CN112148743A - Method, device, equipment and storage medium for updating intelligent customer service knowledge base - Google Patents
Method, device, equipment and storage medium for updating intelligent customer service knowledge base Download PDFInfo
- Publication number
- CN112148743A CN112148743A CN202010987578.6A CN202010987578A CN112148743A CN 112148743 A CN112148743 A CN 112148743A CN 202010987578 A CN202010987578 A CN 202010987578A CN 112148743 A CN112148743 A CN 112148743A
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- intelligent
- customer service
- knowledge base
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004140 cleaning Methods 0.000 claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims description 51
- 239000012088 reference solution Substances 0.000 claims description 25
- 238000001914 filtration Methods 0.000 claims description 5
- 239000000243 solution Substances 0.000 description 39
- 238000010586 diagram Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 7
- 238000003058 natural language processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2308—Concurrency control
- G06F16/2315—Optimistic concurrency control
- G06F16/2322—Optimistic concurrency control using timestamps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to an updating method, device, equipment and storage medium of an intelligent customer service knowledge base. The method comprises the following steps: acquiring at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at each interval of preset acquisition time; adding the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition into an intelligent customer service knowledge base; acquiring at least one piece of intelligent question and answer record data and question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time; deleting the intelligent question-answer record data of which the question answer matching degree of the intelligent question-answer data meets the second set matching condition from the intelligent customer service knowledge base, and adding data into the intelligent knowledge base and deleting dirty data in time; and a comprehensive intelligent knowledge base can be created while labor cost is saved.
Description
Technical Field
The embodiment of the disclosure relates to computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for updating an intelligent customer service knowledge base.
Background
The intelligent customer service means that the problem of the user is automatically identified through a machine and a corresponding solution is given, in the concrete implementation, the problem of the user is replied through the intelligent customer service, the response speed of the problem of the user can be improved, and the labor cost is saved. The working mode of the intelligent customer service is generally that firstly, the NLP (Natural Language Processing) algorithm is used to identify the user problem, and then the user is sent to the intelligent knowledge base configured in the background to search the corresponding solution and provide the solution to the user. At present, the NLP algorithm has high identification accuracy, so that the establishment of a comprehensive and accurate intelligent knowledge base becomes a key factor for determining the intelligent customer service level.
In the related art, the intelligent knowledge base needs to be maintained manually, specifically, maintenance personnel can periodically retrieve user problems which are not solved by the intelligent customer service, extract some problems which are considered to be more important by the maintenance personnel from the user problems, write corresponding solutions according to business experiences of the maintenance personnel or inquire other colleagues, and finally add the problems and the solutions into the intelligent knowledge base. However, the method mainly extracts the problem according to the experience of the maintenance personnel, and has the problems that the data recorded in the intelligent knowledge base cannot be added in time and the dirty data in the intelligent knowledge base cannot be deleted in time.
Disclosure of Invention
The present disclosure provides an update method, an update device, an update apparatus, and a storage medium for an intelligent customer service knowledge base, so as to at least solve the problems in the related art that data recorded in an intelligent knowledge base is not added in time and dirty data in the intelligent knowledge base cannot be deleted in time.
The technical scheme of the embodiment of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided an update method of an intelligent customer service knowledge base, including: acquiring at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at each interval of preset acquisition time;
adding the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition into the intelligent customer service knowledge base;
acquiring at least one piece of intelligent question and answer record data and the question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time;
and deleting the intelligent question-answer record data of which the question answer matching degree of the intelligent question-answer record data meets a second set matching condition from the intelligent customer service knowledge base.
Optionally, the step of adding the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition to the intelligent customer service knowledge base includes:
performing semantic analysis on the question answer matching degree of the manual question-answer data to obtain a semantic analysis result;
matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree;
and when the reference evaluation level is greater than a first set threshold value, determining that the question answer matching degree of the artificial question and answer data meets a first set matching condition, and adding the corresponding artificial question and answer record data to the intelligent customer service knowledge base.
Optionally, after determining that the degree of matching of the question answers of the artificial question and answer data meets the artificial question and answer record data of the first set matching condition, before adding the artificial question and answer record data to the intelligent customer service knowledge base, the method further includes performing at least one of the following:
deleting special characters contained in the manual question answering record data;
and performing deduplication filtration on each artificial question answering record data based on content similarity.
Optionally, the manual question-and-answer record table and the intelligent question-and-answer record table are recorded in the same table.
Optionally, the step of deleting the intelligent question and answer record data whose question answer matching degree meets a second set matching condition from the intelligent customer service knowledge base includes:
counting the question answer matching degree of each intelligent question-answer data, and comparing the question answer matching degree with a second set threshold value;
and deleting the intelligent question-answer record data corresponding to the question answer matching degree smaller than a second set threshold value from the intelligent customer service knowledge base.
Optionally, the method further includes:
responding to the user problem received by the intelligent customer service, determining a reference solution matched with the user problem in the updated intelligent customer service knowledge base, and feeding back the reference solution to the intelligent customer service;
and adding intelligent question and answer record data generated according to the user question and the reference solution into the intelligent question and answer record table.
According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for updating a literary intelligence customer service knowledge base, including:
the acquisition module is configured to acquire at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at intervals of preset acquisition time;
the adding module is configured to add the artificial question and answer record data of which the question answer matching degree of the artificial question and answer data meets a first set matching condition into the intelligent customer service knowledge base;
the intelligent question-answer system comprises a cleaning module, a question answer matching module and a question answer matching module, wherein the cleaning module is configured to acquire at least one piece of intelligent question-answer record data and the question answer matching degree of each piece of intelligent question-answer record data from an intelligent question-answer record table at intervals of preset cleaning time;
and the deleting module is configured to delete the intelligent question-answer record data of which the question answer matching degree of the intelligent question-answer data meets a second set matching condition from the intelligent customer service knowledge base.
Optionally, the adding module is specifically configured to:
performing semantic analysis on the question answer matching degree of the manual question-answer data to obtain a semantic analysis result;
matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree;
and when the reference evaluation level is greater than a first set threshold value, determining that the question answer matching degree of the artificial question and answer data meets a first set matching condition, and adding the corresponding artificial question and answer record data to the intelligent customer service knowledge base.
Optionally, the apparatus further comprises: a deletion module and a deduplication module;
the deleting module is configured to delete the special characters contained in the manual question and answer record data;
the duplication removing module is configured to perform duplication removing filtering on each manual question answering record data based on content similarity.
Optionally, the deleting module is specifically configured to
Counting the question answer matching degree of each intelligent question-answer data, and comparing the question answer matching degree with a second set threshold value;
and deleting the intelligent question-answer record data corresponding to the question answer matching degree smaller than a second set threshold value from the intelligent customer service knowledge base.
Optionally, the apparatus further comprises: a feedback module configured to
Responding to the user problem received by the intelligent customer service, determining a reference solution matched with the user problem in the updated intelligent customer service knowledge base, and feeding back the reference solution to the intelligent customer service;
and adding intelligent question and answer record data generated according to the user question and the reference solution into the intelligent question and answer record table.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the instructions to implement the method for updating an intelligent customer service knowledge base according to any one of the embodiments of the present disclosure.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium, wherein instructions of the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform an update method of an intelligent customer service knowledge base according to any one of the embodiments of the present disclosure.
According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, wherein when the instructions in the computer program product are executed by a processor of an electronic device, the method for updating an intelligent customer service knowledge base according to any of the embodiments of the present disclosure is implemented.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects: acquiring at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at each interval of preset acquisition time; adding the manual question and answer record data of which the question answer matching degree meets a first set matching condition into an intelligent customer service knowledge base; acquiring at least one piece of intelligent question and answer record data and question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time; the intelligent question-answer record data with the question answer matching degree meeting the second set matching condition of the intelligent question-answer record data are deleted from the intelligent customer service knowledge base, so that the problems that the data recorded in the intelligent knowledge base in the related technology cannot be added in time and the dirty data in the intelligent knowledge base (the intelligent question-answer record data meeting the second set matching condition) cannot be deleted in time can be solved, the data can be timely added in the intelligent knowledge base and the dirty data can be timely deleted, and the comprehensive intelligent knowledge base can be created while the labor cost is saved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a flow diagram illustrating a method for updating an intelligent customer service repository, according to an example embodiment.
FIG. 2 is a flow diagram illustrating a method for updating an intelligent customer service repository, according to an example embodiment.
FIG. 3 is a flow diagram illustrating a method for updating an intelligent customer service repository, according to an example embodiment.
FIG. 4 is an overall architecture diagram illustrating one type of updating a smart customer service knowledge base in accordance with an exemplary embodiment.
FIG. 5 is a block diagram illustrating an apparatus for updating an intelligent customer service knowledge base in accordance with an exemplary embodiment.
FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Fig. 1 is a flowchart illustrating an updating method of an intelligent customer service knowledge base according to an exemplary embodiment, and as shown in fig. 1, the updating method of the intelligent customer service knowledge base may be performed by an updating apparatus of the intelligent customer service knowledge base, the apparatus may be implemented by software and/or hardware, and is used in an electronic device, which may be a server, a computer, a tablet computer, or the like, and the present embodiment is not limited thereto, and the method includes the following steps.
In step S11, at least one piece of manual question and answer record data and the matching degree of the answers to the questions of each piece of manual question and answer record data are obtained from the manual question and answer record table at every preset acquisition time.
The preset collection time may be 1 minute, 2 minutes, or 5 minutes, and the like, which is not limited in this embodiment. For example, in this embodiment, the collection operation may be initiated every 2 minutes, and at least one manual question and answer record data is obtained from the manual question and answer record table.
In this embodiment, the manual question and answer record table may include manual question and answer record data generated in a process of a user and manual customer service conversation, and question answer matching degrees of the manual question and answer data, where the question answer matching degrees of the manual question and answer data may be satisfaction evaluation data of the user on the manual question and answer data; for example, the user is satisfied with the solution provided by the customer service and the evaluation is given according to the satisfaction. It should be noted that, in this embodiment, the satisfaction evaluation data of the user on the manual question and answer data may be a score numerical value such as 65, 85, or 90, or may also be an evaluation grade such as poor, general, more satisfactory, or satisfactory, which is not limited in this embodiment.
For example, the manual question and answer record data generated during the user and manual customer service dialogue may be: "user: when can a shipment? Manual customer service: within seven days; and unsatisfactory "; wherein, the dissatisfaction is the satisfaction evaluation of the user to the information replied by the manual customer service; the manual question and answer record data generated in the process of the user and manual customer service conversation can also be: "user: when can a shipment? Manual customer service: within three days; and 80 cents "; wherein, the 80 points is the satisfaction degree evaluation of the user to the information returned by the manual customer service.
In an optional implementation manner of this embodiment, at least one piece of manual question and answer record data, for example, 2, 10, or 100, may be obtained from the manual question and answer record table every 5 minutes, which is not limited in this embodiment.
It should be noted that the manual customer service and the intelligent customer service related in this embodiment may answer the questions posed by the user in a voice manner, or may answer the questions posed by the user in a text manner. For example, in a voice dialog system (e.g., telephone call), human customer service and intelligent customer service may answer questions posed by a user by voice; in certain shopping software, artificial customers and intelligent customer service can answer questions posed by users in a text mode.
In step S12, the manual question and answer record data whose question answer matching degree of the manual question and answer data satisfies the first set matching condition is added to the intelligent customer service knowledge base.
The first set matching condition may be that the degree of matching of the answers to the questions of the question-and-answer data is greater than or equal to a first set threshold; the first set threshold may be a score value such as 60 points, 75 points, or 90 points, or may be a better or more satisfactory evaluation level, which is not limited in this embodiment.
It should be noted that, in this embodiment, the intelligent customer service may obtain a solution corresponding to a problem proposed by the user from the intelligent customer service knowledge base. For example, a user asks "when can a shipment? At this point, the intelligent customer service may determine a solution corresponding to the problem in the intelligent customer service repository and feed the solution back to the user.
In an optional implementation manner of this embodiment, after at least one piece of manual question and answer record data is obtained from the manual question and answer record table according to a preset collection rule, the collected manual question and answer record data may be further counted, and the manual question and answer record data whose question answer matching degree of the manual question and answer data meets a first set matching condition is added to the intelligent customer service knowledge base.
Illustratively, if 100 pieces of manual question and answer record data are acquired from the manual question and answer record table according to a preset acquisition rule, the 100 pieces of manual question and answer record data are counted, and it is determined that the question answer matching degree of 10 pieces of manual question and answer record data is greater than 90 points (a first set threshold), the 10 pieces of manual question and answer record data can be added to the intelligent customer service knowledge base.
In another specific example of this embodiment, if 100 pieces of manual question and answer record data are acquired from the manual question and answer record table according to a preset acquisition rule, the 100 pieces of manual question and answer record data are counted, and it is determined that the question answer matching degree of 10 pieces of manual question and answer record data is satisfactory (the first set threshold), then the 10 pieces of manual question and answer record data may be added to the intelligent customer service knowledge base.
In step S13, at least one piece of smart question and answer record data and the question answer matching degree of each piece of smart question and answer record data are obtained from the smart question and answer record table every preset cleaning time.
The preset cleaning time may be 1 minute, 2 minutes, or 5 minutes, and the like, which is not limited in this embodiment. For example, in this embodiment, the collection operation may be initiated every 2 minutes, and at least one piece of smart question-and-answer record data may be obtained from the smart question-and-answer record table.
In this embodiment, the intelligent question and answer record table may include intelligent question and answer record data generated in a process of a conversation between the user and the intelligent customer service, and question answer matching degrees of the intelligent question and answer data, where the question answer matching degrees of the intelligent question and answer data may be satisfaction evaluation data of the user on the intelligent question and answer data; for example, the user's satisfaction with the solution provided by the smart customer service and the rating given according to the satisfaction. It should be noted that, in this embodiment, the satisfaction evaluation data of the user on the intelligent question and answer data may be a score numerical value such as 65, 85, or 90, or may also be an evaluation grade such as poor, general, more satisfactory, or satisfactory, which is not limited in this embodiment.
In an optional implementation manner of this embodiment, at least one person smart answer record data, for example, 2, 10, or 100, may be obtained from the smart question-answer record table every 5 minutes, which is not limited in this embodiment.
In step S14, the smart question-and-answer record data in which the degree of matching between the answers to the questions in the smart question-and-answer data satisfies the second set matching condition is deleted from the smart customer service knowledge base.
The second set matching condition may be that the question answer matching degree of the intelligent question-answer data is less than or equal to a second set threshold; the second set threshold may be a score value such as 60 points, 55 points, or 40 points, or may be an evaluation level such as poor or unsatisfactory, and is not limited in this embodiment.
In an optional implementation manner of this embodiment, after at least one piece of intelligent question and answer record data is acquired from the intelligent question and answer record table at intervals of preset cleaning time, statistics may be further performed on the acquired intelligent question and answer record data, and the intelligent question and answer record data whose question answer matching degree of the intelligent question and answer data meets a second set matching condition is deleted from the intelligent knowledge base.
Optionally, the deleting the intelligent question and answer record data with the question answer matching degree of the intelligent question and answer record data meeting the second set matching condition from the intelligent customer service knowledge base may include: counting the question answer matching degree of each intelligent question-answer data, and comparing the question answer matching degree with a second set threshold value; and deleting the intelligent question-answer record data corresponding to the question answer matching degree which is less than or equal to the second set threshold value from the intelligent customer service knowledge base.
Illustratively, if 100 pieces of intelligent question and answer record data are acquired from the intelligent question and answer record table according to a preset cleaning rule, the 100 pieces of intelligent question and answer record data are counted, and it is determined that the question answer matching degree of 10 pieces of intelligent question and answer record data is less than 60 points (a second set threshold), the 10 pieces of intelligent question and answer record data can be deleted from the intelligent customer service knowledge base.
In another specific example of this embodiment, after 100 pieces of smart question and answer record data are acquired from the smart question and answer record table according to a preset cleaning rule, the 100 pieces of smart question and answer record data are counted, and it is determined that the question answer matching degree of 10 pieces of smart question and answer record data is unsatisfactory (a second set threshold), then the 10 pieces of smart question and answer record data may be deleted from the smart customer service knowledge base.
According to the scheme of the embodiment, at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data are obtained from the manual question and answer record table at intervals of preset acquisition time; adding the manual question and answer record data of which the question answer matching degree meets a first set matching condition into an intelligent customer service knowledge base; acquiring at least one piece of intelligent question and answer record data and question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time; the intelligent question-answer record data with the question answer matching degree meeting the second set matching condition of the intelligent question-answer record data are deleted from the intelligent customer service knowledge base, so that the problems that the data recorded in the intelligent knowledge base in the related technology are not added in time and the dirty data in the intelligent knowledge base (the intelligent question-answer record data meeting the second set matching condition) cannot be deleted in time can be solved, the data can be timely added in the intelligent knowledge base and the dirty data can be timely deleted, and the comprehensive intelligent knowledge base can be created while the labor cost is saved.
Fig. 2 is a flowchart illustrating an updating method of an intelligent customer service knowledge base according to an exemplary embodiment, which is a further refinement of the above technical solution, and the technical solution in this embodiment may be combined with various alternatives in one or more embodiments described above. As shown in fig. 2, the method for updating the intelligent customer service knowledge base includes the following steps.
In step S21, at least one piece of manual question and answer record data and the matching degree of the answer to the question of each piece of manual question and answer record data are obtained from the manual question and answer record table at every preset collection time.
In step S22, the matching degree of the question answers to the manual question-and-answer data is subjected to semantic analysis to obtain a semantic analysis result.
In an optional implementation manner of this embodiment, after acquiring at least one piece of manual question and answer record data and a question answer matching degree of each piece of manual question and answer record data from the manual question and answer record table at every preset acquisition time interval, if the manual question and answer data is voice data, for example, a call recording; the semantic analysis can be further carried out on the question answer matching pairs of the manual question and answer data, namely the satisfaction evaluation data of the user on the manual question and answer data is analyzed, and therefore a semantic analysis result is obtained.
Illustratively, in this embodiment, the matching degree of the answers to the questions of the artificial question-and-answer data may be analyzed through an NLP algorithm to obtain a semantic analysis result; for example, the semantic analysis result may be satisfactory, unsatisfactory, or better, and the like, which is not limited in this embodiment.
In step S23, the semantic analysis result is matched with a preset evaluation level to determine a reference evaluation level corresponding to the question answer matching degree.
The preset evaluation level may be one level, two levels, medium level, or high level, and the present embodiment is not limited thereto. In specific implementation, evaluation levels of different criteria may be set according to different scenes and different habits of users, which is not limited in this embodiment.
In an optional implementation manner of this embodiment, after obtaining the semantic analysis result, the obtained semantic analysis result may be further matched with a preset evaluation level, so as to determine a reference evaluation level corresponding to the question answer matching degree.
Illustratively, if the semantic analysis result obtained by analyzing the question answer matching degree of the artificial question and answer data through the NLP algorithm is "satisfactory", the semantic analysis result is matched with a preset evaluation level, and a reference evaluation level corresponding to the question answer matching degree is determined to be high.
In step S24, when the reference evaluation level is greater than the first set threshold, it is determined that the question answer matching degree of the manual question and answer data satisfies the first set matching condition, and the corresponding manual question and answer record data is added to the intelligent customer service knowledge base.
Wherein, the first set threshold is associated with the preset evaluation level in the embodiment; for example, if the preset evaluation levels are one level, two levels, three levels, four levels, and five levels, the first set threshold may be three levels or four levels, which is not limited in this embodiment; if the preset evaluation levels are low, medium, high, and high, the first set threshold may be medium or high, which is not limited in this embodiment.
In a specific example of this embodiment, if the question answer matching degree of the artificial question and answer data is analyzed by the NLP algorithm, and the obtained semantic analysis result is matched with the preset evaluation level, the reference evaluation level corresponding to the question answer matching degree is determined to be high level, and if the first set threshold is medium level, it may be determined that the question answer matching degree of the artificial question and answer data satisfies the first set matching condition, and the corresponding artificial question and answer record data may be added to the intelligent customer service knowledge base.
In step S25, at least one piece of smart question and answer record data and the question answer matching degree of each piece of smart question and answer record data are obtained from the smart question and answer record table every preset cleaning time.
In step S26, the smart question-and-answer record data in which the degree of matching between the answers to the questions in the smart question-and-answer data satisfies the second set matching condition is deleted from the smart customer service knowledge base.
According to the scheme of the embodiment, a semantic analysis result is obtained by performing semantic analysis on the question answer matching degree of the manual question-answer data; matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree; when the reference evaluation level is greater than a third set threshold value, the question answer matching degree of the manual question and answer data is determined to meet a first set matching condition, the corresponding manual question and answer record data is added to the intelligent customer service knowledge base, the problem that data recorded in the intelligent knowledge base in the related technology is not added timely can be solved, the data can be timely added into the intelligent knowledge base, and a basis is provided for creating a comprehensive intelligent knowledge base.
Fig. 3 is a flowchart illustrating an updating method of an intelligent customer service knowledge base according to an exemplary embodiment, which is a further refinement of the above technical solution, and the technical solution in this embodiment may be combined with various alternatives in one or more embodiments described above. As shown in fig. 3, the method for updating the intelligent customer service knowledge base includes the following steps.
In step S31, at least one piece of manual question and answer record data and the matching degree of the answers to the questions of each piece of manual question and answer record data are obtained from the manual question and answer record table at every preset acquisition time.
In step S32, the manual question and answer record data whose question answer matching degree of the manual question and answer data satisfies the first set matching condition is added to the intelligent customer service knowledge base.
In an optional implementation manner of this embodiment, after determining that the degree of matching of the answers to the questions of the artificial question-and-answer data satisfies the artificial question-and-answer record data of the first set matching condition, before adding the artificial question-and-answer record data to the intelligent customer service knowledge base, the method may further include: and deleting special characters contained in the manual question and answer record data, or carrying out duplication removal filtering on each manual question and answer record data based on content similarity.
Illustratively, before the manual question and answer recording data a satisfying the first set matching condition is added to the intelligent knowledge base, if it is determined that special characters, such as "&", "ж", or "╗", are contained in the manual question and answer recording data a, the special characters may be deleted; if it is determined that the content similarity between the manual question and answer record data a and the manual question and answer record data B is greater than 98%, 80% or completely similar, the manual question and answer record data a or the manual question and answer record data B can be deleted, and only one piece of manual question and answer record data B is reserved in the intelligent knowledge base.
The method has the advantages that the data capacity stored in the intelligent customer service knowledge base can be reduced, the time for determining the solution is not increased due to the existence of a large amount of redundant data, and the execution efficiency of the algorithm is improved.
In step S33, at least one piece of smart question and answer record data and the question answer matching degree of each piece of smart question and answer record data are obtained from the smart question and answer record table every preset cleaning time.
In step S34, the smart question-and-answer record data in which the degree of matching between the answers to the questions in the smart question-and-answer data satisfies the second set matching condition is deleted from the smart customer service knowledge base.
In step S35, in response to the user question received by the smart customer service, a reference solution matching the user question in the updated smart customer service knowledge base is determined, and the reference solution is fed back to the smart customer service.
The user question received by the intelligent customer service may be any one of questions, for example, when to deliver a product, how to return a product, or how to modify an address, and the like, which is not limited in this embodiment; meanwhile, the received user question may be text information or voice information, which is not limited in this embodiment.
In an optional manner of this embodiment, after the intelligent customer service receives the user problem, a reference solution matching the user problem in the updated intelligent customer service knowledge base may be further determined, and the reference solution is fed back to the intelligent customer service. Illustratively, if the user question received by the smart customer service is when to ship a shipment; the intelligent customer service inquires a reference solution matched with the user problem in an intelligent customer service knowledge base according to the user problem, for example, within three days; and further feeding back the determined solution to the intelligent customer service, so that the intelligent customer service feeds back the solution to the user.
It should be noted that, in this embodiment, the intelligent customer service may determine a plurality of solutions in the intelligent customer service knowledge base at the same time for the received user problem; after determining the plurality of solutions, the intelligent customer service may filter the solutions, for example, the solutions may be filtered according to the matching degree of the answers of the historical questions of the plurality of solutions, and the solution with the highest matching degree of the answers of the historical questions is fed back to the intelligent customer service. The advantage of this arrangement is that the user is assured of the best solution.
In step S36, the smart question-and-answer record data generated from the user question and the reference solution is added to the smart question-and-answer record table.
In a specific implementation, after the intelligent customer service receives the user problem, determines a reference solution matched with the user problem in the updated intelligent customer service knowledge base, and feeds the reference solution back to the intelligent customer service, the intelligent customer service can further generate intelligent question and answer record data according to the user problem and the reference solution, and add the generated intelligent question and answer record data to the intelligent question and answer record table.
It should be noted that the intelligent question-and-answer record table in this embodiment and the manual question-and-answer record table in the above embodiment are recorded in the same table. It is understood that in the present disclosure, either manual or intelligent questioning and answering log data may be obtained in this table.
In the scheme of the embodiment, in response to the user problem received by the intelligent customer service, a reference solution matched with the user problem in the updated intelligent customer service knowledge base is determined, and the reference solution is fed back to the intelligent customer service; the intelligent question-answer record data generated according to the user questions and the reference solution are added into the intelligent question-answer record table, so that the user questions can be solved through intelligent customer service, and a large amount of labor cost is saved.
In order to make those skilled in the art better understand the method for updating the intelligent customer service knowledge base involved in this embodiment, a specific example is used below, and the specific process includes:
1. and adding a knowledge base.
In an alternative implementation manner of this embodiment, a solution collector may be developed, and the service record data of the human customer service is periodically scanned by the solution collector at a relatively high frequency (for example, 1 time per minute), and the problems and solutions with relatively high satisfaction degree are collected in combination with the satisfaction degree evaluation, and then added to the knowledge base in batch, wherein the knowledge base involved in this embodiment is the intelligent customer service knowledge base involved in the above embodiments.
2. And (4) using a knowledge base.
The intelligent customer service acquires the solution from the knowledge base and returns the solution to the user, meanwhile, the point is buried in the satisfaction evaluation position, and when the user evaluates the satisfaction, a satisfaction record is automatically added to the solution.
3. And (5) removing dirty data.
In an alternative implementation of the embodiment, a data cleaner may be developed and periodically go through each solution in the knowledge base by developing the data cleaner, calculating their satisfaction score, and if the score is too low, removing it from the knowledge base.
4. And (5) overall architecture.
FIG. 4 is an overall architecture diagram of an updated intelligent customer service knowledge base, in a particular implementation, in which a user 41 first interacts with a human customer service 42 to generate a question-answer record and a satisfaction rating record, which are stored in a question-answer-rating record table 43;
the data collector 44 runs silently in the background, collects data once in the question-answer-evaluation record table 43 every minute, collects question-answer records with higher satisfaction degrees, preprocesses (removes special characters, judges heavily and the like), and then adds the records into the knowledge base 45;
when the intelligent customer service 46 works, every time a question of the user 41 is received, the intelligent customer service searches a corresponding solution in the knowledge base, then returns the solution to the user 41, and simultaneously generates a question and answer record and a satisfaction evaluation record which are stored in a question and answer-evaluation record table 43; if the reference solution corresponding to the user problem cannot be searched, the user 41 is forwarded to the manual customer service 42, and the problem of the user 41 is solved through the manual customer service 42;
the data cleaner 47 also runs silently in the background, scans the question-answer-evaluation record 43 table once a day, scans solutions obtained through the knowledge base, judges the satisfaction evaluation, and cleans up the solutions from the knowledge base 45 if the satisfaction is low.
In the above example, the user 41 and the artificial customer service 42, and the user 41 and the intelligent customer service 46 can perform a conversation through the message system 40, wherein the message system 40 may be a voice conversation system or a text conversation system, which is not limited in this embodiment.
In the above example, 1. in the related art, retrieval, extraction, writing and addition are completely carried out manually, and the efficiency is very low; 2. as the business scale becomes huge, more and more people are needed to maintain the knowledge base, and the labor cost is high; 3. problems are extracted according to experiences of maintenance personnel, some important problems may be missed, and the knowledge base is incomplete; 4. maintenance personnel add the knowledge base regularly, but sometimes a large number of similar problems are generated instantaneously due to some sudden conditions, so that the knowledge base is not added timely; 5. with the continuous change of the business, some solutions may be out of date, and the solutions cannot be removed in time by manpower, so that the knowledge base is polluted; the method has the advantages that manpower can be saved, maintenance efficiency is improved, the knowledge base is more comprehensively covered, the knowledge base is more timely added, and dirty data can be timely cleaned in the process of updating the knowledge base.
FIG. 5 is a block diagram illustrating an apparatus for updating an intelligent customer service repository, according to an example embodiment. Referring to fig. 5, the apparatus includes an acquisition module 51, an addition module 52, a cleaning module 53, and a deletion module 54.
An obtaining module 51, configured to obtain at least one piece of artificial question and answer record data from an artificial question and answer record table and a question answer matching degree of each piece of artificial question and answer record data at intervals of preset collecting time;
an adding module 52 configured to add the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition into the intelligent customer service knowledge base;
a cleaning module 53 configured to obtain at least one piece of intelligent question and answer record data from an intelligent question and answer record table and a question answer matching degree of each piece of intelligent question and answer record data at intervals of a preset cleaning time;
and a deleting module 54 configured to delete the intelligent question and answer record data of which the question answer matching degree of the intelligent question and answer data meets the second set matching condition from the intelligent customer service knowledge base.
According to the scheme of the embodiment, at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data are obtained from a manual question and answer record table at intervals of preset acquisition time through an obtaining module; adding the artificial question and answer record data of which the question answer matching degree of the artificial question and answer data meets the first set matching condition into an intelligent customer service knowledge base through an adding module; acquiring at least one piece of intelligent question and answer record data and the question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time by a cleaning module; (ii) a The intelligent question-answer recorded data of which the question answer matching degree of the intelligent question-answer data meets the second set matching condition are deleted from the intelligent customer service knowledge base through the deletion module, so that the problems that the data recorded in the intelligent knowledge base in the related technology cannot be added in time and the dirty data in the intelligent knowledge base cannot be deleted in time are solved, and the data can be added in the intelligent knowledge base in time and the dirty data can be deleted; and a comprehensive intelligent knowledge base can be created while labor cost is saved.
Optionally, the adding module is specifically configured to:
performing semantic analysis on the question answer matching degree of the manual question-answer data to obtain a semantic analysis result;
matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree;
and when the reference evaluation level is greater than a first set threshold value, determining that the question answer matching degree of the artificial question and answer data meets a first set matching condition, and adding the corresponding artificial question and answer record data to the intelligent customer service knowledge base.
Optionally, the apparatus further comprises: a deletion module and a deduplication module;
the deleting module is configured to delete the special characters contained in the manual question and answer record data;
the duplication removing module is configured to perform duplication removing filtering on each manual question answering record data based on content similarity.
Optionally, the deleting module is specifically configured to
Counting the question answer matching degree of each intelligent question-answer data, and comparing the question answer matching degree with a second set threshold value;
and deleting the intelligent question-answer record data corresponding to the question answer matching degree which is less than or equal to a second set threshold value from the intelligent customer service knowledge base.
Optionally, the apparatus further comprises: a feedback module configured to
Responding to the user problem received by the intelligent customer service, determining a reference solution matched with the user problem in the updated intelligent customer service knowledge base, and feeding back the reference solution to the intelligent customer service;
and adding intelligent question and answer record data generated according to the user question and the reference solution into the intelligent question and answer record table. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 6 is a block diagram illustrating a structure of an electronic device according to an example embodiment. As shown in fig. 6, the server includes a processor 61; a Memory 62 for storing executable instructions for the processor 61, the Memory 62 may include a Random Access Memory (RAM) and a Read-Only Memory (ROM); wherein the processor 61 is configured to execute the instructions to implement the above-mentioned update method of the intelligent customer service knowledge base.
In an exemplary embodiment, there is also provided a storage medium comprising instructions, such as a memory 62 storing executable instructions, which are executable by a processor 61 of an electronic device (server or smart terminal) to perform the above method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is also provided, and when the instructions in the computer program product are executed by a processor of an electronic device (server or intelligent terminal), the method for updating the intelligent customer service knowledge base is realized.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. An updating method of an intelligent customer service knowledge base is characterized by comprising the following steps:
acquiring at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at each interval of preset acquisition time;
adding the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition into the intelligent customer service knowledge base;
acquiring at least one piece of intelligent question and answer record data and the question answer matching degree of each piece of intelligent question and answer record data from an intelligent question and answer record table at intervals of preset cleaning time;
and deleting the intelligent question-answer record data of which the question answer matching degree of the intelligent question-answer record data meets a second set matching condition from the intelligent customer service knowledge base.
2. The method according to claim 1, wherein the step of adding the manual question and answer record data of which the question answer matching degree of the manual question and answer data meets a first set matching condition to the intelligent customer service knowledge base comprises:
performing semantic analysis on the question answer matching degree of the manual question-answer data to obtain a semantic analysis result;
matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree;
and when the reference evaluation level is greater than a first set threshold value, determining that the question answer matching degree of the artificial question and answer data meets a first set matching condition, and adding the corresponding artificial question and answer record data to the intelligent customer service knowledge base.
3. The method according to claim 1, wherein after determining the manual question and answer record data whose question answer matching degree meets the first set matching condition, before adding to the intelligent customer service knowledge base, the method further comprises performing at least one of the following:
deleting special characters contained in the manual question answering record data;
and performing deduplication filtration on each artificial question answering record data based on content similarity.
4. The method of claim 1, wherein the manual questionnaire and the smart questionnaire are recorded in the same table.
5. The method according to claim 1, wherein the step of deleting the intelligent question and answer record data of which the question answer matching degree meets a second set matching condition from the intelligent customer service knowledge base comprises the following steps:
counting the question answer matching degree of each intelligent question-answer data, and comparing the question answer matching degree with a second set threshold value;
and deleting the intelligent question-answer record data corresponding to the question answer matching degree which is less than or equal to a second set threshold value from the intelligent customer service knowledge base.
6. The method of claim 1, further comprising:
responding to the user problem received by the intelligent customer service, determining a reference solution matched with the user problem in the updated intelligent customer service knowledge base, and feeding back the reference solution to the intelligent customer service;
and adding intelligent question and answer record data generated according to the user question and the reference solution into the intelligent question and answer record table.
7. An update device of an intelligent customer service knowledge base is characterized by comprising:
the acquisition module is configured to acquire at least one piece of manual question and answer record data and the question answer matching degree of each piece of manual question and answer record data from a manual question and answer record table at intervals of preset acquisition time;
the adding module is configured to add the artificial question and answer record data of which the question answer matching degree of the artificial question and answer data meets a first set matching condition into the intelligent customer service knowledge base;
the intelligent question-answer system comprises a cleaning module, a question answer matching module and a question answer matching module, wherein the cleaning module is configured to acquire at least one piece of intelligent question-answer record data and the question answer matching degree of each piece of intelligent question-answer record data from an intelligent question-answer record table at intervals of preset cleaning time;
and the deleting module is configured to delete the intelligent question-answer record data of which the question answer matching degree of the intelligent question-answer data meets a second set matching condition from the intelligent customer service knowledge base.
8. The apparatus of claim 7, wherein the adding module is specifically configured to:
performing semantic analysis on the question answer matching degree of the manual question-answer data to obtain a semantic analysis result;
matching the semantic analysis result with a preset evaluation grade to determine a reference evaluation grade corresponding to the question answer matching degree;
and when the reference evaluation level is greater than a first set threshold value, determining that the question answer matching degree of the artificial question and answer data meets a first set matching condition, and adding the corresponding artificial question and answer record data to the intelligent customer service knowledge base.
9. An electronic device, comprising:
a processor;
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the instructions to implement the method of updating an intelligent customer service knowledge base according to any one of claims 1 to 6.
10. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of updating a smart customer service knowledge base according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010987578.6A CN112148743A (en) | 2020-09-18 | 2020-09-18 | Method, device, equipment and storage medium for updating intelligent customer service knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010987578.6A CN112148743A (en) | 2020-09-18 | 2020-09-18 | Method, device, equipment and storage medium for updating intelligent customer service knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112148743A true CN112148743A (en) | 2020-12-29 |
Family
ID=73892470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010987578.6A Pending CN112148743A (en) | 2020-09-18 | 2020-09-18 | Method, device, equipment and storage medium for updating intelligent customer service knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112148743A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064887A (en) * | 2021-03-22 | 2021-07-02 | 平安银行股份有限公司 | Data management method, device, equipment and storage medium |
| CN113127616A (en) * | 2021-03-25 | 2021-07-16 | 白鹭 | Intelligent conversation recommendation method and device applied to field conversation scene |
| CN113342946A (en) * | 2021-05-19 | 2021-09-03 | 北京百度网讯科技有限公司 | Model training method and device for customer service robot, electronic equipment and medium |
| CN113407695A (en) * | 2021-06-23 | 2021-09-17 | 上海华客信息科技有限公司 | Hotel customer service method, system, electronic equipment and storage medium based on knowledge base |
| CN113743124A (en) * | 2021-08-25 | 2021-12-03 | 南京星云数字技术有限公司 | Intelligent question-answer exception processing method and device and electronic equipment |
| CN115599889A (en) * | 2022-10-31 | 2023-01-13 | 北京力码科技有限公司（Cn） | Online customer service intelligent answering method and system applied to financial insurance platform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
| CN106844686A (en) * | 2017-01-26 | 2017-06-13 | 武汉奇米网络科技有限公司 | Intelligent customer service question and answer robot and its implementation based on SOLR |
| CN107066541A (en) * | 2017-03-13 | 2017-08-18 | 平安科技（深圳）有限公司 | The processing method and system of customer service question and answer data |
| CN108415980A (en) * | 2018-02-09 | 2018-08-17 | 平安科技（深圳）有限公司 | Question and answer data processing method, electronic device and storage medium |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110825860A (en) * | 2019-10-24 | 2020-02-21 | 厦门快商通科技股份有限公司 | Knowledge base question and answer extraction method and system, mobile terminal and storage medium |
| CN111414463A (en) * | 2020-02-26 | 2020-07-14 | 中国平安财产保险股份有限公司 | Knowledge base updating method, device and storage medium |
| CN114372130A (en) * | 2021-12-28 | 2022-04-19 | 海南电网有限责任公司 | Online customer service system based on intelligent voice question answering |
-
2020
- 2020-09-18 CN CN202010987578.6A patent/CN112148743A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
| CN106844686A (en) * | 2017-01-26 | 2017-06-13 | 武汉奇米网络科技有限公司 | Intelligent customer service question and answer robot and its implementation based on SOLR |
| CN107066541A (en) * | 2017-03-13 | 2017-08-18 | 平安科技（深圳）有限公司 | The processing method and system of customer service question and answer data |
| CN108415980A (en) * | 2018-02-09 | 2018-08-17 | 平安科技（深圳）有限公司 | Question and answer data processing method, electronic device and storage medium |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110825860A (en) * | 2019-10-24 | 2020-02-21 | 厦门快商通科技股份有限公司 | Knowledge base question and answer extraction method and system, mobile terminal and storage medium |
| CN111414463A (en) * | 2020-02-26 | 2020-07-14 | 中国平安财产保险股份有限公司 | Knowledge base updating method, device and storage medium |
| CN114372130A (en) * | 2021-12-28 | 2022-04-19 | 海南电网有限责任公司 | Online customer service system based on intelligent voice question answering |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064887A (en) * | 2021-03-22 | 2021-07-02 | 平安银行股份有限公司 | Data management method, device, equipment and storage medium |
| CN113064887B (en) * | 2021-03-22 | 2023-12-08 | 平安银行股份有限公司 | Data management method, device, equipment and storage medium |
| CN113127616A (en) * | 2021-03-25 | 2021-07-16 | 白鹭 | Intelligent conversation recommendation method and device applied to field conversation scene |
| CN113342946A (en) * | 2021-05-19 | 2021-09-03 | 北京百度网讯科技有限公司 | Model training method and device for customer service robot, electronic equipment and medium |
| CN113342946B (en) * | 2021-05-19 | 2022-11-15 | 北京百度网讯科技有限公司 | Model training method and device for customer service robot, electronic equipment and medium |
| CN113407695A (en) * | 2021-06-23 | 2021-09-17 | 上海华客信息科技有限公司 | Hotel customer service method, system, electronic equipment and storage medium based on knowledge base |
| CN113743124A (en) * | 2021-08-25 | 2021-12-03 | 南京星云数字技术有限公司 | Intelligent question-answer exception processing method and device and electronic equipment |
| CN113743124B (en) * | 2021-08-25 | 2024-03-29 | 南京星云数字技术有限公司 | Intelligent question-answering exception processing method and device and electronic equipment |
| CN115599889A (en) * | 2022-10-31 | 2023-01-13 | 北京力码科技有限公司（Cn） | Online customer service intelligent answering method and system applied to financial insurance platform |
| CN115599889B (en) * | 2022-10-31 | 2023-09-22 | 北京力码科技有限公司 | Intelligent answer method and system applied to online customer service of financial insurance platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148743A (en) | Method, device, equipment and storage medium for updating intelligent customer service knowledge base | |
| CN105354196A (en) | Information pushing method and information pushing apparatus | |
| CN107526807A (en) | Information recommendation method and device | |
| CN108345640A (en) | A kind of question and answer building of corpus method based on neural network semantic analysis | |
| CN111666351A (en) | Fuzzy clustering system based on user behavior data | |
| CN106453971B (en) | The acquisition methods and call center's quality inspection system of call center's quality inspection voice | |
| CN107832333B (en) | Method and system for constructing user network data fingerprint based on distributed processing and DPI data | |
| CN112435047A (en) | Marketing outbound data recommendation method based on buried point data | |
| CN112019692A (en) | Telephone traffic record storage method, system and computer readable medium | |
| CN114969303A (en) | Questionnaire investigation method, device, equipment and storage medium | |
| CN113918529A (en) | Questionnaire survey method and device based on small program and storage medium | |
| CN116861063B (en) | Method for exploring commercial value degree of social media hot search | |
| CN116452212B (en) | Intelligent customer service commodity knowledge base information management method and system | |
| CN104484330B (en) | Comment spam pre-selection method and device based on stepping keyword threshold value combined evaluation | |
| KR20020020584A (en) | Internet survey system and method and media for storing program source thereof | |
| CN113393273A (en) | Accurate marketing method | |
| CN109710818B (en) | Answer weight determination method, answer determination device and storage medium | |
| CN109189833B (en) | Knowledge base mining method and device | |
| CN103838765B (en) | Associated person information storage method and device, electronic equipment | |
| CN110580342A (en) | public number question-answer response method and device | |
| CN112148860B (en) | Question recommending method and device for text robot | |
| CN116582702B (en) | Network video play amount prediction method, system and medium based on big data | |
| CN116402396A (en) | Customer service quality inspection management method, customer service quality inspection management device, customer service quality inspection equipment and storage medium | |
| CN113704585A (en) | Focus team member screening method, device, terminal and storage medium | |
| CN117909579A (en) | Recommendation system, recommendation method, recommendation device, electronic equipment and storage medium |
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 |