summary creation method may include the following steps:

[0077] Step 201: When a voice conversation is conducted between a call platform and a target user, an IVR track of the target user is collected, and the service status data of the target user is obtained.

[0078] Step 202: After the voice platform ends the voice conversation with the target user, the calling intention of the target user is identified based on the IVR track and the service status data.

[0079] Step 203: extract keywords that can represent the call intention from the call intention.

[0080] Step 204: query the word segmentation library and the service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword.

[0081] Step 205: Generate a service summary based on the keywords and their corresponding service provider tags.

[0082] The embodiment of this specification automatically identifies the user's calling intention based on the IVR trajectory and business status, and queries the word segmentation library and the service agent label mapping relationship table based on the keywords that can represent the calling intention in the call intention, thereby determining the service agent label corresponding to the keyword. Finally, a service summary is automatically generated based on the keyword and its corresponding service agent label, thereby realizing the automatic creation of the service summary, eliminating the need for front-line agents on the call center side to manually create the service summary, thereby improving the creation efficiency and content accuracy of the call center service summary and saving labor costs.

[0083] Voice conversations between the call center and users are typically initiated by users (e.g., user-initiated business inquiries or complaints). They can also be initiated by the call center (e.g., a call center follow-up call). Since each voice conversation is associated with a service summary, a corresponding service summary can be created for each voice conversation. Therefore, the target user can be the user associated with a specific voice conversation.

[0084] Collecting the target user's IVR track during a voice conversation between the call platform and the target user refers to collecting the target user's IVR track when the call platform establishes a voice conversation channel with the target user's corresponding client. In specific implementations, the small summary server can instruct or request the call platform (or IVR system) to collect the target user's IVR track. In other words, the small summary server can obtain the target user's IVR track from the call platform (or IVR system).

[0085] An IVR track records information such as conversation nodes (i.e., conversation stages), interactive actions (e.g., button selections), and dwell time (e.g., the duration of each conversation node) during a user's interaction with the call center (or IVR system). The call center (or IVR system) can then provide users with timely action options based on their interactions.

[0086] In IVR traces, user feedback can be divided into two types: positive feedback and negative feedback. Positive feedback refers to actions that directly indicate user intent; negative feedback refers to actions that do not directly indicate user intent (such as frequency of node visits, duration of stay, current status, etc.). In actual data collection, the amount of positive feedback collected from users may be relatively small. To accurately identify user intent, negative feedback can also be used as a reference.

[0087] For example, in one exemplary embodiment, a user calls in to inquire about a loan issue. The user's current loan status is successful, but the system's automatic deduction failed on a certain repayment date, and the current bill is overdue. The IVR system first recommends options such as repayment issues and overdue issues. The user's selection of the system's pre-set options is considered positive feedback. Otherwise, any other action is considered negative feedback.

[0088] For example, in an exemplary embodiment, when the call center platform (or IVR system) connects to a user's call, it can output operation options such as "Welcome to call..., please dial the extension number, press 1 for consultation, press 2 for after-sales, press 3 for the latest promotions, press 9 for complaints and suggestions, and press 0 for number inquiries" through voice. At this time, it is a dialogue node. When the user selects one of the operation options, he or she can enter the next dialogue node.

[0089] IVR traces can reflect the user's calling intention to a certain extent; however, relying solely on IVR traces may make it difficult to fully and objectively identify the user's calling intention. Therefore, in the embodiments of this specification, while collecting the target user's IVR trace, the target user's business status data can also be obtained. For example, in an exemplary embodiment, taking the loan business as an example, the business status data includes: the user's loan application, loan review, loan disbursement, repayment, overdue status, etc. in various channels. In addition, as needed, the business status data may also include other information (such as incoming call channels, historical incoming calls, whether a work order has been created, etc.)

[0090] Service status data reflects the user's latest service status. User behavior may vary under different service statuses. Therefore, service status data can also be used to assist in identifying the user's calling intent. For example, in one exemplary embodiment, when a user calls to inquire about repayment matters, if the user's repayment status indicates that the current repayment has failed, it can be determined that the user's calling intent is to inquire about the cause of the repayment failure and the corresponding solution.

[0091] refer to Figure 3 As shown, in some embodiments, identifying the call schematic diagram of the target user according to the IVR track and the service status data may include the following steps:

[0092] Step 301: Use the IVR trajectory and the service status data as a user behavior state vector corresponding to the target user in this voice conversation.

[0093] The parameter values ​​of each parameter in IVR trajectory and service status data are generally numeric or constant. These parameter values ​​can be arranged in sequence to form a vector. Therefore, the IVR trajectory and service status data for the same voice conversation can be used as the corresponding user behavior state vector for that voice conversation.

[0094] Step 302: Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix to obtain a similarity set; the user behavior state matrix includes user behavior state vectors corresponding to the identified call intentions of all users.

[0095] In some embodiments, the identified call intentions of all users may be the identified call intentions of all users within a specified historical period. The specified historical period may be pre-set as needed. For example, the specified historical period may be the last six months, one year, or the last three years.

[0096] Obviously, in order to facilitate subsequent similarity calculation, 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 conversation.

[0097] For example, in an exemplary embodiment, the user behavior state vector corresponding to the target user in this voice conversation is a1, b1, c1, x1, y1, where a1, b1, c1 are the parameter values ​​corresponding to the IVR trajectory of the target user in this voice conversation, and x1, y1 are the parameter values ​​corresponding to the service state of the target user in this voice conversation. Then the i-th user behavior state vector in the user behavior state matrix can be expressed as: a i ,b i ,c i ,x i ,y i , where a i ,b i ,c i ,x i ,y i Corresponding to a1, b1, c1, x1, y1, that is, a i and a1 are two parameter values ​​under the same parameters, b i and b1 are two parameter values ​​under the same parameters, c i and c1 are two parameter values ​​under the same parameters, x i and x1 are two parameter values ​​under the same parameters, y i and y1 are two parameter values ​​under the same parameters.

[0098] 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 a vector similarity algorithm such as Euclidean distance and cosine distance, and these similarities can form a similarity set.

[0099] In other embodiments, considering that different parameters in the IVR trajectory and business status data have different contributions or influences on the identification of call intent, in order to further improve the progress of call intent identification, different weights can be set for each parameter in the IVR trajectory and business status data as needed during specific implementation. For example, in an exemplary embodiment, taking the IVR trajectory as an example, the parameters corresponding to positive feedback behavior can be assigned higher weights, the parameters corresponding to negative feedback behavior can be assigned lower weights, and so on. In this scenario, the user behavior state vector can be a weighted user behavior state vector, for example, a1, b1, c1, x1, y1 are weighted to become λ1a1, λ2b1, λ2c1, λ4x1, λ5y1.

[0100] Step 303: Determine a target vector in the user behavior state matrix based on the similarity set; the target vector is the user behavior state vector having the highest similarity to the user behavior state vector corresponding to the target user in the current voice conversation.

[0101] By sorting the similarity set, the user behavior state vector (ie, the target vector) having the highest similarity to the user behavior state vector corresponding to the target user in the current voice conversation can be determined.

[0102] Step 304: Use the calling intention corresponding to the target vector as the calling intention of the target user in this voice conversation.

[0103] The highest similarity between two user behavior state vectors indicates that the corresponding IVR trajectory and service status data are extremely similar (or even identical). As described above, both IVR trajectory and service status can represent call intent. Therefore, the call intent corresponding to the target vector can be used as the target user's call intent for this voice conversation. Compared to considering only the IVR trajectory, this call intent recognition method that combines IVR trajectory and service status data in the embodiments of this specification can improve the accuracy of call intent recognition.

[0104] In some embodiments, extracting keywords representing the call intent from the call intent may include first using a word segmentation tool (such as Jieba) to segment the call intent, and then using a keyword recognition tool (such as SurTime, Adwords, etc.) to identify keywords from the segmentation results. For example, in one exemplary embodiment, using a loan repayment scenario, if the text corresponding to the call intent is: "Repayment process, normal repayment service, settlement processing," the keywords "repayment, normal, settlement" may be extracted.

[0105] The mapping relationship table between the word segmentation library and the service provider label is pre-configured to indicate the correspondence between each business-related keyword and the corresponding service provider label. Among them, the service provider label is used to uniquely identify a type of service provider (i.e., the person responsible for the response). For example, "normal repayment" corresponds to "the person responsible for normal repayment", "settlement processing" corresponds to "the person responsible for the settlement processing", and so on. Therefore, by querying the word segmentation library and the service provider label mapping relationship table by keywords, the service provider label corresponding to the keyword can be accurately identified. In some embodiments, the keyword can be used as input to query the word segmentation library and the service provider label mapping relationship table in a recursive query manner to determine the service provider label corresponding to the keyword.

[0106] Generating a service summary based on the keywords and their corresponding service agent tags may refer to: filling information such as the keywords and their corresponding service agent tags into a preset service summary template, thereby automatically generating a service summary for this voice conversation.

[0107] This embodiment of the specification provides another method for creating a call center service summary, which can be applied to the above-mentioned summary service side. Figure 4 As shown, in some other embodiments, the call center service summary creation method may include the following steps:

[0108] Step 401: When a voice conversation is conducted between a call platform and a target user, an IVR track of the target user is collected, and the service status data of the target user is obtained.

[0109] Step 402: After the voice conversation between the call platform and the target user ends, the IVR trajectory is normalized.

[0110] Step 403: Identify the target user's calling intention based on the IVR track and the service status data.

[0111] Step 404: extract keywords that can represent the call intention from the call intention.

[0112] Step 405: query the word segmentation library and the service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword.

[0113] Step 406: Generate a service summary based on the keywords and their corresponding service provider tags.

[0114] and Figure 2 Compared with the call center service summary creation method shown in the figure, Figure 4The call center service summary creation method shown includes a step for normalizing the IVR trace after the call center platform completes the voice conversation with the target user. Normalization maps large values ​​to a smaller range, improving the efficiency of subsequent vector similarity calculations. During implementation, the normalization algorithm can be selected as needed.

[0115] For example, in some embodiments, normalizing the IVR trace may include:

[0116] According to the formula Normalizing the IVR trajectory;

[0117] 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the value of x for the i-th parameter within the specified data range i The maximum value of . The parameter value can be normalized to between 0 and 1.

[0118] For example, in some other embodiments, normalizing the IVR trace may include:

[0119] According to the formula Normalizing the IVR trajectory;

[0120] 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the value of x for the i-th parameter within the specified data range i The maximum value of 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.

[0121] This embodiment of the specification provides another method for creating a call center service summary, which can be applied to the above-mentioned summary service side. Figure 5 As shown, in some other embodiments, the call center service summary creation method may include the following steps:

[0122] Step 501: When a voice conversation is conducted between a call platform and a target user, an IVR track of the target user is collected, and the service status data of the target user is obtained.

[0123] Step 502: After the voice conversation between the call platform and the target user ends, the IVR trajectory is normalized.

[0124] Step 503: Identify the target user's calling intention based on the IVR track and the service status data.

[0125] Step 504: extract keywords that can represent the call intention from the call intention.

[0126] Step 505: query the word segmentation database and the service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword.

[0127] Step 506: Generate a service summary based on the keywords and their corresponding service provider tags.

[0128] Step 507: Push the service summary to the target agent for confirmation or modification; the target agent is the agent who participates in the voice conversation in the call platform.

[0129] and Figure 4 Compared with the call center service summary creation method shown in the figure, Figure 5 In the call center service summary creation method shown, a service summary confirmation step is added after the service summary is generated; this helps to improve the accuracy of matching service personnel.

[0130] Although the process flows described above include multiple operations occurring in a particular order, it should be understood that these processes may include more or fewer operations, which may be performed sequentially or in parallel (eg, using parallel processors or a multi-threaded environment).

[0131] Corresponding to the above-mentioned call center service summary creation method, the embodiment of this specification also provides a call center service summary creation device, which can be configured on the above-mentioned summary service end, referring to Figure 6 As shown, in some embodiments, the call center service summary creation device may include:

[0132] The data collection module 61 is used to collect the IVR track of the target user when the voice platform conducts a voice conversation with the target user, and obtain the service status data of the target user;

[0133] An intention recognition module 62 is configured to recognize the target user's calling intention based on the IVR track and the service status data after the voice conversation between the call platform and the target user ends.

[0134] Intent word segmentation module 63, used to extract keywords that can represent the call intent from the call intent;

[0135] The label mapping module 64 is used to query the word segmentation library and the service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword;

[0136] The summary generating module 65 is configured to generate a service summary based on the keywords and their corresponding service provider tags.

[0137] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0138] It should be noted that in the embodiments of this specification, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user and fully authorized by all parties.

[0139] The embodiment of this specification also provides a computer device. Figure 7 As shown, 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 of which may implement one or more hardware threads. The computer device 702 may also include any memory 706 for storing any type of information, such as code, settings, data, etc. In one specific embodiment, the memory 706 may contain a computer program executable by the processor 704. When executed by the processor 704, the computer program may execute instructions for the call center service summary creation method described in any of the above embodiments. For example, and without limitation, the memory 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory may use any technology to store information. Furthermore, any memory may provide volatile or non-volatile retention of information. Furthermore, any memory may represent a fixed or removable component of the computer device 702. In one embodiment, when the processor 704 executes the associated instructions stored in any memory or combination of memories, the computer device 702 may perform any operation of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like.

[0140] The computer device 702 may also include an input / output interface 710 (I / O) for receiving various inputs (via input devices 712) and for providing various outputs (via output devices 714). A specific 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), input devices 712, and output devices 714 may not be included, and the computer device 702 may simply be a computer device in a network. The 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 the components described above together.

[0141] The communication link 722 can be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 722 can include any combination of hardwired links, wireless links, routers, gateway functions, name list servers, etc., governed by any protocol or combination of protocols.

[0142] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), computer-readable storage media, and computer program products of some embodiments of the present specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processor to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processor generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0143] 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, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, the instruction device being implemented in the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processor so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0145] In a typical configuration, a computer device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0146] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0147] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined in this specification, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0148] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] Embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processors connected via a communications network. In distributed computing environments, program modules may be located in local and remote computer storage media, including storage devices.

[0150] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0151] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0152] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example 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 do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0153] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for creating a call center service summary, characterized in that: include: When the call platform conducts a voice conversation with the target user, it collects the IVR track of the target user and obtains the service status data of the target user; After the voice platform and the target user end the voice conversation, identifying the target user's calling intention according to the IVR track and the service status data; Extracting keywords that can represent the call intention from the call intention; According to the keyword, the word segmentation library and the service agent label mapping relationship table are searched to determine the service agent label corresponding to the keyword; Generate a service summary based on the keywords and their corresponding service provider tags; Identifying the target user's calling intention according to the IVR track and the service status data includes: The IVR trajectory and the service status data are used as the user behavior state vector corresponding to the target user in the current voice conversation; wherein different weights are set for each parameter in the IVR trajectory and the service status data, and the user behavior state vector is a weighted user behavior state vector; Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix to obtain a similarity set; the user behavior state matrix includes user behavior state vectors corresponding to the identified call intentions of all users; Determining a target vector in the user behavior state matrix based on the similarity set; the target vector is the user behavior state vector having the highest similarity to the user behavior state vector corresponding to the target user in the current voice conversation; The calling intention corresponding to the target vector is used as the calling intention of the target user in this voice conversation.

2. The call center service summary creation method according to claim 1, wherein: After generating a service summary based on the keywords and their corresponding service provider tags, the method further includes: The service summary is pushed to the target agent for confirmation or modification; the target agent is the agent who participates in the voice conversation in the call platform.

3. The call center service summary creation method according to claim 1, wherein: Before identifying the target user's calling intention according to the IVR track and the service status data, the method further includes: According to the formula Normalizing the IVR trajectory; 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the x of the i-th parameter within the specified data range i The maximum value of .

4. The call center service summary creation method according to claim 1, wherein: Before identifying the target user's calling intention according to the IVR track and the service status data, the method further includes: According to the formula Normalizing the IVR trajectory; 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 i-th parameter in the IVR trajectory, x min is the maximum value of the i-th parameter within the specified data range, x max is the x of the i-th parameter within the specified data range i The maximum value of a and b are preset constants, and a and b satisfy 5. The call center service summary creation method according to claim 1, wherein: The querying of the word segmentation library and the service provider label mapping relationship table according to the keyword to determine the service provider label corresponding to the keyword includes: The keyword is used as input, and the mapping relationship table between the word segmentation library and the service provider label is queried in a recursive query manner to determine the service provider label corresponding to the keyword.

6. A device for creating a call center service summary, characterized in that: include: A data collection module is used to collect the IVR track of the target user when the call platform conducts a voice conversation with the target user, and obtain the service status data of the target user; an intention recognition module, configured to identify the target user's calling intention based on the IVR track and the service status data after the voice conversation between the call platform and the target user ends; An intention word segmentation module is used to extract keywords that can represent the call intention from the call intention; A label mapping module is used to query the word segmentation library and the service agent label mapping relationship table according to the keyword to determine the service agent label corresponding to the keyword; A summary generation module is used to generate a service summary based on the keywords and their corresponding service provider tags; Identifying the target user's calling intention according to the IVR track and the service status data includes: The IVR trajectory and the service status data are used as the user behavior state vector corresponding to the target user in the current voice conversation; wherein different weights are set for each parameter in the IVR trajectory and the service status data, and the user behavior state vector is a weighted user behavior state vector; Determine the similarity between the user behavior state vector and each user behavior state vector in the user behavior state matrix to obtain a similarity set; the user behavior state matrix includes user behavior state vectors corresponding to the identified call intentions of all users; Determining a target vector in the user behavior state matrix based on the similarity set; the target vector is the user behavior state vector having the highest similarity to the user behavior state vector corresponding to the target user in the current voice conversation; The calling intention corresponding to the target vector is used as the calling intention of the target user in this voice conversation.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 5.

8. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes the instructions of the method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program executes instructions of the method according to any one of claims 1 to 5.

Images