CN113849617A

CN113849617A - Customer service quality inspection method and device, computer equipment and storage medium

Info

Publication number: CN113849617A
Application number: CN202111115234.7A
Authority: CN
Inventors: 张小砖; 刘杰; 汶林丁
Original assignee: Shenzhen Zhuiyi Technology Co Ltd
Current assignee: Shenzhen Zhuiyi Technology Co Ltd
Priority date: 2021-09-23
Filing date: 2021-09-23
Publication date: 2021-12-28

Abstract

The application discloses a customer service quality inspection method and device, computer equipment and a storage medium, and relates to the technical field of internet. The method comprises the following steps: receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service; responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for representing the user characteristics of the client; acquiring an operator associated with the user tag as a target operator; generating a target quality inspection rule according to the target operator; and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service. Therefore, the quality inspection rule is prevented from being manually selected or configured by quality inspection personnel each time the quality inspection is carried out, and the efficiency of customer service quality inspection is improved.

Description

Customer service quality inspection method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of internet technologies, and in particular, to a customer service quality inspection method, an apparatus, a computer device, and a storage medium.

Background

At present, each business has higher requirements on the service quality of customer service personnel, so that the customer service communication records of the customer service personnel can be extracted randomly or according to the seat number, the extracted customer service communication records are checked, and the server quality of each customer service personnel is evaluated based on the checking result.

However, in practical application, the quality testing operation process of quality testing personnel is complicated, and the experience is poor.

Disclosure of Invention

In view of the above, the present application provides a customer service quality inspection method, an apparatus, a computer device, and a storage medium.

In a first aspect, an embodiment of the present application provides a customer service quality inspection method, where the method includes: receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service; responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for representing the user characteristics of the client; acquiring an operator associated with the user tag as a target operator; generating a target quality inspection rule according to the target operator; and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In a second aspect, an embodiment of the present application provides a customer service quality inspection device, where the device includes: the system comprises a request receiving module, a label obtaining module, an operator obtaining module, a rule generating module and a quality inspection module. The request receiving module is used for receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service; the label obtaining module is used for responding to the quality inspection request and obtaining a user label of the client in the session data, wherein the user label is used for representing the user characteristics of the client; the operator acquisition module is used for acquiring an operator associated with the user tag as a target operator; the rule generating module is used for generating a target quality inspection rule according to the target operator; and the quality inspection module is used for performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In a third aspect, an embodiment of the present application provides a computer device, including: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the customer service quality inspection method provided by the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a program code is stored in the computer-readable storage medium, and the program code may be invoked by a processor to execute the customer service quality inspection method provided in the first aspect.

In the scheme provided by the application, a quality inspection request sent by a quality inspection client is received, wherein the quality inspection request carries session data of a target customer service; responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for representing the user characteristics of the client; acquiring an operator associated with the user tag as a target operator; generating a target quality inspection rule according to the target operator; and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the customer service. Therefore, an operator associated with the user tag of the client in the session data can be obtained, a quality inspection rule matched with the session data is automatically generated based on the operator, quality inspection is carried out on the session data based on the generated quality inspection rule, the condition that quality inspection personnel manually select or configure the quality inspection rule when quality inspection is carried out every time is avoided, and the efficiency of customer service quality inspection is improved; moreover, the quality inspection request only carries session data and does not carry data of quality inspection rules, that is, the data contained in the quality inspection request every time is simple, the problem of low quality inspection performance caused by the fact that the quality inspection request carries more data is solved, and the efficiency of customer service quality inspection is further improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 shows a schematic diagram of an application scenario provided in an embodiment of the present application.

Fig. 2 is a schematic flow chart illustrating a customer service quality inspection method according to an embodiment of the present disclosure.

Fig. 3 is a schematic flow chart illustrating a customer service quality inspection method according to another embodiment of the present disclosure.

Fig. 4 is a schematic flow chart illustrating a customer service quality inspection method according to another embodiment of the present disclosure.

Fig. 5 is a schematic interface diagram illustrating an editing rule provided in an embodiment of the present application.

Fig. 6 is a schematic flow chart illustrating the creation of quality control rules according to another embodiment of the present application.

Fig. 7 is a flowchart illustrating a customer service quality inspection method according to still another embodiment of the present application.

Fig. 8 is a flowchart illustrating a customer service quality inspection method according to still another embodiment of the present application.

Fig. 9 is a flowchart illustrating a customer service quality inspection method according to still another embodiment of the present application.

Fig. 10 is a schematic flow chart illustrating a customer service quality inspection method according to yet another embodiment of the present application.

Fig. 11 is a block diagram of a customer service quality inspection device according to an embodiment of the present application.

Fig. 12 is a block diagram of a computer device for executing a customer service quality inspection method according to an embodiment of the present application.

Fig. 13 is a storage unit for storing or carrying program codes for implementing the customer service quality inspection method according to the embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

At present, each business has higher requirements on the service quality of customer service personnel, so that the customer service communication records of the customer service personnel can be extracted randomly or according to the seat number, the extracted customer service communication records are checked, and the server quality of each customer service personnel is evaluated based on the checking result. However, in practical applications, before quality inspection is performed on the customer service communication records of the customer service staff each time, the quality inspection staff needs to select or configure the quality inspection rules by themselves, so that the quality inspection operation process of the quality inspection staff is complicated, and the experience is poor.

In view of the above problems, the inventors propose a customer service quality inspection method, a customer service quality inspection device, a computer device, and a storage medium, which can obtain an operator associated with a user tag of a client in session data, automatically generate a quality inspection rule adapted to the session data based on the operator, and perform quality inspection on the session data based on the generated quality inspection rule. This is described in detail below.

The following introduces an application environment of the customer service quality inspection method provided by the embodiment of the present application.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an application environment provided for an embodiment of the present application, and an application scenario may include a customer service quality inspection system 10, which may include a computer device 110, a quality inspection client 120, and a plurality of electronic terminals 130. The computer device 110 may be a server, or may be other electronic devices that store and process data; the quality inspection client 120 may be a smart notebook, a smart phone, a smart tablet, or the like; the electronic terminal 130 may be a smart notebook, a smart phone, a smart tablet, and the like, which is not limited in this embodiment.

In some embodiments, quality control client 120 establishes communication connections with computer device 110 and electronic terminal 130, respectively. The customer service staff can perform session communication (such as voice communication or text information communication) with the counselor through the electronic terminal 130, wherein session data generated by the session communication can be stored in the electronic terminal 120; the quality testing personnel can create a quality testing task at the quality testing client 120, choose to perform quality testing on the session data of any one of the plurality of electronic terminals 130, and send a quality testing request to the computer device 110, the computer device 110 receives the quality testing request, and automatically generates an adaptive quality testing rule according to the session data carried in the quality testing request, and performs quality testing on the session data. The session data may be obtained from an electronic terminal used by a customer service person to be quality-checked in the plurality of electronic terminals 130 when the quality-check person creates a quality-check task.

In other embodiments, the session data generated by the customer service staff performing session communication with the counseling staff through the electronic terminal 130 can be sent to the quality inspection client 120 for storage in real time, and when the quality inspection staff sends a quality inspection request to the computer equipment through the quality inspection client 120, the quality inspection staff directly calls the session data to be quality inspected, which is stored in the quality inspection client, and adds the session data to the quality inspection request; the computer device 110 receives the quality inspection request, automatically generates an adaptive quality inspection rule according to the session data carried in the quality inspection request, and performs quality inspection on the session data.

Referring to fig. 2, fig. 2 is a diagram illustrating a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to an embodiment of the present disclosure. The customer service quality inspection method provided by the embodiment of the present application will be described in detail with reference to fig. 2. The customer service quality inspection method can comprise the following steps:

step S210: and receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service.

In this embodiment, in order to ensure the customer service quality of the customer service staff in the customer service, the quality inspection method may be used to acquire session data of the customer service staff to inspect the customer service quality of the customer service staff, where the session data may be historical session data or real-time session data, and this embodiment is not limited thereto. However, in practical applications, a quality control person generally selects or configures a quality control rule for session data before sending a quality control request, and based on this, the quality control request may include the session data and data related to the quality control rule at the same time, so that each quality control request may carry data related to repeated quality control rules, which results in a large amount of redundant data, and further results in an increase in data to be processed by computer equipment, and a decrease in quality control efficiency.

Therefore, the quality inspection request only contains session data of the target customer service and does not contain data related to the quality inspection rule, and the quality inspection rule aiming at the session data is automatically generated by the computer device based on the information in the session data, so that the quality inspection efficiency is improved. The target customer service may be a customer service person to be quality-checked, which is selected by the quality-checking person at the quality-checking client, and the number of the target customer services may be one or more, which is not limited in this embodiment.

Step S220: and responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for characterizing the user characteristics of the client.

In this embodiment, when the customer service staff performs the customer service, the facing types of the customers are various, for example, the male customer, the female customer, the midwifery customer, the luxury customer, the young customer, the elderly customer, the urban family customer, the rural family customer, the room-having customer or the room-free customer, and the like, which is not limited in this embodiment. In the face of different types of clients, different dialects, tone and attitudes of customer service personnel are required, for example, in the face of old clients, the speaking speed of the customer service personnel is as slow as possible and the speaking voice is as high as possible; in the face of young customers, the speaking speed of the customer service staff can be slightly faster and the speaking voice is not too loud. If the same quality inspection rule is used for quality inspection of session data of different types of clients, the accuracy and the effect of the quality inspection are poor. Therefore, in order to improve the quality inspection accuracy of the session data, different quality inspection rules can be used when the quality inspection is performed on the session data of different types of clients. Wherein, the quality control rule can be determined according to the type of the client, so that the session data of the client can be better adapted during quality control.

Specifically, a user tag of the client in the session data may be obtained, where the user tag is used to characterize a user characteristic of the client, and the user characteristic may also be understood as a type of the client, such as male, female, young male, or young female; one or more user tags may be provided, which is not limited in this embodiment.

In some embodiments, the user tag of the client may be carried in the session data, and specifically, the user tag may be a user tag manually added in the data of the session with the client according to the content of the session communication when the customer service personnel performs the session communication with the client. For example, based on the customer saying "want to buy an off-road vehicle," the customer service personnel may add a user tag of "buying intent" to the user in the session data. Therefore, the computer equipment can quickly acquire the user tags of the clients in the session data, the response speed of the computer equipment is improved, and the quality inspection efficiency is further improved.

In other embodiments, the user tag of the client may also be obtained by analyzing the session data, for example, analyzing the intention of the client in the session data, and generating the user tag of the client based on the intention of the client. Therefore, the user label of the client can be determined more accurately and perfectly by analyzing the session data through the computer equipment and automatically generating the user label, the quality inspection of the session data can be performed more comprehensively, and the accuracy of the quality inspection is improved.

Step S230: and acquiring an operator associated with the user tag as a target operator.

In this embodiment, a plurality of operators, a plurality of user tags, and a mapping relationship between each user tag and its associated operator may be stored in advance in the computer device. Each user tag can be associated with one operator, and can also be associated with multiple operators at the same time, which is not limited in this embodiment; the operators may include business operators, logical operators, session filtering operators, and the like, where the business operators may be understood as specific quality inspection requirements for the session data, such as semantic tags, keywords, regular expressions, speech rate recognition, response timeout, and call preemption, the session filtering operators may be understood as screening conditions for the session data, such as during a full session, after a session starts, before a session ends, after a last condition, before a last condition, and when a last condition hits a statement, the logical operators may be understood as logical relationships during quality inspection, such as and, or, include, not include, all, any, and the like, and this embodiment is not limited thereto.

Therefore, after the user tag of the client is determined, the operator associated with the user tag can be obtained as the target operator based on the mapping relation.

Step S240: and generating a target quality inspection rule according to the target operator.

Based on this, after the target operator associated with the user tag is obtained, the target quality inspection rule can be generated according to the target operator. For example, if the target operator is "in full session" and "call snatching does not exceed 3 times", correspondingly, a target quality inspection rule of "in full session call snatching does not exceed 3 times" may be generated.

Step S250: and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In this embodiment, after the target quality inspection rule is generated, quality inspection may be performed on the session data based on the target quality inspection rule, so as to obtain a quality inspection result for the target customer service. The quality inspection result may be that in the session data, the communication between the target customer service and the client meets the target quality inspection rule, or the communication between the target customer service and the client does not meet the target quality inspection rule.

In the embodiment, the operator associated with the user tag of the client in the session data is obtained, the quality inspection rule adapted to the session data is automatically generated based on the operator, and the quality inspection rule is performed on the session data based on the generated quality inspection rule, so that the quality inspection rule is prevented from being manually selected or configured by a quality inspector when the quality inspection is performed each time, and the efficiency and the accuracy of customer service quality inspection are improved; moreover, the quality inspection request only carries session data and does not carry data of quality inspection rules, that is, the data contained in the quality inspection request every time is simple, the problem of low quality inspection performance caused by the fact that the quality inspection request carries more data is solved, and the efficiency of customer service quality inspection is further improved.

Referring to fig. 3, fig. 3 is a diagram illustrating a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to another embodiment of the present disclosure. The customer service quality inspection method provided by the embodiment of the present application will be described in detail below with reference to fig. 3. The customer service quality inspection method can comprise the following steps:

step S310: and receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service.

Step S320: and responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for characterizing the user characteristics of the client.

In this embodiment, the specific contents in step S310 to step S320 may refer to the contents in the foregoing embodiments, and are not described herein again.

Step S330: and judging whether the user tag is matched with any preset user tag in a plurality of preset user tags.

In this embodiment, the preset user tag may be a user tag pre-stored in the computer device, and the preset user tag may be obtained based on statistics of user tags of customers in the historical session data, for example, young men, young women, house purchasing needs, car purchasing needs, midwife customers, luxury customers, and the like, which is not limited in this embodiment.

Optionally, after the user tag of the client in the session data is obtained, it may be determined whether the user tag matches any preset user tag in the plurality of preset user tags.

Step S340: if the user tag is matched with a target user tag in the plurality of preset user tags, acquiring an operator associated with the target user tag as the target operator based on a mapping relation between the preset user tag and the operator.

Based on this, if it is determined that the user tag matches a target user tag in the plurality of preset user tags, an operator associated with the target user tag may be obtained as a target operator according to a mapping relationship between the preset user tag and the operator. The mapping relation between the preset user tags and the operators can be configured in advance by quality inspection personnel, the quality inspection personnel can select the operators matched with the preset user tags according to the preset user tags, and the mapping relation is established between each preset user tag and the operator matched with the preset user tag.

Step S350: and generating a target quality inspection rule according to the target operator.

In this embodiment, the specific content in step S350 may refer to the content in the foregoing embodiments, and is not described herein again.

Step S360: and if the user label is not matched with each preset user label in the plurality of preset user labels, returning a rule obtaining request to the quality inspection client.

In this embodiment, when it is determined that the user tag is not matched with each of the plurality of preset user tags, it represents that an operator associated with the user tag is not stored in advance in the computer device, and therefore, a rule acquisition request can be fed back to the quality inspection client; the rule obtaining request is used for prompting quality control personnel, the quality control rule cannot be automatically generated according to the user tag of the client in the session data at present, and the quality control personnel are advised to manually select the rule.

The quality inspection client can be used for displaying all quality inspection rules and rule identifications corresponding to all quality inspection rules after receiving the rule acquisition request, so that quality inspection personnel can select the quality inspection rules for the current session data. Therefore, when the computer equipment cannot automatically generate the quality inspection rule according to the user label, the computer equipment acquires the request to the quality inspection client through the feedback rule, prompts a quality inspection person to manually select the rule, can avoid the problems of customer service quality inspection stagnation and the like caused by the fact that the quality inspection rule cannot be automatically generated, can timely promote the customer service quality inspection process, and ensures the efficiency of customer service quality inspection.

Step S370: and receiving a rule identifier sent by the quality inspection client according to the rule acquisition request.

Step S380: and determining a corresponding quality inspection rule as the target quality inspection rule according to the rule identification.

Based on this, after the quality testing personnel select the corresponding quality testing rule at the quality testing client, the computer equipment can receive the rule identification of the quality testing rule sent by the quality testing client according to the rule acquisition request. The computer device may also pre-store a plurality of quality inspection rules in the quality inspection client and a rule identifier corresponding to each quality inspection rule, so that the quality inspection rule corresponding to the rule identifier may be determined as the target quality inspection rule according to the rule identifier.

In some embodiments, when the rule identifier is multiple, the rule corresponding to each rule identifier in the multiple rule identifiers is obtained as the target quality inspection rule based on the correspondence between the rule identifier and the quality inspection rule. It can be understood that a quality testing person can select a plurality of rule identifications at a quality testing client, and correspondingly, the computer device can receive the plurality of rule identifications and take the rule corresponding to each rule identification in the plurality of rule identifications as a target quality testing rule. In other words, the target quality inspection rule includes a plurality of rules, and when quality inspection is performed on the session data, quality inspection needs to be performed according to each rule in the target quality inspection rule. Therefore, comprehensiveness of session data quality inspection can be improved through a plurality of quality inspection rules. For example, referring to fig. 4, when the computer device can perform quality inspection on the session data of the customer service staff of the agent a, the computer device may request the quality inspection engine to perform quality inspection based on the target quality inspection rule, and the quality inspection engine may perform quality inspection on the session data through the data structure corresponding to the target quality inspection rule to obtain a final quality inspection result.

The quality inspection rule may be configured in advance by a quality inspector, and referring to fig. 5, the quality inspection rule may be generated by selecting an adaptive session filter operator 510, a logic operator 520, and a business operator 530 at an interface where a user edits the quality inspection rule, and selecting a quality inspection target as an agent (i.e., a customer service person) or a customer, and may further input a rule name, a rule type, and a rule description of the quality inspection rule. The rule description can represent the approximate quality inspection content of the quality inspection rule, so that when other quality inspection personnel are required to select the quality inspection rule in the following process, the quality inspection content of each quality inspection rule can be known quickly, the speed of selecting the quality inspection rule is increased, and the efficiency of customer service quality inspection is improved. When the quality inspection rule is configured, only one condition combination may be configured, or a plurality of condition combinations may be added, and when a plurality of condition combinations exist, a logical operator may be added between adjacent condition combinations.

Optionally, referring to fig. 6, after the complete quality inspection rule is created, the quality inspection rule may be stored, and the computer device invokes the data structure corresponding to the quality inspection, issues the data structure to the quality inspection engine, and stores the rule identifier corresponding to the quality inspection rule, so as to subsequently invoke the corresponding data structure in the quality inspection engine according to the rule identifier to perform quality inspection on the session data. Moreover, after the creation of all quality inspection rules is completed, quality inspection personnel can adjust the quality inspection rules according to actual conditions, so that the quality inspection rules better meet the current quality inspection requirements. Therefore, the adjustment of the quality inspection rules can be more flexible and changeable, and the data structures related to all the quality inspection rules are stored in the computer equipment, so that all operators are stored in the computer equipment, and different quality inspection rules are different combinations of the operators. Therefore, even if the quality inspection rule is added, redundant data cannot be generated, the creation of the rule is decoupled, and the performance of customer service quality inspection is greatly improved.

In some embodiments, the user tag that does not match the preset user tag may be added to the preset user tag, a mapping relationship between the target quality inspection rule and the user tag may be established, and the mapping relationship may be stored. Therefore, when quality inspection is carried out on other session data carrying the same user label in the follow-up process, the corresponding target quality inspection rule can be directly called to carry out quality inspection on the session data quickly according to the mapping relation, and the response speed and efficiency of customer service quality inspection are improved.

In other embodiments, if the user tag is not matched with each preset user tag in a plurality of preset user tags, returning an operator acquisition request to the quality inspection client; receiving an operator identifier sent by the quality inspection client according to the operator acquisition request; determining an operator corresponding to the operator identifier in a plurality of prestored operators as a target operator according to the operator identifier; and generating a target quality inspection rule according to the target operator.

Step S390: and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In this embodiment, the specific content in step S390 may refer to the content in the foregoing embodiments, and is not described herein again.

In this embodiment, the obtained user tag is matched with a preset user tag, and when the preset user tag matched with the user tag exists, a target quality inspection rule is generated according to an operator corresponding to the preset user tag; and when the preset user tag matched with the user tag does not exist, feeding back a rule acquisition request to the quality inspection client, and manually selecting the adaptive quality inspection rule by a quality inspector to perform quality inspection on the session data. Therefore, whether the matched preset user label exists or not, the adaptive target quality inspection rule can be obtained, the customer service quality inspection is carried out on the session data, the smooth promotion of the customer service quality inspection is ensured, and the efficiency of the customer service quality inspection is further ensured.

Referring to fig. 7, fig. 7 is a diagram illustrating a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to still another embodiment of the present disclosure. The customer service quality inspection method provided by the embodiment of the present application will be described in detail below with reference to fig. 7. The customer service quality inspection method can comprise the following steps:

step S410: and receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service.

Step S420: and responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for characterizing the user characteristics of the client.

Step S430: and acquiring an operator associated with the user tag as a target operator.

In this embodiment, the specific contents in step S410 to step S430 may refer to the contents in the foregoing embodiments, and are not described herein again.

Step S440: and generating the target quality inspection rule according to the logic operator, the business operator and the session filter operator.

In this embodiment, the session filter operator may be understood as a filtering condition for session data, for example, the whole session represents that all session data is to be quality checked, or the first 10 sentences of the session start represent that the first 10 sentences of the session data are extracted for customer service quality check. The business operator can be understood as a specific quality inspection condition for the session data, for example, when the business operator is a keyword, it is determined whether the session data includes the keyword, if so, it is determined that the session data hits the business operator, and if not, it is determined that the session data misses the business operator. The logical operator can be understood as a logical relationship in the quality inspection process, for example, if the logical operator between the business operator a and the business operator B is "and", it represents that the session data must hit the business operator a and the business operator B at the same time, and can be determined to meet the target quality inspection rule.

In some embodiments, a quality check condition is generated based on the business operator and the session filter operator; and generating a target quality inspection rule based on the quality inspection condition and the logic operator. Alternatively, when the number of the quality inspection conditions is only one, the target quality inspection rule may be generated only according to the quality inspection conditions; when the number of the quality inspection conditions is multiple, the logical operator aiming at the multiple quality inspection conditions in the logical operator can be obtained and used as the first logical operator; generating a condition combination based on a plurality of quality inspection conditions and the first logical operator; and generating the target quality inspection rule according to the condition combination. Therefore, the target quality inspection rule can only comprise one quality inspection condition, and the conversation data can be subjected to customer service quality inspection in a certain aspect in a targeted manner, for example, only the speaking tone of a customer service person is subjected to quality inspection; the system can also simultaneously contain a plurality of quality inspection conditions, perform customer service quality inspection on conversation data from a plurality of aspects, and perform quality inspection on the speaking mood, speaking speed, speaking accuracy and other aspects of customer service personnel at the same time, so that the customer service quality inspection can be realized more comprehensively, the quality inspection result of the customer service quality inspection is enriched, and the problems of excessive one-sidedness of the quality inspection result and the like are avoided.

In other embodiments, a quality check condition is generated based on the business operator and the session filter operator; when the number of the quality inspection conditions is multiple, acquiring a logical operator aiming at the multiple quality inspection conditions in the logical operator as a first logical operator; generating a condition combination based on a plurality of quality inspection conditions and the first logical operator; when the number of the condition combinations is multiple, acquiring a logical operator aiming at the multiple condition combinations in the logical operator as a second logical operator; and generating a target quality inspection rule based on the second logic operator and the plurality of condition combinations. Therefore, the target quality inspection rule can simultaneously comprise a plurality of condition combinations, and the plurality of condition combinations are combined through the second logic operator to generate a more comprehensive and more complicated target quality inspection rule, so that customer service quality inspection is performed on the session data more accurately and comprehensively, a more comprehensive and more accurate quality inspection result is obtained, and the reliability of the quality inspection result is improved.

Step S450: and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In this embodiment, the specific content in step S450 may refer to the content in the foregoing embodiments, and is not described herein again.

In this embodiment, the operator corresponding to the user tag may simultaneously include a logic operator, a business operator, and a session filter operator, and different target quality inspection rules may be generated based on different combinations of the three operators. Therefore, the content and the type of the abundant target quality inspection rules can realize targeted customer service quality inspection on the session data in a certain aspect, can also realize customer service quality inspection on the session data from multiple aspects, enriches the quality inspection results of the customer service quality inspection, and avoids the problems of too high one-sidedness of the quality inspection results and the like.

Referring to fig. 8, fig. 8 is a diagram illustrating a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to still another embodiment of the present disclosure. The customer service quality inspection method provided by the embodiment of the present application will be described in detail below with reference to fig. 8. The customer service quality inspection method can comprise the following steps:

step S510: and receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service.

Step S520: and responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for characterizing the user characteristics of the client.

Step S530: and acquiring an operator associated with the user tag as a target operator.

Step S540: and generating a target quality inspection rule according to the target operator, wherein the target quality inspection rule comprises a logic operator, a business operator and a session filtering operator.

In this embodiment, the specific contents in step S510 to step S540 may refer to the contents in the foregoing embodiments, and are not described herein again.

Step S550: and filtering the session data based on the session filtering operator to obtain target session data.

In this embodiment, when performing quality inspection on the session data according to the generated target quality inspection rule, the session data may be filtered based on the session filter operator to obtain the target session data. For example, when the session filter operator is "10 sentences before the session is ended", the computer device acquires 10 sentences before the session data is ended as the target session data.

Step S560: and judging whether the target session data hit the logic operator and the business operator.

Wherein the logical operator can connect multiple business operators into a more complex operator. Therefore, after the target session data is obtained, whether the target session data hits a logic operator and a business operator in the target quality inspection rule can be further judged, that is, whether the target session data hits a more complex operator formed by combining the logic operator and a plurality of business operators is judged.

Step S570: and if the target session data hit the logic operator and the business operator, judging that the session data conform to the target quality inspection rule.

Optionally, if the target session data hit the logic operator and the service operator, the session data are judged to accord with the target quality inspection rule. For example, the logical operator is "and", the business operator includes business operator a and business operator B, and at this time, when the target session data hits business operator a and at the same time hits business operator B, it is determined that the session data conforms to the target quality inspection rule.

Step S580: and if the target session data does not hit the logic operator and the business operator, judging that the session data does not accord with the target quality inspection rule.

Optionally, if the target session data does not hit the logic operator and the service operator, it is determined that the session data does not conform to the target quality inspection rule. The target session data miss-hit logic operator and service operator can be understood as target session data miss-hit service operator, or target session data miss-hit logic operator and service operator.

For example, the logical operator is "and", the business operator includes business operator a and business operator B, if the target session data hits business operator a, but does not hit business operator B, it is determined that the session data does not conform to the target quality inspection rule; and if the target session data does not hit the service operator A and the service operator B, judging that the session data does not accord with the target quality inspection rule.

Step S590: and outputting a quality inspection result, wherein the quality inspection result comprises the hitting situation of the target session data hitting the logic operator and the business operator.

In this embodiment, the customer service quality inspection process is completed by judging whether the target session data hits the logical operator and the service operator, and at this time, a quality inspection result can be output, where the quality inspection result includes a hit condition of the target session data hitting the logical operator and the service operator, and it can be understood that the output quality inspection result includes whether the session data meets a target quality inspection rule, which logical operators are hit by the target session data, and which service operators are hit by the target session data.

In some embodiments, after the quality inspection result is output, a customer service score for a customer service person in the session data to be quality inspected is generated according to a preset scoring strategy and the quality inspection result, the customer service score is used for representing the service quality of the customer service person, and the level of the service quality is positively correlated with the size of the customer service score. Specifically, when it is determined that the session data conforms to the target quality inspection rule, a sum of the basic score and a first adjustment score is obtained as the customer service score, where the first adjustment score is a positive number, and may be preset or adjusted according to different application scenarios, and this embodiment does not limit this; when the session data are judged to be not in accordance with the target quality inspection rule, the number of the service operators missed by the target session data is obtained and used as the target number; acquiring the ratio of the target number to the number of the service operators; judging whether the ratio is smaller than a preset ratio threshold value or not, if so, acquiring the sum of the basic score and the second adjustment score as a customer service score; and if not, acquiring the sum of the basic score and the third adjustment score as the customer service score. The second adjustment score and the third adjustment score are negative numbers, and the numerical values thereof may be preset or adjusted according to different application scenarios. Therefore, based on the output quality inspection result, the customer service score is further generated, the service quality of the customer service staff is quantized into the specific customer service score, and the service quality of the customer service staff can be better displayed.

In this embodiment, the target quality inspection rule includes a session filter operator, a logic operator, and a service operator, and session data can be screened through the session filter operator, that is, quality inspection can be performed on all session data, or quality inspection can be performed only on a certain part of session data in the session data, so that flexibility of quality inspection is improved; moreover, more complex and comprehensive operators can be formed between the logic operator and the plurality of service operators, so that the target quality inspection rule is more complex and comprehensive, and more comprehensive and accurate quality inspection results can be obtained; moreover, the quality inspection result not only contains whether the session data accords with the target quality inspection rule, but also contains the hit condition of the session data hitting the logic operator and the business operator in the target quality inspection rule, so that the specific content of which aspects are violated by the customer service staff in the more detailed output session data is realized.

Referring to fig. 9, fig. 9 is a block diagram of a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to still another embodiment of the present disclosure. The customer service quality inspection method provided by the embodiment of the present application will be described in detail below with reference to fig. 9. The customer service quality inspection method can comprise the following steps:

step S610: receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service, and the session data carries an identity of the client.

In this embodiment, the specific content in step S610 may refer to the content in the foregoing embodiments, and is not described herein again.

Step S620: and responding to the quality inspection request, and acquiring user information corresponding to the identity of the client from a preset user information base to serve as target user information.

In this embodiment, before the customer communicates with the customer service staff, the customer may fill in user information related to the customer, such as age, gender, hobbies, needs, annual income, and the like; the identity may be a name or a user name of the user, and the embodiment is not limited thereto. Correspondingly, the user information filled by the user can be stored in the user client used by the user, and when the user carries out session communication with the target customer service, the user information can be transmitted to the quality inspection client of the target customer service. The preset user information base can be deployed in a quality inspection client, a computer device, or both the quality inspection client and the computer device.

Optionally, the computer device may obtain user information corresponding to the identity of the client from a user information base in the quality inspection client as target user information; the user information corresponding to the identification of the client may also be obtained from a user information base in the computer device, which is not limited in this embodiment.

Step S630: and generating a user label of the client according to the target user information.

Based on this, after the target user information of the client is obtained, the user label of the client can be generated according to the target user information. Specifically, the user characteristics of the client can be determined according to the target user information, and then the user mark of the client is generated according to the user characteristics

Illustratively, if the target user information is: female, 25 years old, no property, 30 ten thousand annual income, etc., so that the user characteristics of the customer can be determined to be middle-aged female, income middle-property, no property, based on which the user tags of the customer, such as "middle-aged female", "may have intent to buy house", "midwife customer", can be generated according to the above-mentioned user characteristics.

Step S640: and acquiring an operator associated with the user tag as a target operator.

Step S650: and generating a target quality inspection rule according to the target operator.

Step S660: and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In this embodiment, the specific contents in step S640 to step S660 may refer to the contents in the foregoing embodiments, and are not described herein again.

In this embodiment, a user tag for a client may be generated based on user information of the client, and then a target quality inspection rule is generated based on a target operator associated with the user tag to perform quality inspection on session data. Therefore, the user label for the client is generated by analyzing the user information filled by the client, so that more comprehensive and abundant user labels can be obtained, the target quality inspection rule generated based on the user label is more comprehensive and various, and the comprehensiveness and the quality inspection accuracy of the customer service quality inspection are improved.

Referring to fig. 10, fig. 10 is a diagram illustrating a customer service quality inspection method, an apparatus, a computer device, and a storage medium according to still another embodiment of the present application. The customer service quality inspection method provided by the embodiment of the present application will be described in detail below with reference to fig. 10. The customer service quality inspection method can comprise the following steps:

step S710: and receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service.

In this embodiment, the specific content in step S710 may refer to the content in the foregoing embodiments, and is not described herein again.

Step S720: and in response to the quality inspection request, extracting the session data of the client from the session data as target session data.

In the present embodiment, in order to obtain a more accurate and comprehensive user tag for a client in the session data, the user tag for the client may be obtained by analyzing the session content of the client in the session data. Specifically, the session data of the client may be extracted from the session data as the target session data by a voice separation technique.

Step S730: and performing semantic recognition on the target session data to obtain the intention of the client.

Further, after the target session data is obtained, semantic recognition can be performed on the target session data to obtain the intention of the client.

In some embodiments, if the type of the target session data is text information, semantic recognition can be directly performed on the target session data to obtain the intention of the client.

In other embodiments, if the type of the target session data is audio information, the target session data may be converted into text information to obtain a target session text; and performing semantic recognition on the target session text to obtain the intention of the client.

Step S740: and extracting keywords in the intention as user tags of the client.

In this embodiment, after the intention of the client is obtained, since the intention may be text information with a large number of characters, a keyword in the intention of the client may be extracted as a user tag of the client. For example, if the intention of the client is "i want to buy a house and the house is a small house type", two keywords "buy the house" and "small house type" may be extracted as the user tags of the client. Therefore, through the mode of extracting the keywords from the intention, more comprehensive user labels can be obtained, more comprehensive quality inspection rules can be generated, quality inspection is carried out on the session data, and comprehensiveness and accuracy of customer service quality inspection are improved.

In some embodiments, after extracting the keyword in the intention of the customer, a preset user tag matching the keyword in the intention may also be obtained from the plurality of preset user tags as the user tag of the customer. For example, if the intention of the client is "i want to buy a house, the house is a small house type", the extracted keywords are "house buying" and "small house type", the plurality of preset user tags include "a small house type house buying demand" and "a large house type house buying demand", based on which, the preset user tag matched with the extracted keywords can be determined to be the "small house type house buying demand", and then the "small house type house buying demand" can be used as the user tag of the client. Therefore, the preset user label which is most matched with the intention of the client can be determined from the preset user labels to serve as the user label of the client, and the target quality inspection rule generated based on the user label is more accurate and is suitable for the current session data.

Step S750: and acquiring an operator associated with the user tag as a target operator.

Step S760: and generating a target quality inspection rule according to the target operator.

Step S770: and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In this embodiment, the specific contents in step S750 to step S770 may refer to the contents in the foregoing embodiments, and are not described herein again.

In this embodiment, the user tag for the client is acquired by performing intent recognition on the session content of the client, and then the target quality inspection rule is generated based on the user tag to perform quality inspection on the session data. Therefore, through the intention identification mode, more accurate and comprehensive user labels can be obtained, more comprehensive quality inspection rules can be generated, quality inspection is carried out on session data, and comprehensiveness and accuracy of customer service quality inspection are improved.

Referring to fig. 11, a block diagram of a customer service quality inspection apparatus 800 according to an embodiment of the present disclosure is shown. The apparatus 800 may include: request receiving module 810, tag obtaining module 820, operator obtaining module 830, rule generating module 840 and quality inspection module 850.

The request receiving module 810 is configured to receive a quality inspection request sent by a quality inspection client, where the quality inspection request carries session data of a target customer service.

The tag obtaining module 820 is configured to obtain, in response to the quality inspection request, a user tag of the customer in the session data, where the user tag is used to characterize a user characteristic of the customer.

The operator obtaining module 830 is configured to obtain an operator associated with the user tag as a target operator.

The rule generating module 840 is configured to generate a target quality inspection rule according to the target operator.

The quality inspection module 850 is configured to perform quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

In some embodiments, operator acquisition module 830 may include: the device comprises a first judging unit and an operator acquiring unit. The first determining unit may be configured to determine whether the user tag matches any preset user tag of a plurality of preset user tags. The operator obtaining unit may be configured to, if the user tag is matched with a target user tag in the plurality of preset user tags, obtain, based on a mapping relationship between the preset user tags and operators, an operator associated with the target user tag as the target operator.

In this manner, the customer service quality inspection apparatus 800 may further include: the device comprises a request feedback module, an identification receiving module and a rule determining module. The request feedback module may be configured to, after determining whether the user tag is matched with any one of the plurality of preset user tags, return a rule acquisition request to the quality inspection client if the user tag is not matched with each of the plurality of preset user tags. The identifier receiving module may be configured to receive a rule identifier sent by the quality inspection client according to the rule obtaining request. The rule determining module may be configured to determine, according to the rule identifier, a corresponding quality inspection rule as the target quality inspection rule. The quality inspection module 850 may be configured to perform quality inspection on the session data based on the target quality inspection rule, so as to obtain a quality inspection result corresponding to the target customer service.

In some embodiments, the rule identifier is a plurality of identifiers, and the rule determining module may be specifically configured to: and acquiring a rule corresponding to each rule identifier in the plurality of rule identifiers as the target quality inspection rule based on the corresponding relation between the rule identifiers and the quality inspection rules.

In some embodiments, the target operator includes a logic operator, a business operator, and a session filter operator, and the rule generating module 840 may be specifically configured to: and generating the target quality inspection rule according to the logic operator, the business operator and the session filter operator.

In this manner, the rule generation module 840 may include: quality inspection condition generating means and rule generating means. The quality inspection condition generating unit can be used for generating the quality inspection condition according to the business operator and the session filter operator. The rule generating unit may be configured to generate a target quality inspection rule based on the quality inspection condition and the logical operator.

In some embodiments, when the number of the quality inspection conditions is plural, the rule generating unit may include: the first operator acquisition subunit, the combination generation subunit and the rule generation subunit. The first operator obtaining subunit may be configured to obtain, as the first logical operator, a logical operator for the multiple quality inspection conditions in the logical operator. The combination generation subunit may be configured to generate a combination of conditions based on a plurality of quality inspection conditions and the first logical operator. The rule generating subunit may be configured to generate the target quality inspection rule according to the condition combination.

In other embodiments, when the number of condition combinations is multiple, the rule generating subunit may be specifically configured to: acquiring a logical operator aiming at a plurality of condition combinations in the logical operators as a second logical operator; and generating the target quality inspection rule based on the second logical operator and the plurality of condition combinations.

In some embodiments, the target quality inspection rule includes a logic operator, a business operator, and a session filter operator, and the quality inspection module 850 may include: a session filtering unit and a second judging unit. The session filtering unit may be configured to filter the session data based on the session filter operator to obtain target session data. The second determination unit may be configured to: judging whether the target session data hit the logic operator and the business operator; if the target session data hit the logic operator and the business operator, judging that the session data conform to the target quality inspection rule; and if the target session data does not hit the logic operator and the business operator, judging that the session data does not accord with the target quality inspection rule.

In some embodiments, customer service quality inspection device 800 may include: and an output module. The output module may be configured to output a quality inspection result after the determination is made whether the target session data both hits the logic operator and the service operator, where the quality inspection result includes a hit condition that the target session data hits the logic operator and the service operator.

In some embodiments, customer service quality inspection device 800 may include: and a scoring module. The scoring module may be configured to generate, after the quality inspection result is output, a customer service score for a customer service person in the session data to be subjected to quality inspection according to a preset scoring policy and the quality inspection result, where the customer service score is used to represent service quality of the customer service person, and the level of the service quality is positively correlated with the size of the customer service score.

In some embodiments, the session data carries an identity of the client, and the tag obtaining module 820 may include: a user information acquisition unit and a label generation unit. The user information obtaining unit may be configured to obtain, from a preset user information library, user information corresponding to the identity of the client as target user information. The tag generating unit may be configured to generate a user tag of the customer according to the target user information.

In other embodiments, the tag obtaining module 820 may include: a conversation extraction unit, an intention identification unit and a label extraction unit. Wherein the session extraction unit may be configured to extract the session data of the client from the session data as target session data. The intention identification unit can be used for carrying out semantic identification on the target session data to obtain the intention of the client. The tag extraction unit may be configured to extract a keyword in the intention as a user tag of the customer.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, the coupling between the modules may be electrical, mechanical or other type of coupling.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

To sum up, in the scheme provided by the embodiment of the application, a quality inspection request sent by a quality inspection client is received, and the quality inspection request carries session data of a target customer service; responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for representing the user characteristics of the client; acquiring an operator associated with the user tag as a target operator; generating a target quality inspection rule according to the target operator; and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the customer service. Therefore, an operator associated with the user tag of the client in the session data can be obtained, a quality inspection rule matched with the session data is automatically generated based on the operator, quality inspection is carried out on the session data based on the generated quality inspection rule, the condition that quality inspection personnel manually select or configure the quality inspection rule when quality inspection is carried out every time is avoided, and the efficiency of customer service quality inspection is improved; moreover, the quality inspection request only carries session data and does not carry data of quality inspection rules, that is, the data contained in the quality inspection request every time is simple, the problem of low quality inspection performance caused by the fact that the quality inspection request carries more data is solved, and the efficiency of customer service quality inspection is further improved.

A computer device provided by the present application will be described with reference to the drawings.

Referring to fig. 12, fig. 12 is a block diagram illustrating a structure of a computer device 900 according to an embodiment of the present application, where the computer device 900 may execute a customer service quality inspection method according to the embodiment of the present application. Computer device 900 may be a device that is capable of running applications, among other things.

The computer device 900 in embodiments of the present application may include one or more of the following components: a processor 901, a memory 902, and one or more applications, wherein the one or more applications may be stored in the memory 902 and configured to be executed by the one or more processors 901, the one or more programs configured to perform a method as described in the aforementioned method embodiments.

Processor 901 may include one or more processing cores. The processor 901 interfaces with various interfaces and circuitry throughout the computer device 900 to perform various functions of the computer device 900 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 902 and invoking data stored in the memory 902. Alternatively, the processor 901 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 901 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may be integrated into the processor 901, and implemented by a communication chip.

The Memory 902 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 902 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 902 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area may also store data created during use by the computer device 900 (such as the various correspondences described above), and so on.

In the several embodiments provided in the present application, the coupling or direct coupling or communication connection between the modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be in an electrical, mechanical or other form.

Referring to fig. 13, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable medium 1000 has stored therein program code that can be called by a processor to execute the method described in the above-described method embodiments.

The computer-readable storage medium 1000 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1000 includes a non-transitory computer-readable storage medium. The computer readable storage medium 1000 has storage space for program code 1010 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 1010 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A customer service quality inspection method, characterized by comprising:

receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service;

responding to the quality inspection request, and acquiring a user tag of the client in the session data, wherein the user tag is used for representing the user characteristics of the client;

acquiring an operator associated with the user tag as a target operator;

generating a target quality inspection rule according to the target operator;

and performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the target customer service.

2. The method of claim 1, wherein the obtaining an operator corresponding to the user tag as a target operator comprises:

judging whether the user tag is matched with any one of a plurality of preset user tags or not;

if the user tag is matched with a target user tag in the plurality of preset user tags, acquiring an operator associated with the target user tag as the target operator based on a mapping relation between the preset user tag and the operator.

3. The method of claim 2, wherein after determining whether the user tag matches any of a plurality of predetermined user tags, the method further comprises:

if the user tag is not matched with each preset user tag in the plurality of preset user tags, returning a rule obtaining request to the quality inspection client;

receiving a rule identifier sent by the quality inspection client according to the rule acquisition request;

determining a corresponding quality inspection rule as the target quality inspection rule according to the rule identification;

and executing the target quality inspection rule based on the session data to perform quality inspection to obtain a quality inspection result corresponding to the customer service.

4. The method according to claim 3, wherein the rule identifier is plural, and the determining a corresponding quality inspection rule as the target quality inspection rule according to the rule identifier comprises:

and acquiring a rule corresponding to each rule identifier in the plurality of rule identifiers as the target quality inspection rule based on the corresponding relation between the rule identifiers and the quality inspection rules.

5. The method of claim 1, wherein the target operators comprise a logical operator, a business operator, and a session filter operator, and wherein generating the target quality inspection rule according to the target operators comprises:

and generating the target quality inspection rule according to the logic operator, the business operator and the session filter operator.

6. The method of claim 5, wherein generating the target quality inspection rule according to the logical operator, the business operator, and the session filter operator comprises:

generating a quality inspection condition according to the business operator and the session filter operator;

and generating a target quality inspection rule based on the quality inspection condition and the logic operator.

7. The method of claim 6, wherein when the number of quality inspection conditions is plural, the generating a target quality inspection rule based on the quality inspection conditions and the logical operator comprises:

acquiring a logical operator aiming at a plurality of quality inspection conditions in the logical operator as a first logical operator;

generating a condition combination based on a plurality of quality inspection conditions and the first logical operator;

and generating the target quality inspection rule according to the condition combination.

8. The method according to claim 7, wherein when the number of the condition combinations is plural, the generating the target quality inspection rule according to the condition combinations comprises:

acquiring a logical operator aiming at a plurality of condition combinations in the logical operators as a second logical operator;

and generating the target quality inspection rule based on the second logical operator and the plurality of condition combinations.

9. The method of claim 1, wherein the target quality inspection rule comprises a logic operator, a business operator and a session filter operator, and the quality inspection of the session data based on the target quality inspection rule comprises:

filtering the session data based on the session filtering operator to obtain target session data;

judging whether the target session data hit the logic operator and the business operator;

if the target session data hit the logic operator and the business operator, judging that the session data conform to the target quality inspection rule;

and if the target session data does not hit the logic operator and the business operator, judging that the session data does not accord with the target quality inspection rule.

10. The method of claim 9, wherein after said determining whether said target session data both hit said logical operator and said business operator, said method further comprises:

and outputting a quality inspection result, wherein the quality inspection result comprises the hitting situation of the target session data hitting the logic operator and the business operator.

11. The method of claim 10, wherein after outputting the quality inspection result, the method further comprises:

and generating a customer service score for the customer service staff in the session data to be subjected to the quality inspection according to a preset scoring strategy and the quality inspection result, wherein the customer service score is used for representing the service quality of the customer service staff, and the service quality is positively correlated with the customer service score.

12. The method according to any one of claims 1 to 11, wherein the session data carries an identity of the client, and the obtaining of the user tag of the client in the session data includes:

acquiring user information corresponding to the identity of the client from a preset user information base to serve as target user information;

and generating a user label of the client according to the target user information.

13. The method according to any one of claims 1-11, wherein the obtaining of the user tag of the client in the session data comprises:

extracting the session data of the client from the session data as target session data;

performing semantic recognition on the target session data to obtain the intention of the client;

and extracting keywords in the intention as user tags of the client.

14. A customer service quality inspection device, the device comprising:

the request receiving module is used for receiving a quality inspection request sent by a quality inspection client, wherein the quality inspection request carries session data of a target customer service;

the label obtaining module is used for responding to the quality inspection request and obtaining a user label of the client in the session data, wherein the user label is used for representing the user characteristics of the client;

the operator acquisition module is used for acquiring an operator associated with the user tag as a target operator;

the rule generating module is used for generating a target quality inspection rule according to the target operator;

and the quality inspection module is used for performing quality inspection on the session data based on the target quality inspection rule to obtain a quality inspection result corresponding to the customer service.

15. A computer device, comprising:

one or more processors;

a memory;

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-13.

16. A computer-readable storage medium, characterized in that a program code is stored in the computer-readable storage medium, which program code can be called by a processor to perform the method according to any of claims 1-13.