Data processing method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a data processing method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining first operation data which is obtained in a dialogue interaction process; performing hierarchical processing on the first operation data to obtain interaction behavior data of an interaction object; according to the interaction behavior data, the interaction behavior of the interaction object is analyzed, a data analysis result is obtained, and the data analysis result is used for representing the interaction efficiency of the dialogue interaction. According to the embodiment of the invention, the interaction efficiency of the dialogue interaction process can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data processing method and device, an electronic device, a storage medium, and a program product. Background Art

[0002] An interactive voice response (IVR) system is an automatic voice response system that can provide users with self-service and information query. For example, in the financial field, automatic voice navigation based on the IVR system can guide users to choose corresponding services or financial products.

[0003] In the related art, the interactive voice response process of the IVR system is often manually configured based on subjective experience, and a dialogue interaction is provided for the interactive object based on the interactive voice response process, which has the problem of low interaction efficiency. Summary of the invention

[0004] The present disclosure provides a data processing method and device, an electronic device, a storage medium, and a program product.

[0005] In a first aspect, the present disclosure provides a data processing method, the data processing method comprising:

[0006] Acquire first operation data, where the first operation data is obtained during the dialogue interaction process;

[0007] Performing hierarchical processing on the first operation data to obtain interaction behavior data of the interaction object;

[0008] The interactive behavior of the interactive object is analyzed according to the interactive behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interactive efficiency of the dialog interaction.

[0009] In a second aspect, the present disclosure provides a data processing device, the device comprising:

[0010] A data acquisition module, used to acquire first operation data, where the first operation data is obtained during the dialogue interaction process;

[0011] A hierarchical processing module, used for performing hierarchical processing on the first operation data to obtain interactive behavior data of the interactive object;

[0012] A behavior analysis module is used to analyze the interaction behavior of the interaction object according to the interaction behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interaction efficiency of the dialogue interaction.

[0013] In a third aspect, the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, and one or more of the computer programs are executed by the at least one processor so that the at least one processor can execute the data processing method of the first aspect above.

[0014] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the data processing method of the first aspect when executed by a processor.

[0015] In a fifth aspect, the present disclosure provides a computer program product, characterized in that it includes a computer-readable code, or a non-volatile computer-readable storage medium carrying a computer-readable code, and when the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned data processing method.

[0016] The embodiments provided by the present disclosure can obtain first operating data in the process of dialogue interaction, and perform layered processing on the first operating data to obtain interactive behavior data of interactive objects, and analyze the response processing process of the system in the dialogue interaction; analyze the interactive behavior of the interactive objects according to the interactive behavior data to obtain data analysis results, and intuitively characterize the interactive efficiency of the dialogue interaction, so that the system response process in the dialogue interaction can be updated based on the data analysis results, thereby improving the interactive efficiency of the dialogue interaction.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings, in which:

[0019] Figure 1 A flowchart of a data processing method provided by an embodiment of the present disclosure;

[0020] Figure 2 A schematic diagram of a data analysis framework provided by an embodiment of the present disclosure;

[0021] Figure 3 A block diagram of a data processing device provided in an embodiment of the present disclosure;

[0022] Figure 4 A block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0024] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0025] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0026] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "including" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0027] In the technical solution disclosed in this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution complies with relevant national laws and regulations (for example, the "Information Security Technology Personal Information Security Specification", etc.). For example: corresponding prescribed measures are taken for personal information access control; prescribed restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; when using personal information, clear identity orientation is eliminated to avoid precise positioning of specific individuals.

[0028] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0029] For ease of understanding, the following professional terms used in the embodiments of the present disclosure are explained and will not be repeated later.

[0030] In the traditional sense, a call center refers to a call response center that mainly receives calls and is used to provide users with various call response services. With the rapid development of technology, modern call centers generally refer to call processing systems that use modern communication and computer technologies, such as interactive voice response (IVR) systems, to automatically and flexibly handle a variety of different incoming and outgoing telephone operations and services.

[0031] Call volume refers to the number of calls received by a call center system within a certain period of time, which can be used to characterize the needs of interactive objects and service popularity. The interactive objects in the embodiments of the present disclosure may be objects that interact with the IVR system in the call center, for example, corporate customers.

[0032] The connect rate refers to the proportion of calls that are successfully connected, which can be used to characterize the performance of the IVR system and the satisfaction of the interacting party.

[0033] Average Handle Time refers to the average time that the interaction object interacts with the IVR system.

[0034] Transfer Rate refers to the proportion of interactions that need to be transferred to human customer service for response.

[0035] Abandon Rate refers to the proportion of interactions where the recipient abandons the call while waiting for the IVR system to respond.

[0036] Customer Satisfaction refers to customer satisfaction with the IVR system.

[0037] Repeat Call Rate refers to the proportion of customers who need to call multiple times because the IVR system cannot solve their problems.

[0038] Generally, after receiving a call request from an interactive object, the call center system can generally provide the interactive object with self-service and information query based on the IVR system to solve the problem of being unable to respond to the interactive object's call request in time when the manual agent is busy.

[0039] In the related art, before using the IVR system to perform a conversation interaction, it is usually necessary to create an IVR version, manually create a fixed IVR process based on subjective experience, and select an access number bound to the IVR process when choosing to publish the IVR process. In this way, when the interactive object dials the access number to initiate a call request, it will interact with the interactive object based on the fixed IVR process bound to the access number. However, due to the diversity of interactive objects, this method of interactive voice response interaction processing with the interactive object based on a fixed IVR process often has the problem of low interaction efficiency.

[0040] That is, in the related art, people often do not pay attention to how to store and analyze the operation data generated by the IVR system, but only rely on artificial subjective experience to configure a fixed IVR process to perform a fixed dialogue interaction process on thousands of interactive objects. Due to the different needs of different interactive objects, this method often affects the interaction efficiency. To this end, in the embodiment of the present disclosure, considering that the original operation data (hereinafter referred to as the first operation data) generated by the IVR system in the process of executing the dialogue interaction is isolated and has no business meaning at the beginning, however, it can be considered to perform a hierarchical analysis on the isolated first operation data, so as to perform statistical analysis on the isolated first operation data from different dimensions, and obtain interactive behavior data with actual business meaning that can characterize the interactive behavior of the interactive object. The analyzed interactive behavior data can intuitively characterize the response processing process of the IVR system. Therefore, through the interactive behavior data, a data analysis result that characterizes the interaction efficiency of the dialogue interaction process from at least one dimension such as the call response dimension and the voice navigation dimension can be generated. Based on the data analysis result, the response process of the dialogue interaction is updated, and the response processing is performed based on the updated response process, which can improve the interaction efficiency of the dialogue interaction.

[0041] See also Figure 1 and Figure 2 , which are respectively a flow chart of a data processing method provided by an embodiment of the present disclosure and a schematic diagram of a framework of data analysis and processing. The method can be applied to electronic devices, for example, can be used in a server, or can also be applied to a terminal device as required, without special limitation here.

[0042] It should be noted that the call center system in the embodiment of the present disclosure may include the following components: ivr configuration component (ivr-manager), voice gateway, ivr processing component (ivr-engine), service gateway, ivr data analysis component (ivr-logsys). The present disclosure does not limit the number and type of specific components included in the call center system.

[0043] Among them, the ivr data analysis component can be deployed in an electronic device that executes the method described in the embodiment of the present disclosure; the ivr configuration component can be used to receive the user's process configuration for the IVR configuration tool and the release configuration of the access number; the voice gateway can be implemented based on Freeswitch (a soft switching solution for telephones), which can be responsible for providing routing and interconnection communications for audio, text or any other form of media and providing self-service IVR services; the ivr processing component can be used to receive calls from the voice gateway, and calculate the process nodes that need to be initialized based on the access number and call number passed when the voice gateway is called; the service gateway, for example, can be an operator gateway, which is used to connect to the lines of each operator.

[0044] like Figure 1 As shown, the data processing method provided by the embodiment of the present disclosure includes the following steps S101-S103, which are described in detail below.

[0045] Step S101, obtaining first operation data, where the first operation data is obtained during a dialog interaction process.

[0046] refer to Figure 2 The first operation data may be the operation data of each node in the IVR system during the dialogue interaction, wherein the node may be any one or more nodes in the IVR process on which the IVR system depends to execute the dialogue interaction. The IVR process may be pre-configured by the user. Usually, in the IVR system, an IVR process may be configured for each access number of the call center system.

[0047] In the example, multiple nodes can be configured in an IVR process, for example, a playback node, a playback and number receiving node, an interface call node, a read channel variable node, a write channel variable node, a variable assignment node, a service time node, a working time node, a hash diversion node, a whitelist diversion node, a skill group transfer node, a voice navigation node and other nodes. Among them, the playback node is the main node corresponding to the key navigation, which is usually used to broadcast a preset voice, which is used to prompt the interactive object to enter a navigation key or enter the identity verification information that needs to be verified; the playback and number receiving node can be used to receive the user's key input; the settings of other nodes can be set as needed, and there is no special limitation here.

[0048] The first operation data may be data generated by each node of the IVR process during the execution process to reflect the execution result thereof. The first operation data usually has no business meaning, and the first operation data generated by each node are often isolated from each other and have no business association.

[0049] In the example, the first operating data corresponding to the playback node may include the node start time, the node completion time, the broadcast voice content, the user input content, the preset allowed input content, etc.; the first operating data corresponding to the playback and number collection node may include the time of entering the node task, the time of completing the task, the content of the playback, the content input by the user (number collection value), and the allowed number collection content; the first operating data corresponding to the interface call node may include the time of entering the node task, the time of completing the task, the parameters of calling the interface, the address of calling the interface, the parameters returned by the interface, and the time consumed by the interface call; the first operating data corresponding to the read channel variable node may include the time of entering the node task, the time of completing the task, the location of the variable to be read, and the value of the variable to be read; the first operating data corresponding to the write channel variable node may include the time of entering the node task, the time of completing the task, the location of the variable to be written, and the value of the variable to be written.

[0050] In the example, the first operating data corresponding to the variable assignment node may include the time of entering the node task, the time of completing the task, the object to be assigned, and the assigned value; the first operating data corresponding to the service time node may include the time of entering the node task, the time of completing the task, the time point for judgment, the conditions for service time judgment, and the result of service time judgment; the first operating data corresponding to the working time node may include the time of entering the node task, the time of completing the task, the time point for judgment, the conditions for working time judgment, and the result of working time judgment; the first operating data corresponding to the hash diversion node may include the time of entering the node task, the time of completing the task, the content of the object to be hashed, the percentage value of the hash calculation, the ratio of hash diversion, and the result of hash diversion judgment.

[0051] In the example, the first operating data corresponding to the whitelist diversion node may include the time of entering the node task, the time of completing the task, the number of calls, and the whitelist diversion judgment result; the first operating data corresponding to the skill group transfer node may include the node start time, the node completion time, the skill group identifier to be transferred (for example, the skill group name), the transfer script content, the transfer waiting voice, etc.; the first operating data corresponding to the voice navigation node may include the node start time, the node completion time, the preset navigation voice content, etc.

[0052] It should be noted that, in the embodiment of the present disclosure, before obtaining the first operating data, it is necessary to obtain authorization from the interactive object to perform data analysis and processing on the first operating data before using it. For example, a preset voice message can be broadcast in the initial stage of starting a conversation to solicit authorization from the interactive object to use the first operating data generated by it. If the interactive object agrees to authorize the use, step S101 can be executed. Otherwise, the method of the embodiment of the present disclosure will not be used to process the first operating data.

[0053] The interaction object may be any object that initiates a call request to the call center system, for example, may be a corporate customer or an individual customer.

[0054] In the embodiment of the present disclosure, the first operation data may be obtained by: obtaining the first operation data from a first message queue corresponding to the first operation data.

[0055] The first message queue can be, for example, a Kafka message queue. For example, a topic for storing the first layer, that is, the first operating data, can be set in the Kafka message queue. The IVR system can write the generated first operating data into the corresponding topic of the Kafka message queue during the execution of the dialogue interaction. Thereafter, the first operating data can be obtained by reading the data under the topic.

[0056] Step S102: performing layered processing on the first operation data to obtain interaction behavior data of the interaction object.

[0057] In the embodiment of the present disclosure, the layered processing may include at least three layers of analysis processing, wherein, when the first operating data is set as the first layer data, that is, the original operating data generated by the IVR system, the first layer analysis may be a multi-dimensional abstract statistics of the detailed data generated by each node of each IVR process in the first layer data, so as to generate a plurality of detailed data that can preliminarily reflect the interactive behavior of the interactive object, that is, the second layer data; the second layer analysis refers to, for the plurality of detailed data generated by the first layer analysis, by combining their various corresponding historical detailed data, respectively, and summarizing and analyzing them, so as to obtain detailed data that can reflect the interactive behavior of the interactive object within a certain time range, that is, the third layer data; the third layer analysis may be a statistical analysis of the plurality of detailed data generated by the second layer analysis, so as to obtain the final interactive behavior data, that is, the fourth layer data.

[0058] In the disclosed embodiment, the interaction behavior data may be determined based on the interaction activities performed by the interaction objects during the dialog interaction process.

[0059] Among them, interactive activities refer to the activities of different execution operations of corresponding interactive objects preset in the IVR process. For example, for interactive activities with activity type "70", it generally corresponds to the "back" behavior of the interactive object. For example, after the user inputs the key "1" based on the voice content of the voice navigation broadcast, after the IVR system responds to the key input by the user and broadcasts the voice broadcast content corresponding to the key, if the user finds that the selection is wrong, he can return to the previous layer of navigation content by entering other keys, for example, by entering the key "0" to regret the previous layer of voice navigation. At this time, it can be identified that the user has performed an interactive activity of type "70" by identifying the key "0" input by the user, that is, the "back" behavior has been performed. The start mark of the interactive activity is "executing an activity with activity type 70", and the end mark is "activity execution completed or hanging up".

[0060] In the example, interactive activities also include business processing within voice navigation (the start mark is "execute activities with activity type 61", and the end mark is "activity execution is completed or hang up"), business processing within key navigation (the start mark is "execute a node with a specific node code, or key navigation execution is completed", and the end mark is "enter the next round of key navigation, or hang up, or enter voice navigation"), transfer to manual processing (the start mark is "execute activities with activity types 51, 53, 68, 69, etc.", and the end mark is "activity execution is completed or hang up"), enter voice navigation (the start mark is "execute activities with activity type 62", and the end mark is "hang up or enter key navigation"), enter key navigation (the start mark is "execute a node with a specific node code, for example: node code is AJ001", and the end mark is "hang up or enter voice navigation"), etc.

[0061] Of course, this is only an example, and in actual implementation, the interactive activity may include various types of interactive activities corresponding to different behaviors of the interactive object, which are not specifically limited here.

[0062] It is understandable that, in actual implementation, considering that the first operation data may include duplicate, erroneous or incomplete data, before executing step S102, the method may further include: performing data cleaning on the first operation data. The present disclosure does not limit the specific method of data cleaning.

[0063] Step S103: analyzing the interaction behavior of the interaction object according to the interaction behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interaction efficiency of the dialog interaction.

[0064] After the first operation data generated by each node of the IVR process in the dialogue interaction process is analyzed layer by layer based on step S102 to obtain the interactive behavior data including the interactive behavior for representing the interactive behavior of the interactive object, the interactive behavior of the interactive object can be analyzed through the interactive behavior data to generate a data analysis result.

[0065] In the embodiments of the present disclosure, considering that the dimensions that best reflect the interaction efficiency in the dialogue interaction process are usually the call response capability and the voice navigation capability, the data analysis results may include analysis results that reflect the interaction efficiency of the dialogue interaction process from at least one dimension such as the call response dimension and the voice navigation dimension.

[0066] Based on the data analysis results, it is possible to determine the nodes that need to be optimized in the IVR process that the IVR system relies on in the process of executing conversational interaction. For example, if the voice navigation opening rate is small and the call transfer rate to manual is high, it usually means that the IVR system often cannot accurately understand the call intention of the interactive object, especially when combined with data such as the navigation success rate and the average navigation interaction time in the voice navigation statistical data. It can further reflect that the IVR system may not be able to accurately understand the call intention of the interactive object. Therefore, it is possible to consider updating and optimizing the service time nodes, voice navigation nodes and other nodes in the IVR process that involve understanding the call intention of the interactive object, so that the IVR system can improve the voice navigation opening rate, reduce the call transfer rate to manual, reduce the average interaction time of voice navigation, and improve the navigation success rate by accurately understanding the call intention of the interactive object.

[0067] It can be seen that based on the data processing method provided by the embodiment of the present disclosure, when the interactive object is authorized to use the first operating data generated in the process of interacting with it, the first operating data is layered and processed to abstractly obtain interactive behavior data that can be used to represent the interactive behavior of the interactive object. Since the interactive behavior data can intuitively characterize the efficiency of the response processing of the IVR system, the interactive behavior data can be used to generate data analysis results that characterize the interaction efficiency of the dialogue interaction process from at least one dimension such as call response dimension and voice navigation dimension. The response process of the dialogue interaction process is updated based on the data analysis results, and response processing is performed based on the updated response process, which can improve the interaction efficiency of the dialogue interaction process.

[0068] In some embodiments, in step S102, the first operating data is layered to obtain interactive behavior data of the interactive object, including: performing a first statistical processing on the first operating data based on a first statistical indicator to obtain first detailed data, wherein the first detailed data corresponds one-to-one to the first statistical indicator; and obtaining the interactive behavior data based on the first detailed data.

[0069] In an embodiment of the present disclosure, the first statistical indicator may include at least one of the following: call details, navigation details, voice navigation interaction details, node details, task details, process details, jump details and interactive activity type. The present disclosure does not limit the specific content of the first statistical indicator.

[0070] See also Figure 2 In actual implementation, for call detail indicators, after statistical processing of the first operation data, call detail data from three sub-dimensions, namely, time dimension, ivr-related dimension and number-related dimension, can be obtained. For example, it may include: call identifier, tenant identifier, ivr identifier, ivr name, ivr version identifier, ivr version, calling number, called number, landing number, power-on time, hang-up time (i.e., hang-up event), session identifier, call type (e.g., incoming call or outgoing call), original call type, process instance identifier, process template identifier, whether to collect call voice, collected call voice identifier, call voice start time, etc.; wherein, ivr identifier and ivr name are data used to reflect ivr-related dimension, namely, reflect the name of the IVR system used, ivr version identifier and ivr version are data used to reflect ivr version dimension; calling number, called number and landing number are data used to reflect number-related dimension; power-on time and hang-up time are data used to reflect power-on time dimension and leaving time dimension respectively.

[0071] For the process detail indicators, after statistical processing of the first operation data, data from three sub-dimensions, namely, time dimension, ivr association dimension and call dimension, can be obtained. For example, the data may include: process identifier, tenant identifier, ivr identifier, ivr name, ivr version identifier, ivr version, call identifier, session identifier, power-on time, process template identifier, process instance identifier, process type, rollback type, redo type, process execution result (for result-oriented process instance: success or failure), process status, start node instance identifier, end node instance identifier, number of rollbacks, creation time, execution time, process instance description, update time and the like; wherein, the redo type may include: parallel redo type and serial redo type, the parallel redo type means that the redo process and the rollback process are carried out simultaneously, and the serial redo type means that the redo process is executed after the rollback process is completed; the process status may include: create, run, suspend, cancel, complete, cancelling release, apply for rollback and rollback and the like.

[0072] For the navigation detail indicators, after statistical processing of the first operation data, the navigation detail data from sub-dimensions such as time dimension, ivr association dimension, incoming call number dimension, call dimension and business line (baseline) dimension can be obtained, for example, it may include: navigation identifier, tenant identifier, ivr identifier, ivr name, ivr version identifier, ivr version, business line identifier, business line name, node identifier, call identifier, session identifier, incoming call time, calling number, entry navigation time, exit navigation time, rule name, guiding words, target semantics, number of incorrect navigation button presses, whether to roll back, model type used (0: keyword model 1: entity model), business node type (-1: default value, 1: manual, 2: self-service, 3: SMS, 4: flash message, 5: APP, 6: push), whether rollback is allowed, whether rollback is successful, routing identifier, routing type, channel type, this navigation result identifier (Y: success, N: failure, C: cancel) and other contents.

[0073] For the voice navigation interaction detail indicators, after statistical processing of the first operation data, detailed voice interaction data from sub-dimensions such as time dimension, ivr dimension, number dimension, call dimension, business line dimension and navigation dimension can be obtained. For example, it may include: interaction identifier, tenant identifier, ivr identifier, ivr name, ivr version identifier, ivr version, business line identifier, business line name, task identifier, call identifier, session identifier, power-on time, caller number, navigation identifier, business line identifier, number of incorrect navigation button presses in this round, voice recognition service identifier, voice recognition service start time, voice recognition service End time, speech recognition text, intermediate results of speech recognition during menu broadcast, speech recognition service status, speech recognition service interruption type, speech recognition service interruption details, nlusession identifier, nlu start time, nlu end time, model type, nlu status, nlu results, nlu duration, Nlu return categories, spoken words, standard words, interaction node identifier, interaction node name, current round of interaction results, service recording name, navigation result identifier, whether to match the exit, follow-up or transfer speech text, whether to allow rollback, whether to rollback, whether to rollback successfully, etc.

[0074] For the node detail indicators, after statistical processing of the first operation data, the node detail data from sub-dimensions such as time dimension, ivr dimension, call dimension, and process dimension can be obtained, for example, it may include: node instance identifier, tenant identifier, ivr identifier, Ivr name, Ivr version identifier, Ivr version, process identifier, call identifier, session identifier, power-on time, process instance identifier, process template identifier, node identifier, node name, node type, node status (including: 1 ready inactive, 2 active, 3 suspended, 4 completed, 5 collaborative waiting, 6 compensation waiting, 7 activity canceled), fallback number, skip type (0 non-skip, 1 skip, 2 automatic pass), whether to compensate (0 non-compensation, 1 compensation), creation time, execution time, whether to add node report, node code, whether to add short path, task name, update time and other contents.

[0075] For the task detail indicators, after statistical processing of the first operation data, the task detail data from sub-dimensions such as time dimension, ivr dimension, call dimension, etc. can be obtained, for example, it may include: task instance identifier, tenant identifier, ivr identifier, Ivr name, Ivr version identifier, Ivr version, node identifier, call identifier, session identifier, power-on time, process instance, node instance identifier, node task identifier, task type (2 manual tasks 3 automatic tasks), execution order (default 0), whether visible (0 invisible, 1 visible), task attributes (0 normal, 1 re, 2 compensation), ivr task type of the task, node code where the task is located, execution type (0 automatic, 1 manual), completion type (0 automatic, 1 manual), task status (0 to be claimed, 1 claimed, 2 completed, 3 suspended, 4 application for refund, 5 collaborative waiting, 6 compensation waiting, 9 canceled), creation time, execution time, lua task data, task completion data, update time, task data and other contents.

[0076] For the jump detail indicators, after statistical processing of the first operation data, task detail data from sub-dimensions such as time dimension, ivr dimension, call dimension, etc. can be obtained, for example, it may include: jump instance identifier, tenant identifier, ivr identifier, Ivr name, Ivr version identifier, Ivr version, call identifier, session identifier, power-on time, jump type (1 conditional jump, 2 unconditional jump, 3 loop jump), jump name, process instance identifier, start node instance identifier, target node instance identifier, start node identifier, start node name, target node identifier, start time, update time and other contents.

[0077] It should be understood that those skilled in the art may set the first statistical indicator and the corresponding detailed data according to actual conditions, and the present disclosure does not impose any limitation on this.

[0078] In some embodiments, the first detailed data also includes interactive object behavior detailed data.

[0079] It should be noted that, for the interaction object behavior detailed data in the first detailed data; in this implementation manner, performing the first statistical processing on the first operation data based on the first statistical indicator to obtain the first detailed data may include:

[0080] Based on the interaction activity type indicator, first data of the interaction behavior of the interaction object is obtained from the first operation data, wherein the first data includes an interaction behavior identifier, a start time of the interaction behavior, an end time of the interaction behavior, and an interaction duration of the interaction behavior; based on the first data, detailed data of the interaction object behavior is obtained.

[0081] Referring to Table 1, in the embodiment of the present disclosure, the corresponding relationship between the interaction activity type and the interaction behavior of the interaction object can be expressed as follows:

[0082] Table 1

[0083]

[0084] That is, in the embodiment of the present disclosure, each executed activity can be obtained in turn according to the order in which the IVR system executes the dialogue interaction process in response to a call request, and the interaction object, that is, the start time, end time and other data of the user interaction behavior can be determined according to the type of activity and the activity encoding.

[0085] In some embodiments, the interaction object behavior detail data is used to abstract the first operation data without business meaning generated during the execution of the dialogue interaction into data with business meaning that reflects various interaction behaviors of the interaction object according to certain business tags and the logic of internal system twisting.

[0086] For example, when executing voice navigation processing, the main interaction with the interactive object, that is, the user, is in the activity of activity type 62. The interaction method can be used to interact with the interactive object in the manner configured in the IVR process until the intention of the interactive object is determined, and then this node is ended. At this time, this type of node 62 represents the interactive behavior of the interactive object entering voice navigation; and after the voice navigation dialogue determines the intention of the interactive object, it can usually enter the node of activity type 61. This node can be routed to different systems according to the intention service of the interactive object, for example, it can be routed to other IVR processes, or go to the SMS platform to send corresponding SMS operations. When the interactive object completes these services or hangs up, the 61 activity node will be ended. Therefore, based on the first operation data of this node, the voice navigation, service type and name, as well as The interactive object response data with business significance, such as the processing time; and for the key navigation behavior, considering that the playback and number receiving nodes in the IVR process can be used for navigation as well as for security verification and other operations, the business drawing personnel need to mark the corresponding key navigation nodes for different processes, and then determine whether to enter the key navigation through the unique mark under the process, such as the node code; afterwards, for the key navigation, its first data is the same as entering the key navigation, and it is necessary to identify the corresponding nodes to determine which ones are handling the business; afterwards, the types of manual transfer nodes are usually fixed, and different nodes often correspond to different manual transfer strategies. Therefore, although 51, 53, 68, 69 and other interactive activity types all indicate that manual transfer has been made, the strategies of each node are different, so they also need to be used as the first data for subsequent summary processing.

[0087] In some embodiments, the step of obtaining the interaction behavior data according to the first detailed data may include:

[0088] A second statistical processing is performed on the first detailed data according to the second statistical indicator to obtain second detailed data; and the interactive behavior data is obtained according to the second detailed data.

[0089] See also Figure 2 In actual implementation, after generating the first detailed data, the first detailed data can be put into a second message queue, which can be, for example, a Kafka message queue. Afterwards, the second statistical processing can be performed by obtaining the second detailed data from the second message queue.

[0090] In the embodiment of the present disclosure, the second statistical processing may be to combine multiple pieces of second detailed data according to a common corresponding dimension. The second statistical indicator may be an indicator reflecting the dimension commonly corresponding to two or more pieces of second detailed data, for example, a time indicator, a number indicator, etc.

[0091] In actual implementation, the second detailed data may include voice navigation detailed data generated based on the navigation detailed data and the interactive object behavior detailed data, key navigation detailed data generated based on the task detailed data and the interactive object behavior detailed data, and may also include first call detailed data generated based on the voice navigation detailed data and the key navigation detailed data. The present disclosure does not limit the specific content of the second detailed data.

[0092] The voice navigation detail data may include data in call dimension, call number dimension and time dimension, for example, may include: navigation identifier, tenant identifier, business line identifier, business line name, call identifier, session identifier, call time, caller number, entry navigation time, exit navigation time, rule name, rule click rate, whether to roll back, business node type (-1: default value, 1: manual, 2: self-service, 3: SMS, 4: flash message, 5: APP, 6: push;), whether rollback is allowed, whether rollback is successful, this navigation result identifier (Y: success, N: failure, C: cancel), navigation duration, business processing result, business processing duration, business processing name, business processing type, etc.

[0093] The button navigation details data may include data from the call dimension, the incoming call number dimension and the time dimension, for example, it may include: button navigation identifier, call identifier, incoming call time, on-hook time, single navigation duration, button navigation success identifier, number of interaction rounds, service handling duration, service handling result, service handling name, service handling type, etc.

[0094] The first call detail data may include data in the dimensions of incoming call number and event, for example, may include: call identification, call time, hang-up time, call duration, whether to enter voice navigation, number of voice navigations, number of voice navigation interaction rounds, number of voice navigation services, voice opening identification, voice navigation to manual identification, voice navigation to manual success identification, total duration of voice services, whether to enter key navigation, number of key navigations, number of key navigation interaction rounds, number of key navigation services, key navigation to manual identification, key navigation to manual success identification, total duration of key services, etc.

[0095] In some embodiments, the second detailed data includes voice navigation detailed data, key navigation detailed data and first call detailed data; and the step of obtaining the interaction behavior data according to the second detailed data includes:

[0096] According to the call response index and / or the voice navigation index, a third statistical processing is performed on the data characterizing the interactive behavior of the interactive object contained in at least one of the voice navigation detail data, the button navigation detail data and the first call detail data to obtain the interactive behavior data.

[0097] See also Figure 2 In the embodiment of the present disclosure, the interactive behavior data may be data generated by summarizing the second detailed data. The interactive behavior data may include call statistics data of call response indicators corresponding to the call response dimension, and voice navigation statistics data of voice navigation indicators corresponding to the voice navigation dimension.

[0098] Among them, the call statistics data determined according to the call response index may include: the total number of calls, call duration, the number of voice navigation calls, the number of voice navigation open calls, the number of voice navigation to key navigation calls, the voice navigation diversion rate, the voice navigation to key navigation rate, the number of multi-service handling calls, the multi-service handling call rate, the number of calls transferred to manual, the call transfer rate, the number of calls that actually transferred to manual after entering voice navigation, the call transfer rate that actually transferred to manual after entering voice navigation, the number of calls that actually transferred to manual after entering voice navigation, the number of calls that actually transferred to manual after entering voice navigation, the number of voice navigation calls that did not transfer to manual due to key switching, and the rate of voice navigation calls that did not transfer to manual due to key switching.

[0099] The voice navigation statistical data determined according to the voice navigation indicators may include: the total number of navigations, the total navigation duration, the number of successful navigations, the navigation success rate, the average number of navigation interaction rounds, the average navigation interaction duration, the number of successful calls to the speech recognition service (ASR, Automatic Speech Recognition), the number of non-rejections of natural language understanding (NLU, Natural Language Understanding), the number of successful interactions, the number of successful navigations, the number of SMS exports, the SMS export rate, the number of manual exports, the manual export rate, the number of self-service exports and the self-service export rate, etc. One or more of the following contents.

[0100] In some embodiments, the conversation interaction includes multiple interaction nodes, each of which corresponds to a stage of the conversation interaction between the interaction object and the IVR system, such as a voice navigation interaction stage, a key navigation interaction stage, etc. Among them, the interaction node may include a playback node (playing audio used to guide the interaction object on how to interact), a playback number receiving node (receiving the content (number receiving value) input by the interaction object and playing the corresponding audio), an interface call (calling the interface address and parameters of the conversation interaction, etc.), a read channel variable (reading variables in the conversation interaction) node, a write channel variable (writing variables in the conversation interaction) node, a variable assignment (assigning values ​​to variables in the conversation interaction) node, a service time (service time of the conversation interaction) node, a hash diversion (calculating the hash value of the interaction object and diverting according to the hash value) node, a whitelist diversion (diverting according to whether the interaction object is in the whitelist) node, a skill group transfer node (whether to transfer the conversation interaction with the interaction object to other service parties), a voice navigation node, etc.

[0101] It should be understood that those skilled in the art may set the number and type of interaction nodes according to actual conditions, and the present disclosure does not limit this.

[0102] In some embodiments, in step S103, the interactive behavior of the interactive object is analyzed according to the interactive behavior data to obtain a data analysis result, including:

[0103] Determining, based on the interaction behavior data, an update strategy for a first node among the plurality of interaction nodes;

[0104] The data analysis result is obtained according to the first node identifier and the update strategy.

[0105] For example, in the interactive behavior data, at least one dimension, such as the call response dimension and the voice navigation statistical dimension, can reflect the call response capability or voice navigation capability of the IVR system when executing the conversation interaction process. Both of these directly affect the interaction processing efficiency.

[0106] In this case, the interactive behavior data corresponding to the two dimensions, namely, the call statistics data and the voice navigation statistics data, can be analyzed to obtain the first node that needs to be updated among the multiple interactive nodes used by the current IVR system when executing the dialogue interaction process, as well as the update strategy of the first node. Then, the data analysis result is obtained according to the first node identifier and the update strategy. Among them, the first node identifier and the update strategy can be directly used as the data analysis result, or the first node identifier and the update strategy can be further processed to obtain the data analysis result. The present disclosure does not limit the specific processing method.

[0107] In some embodiments, the first node is used to characterize a node whose interaction efficiency is lower than the efficiency threshold and needs to be improved; the update strategy of the first node is used to characterize information such as the update method and update content of the first node. Among them, the efficiency threshold can be the average interaction time of all customers in a certain business interaction behavior, which can be set according to the business type and interaction type, etc., and the present disclosure does not limit this.

[0108] In the example, if the analysis finds that the average call duration between some playback nodes and playback and receiving nodes exceeds the threshold, it is considered that the played audio is too long, and the corresponding playback node and / or playback and receiving node is determined as the first node. The update strategy includes adjusting the audio content of the corresponding playback node to reduce the playback time of the audio, and / or adding 0 (skipping audio) to the receiving value of the corresponding playback and receiving node, so as to shorten the duration of each round of interaction and improve service efficiency.

[0109] In the example, if the analysis finds that multiple levels of nodes are required to implement the rollback to the top during business processing, the rollback operation process is considered too complicated, and the corresponding playback and number receiving node in the multi-level nodes is determined as the first node. The update strategy includes adding 9 (one-click return to the top) to the number receiving value of the playback and number receiving node, so as to simplify the rollback operation process and improve customer operation efficiency.

[0110] It should be understood that those skilled in the art may set a specific selection method for the first node and a specific update strategy for the first node according to actual conditions and business requirements, and the present disclosure does not limit this.

[0111] In this way, it is possible to identify interactive nodes with low response processing efficiency and determine corresponding update strategies, thereby improving response processing efficiency and enhancing the effect of dialogue interaction services.

[0112] In some embodiments, after obtaining the data analysis results, the method may further include:

[0113] The first node is updated based on the update strategy; and the dialog interaction is performed based on the updated first node.

[0114] For example, after obtaining the data analysis results, the first node may be updated according to the update strategy in the data analysis results. The first node of the conversation interaction in the IVR system may be updated once every period of time (e.g., 1 day, 1 week, 1 month), and the present disclosure does not limit this.

[0115] In some embodiments, after the update, when the system receives a new interaction request sent by the interactive object, it can conduct a conversation interaction process based on the updated first node to improve the system's response processing efficiency, thereby improving the interaction efficiency with the interactive object and enhancing the customer's interaction experience.

[0116] In this way, the system's response processing efficiency during the dialogue interaction process can be continuously improved.

[0117] According to the data processing method of the embodiment of the present disclosure, the first operation data in the dialogue interaction process can be obtained, and the first operation data can be processed in layers, so as to perform statistical analysis on the isolated first operation data from different dimensions, and obtain interactive behavior data with actual business meaning that can characterize the interactive behavior of the interactive object. The analyzed interactive behavior data can intuitively characterize the response processing process of the IVR system. Furthermore, the interactive behavior of the interactive object is analyzed according to the interactive behavior data to obtain the data analysis result, which intuitively characterizes the interactive efficiency of the dialogue interaction, so that the system response process in the dialogue interaction can be updated based on the data analysis result, thereby improving the interactive efficiency of the dialogue interaction.

[0118] According to the data processing method of the embodiment of the present disclosure, the obtained interactive behavior data can be applied to various subsequent processing scenarios to obtain data analysis results adapted to the scenarios. For example, according to the layered interactive behavior data, the needs and preferences of the interactive objects can be analyzed more accurately, thereby providing more personalized services, improving service efficiency and customer satisfaction, and reducing the cost of services; according to the layered interactive behavior data, the overall needs and market trends of the interactive objects can be evaluated more accurately, and risks can be evaluated more accurately, thereby providing more accurate support for corporate decision-making and reducing the risk losses of the enterprise; according to the layered interactive behavior data, the data structure can be clarified and complex problems can be simplified. Each layer of interactive behavior data only solves specific problems, which can be more convenient and understandable when used and maintained; the layered interactive behavior data also unifies the data caliber, provides a unified data export and unifies the output caliber; standardizes data layering, facilitates the development of a common middle layer, and can greatly reduce repetitive development and computing work.

[0119] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present disclosure will not repeat them. It can be understood by those skilled in the art that in the above-mentioned method of the specific implementation method, the specific execution order of each step should be determined according to its function and possible internal logic.

[0120] In addition, the present disclosure also provides a data processing device, an electronic device, and a computer-readable storage medium, all of which can implement any data processing method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to in the corresponding records of the method part and will not be repeated here.

[0121] Figure 3 A block diagram of a data processing device provided in an embodiment of the present disclosure.

[0122] Reference Figure 3 , the embodiment of the present disclosure provides a data processing device, the data processing device 300 includes:

[0123] A data acquisition module 31 is used to acquire first operation data, where the first operation data is obtained during the dialogue interaction process;

[0124] A hierarchical processing module 32, configured to perform hierarchical processing on the first operation data to obtain interactive behavior data of the interactive object;

[0125] The behavior analysis module 33 is used to analyze the interaction behavior of the interaction object according to the interaction behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interaction efficiency of the dialogue interaction.

[0126] In some embodiments, the hierarchical processing module 32 is used to: perform a first statistical processing on the first operating data based on a first statistical indicator to obtain first detailed data, wherein the first detailed data corresponds one-to-one to the first statistical indicator; and obtain the interactive behavior data based on the first detailed data.

[0127] In some embodiments, the first detailed data includes interactive object behavior detailed data;

[0128] The hierarchical processing module 32 is specifically used to: based on the interactive activity type indicator, obtain the first data of the interactive behavior of the interactive object from the first operating data, wherein the first data includes the interactive behavior identifier, the start time of the interactive behavior, the end time of the interactive behavior and the interaction duration of the interactive behavior; according to the first data, obtain the detailed data of the interactive object behavior.

[0129] In some embodiments, the hierarchical processing module 32 is specifically used to: perform a second statistical processing on the first detailed data according to a second statistical indicator to obtain second detailed data; and obtain the interactive behavior data according to the second detailed data.

[0130] In some embodiments, the second detailed data includes voice navigation detailed data, key navigation detailed data and first call detailed data;

[0131] The hierarchical processing module 32 is specifically used to: perform a third statistical processing on the data characterizing the interactive behavior of the interactive object contained in at least one of the voice navigation detail data, the button navigation detail data and the first call detail data according to the call response index and / or the voice navigation index, so as to obtain third detailed data; and obtain the interactive behavior data according to the third detailed data.

[0132] In some embodiments, the dialog interaction includes a plurality of interaction nodes;

[0133] The behavior analysis module 33 is used to: determine an update strategy for a first node among the multiple interactive nodes according to the interactive behavior data; and obtain the data analysis result according to the first node identifier and the update strategy.

[0134] In some embodiments, the apparatus further comprises:

[0135] An updating module, configured to perform an updating process on the first node based on the updating strategy;

[0136] An interaction module is used to perform the dialog interaction based on the updated first node.

[0137] Each module in the above data processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0138] Figure 4 A block diagram of an electronic device provided in an embodiment of the present disclosure.

[0139] Reference Figure 4 An embodiment of the present disclosure provides an electronic device, which includes: at least one processor 401; at least one memory 402, and one or more I / O interfaces 403, connected between the processor 401 and the memory 402; wherein the memory 402 stores one or more computer programs that can be executed by the at least one processor 401, and the one or more computer programs are executed by the at least one processor 401 so that the at least one processor 401 can execute the above-mentioned data processing method.

[0140] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0141] The present disclosure also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned data processing method when executed by a processor. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0142] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned data processing method.

[0143] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0144] As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is known to those of ordinary skill in the art that communication media typically contain computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0145] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0146] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0147] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0148] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0149] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0150] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0151] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0152] Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for limiting purposes. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly noted, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, those skilled in the art will appreciate that various changes in form and detail may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. A data processing method, characterized in that: include: Acquire first operation data, where the first operation data is obtained during the dialogue interaction process; Performing hierarchical processing on the first operation data to obtain interaction behavior data of the interaction object; The interactive behavior of the interactive object is analyzed according to the interactive behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interactive efficiency of the dialog interaction.

2. The method according to claim 1, characterized in that The step of performing layered processing on the first operation data to obtain interaction behavior data of the interaction object includes: Performing a first statistical processing on the first operation data based on the first statistical indicator to obtain first detailed data, wherein the first detailed data corresponds to the first statistical indicator one by one; The interaction behavior data is obtained according to the first detailed data.

3. The method according to claim 2, characterized in that The first detailed data includes interaction object behavior detailed data; The performing first statistical processing on the first operation data based on the first statistical indicator to obtain first detailed data includes: Based on the interactive activity type indicator, obtaining first data of the interactive behavior of the interactive object from the first running data, wherein the first data includes an interactive behavior identifier, a start time of the interactive behavior, an end time of the interactive behavior, and an interactive duration of the interactive behavior; According to the first data, the interaction object behavior detailed data is obtained.

4. The method according to claim 2, characterized in that: The step of obtaining the interaction behavior data according to the first detailed data includes: Performing second statistical processing on the first detailed data according to a second statistical indicator to obtain second detailed data; The interaction behavior data is obtained according to the second detailed data.

5. The method according to claim 4, characterized in that The second detailed data includes voice navigation detailed data, key navigation detailed data and first call detailed data; The step of obtaining the interaction behavior data according to the second detailed data includes: According to the call response index and / or the voice navigation index, a third statistical processing is performed on the data characterizing the interactive behavior of the interactive object contained in at least one of the voice navigation detail data, the button navigation detail data and the first call detail data to obtain the interactive behavior data.

6. The method according to claim 1, characterized in that The dialog interaction includes a plurality of interaction nodes; Analyzing the interactive behavior of the interactive object according to the interactive behavior data to obtain a data analysis result includes: Determining, based on the interaction behavior data, an update strategy for a first node among the plurality of interaction nodes; The data analysis result is obtained according to the first node identifier and the update strategy.

7. The method according to claim 6, characterized in that After obtaining the data analysis result, the method further includes: Performing an update process on the first node based on the update strategy; The dialog interaction is performed based on the updated first node.

8. A data processing device, characterized in that: include: A data acquisition module, used to acquire first operation data, where the first operation data is obtained during the dialogue interaction process; A hierarchical processing module, used for performing hierarchical processing on the first operation data to obtain interactive behavior data of the interactive object; A behavior analysis module is used to analyze the interaction behavior of the interaction object according to the interaction behavior data to obtain a data analysis result, wherein the data analysis result is used to represent the interaction efficiency of the dialogue interaction.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the data processing method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The invention comprises a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the data processing method as described in any one of claims 1 to 7.

Images