CN117555997A - Method and device for determining session information - Google Patents

Method and device for determining session information Download PDF

Info

Publication number
CN117555997A
CN117555997A CN202210926752.5A CN202210926752A CN117555997A CN 117555997 A CN117555997 A CN 117555997A CN 202210926752 A CN202210926752 A CN 202210926752A CN 117555997 A CN117555997 A CN 117555997A
Authority
CN
China
Prior art keywords
customer service
data
session
operation interface
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210926752.5A
Other languages
Chinese (zh)
Inventor
李浩天
郝瑞瑞
刘海茹
杜潇
甘砺智
严历
陈瑞年
孙超博
张正
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202210926752.5A priority Critical patent/CN117555997A/en
Publication of CN117555997A publication Critical patent/CN117555997A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The specification discloses a method and a device for determining session information, which can receive a session request of a user and determine a reply template which is generated in advance according to the corresponding relation between a customer service operation interface and sentences in historical session data. And responding to the statement sent by the user, and determining a customer service operation interface corresponding to the statement. And calling the customer service operation interface, generating session information according to the return value of the customer service operation interface and the reply template, and replying to the user. Therefore, after receiving the statement sent by the user, the session information is flexibly generated to reply the user according to the return value obtained by calling the customer service operation interface corresponding to the statement and the preset reply template, and the reply template is not required to be marked manually, so that the cost is saved.

Description

Method and device for determining session information
Technical Field
The present disclosure relates to the field of data processing, and in particular, to a method and apparatus for determining session information.
Background
With the development of the internet, users often need customer service to solve the problem when transacting business on the network. Because of the large number of internet services and large pressure of manual customer service, service providers often adopt intelligent customer service to solve the problem for users.
In the prior art, different users often raise different problems when transacting business, so that in order to enable the intelligent customer service to cope with various problems raised by the users, a large number of session records need to be manually marked so as to train the intelligent customer service, and the intelligent customer service can recover various problems raised by the users.
However, the intelligent customer service reply is too dead, and because of various problems proposed by users, the manual labeling is large in complexity and too high in cost, so that the cost of the intelligent customer service is too high.
Disclosure of Invention
The present disclosure provides a method and apparatus for determining session information, so as to partially solve the above-mentioned problems in the prior art.
The technical scheme adopted in the specification is as follows:
the present specification provides a method of determining session information, comprising:
receiving a session request of a user;
determining a pre-generated reply template, wherein the reply template is determined according to the corresponding relation between a customer service operation interface and sentences in historical session data, and the corresponding relation is determined through each business data and the historical session data collected by burying points at the customer service operation interface;
responding to the statement sent by the user, and determining a customer service operation interface;
And calling the customer service operation interface, and generating a session information reply user according to the return value of the customer service operation interface and the reply template.
Optionally, generating the session information reply user according to the return value of the customer service operation interface and the reply template specifically includes:
determining the credit rating of the user according to the stored user information of the user;
generating a plurality of pieces of session information to be selected corresponding to different credit levels according to the return value of the customer service operation interface and the reply template;
and determining session information corresponding to the credit rating of the user from the session information to be selected, and replying to the user.
Optionally, receiving a session request of the user specifically includes:
receiving a session request of a user and determining session content;
and determining a service scene corresponding to the session of the user according to the session content.
Optionally, determining a pre-generated reply template specifically includes:
and determining a pre-generated reply template of the service scene according to the service scene corresponding to the session carried out by the user.
Optionally, determining the reply template according to the corresponding relation between the customer service operation interface and the sentences in the historical session data specifically includes:
Acquiring historical session data and service data acquired by burying points at each customer service operation interface in the service scene, wherein the service data at least comprises customer service identification, interface identification and time stamp;
for each historical session data, determining a plurality of business data matched with the historical session data according to customer service identifiers in the historical session data;
determining the corresponding relation between the customer service operation interface and the sentence from the historical session data according to the interface identifiers and the time stamps in the matched service data;
and determining a reply template of the service scene according to the corresponding relation between sentences and customer service operation interfaces in the historical session data under the service scene.
Optionally, before acquiring each service data collected at the buried point at each customer service operation interface in the service scenario, the method further includes:
acquiring each customer service flow constructed for each common problem under the service scene;
screening session information determined based on the data returned by calling the customer service operation interface from the customer service flows;
burying points at customer service operation interfaces corresponding to the screened session information.
Optionally, for each historical session data, determining, according to the customer service identifier in the historical session data, a plurality of service data matched with the historical session data, including:
respectively acquiring customer service identifiers and time stamps corresponding to the service data;
and determining a plurality of business data with time stamps being in a session period of the historical session data and customer service identifiers being the same as the customer service identifiers in the historical session data as a plurality of business data matched with the historical session data according to each historical session data, wherein the session period is a period of time for carrying out a session corresponding to the historical session data.
Optionally, determining, according to the interface identifiers and the time stamps in the matched plurality of service data, a corresponding relationship between the customer service operation interface and the sentence from the historical session data specifically includes:
for each business data, determining each sentence after the time stamp according to the time stamp of the business data and the time corresponding to each sentence in the historical conversation data as a to-be-selected sentence;
determining keywords according to the service data;
and determining a first statement to be selected matched with the keyword as a statement with a corresponding relation with the customer service operation interface according to the keyword and each statement to be selected and the sequence of time. The present specification provides a computer readable storage medium storing a computer program which when executed by a processor implements the above-described method of determining session information.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method of determining session information when executing the program.
The above-mentioned at least one technical scheme that this specification adopted can reach following beneficial effect:
in the method of the session information provided in the present specification, a session request of a user may be received, and a reply template generated in advance according to a correspondence between a customer service operation interface and a sentence in historical session data may be determined. And responding to the statement sent by the user, and determining a customer service operation interface corresponding to the statement. And calling the customer service operation interface, generating session information according to the return value of the customer service operation interface and the reply template, and replying to the user.
According to the method, after receiving the statement sent by the user, the user can flexibly generate session information to reply the user according to the return value obtained by calling the customer service operation interface corresponding to the statement and the preset reply template, and the reply template does not need to be marked manually, so that the cost is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. In the drawings:
FIG. 1 is a flow chart of a method for determining session information provided in the present specification;
FIG. 2 is a schematic diagram of an apparatus for determining session information provided herein;
fig. 3 is a schematic view of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present application based on the embodiments herein.
In this specification, since the customer service generally needs to query or manipulate part of data, that is, call the customer service operation interface, when the customer service dialogues with the user, the return value of the customer service operation interface is determined. For example, inquiring about the balance of the user with whom to talk, modifying the order amount of an order of the user with whom to talk. After inquiring or operating the data, the customer service replies to the user according to the result of inquiring or operating the data. After inquiring or operating data, the existing intelligent customer service replies too dead, so that user experience is reduced, and the training cost is high due to the large amount of data to be inquired or operated, so that the training of the intelligent customer service is not facilitated.
The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for determining a reply template in the present specification, specifically including the following steps:
s100: a session request of a user is received.
Because users typically talk to customer service through clients configured in terminals (smart phones, tablet computers, etc.) while they talk to customer service. Thus, in one or more embodiments of the present description, the method of determining session information may be performed by a client configured within a terminal. Of course, since the intelligent customer service may need to query data in response to the user's problem, the data is typically stored in a database connected to the server, and thus, the method of determining session information may also be performed by the server. In this specification, for convenience of explanation, a method in which the client performs the determination of the session information will be described as an example. Of course, the client is specifically what kind of client, and the present specification is not limited, and may be set as required. The server is specifically a single device or a distributed server system composed of multiple devices, which is not limited in this specification and can be set as required.
Specifically, the client may receive a session request of a user in response to an operation of the user.
S102: and determining a pre-generated reply template, wherein the reply template is determined according to the corresponding relation between the customer service operation interface and sentences in the historical session data, and the corresponding relation is determined through the business data and the historical session data collected by the buried points at the customer service operation interface.
In one or more embodiments of the present description, the client may determine a pre-generated reply template upon receiving the user's session request. When the client receives the statement input by the user and needs to be replied based on the data returned by calling the customer service operation interface, the session information can be generated according to the replying template to reply the user. The customer service operation interface is an operation interface that can be called by an artificial customer service or an intelligent customer service, for example, an operation interface for inquiring the balance of a certain user, an operation interface for modifying order information of a certain order, and the like.
Specifically, the client may obtain a stored reply template. The reply template is determined for the client according to the corresponding relation between the customer service operation interface and the sentences in the historical session data. The corresponding relation is determined through the service data and the historical session data collected at the embedded points of the customer service operation interfaces. The historical session data are session data before the current time, and the current time is the time when the client receives the session request of the user.
In the above manner, the client may obtain the stored reply template to generate session information according to the reply template to reply to the user.
S104: and responding to the statement sent by the user, and determining a customer service operation interface.
S106: and calling the customer service operation interface, and generating a session information reply user according to the return value of the customer service operation interface and the reply template.
In one or more embodiments of the present disclosure, after determining the reply template, the client may determine a customer service operation interface after receiving the statement sent by the user, and call the customer service operation interface to determine a return value, so as to generate session information according to the reply template and the return value to reply to the user.
Specifically, first, the client may input a sentence into a trained customer service operation interface model according to the sentence input by the user, and determine a customer service operation interface corresponding to the sentence according to the customer service operation interface model. The customer service operation interface model may be a support vector regression (Support Vector Regression, SVR) model, a Decision tree (Decision tree) model, or the like, and the customer service operation interface model is specifically a model, which is not limited in this specification and may be set as required. Of course, since determining the customer service operation interface corresponding to the sentence according to the sentence input by the user is a relatively mature technology in the prior art, the client may also use other technologies to determine the customer service operation interface corresponding to the sentence input by the user, and specifically, what technology is adopted is not described in detail again in this specification.
And secondly, the client can call the customer service operation interface and generate session information to reply to the user according to the return value of the customer service operation interface and the reply template.
By adopting the mode, the client can determine and call the return value corresponding to the statement according to the statement sent by the user, and generate session information to reply the user according to the return value and the reply template.
Based on the method for determining session information shown in fig. 1, a session request of a user may be received, and a reply template generated in advance according to a corresponding relationship between a customer service operation interface and sentences in historical session data may be determined. And responding to the statement sent by the user, and determining a customer service operation interface corresponding to the statement. And calling the customer service operation interface, generating session information according to the return value of the customer service operation interface and the reply template, and replying to the user.
According to the method, after receiving the statement sent by the user, the user can flexibly generate session information to reply the user according to the return value obtained by calling the customer service operation interface corresponding to the statement and the preset reply template, and the reply template does not need to be marked manually, so that the cost is saved.
In addition, in one or more embodiments of the present disclosure, in order to make the session information of the user recovered after the client invokes the customer service operation interface more similar to the session information of the user recovered by the manual customer service, the customer service operation interface that needs to be queried or operated may be determined in advance, and the points may be buried at each customer service operation interface to determine the service data collected by each buried point.
Specifically, after the point is buried at each customer service operation interface, the client can determine each collected service data. The service data comprises customer service identification, interface identification, time stamp and the like. The customer service identifier is an identifier of a customer service calling the customer service operation interface, the interface identifier is an identifier of the customer service operation interface, and the time stamp is the time when the customer service operation interface is called.
By adopting the mode, the client can determine the service data collected at the buried points of each customer service operation interface, so that the ongoing conversation of the customer service calling the customer service operation interface can be determined according to the service data, and the conversation information returned to the user after the customer service operation interface is called can be determined according to the conversation.
In addition, in one or more embodiments of the present description, the purpose of invoking the same customer service operation interface may be different due to different business scenarios. For example, after the operation interface a is called, the data a and the data b can be queried, the customer service needs to reply the user according to the data a in the first service scene, and the customer service needs to reply the user according to the data b in the second service scene. Therefore, for different service scenes, the sentences of the reply user after the customer service calls the same customer service operation interface are different. The client may then determine a traffic scenario corresponding to the session conducted by the user.
Specifically, first, the client may determine the session content after receiving the session request of the user. And determining a service scene corresponding to the session conducted by the user according to the session content. The service scenario corresponding to the session is determined according to the session content, which is a relatively mature prior art, and is not described herein in detail.
Secondly, the client can determine a pre-generated reply template of the service scene according to the service scene. To generate session information to reply to the user.
By adopting the mode, the client can generate session information for each service scene according to the reply template corresponding to the service scene to reply after receiving the session request of the service scene.
In addition, in one or more embodiments of the present disclosure, after determining each collected service data, each service data may be matched with each session data, so as to determine how the client replies to the user after calling the customer service operation interface.
Specifically, first, the client may acquire each session data. Because the purpose of the obtained session data is to match with the service data, and the service data is collected at the embedded point of the service operation interface, the embedded point of the service operation interface is not usually embedded. Therefore, each session data is the session data corresponding to the customer service dialogue after each customer service operation interface buries. The session data includes customer service identification, each sentence, time corresponding to each sentence, user identification of the user, credit rating of the user, and the like.
Secondly, acquiring customer service identifiers corresponding to the service data, and determining the service data, of which the corresponding customer service identifiers are the same as the customer service identifiers of the session data, as a plurality of service data matched with the session data according to the customer service identifiers of the session data and the customer service identifiers corresponding to the service data for each session data. The customer service identifier corresponding to the session data is an identifier of a customer service participating in the session corresponding to the session data, and the customer service identifier of the service data is an identifier of a customer service calling the customer service operation interface corresponding to the service data. When the customer service identifier of the service data is the same as the customer service identifier of the service data, the customer service operation interface corresponding to the service data is called when the customer service participates in the session corresponding to the session data.
By adopting the mode, the client can match each session data with each service data, so that the service data corresponding to each session data is determined, and how the user is replied after the manual customer service is called, and how the user is replied after the client is called.
In addition, in one or more embodiments of the present disclosure, after determining a plurality of service data that match each session data, the user may reply to the statement after determining that the manual service calls the service operation interface from each session data.
Specifically, first, for each session data, the client may determine several traffic data that match the session data. And determining the time corresponding to each statement in the session data.
Secondly, for each business data matched with the session data, the client can determine each statement of the time after the time stamp as a candidate statement according to the time stamp of the business data and the time corresponding to each statement in the session data. And determining the first statement to be selected as a statement with a corresponding relation with the customer service operation interface according to the sequence of the time marks corresponding to the statements to be selected.
By adopting the mode, the client can determine the statement of the user after the manual customer service calls the customer service operation interface according to the time corresponding to each statement in each session data and the time stamp of each service data, so as to determine how the client replies to the user after the customer service operation interface is called.
In addition, in one or more embodiments of the present disclosure, after the customer service calls the customer service operation interface, the customer is replied according to the return value of calling the customer service operation interface. For example, after the user needs to know his account balance and the customer service calls the customer service operation interface for inquiring the account balance, the return value is determined to be 10.00 yuan, and the statement of replying to the user is as follows: "Mr. your account balance is 10 yuan whole". When the client inquires the account balance for the user, the inquiring result is likely not 10.00 yuan, so the client needs to reply to the user according to the return value of the called customer service operation interface. Wherein the return value includes a query result, a modification result, and the like. The modification result is whether the modification data is successful. For example, after the customer service modifies the order amount for the user, if the modification is successful, the modification result included in the return value is successful, and if the modification is failed, the modification result included in the return value is failed.
Specifically, first, the client may determine a reply template corresponding to each customer service operation interface in the service scene according to the corresponding relationship between the sentence and the customer service operation interface in the session data in the service scene and the return value of each customer service operation interface. After the client calls each customer service operation interface in the service scene, a session information reply user can be generated according to the reply template corresponding to each customer service operation interface.
When determining the reply templates corresponding to the customer service operation interfaces, determining a return keyword from the sentences according to the return value of each customer service operation interface and the sentences corresponding to the customer service operation interfaces, marking the return keyword in the sentences, taking the sentences marked with the return keyword as the reply templates, deleting the return keyword, taking the sentences after deleting the return keyword as the reply templates, and determining the reply templates in a specific mode, wherein the method can be set according to requirements, and the specification is not limited. The return keyword is a word representing the return value, for example, the return value is 10.00 yuan, and the return keyword is 10, 10 yuan, 10 whole, etc.
By adopting the mode, the client can determine the reply templates aiming at the customer service operation interfaces under various service scenes according to the sentences of the user after the customer service operation interfaces are called by the customer service, so that the client can generate session information to reply the user through the reply templates after the customer service operation interfaces are called by the customer service under various service scenes.
In addition, in one or more embodiments of the present disclosure, since the embedded point at each customer service operation interface in each service scenario may continuously collect service data corresponding to each session data, the reply template corresponding to each service scenario may be continuously updated.
Specifically, the client may determine, according to a preset update period, that the reply template is updated for each service scenario when the update period is reached, according to each service data collected by each customer service operation interface embedded point of the service scenario and each session data under the service scenario.
Of course, in other cases, the client may update the reply templates in each business scenario. Specifically, if the client determines that the number of complaints received by the user reaches the preset complaint number threshold, the client can update each reply template, and when the client receives an update request sent by a background person, each reply template can be updated. The background personnel are the personnel responsible for the operation and maintenance of the client. The specific time to update each reply template can be set according to the needs, and the specification is not limited.
By adopting the method, the client can continuously update the reply templates under each service scene, so that each reply template can more accurately determine the session information reply users.
In addition, in one or more embodiments of the present disclosure, since in general, when a customer service dialogues with a user, the customer service operation interface may be directly called to obtain data to reply to the user, there is no need to collect the data. That is, data is not typically collected, and thus the client may bury points at each customer service operation interface in advance to collect data.
Specifically, first, the client may obtain each customer service flow constructed for each common problem in each service scenario, and screen out session information that needs to be determined by customer service based on the data returned by calling the customer service operation interface from each customer service flow. The customer service flow comprises a plurality of session questions and answers, and session information which is needed to be determined by customer service based on data returned by calling a customer service operation interface can be screened out from the customer service flow by a person or a client. When the client terminal screens, the client terminal can determine the session information which needs to be determined based on the data returned by calling the customer service operation interface by carrying out semantic analysis on each session question and answer in each customer service flow and judging whether the customer service needs to call the customer service operation interface before inputting each statement according to the analysis result. Wherein the session information is a sentence.
Of course, because the customer service flow is a manually set session question and answer, and the problem of the real user may be wonderful, in order to more accurately determine each customer service operation interface needing to be buried, the client may also obtain each session data of the user and the manual customer service, and determine, according to each session information input by the manual customer service in each session data, the session information that the manual customer service needs to be determined based on the data returned by calling the customer service operation interface.
And secondly, the client can determine the interface identification of the customer service operation interface required to be called by each session information through semantic analysis of each session information according to the determined session information. And burying points at customer service operation interfaces corresponding to the interface identifiers according to the determined interface identifiers so as to acquire data. Of course, the interface identification of the customer service operation interface to be called by each session information can be determined manually according to each session information, and then the point is buried at the customer service operation interface corresponding to each interface identification according to each determined interface identification so as to collect data.
Of course, since the types of different customer service interfaces may be different, for example, the customer service interface for modifying data is different from the customer service interface for querying data. Therefore, the client or the person can embed points at the customer service operation interfaces of various types according to the types of the customer service operation interfaces. The data collected by the buried points at the customer service operation interfaces of different types are different. For example, the data collected by the embedded point at the customer service operation interface for modifying the data includes a modification result, which is success or failure, while the data collected by the embedded point at the customer service operation interface for querying the data includes a query result, which is specific data.
By adopting the mode, the points can be buried at the customer service operation interfaces so as to determine the service data collected by the buried points.
In addition, in one or more embodiments of the present disclosure, since the client may learn the interface identifier of each customer service operation interface of the customer service client, the client may also embed points at each customer service operation interface of the customer service client to collect data.
In addition, in one or more embodiments of the present description, since manual customer service is typically required to help a large number of users solve a problem, manual customer service may invoke a large number of operator interfaces when solving a problem for different users. That is, one session data may be matched to a large number of irrelevant service data, and thus, when matching session data with service data, matching can be performed by a session period of each session data and a time stamp of each service data.
Specifically, customer service identifiers and time stamps corresponding to the service data are obtained. And determining the session time period and customer service identification of the session data for each session data. And determining a plurality of service data, of which the corresponding customer service identification is the same as the customer service identification of the session data and the time stamp is in the session period of the session data, as a plurality of service data matched with the session data according to the session period of the session data and the customer service identification. The session time period is a time period formed by the starting time and the ending time of the session corresponding to the session data.
Of course, since the same personnel service may help multiple users to solve the problem at the same time, there may be a case where the personnel service makes multiple calls to one service operation interface in a short time in order to answer the problem of different users. Thus, the service data may include information such as a user identifier, an order status, a user status, etc., where the user identifier is a user identifier input by the human customer service when the customer service operation interface corresponding to the service data is called by the human customer service, that is, a user identifier of a user waiting for the human customer service to reply to a statement according to a return value of the customer service operation interface. The session data may include a user identification, order status, user status, etc., the user identification being a user identification of a user participating in a session to which the session data corresponds. The service data matched with the session data can be determined from the service data according to the information such as the customer service identification, the user identification and the like of the session data and the information such as the customer service identification, the user identification, the order state and the like of the service data.
By adopting the mode, the service data matched with the session data can be more accurately determined, and the statement of the user is recovered after each manual customer service is called by each customer service operation interface.
In addition, in one or more embodiments of the present description, since the customer service may call the customer service operation interface, the first sentence to reply to the user may be "please do you, i inquire you for you, etc. "etc. Accordingly, the statement that there is a correspondence relationship with each customer service operation interface can be determined in the following manner.
Specifically, first, for each session data, a time corresponding to each sentence in the session data is acquired. And determining the time stamp of each service data. And determining each statement after the time stamp as a candidate statement according to the time stamp of the service data and the time corresponding to each statement in the session data.
And secondly, determining keywords according to the service data, wherein the keywords can be return values after the customer service operation interface corresponding to the service data is called, return keywords determined according to the return values after the customer service operation interface corresponding to the service data is called, and the like. Continuing with the above example, the return value is 10.00 yuan, and the return keywords are 10, 10 yuan, 10 whole, etc.
And finally, determining a first candidate sentence matched with the keyword as a sentence with a corresponding relation with the customer service operation interface according to the keyword and each candidate sentence and the sequence of time. When determining whether each candidate sentence is matched with the keyword, semantic analysis can be performed on each candidate sentence, whether the word corresponding to the keyword exists in each candidate sentence or not can be judged, and other modes can be adopted.
By adopting the mode, the statement with the corresponding relation with each customer service operation interface can be more accurately determined, so that the reply template corresponding to each customer service operation interface can be more accurately determined.
In addition, in one or more embodiments of the present description, the agreement with the service provider is violated multiple times due to the existence of partial users with very poor credit. When the customer service is used for helping the users to solve the problems, sentences which are different from sentences which are used for helping the common users to solve the problems can be adopted for replying, so that when the reply templates corresponding to the customer service operation interfaces are determined, the reply templates can be determined, when the session information is determined to reply the users, different session information can be determined for the users with different credit grades to reply.
Specifically, first, when determining the reply template, the client may determine, according to the session data, user information of a user participating in a session corresponding to the session data after determining the session data. And determining the credit rating of the user according to the user information.
And secondly, after the corresponding relation between each statement and each customer service operation interface in the session data is determined, determining each statement with the corresponding relation with each customer service operation interface according to the credit grade of the user participating in the session corresponding to the session data, wherein the corresponding credit grade is determined.
Finally, when determining the reply template, the client can determine the statement corresponding to the customer service operation interface according to the corresponding relation between the statement and the customer service operation interface in each session data in the service scene and the credit level corresponding to the statement of each session data, and determine each statement as the reply template according to each credit level. After the client side faces users with different credit grades and calls the customer service operation interface, the session information corresponding to the credit grade and the customer service operation interface can be generated according to the reply template to reply the users.
By adopting the mode, different session information can be determined for users with different credit levels. After the client side faces users with different credit grades and calls the customer service operation interface, the session information corresponding to the credit grade and the customer service operation interface can be generated according to the reply template to reply the users.
In addition, in one or more embodiments of the present description, different language and sentence patterns may be used to answer the same question due to different manual services. Therefore, when the reply templates corresponding to the customer service operation interfaces are determined, the customer service identification corresponding to the reply templates can be determined.
Specifically, the client can determine, for each service scenario, a reply template carrying a customer service identifier corresponding to each customer service operation interface in the service scenario according to the corresponding relationship between sentences and customer service operation interfaces in each session data in the service scenario and the customer service identifier of each session data. After the client calls the customer service operation interface in each service scene, a reply template can be selected according to the customer service identification, and session information reply users are generated through the selected reply template. When a client solves a problem for a user and a plurality of customer service operation interfaces are required to be called, the client can select a reply template corresponding to the same customer service identifier to generate session information to reply the user after calling the customer service operation interfaces each time.
It should be noted that, all actions for acquiring signals, information or data in the present application are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
The method for determining session information provided above for one or more embodiments of the present disclosure, based on the same concept, further provides a corresponding apparatus for determining session information, as shown in fig. 2.
Fig. 2 is a schematic diagram of an apparatus for determining session information provided in the present specification, which specifically includes:
a receiving module 200 for receiving a session request of a user;
the generating module 202 determines a pre-generated reply template, wherein the reply template is determined according to the corresponding relation between the customer service operation interface and sentences in the historical session data, and the corresponding relation is determined through the business data and the historical session data collected by the buried points at the customer service operation interface;
a determining module 204, configured to determine a customer service operation interface in response to the statement sent by the user;
and the reply module 206 is used for calling the customer service operation interface and generating a session information reply user according to the return value of the customer service operation interface and the reply template.
Optionally, the reply module 206 determines the credit rating of the user according to the stored user information of the user, generates a plurality of pieces of session information to be selected corresponding to different credit ratings according to the return value of the customer service operation interface and the reply template, and determines the session information corresponding to the credit rating of the user from the session information to be selected, so as to reply to the user.
Optionally, the receiving module 200 receives a session request of a user, determines session content, and determines a service scenario corresponding to a session performed by the user according to the session content.
Optionally, the receiving module 200 determines a pre-generated reply template of the service scenario according to the service scenario corresponding to the session performed by the user.
Optionally, the receiving module 200 obtains each historical session data and each service data collected at a buried point at each customer service operation interface in the service scene, where the service data at least includes a customer service identifier, an interface identifier and a timestamp, determines, for each historical session data, a plurality of service data matched with the historical session data according to the customer service identifier in the historical session data, determines, from the historical session data, a correspondence between a customer service operation interface and a sentence according to the interface identifier and the timestamp in the matched plurality of service data, and determines, from the historical session data, a reply template of the service scene according to a correspondence between a sentence in the historical session data in the service scene and the customer service operation interface.
Optionally, the receiving module 200 obtains each customer service flow constructed for each common problem in the service scenario, screens out session information determined based on the data returned by calling the customer service operation interface from each customer service flow, and buries a point at the customer service operation interface corresponding to the screened session information.
Optionally, the receiving module 200 obtains the service identifier and the timestamp corresponding to each service data, and determines, for each historical session data, a plurality of service data with a timestamp within a session period of the historical session data and the service identifier being the same as the service identifier in the historical session data, as a plurality of service data matched with the historical session data, where the session period is a period of time for performing a session corresponding to the historical session data.
Optionally, the receiving module 200 determines, for each service data, each sentence after the timestamp according to the timestamp of the service data and the time corresponding to each sentence in the historical session data, as a candidate sentence, determines a keyword according to the service data, determines, according to the keyword and each candidate sentence, a first candidate sentence matched with the keyword according to the time sequence, and is a sentence having a correspondence with the customer service operation interface.
The present specification also provides a computer readable storage medium storing a computer program operable to perform the method of determining session information provided in fig. 1 above.
The present specification also provides a schematic structural diagram of the electronic device shown in fig. 3. At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile storage, as described in fig. 3, although other hardware required by other services may be included. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to implement the method for determining session information described above with respect to fig. 1. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present application.

Claims (10)

1. A method of determining session information, comprising:
receiving a session request of a user;
determining a pre-generated reply template, wherein the reply template is determined according to the corresponding relation between a customer service operation interface and sentences in historical session data, and the corresponding relation is determined through each business data and the historical session data collected by burying points at the customer service operation interface;
Responding to the statement sent by the user, and determining a customer service operation interface;
and calling the customer service operation interface, and generating a session information reply user according to the return value of the customer service operation interface and the reply template.
2. The method of claim 1, wherein generating a session information reply user according to the return value of the customer service operation interface and the reply template, specifically comprises:
determining the credit rating of the user according to the stored user information of the user;
generating a plurality of pieces of session information to be selected corresponding to different credit levels according to the return value of the customer service operation interface and the reply template;
and determining session information corresponding to the credit rating of the user from the session information to be selected, and replying to the user.
3. The method according to claim 1, characterized in that receiving a session request of a user, in particular comprises:
receiving a session request of a user and determining session content;
and determining a service scene corresponding to the session of the user according to the session content.
4. A method according to claim 3, wherein determining a pre-generated reply template, in particular comprises:
And determining a pre-generated reply template of the service scene according to the service scene corresponding to the session carried out by the user.
5. The method of claim 4, wherein determining the reply template according to the correspondence between customer service operation interface and sentences in the historical session data, specifically comprises:
acquiring historical session data and service data acquired by burying points at each customer service operation interface in the service scene, wherein the service data at least comprises customer service identification, interface identification and time stamp;
for each historical session data, determining a plurality of business data matched with the historical session data according to customer service identifiers in the historical session data;
determining the corresponding relation between the customer service operation interface and the sentence from the historical session data according to the interface identifiers and the time stamps in the matched service data;
and determining a reply template of the service scene according to the corresponding relation between sentences and customer service operation interfaces in the historical session data under the service scene.
6. The method of claim 5, wherein prior to acquiring each service data collected at a buried point at each customer service operation interface in the service scenario, the method further comprises:
Acquiring each customer service flow constructed for each common problem under the service scene;
screening session information determined based on the data returned by calling the customer service operation interface from the customer service flows;
burying points at customer service operation interfaces corresponding to the screened session information.
7. The method according to claim 5, wherein for each historical session data, determining a number of service data matching the historical session data according to customer service identification in the historical session data, specifically comprises:
respectively acquiring customer service identifiers and time stamps corresponding to the service data;
and determining a plurality of business data with time stamps being in a session period of the historical session data and customer service identifiers being the same as the customer service identifiers in the historical session data as a plurality of business data matched with the historical session data according to each historical session data, wherein the session period is a period of time for carrying out a session corresponding to the historical session data.
8. The method according to claim 5, wherein determining the corresponding relation between the customer service operation interface and the sentence from the historical session data according to the interface identifier and the timestamp in the matched plurality of service data specifically comprises:
For each business data, determining each sentence after the time stamp according to the time stamp of the business data and the time corresponding to each sentence in the historical conversation data as a to-be-selected sentence;
determining keywords according to the service data;
and determining a first statement to be selected matched with the keyword as a statement with a corresponding relation with the customer service operation interface according to the keyword and each statement to be selected and the sequence of time.
9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-8.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-8 when executing the program.
CN202210926752.5A 2022-08-03 2022-08-03 Method and device for determining session information Pending CN117555997A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210926752.5A CN117555997A (en) 2022-08-03 2022-08-03 Method and device for determining session information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210926752.5A CN117555997A (en) 2022-08-03 2022-08-03 Method and device for determining session information

Publications (1)

Publication Number Publication Date
CN117555997A true CN117555997A (en) 2024-02-13

Family

ID=89819122

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210926752.5A Pending CN117555997A (en) 2022-08-03 2022-08-03 Method and device for determining session information

Country Status (1)

Country Link
CN (1) CN117555997A (en)

Similar Documents

Publication Publication Date Title
CN109614823B (en) Data processing method, device and equipment
CN109514586B (en) Method and system for realizing intelligent customer service robot
CN110569428B (en) Recommendation model construction method, device and equipment
CN110674408A (en) Service platform, and real-time generation method and device of training sample
CN111966334B (en) Service processing method, device and equipment
CN115203394A (en) Model training method, service execution method and device
CN111400681B (en) Data authority processing method, device and equipment
CN111144132B (en) Semantic recognition method and device
CN112529585A (en) Interactive awakening method, device, equipment and system for risk transaction
CN112735374A (en) Automatic voice interaction method and device
CN115146601A (en) Method and device for executing language processing task, readable storage medium and equipment
CN113408254A (en) Page form information filling method, device, equipment and readable medium
CN116974676A (en) Page content sending method, device and equipment
CN114449063B (en) Message processing method, device and equipment
CN116069915A (en) Government service processing method and device
CN117555997A (en) Method and device for determining session information
CN111324778B (en) Data and service processing method and device and electronic equipment
CN112491943A (en) Data request method, device, storage medium and electronic equipment
CN113672784B (en) Vehicle information processing method, device and system based on block chain
CN110704742B (en) Feature extraction method and device
CN115391503A (en) Application method and device of session flow
CN112487170A (en) Scene configuration-oriented human-computer interaction dialogue robot system
CN111966709A (en) Data query method and device and electronic equipment
CN109145084B (en) Data processing method, data processing device and server
CN112036576A (en) Data processing method and device based on data form and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination