CN107807960B - Intelligent customer service method, electronic device and computer readable storage medium - Google Patents
Intelligent customer service method, electronic device and computer readable storage medium Download PDFInfo
- Publication number
- CN107807960B CN107807960B CN201710932603.9A CN201710932603A CN107807960B CN 107807960 B CN107807960 B CN 107807960B CN 201710932603 A CN201710932603 A CN 201710932603A CN 107807960 B CN107807960 B CN 107807960B
- Authority
- CN
- China
- Prior art keywords
- standard
- words
- word
- word sequence
- question
- 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.)
- Active
Links
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Abstract
The invention discloses an intelligent customer service method, and belongs to the field of semantic recognition. An intelligent customer service method comprises the following steps: s1, constructing a standard knowledge base; s2, constructing a synonym library; s3, receiving a service session request of a client and creating a client service session with the client; s4, analyzing the content of the customer service session to obtain the analysis result of the user service session; s5, searching a standard problem matched with the analysis result from a standard knowledge base according to the analysis result; s6, positioning the dimension of the answer associated with the standard question, and pushing the answer associated with the standard question in the dimension. According to the invention, the dimensionality is added in the knowledge base, so that one standard question can be associated with a plurality of different standard answers in different dimensionalities, and on the basis, answers meeting the self condition of a client are provided according to the specific region of the client or the used equipment, thereby improving the client experience and reducing the pressure of manual client service.
Description
Technical Field
The invention relates to the field of semantic recognition, in particular to an intelligent customer service method, an electronic device and a computer readable storage medium.
Background
With the rapid development of the internet and the improvement of service consciousness of people, network customer service has been popularized in various industries and goes deep into various links of daily business service.
At present, a common network client generally consists of an intelligent client service robot and an artificial client service, wherein the intelligent client service robot locates the problem of the client through semantic analysis, so that the client talks with the robot like a conversation with a natural person, and the problem in a specific field is solved through various expression forms in a natural interaction process. Compared with the traditional customer service mode, the intelligent customer service can realize all-weather service of day and night and holidays, and the burden of manual customer service is distributed, so that the operation cost in the field of enterprise customer service is effectively reduced.
Although the intelligent customer service robot can quickly respond to the requirements of customers to a certain extent, the thinking of the intelligent customer service robot depends on the knowledge base, the intelligent customer service robot can be more clever only if the knowledge base is perfect and accurate in maintenance, and in order to enable the intelligent customer service robot to give accurate answers according to customer questions, usually, one standard question corresponds to one standard answer during the maintenance of the knowledge base, and one standard question can only be maintained once, so that the intelligent robot is prevented from being unsuitable when the answers are selected.
Therefore, when an existing enterprise formulates an activity or a product, the activity or the product is suitable, the content of the same activity in each region may be different, and for the situation, the knowledge base cannot be maintained, so that the intelligent customer service robot cannot answer the customer problem when facing the situation and only depends on manual customer service.
Disclosure of Invention
The invention provides an intelligent customer service method, an electronic device and a computer readable storage medium, aiming at solving the technical problem that an intelligent customer service robot in the prior art can not provide different answers according with the place where a customer belongs to the same problem.
The invention solves the technical problems through the following technical scheme:
an intelligent customer service method comprises the following steps:
s1, constructing a standard knowledge base, storing a plurality of standard questions, associating corresponding answers of the standard questions on one or more dimensions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
s2, constructing a synonym library, and storing a plurality of word groups formed by associating standard words with similar words of the standard words, wherein the standard words are keywords in the standard problem, and the standard words are associated with the similar words for storage;
s3, receiving a service session request of a client and creating a client service session with the client;
s4, analyzing the content of the customer service session to obtain the analysis result of the user service session;
s5, searching a standard problem matched with the analysis result from the standard knowledge base according to the analysis result;
s6, positioning the dimension of the answer associated with the standard question, and pushing the answer associated with the standard question in the dimension, wherein the dimension is android, IOS and IE, and the answer is the operation flow description associated with each dimension.
Preferably, step S1 specifically includes the following sub-steps:
s11, collecting and sorting the question and at least one answer matched with the question;
s12, generating dimensionality according to the answer;
s13, associating answers corresponding to the dimensions to the questions in one or more dimensions, and generating a standard question-answer set;
s14, splitting the standard problem into a word sequence consisting of a plurality of words through a word segmentation tool;
and S15, removing stop words in the word sequence, generating a word sequence consisting of a plurality of key words, and storing the word sequence in association with the standard question.
Preferably, step S2 specifically includes the following sub-steps:
s21, extracting key words in each standard question in the standard knowledge base;
s22, forming a keyword set by all the keywords and carrying out de-duplication processing to obtain a standard word set;
s23, sequentially extracting the standard words in the standard word set, collecting at least one similar meaning word similar to the meaning of the standard words, and associating the similar meaning word with the standard words to form a word group for storage.
Preferably, step S4 specifically includes the following sub-steps:
s41, segmenting words, and utilizing a word segmentation tool to split the content of the customer service conversation into a word sequence consisting of a plurality of words;
s42, extracting target keywords, and generating a simplified word sequence only consisting of the keywords by removing stop words in the word sequence;
s43, judging whether the keywords in the simplified word sequence belong to standard words in a synonym library, if not, replacing the keywords in the simplified word sequence with the standard words in the synonym library to generate a target word sequence only containing the standard words;
and S44, outputting the target word sequence.
Preferably, the substep S43 specifically comprises the following substeps:
s431, obtaining keywords in the simplified word sequence;
s432, comparing the acquired keywords with standard words in a synonym library one by one;
s433, judging whether the synonym library has a standard word matched with the keyword, if so, executing a step S435, otherwise, executing a step S434;
s434, comparing the keyword with the similar synonyms in the synonym library one by one, finding out the synonym same as the keyword, and replacing the position of the keyword in the simplified word sequence with the standard word associated with the synonym;
s435, judging whether the keyword is the last word in the simplified word sequence, if so, executing a step S436, otherwise, executing a step S431;
and S436, generating a target word sequence only containing the standard words.
Preferably, step S5 specifically includes the following sub-steps:
s51, matching the target word sequence with a standard word sequence in a standard knowledge base, and finding out a standard word sequence matched with the target word sequence;
s52, judging whether the number of answers related to the standard question stored in association with the found word sequence is more than 1, if so, executing the step S6, and if so, skipping the step S6 and directly outputting the answer.
Preferably, step S6 specifically includes the following sub-steps:
s61, judging whether the dimensionality of the answers related to the standard question can be acquired through automatic detection, if so, outputting the dimensionality and executing a step S64, and otherwise, executing a step S62;
s62, pushing questions to the client according to the question-chasing rule to question the dimensionality of the answers;
s63, receiving the answer of the client, extracting dimensions from the answer and outputting the dimensions;
and S64, pushing answers related to the standard questions in the dimension according to the output dimension.
Preferably, the question-chasing rule is specifically:
when the number of answers exceeds 3, open questioning is adopted;
when the number of answers is less than or equal to 3, an enumerated question is asked.
An electronic device comprising a memory and a processor, the memory having stored thereon an intelligent customer service system executable by the processor, the intelligent customer service system comprising:
the standard knowledge base is used for storing a plurality of standard questions, associating corresponding answers on one or more dimensions of the standard questions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
the synonym library is used for storing a plurality of word groups formed by associating standard words with the similar meaning words of the standard words, the standard words are the key words in the standard questions, and the standard words and the similar meaning words are stored in an associated manner;
the session connection module is used for receiving a service session request of a client and creating a client service session with the client;
the session analysis module is used for analyzing the content of the customer service session to obtain an analysis result of the user service session;
the matching module is used for searching out a standard problem matched with the analysis result from the standard knowledge base according to the analysis result;
and the positioning pushing module is used for positioning the dimension of the answer associated with the standard question and pushing the answer associated with the standard question in the dimension, wherein the dimension is three dimensions of android, IOS and IE, and the answer is an operation flow description associated with each dimension.
A computer readable storage medium having stored therein an intelligent customer service system executable by at least one processor to cause the at least one processor to perform the steps of the intelligent customer service method as set forth in any one of the preceding claims.
The positive progress effects of the invention are as follows: according to the invention, the dimensionality is added in the knowledge base, so that one standard question can be associated with a plurality of different standard answers in different dimensionalities, and on the basis, answers meeting the self condition of a client are provided according to the specific region of the client or the used equipment, thereby improving the client experience and reducing the pressure of manual client service.
Drawings
FIG. 1 is a diagram illustrating a hardware architecture of an embodiment of an electronic device according to the invention;
FIG. 2 is a schematic diagram illustrating program modules of an embodiment of an intelligent customer service system in an electronic device according to the present invention;
FIG. 3 illustrates a flow chart of a first embodiment of the intelligent customer service method of the present invention;
FIG. 4 is a flow chart illustrating the construction of a standard knowledge base in a second embodiment of the intelligent customer service method of the present invention;
FIG. 5 is a flow chart showing the construction of a thesaurus in the third embodiment of the intelligent customer service method of the present invention;
FIG. 6 is a flow chart illustrating session analysis in a fourth embodiment of the intelligent customer service method of the present invention;
FIG. 7 is a flow chart showing alternative synonyms in a session analysis in a fifth embodiment of the intelligent customer service method of the present invention;
FIG. 8 is a flow chart illustrating matching in a sixth embodiment of the intelligent customer service method of the present invention;
fig. 9 shows a flowchart of locating and pushing answers in the seventh embodiment of the intelligent customer service method of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
First, the present invention provides an electronic device.
Fig. 1 is a schematic diagram of a hardware architecture of an electronic device according to an embodiment of the invention. In the present embodiment, the electronic device 2 is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction. For example, the server may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster composed of a plurality of servers). As shown, the electronic device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and an intelligent customer service system 20, which are communicatively coupled to each other via a system bus.
Wherein:
the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 21 may be an internal storage unit of the electronic device 2, such as a hard disk or a memory of the electronic device 2. In other embodiments, the memory 21 may also be an external storage device of the electronic apparatus 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the electronic apparatus 2. Of course, the memory 21 may also comprise both an internal memory unit of the electronic apparatus 2 and an external memory device thereof. In this embodiment, the memory 21 is generally used for storing an operating system installed in the electronic device 2 and various types of application software, such as program codes of the intelligent customer service system 20. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is generally configured to control the overall operation of the electronic apparatus 2, such as performing data interaction or communication related control and processing with the electronic apparatus 2. In this embodiment, the processor 22 is configured to run the program codes stored in the memory 21 or process data, for example, run the intelligent customer service system 20.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the electronic device 2 and other electronic devices. For example, the network interface 23 is used to connect the electronic apparatus 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the electronic apparatus 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 1 only shows the electronic device 2 with components 21-23, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
In this embodiment, the intelligent customer service system 20 stored in the memory 21 may be divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 2 shows a schematic diagram of program modules of an embodiment of the intelligent customer service system 20, in which the intelligent customer service system 20 can be divided into a standard knowledge base 201, a synonym base 202, a session connection module 203, a session analysis module 204, a matching module 205, and a location push module 206. The program module referred to in the present invention refers to a series of computer program instruction segments capable of performing specific functions, and is more suitable than a program for describing the execution process of the intelligent customer service system 20 in the electronic device 2. The following description will specifically describe the specific functions of the program module 201 and 206.
The standard knowledge base 201 is used for storing a plurality of standard questions, associating corresponding answers on one or more dimensions of the standard questions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
the synonym library 202 is configured to store a plurality of word groups formed by associating standard words with similar words of the standard words, where the standard words are keywords in the standard question, and the standard words are stored in association with the similar words;
the session connection module 203 is configured to receive a service session request of a client, and create a client service session with the client;
the session analysis module 204 is configured to analyze content of a customer service session to obtain an analysis result of the user service session;
the matching module 205 is configured to find a standard problem matching the analysis result from the standard knowledge base according to the analysis result;
the positioning pushing module 206 is configured to position a dimension in which an answer associated with the standard question is located, and push an answer associated with the standard question in the dimension, where the dimension is three dimensions of android, IOS, and IE, and the answer is an operation flow description associated with each dimension.
The intelligent customer service system 20 in this embodiment can provide answers according to the characteristics of the customer by identifying the region of the customer and the equipment used. The following description will be made in detail by taking an example of how a client using an android phone asks to participate in an activity by self-help handling:
1. establishing a service session with a client through a session connection module and receiving a question of the client;
2. analyzing the problem of the client through a session analysis module, splitting the problem into a word sequence consisting of keywords, replacing the keywords which do not belong to the standard words in the word sequence with the standard words in a synonym library, and finally expressing the problem of the client as the standard word sequence only containing the standard words;
3. through a matching module, finding a standard problem associated with the matched word sequence in the standard knowledge base according to the standard word sequence;
4. through the positioning pushing module, the number of the answers related to the standard problem is judged to be larger than 1, then the android system used by the client is further judged, and finally the self-service handling process related to the dimensionality of the android system is pushed to the client.
In this embodiment, the standard knowledge base and the synonym base are maintained in the system in advance, and may be modified and added according to actual situations.
Secondly, the invention provides an intelligent customer service method.
In a first embodiment, as shown in fig. 3, the intelligent customer service method includes the following steps:
s1, constructing a standard knowledge base, storing a plurality of standard questions, associating corresponding answers of the standard questions on one or more dimensions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
s2, constructing a synonym library, and storing a plurality of word groups formed by associating standard words with similar words of the standard words, wherein the standard words are keywords in the standard problem, and the standard words are associated with the similar words for storage;
s3, receiving a service session request of a client and creating a client service session with the client;
s4, analyzing the content of the customer service session to obtain the analysis result of the user service session;
s5, searching a standard problem matched with the analysis result from the standard knowledge base according to the analysis result;
s6, positioning the dimension of the answer associated with the standard question, and pushing the answer associated with the standard question in the dimension, wherein the dimension is android, IOS and IE, and the answer is the operation flow description associated with each dimension.
It should be noted that the construction standard knowledge base in step S1 and the construction synonym base in step S2 are maintained in the system in advance, and need not be maintained once every time they are used, and they may be maintained only when the content needs to be updated, and the maintenance mode may be manual maintenance, automatic maintenance after the system automatically captures information, or maintenance combining both.
Based on the first embodiment, in the second embodiment, as shown in fig. 4, the step S1 specifically includes the following sub-steps:
s11, collecting and sorting the question and at least one answer matched with the question;
when gathering questions, the questions in multiple questioning modes may all point to the same answer, and at this time, one of the questions needs to be determined as a standard question and stored in the standard knowledge base.
The at least one answer is mainly that problems related to the use flow of some systems have different answers due to different system versions, or the activity contents of the same activity have different differences due to different regions, so that clients in different regions have different answers when inquiring the activity contents.
S12, generating dimensionality according to the answer;
specifically, one answer is generated to correspond to one dimension, such as: the system has three versions, namely android, IOS and IE, and three dimensions of android, IOS and IE are generated.
S13, associating answers corresponding to the dimensions to the questions in one or more dimensions, and generating a standard question-answer set;
following the description of S12, corresponding operation flow descriptions are associated in each dimension, i.e., a standard question-answer set is generated.
S14, splitting the standard problem into a word sequence consisting of a plurality of words through a word segmentation tool;
and S15, removing stop words in the word sequence, generating a standard word sequence consisting of a plurality of key words, and storing the standard word sequence in association with the standard question.
The following takes the "old with new" activity (i.e. the old client introduces the new client to participate in the activity) as an example for specific description:
two standard questions are involved-answer sets:
the standard problem one: what are the old activity gifts with new activities?
And (3) answer: 1) area A: presenting a 500 yuan shopping card; 2) and (B) area: giving 300 yuan of telephone charge.
The second standard problem: is old with new activities self-service process?
And (3) answer: 1) an android system: click the bottom right corner activity of this page-select old bring new … …; 2) the IOS system: click the bottom right corner activity of this page-select old bring new … …; 3) IE system: click on the activity in the menu at the top of the page-select old tape new-click … ….
Aiming at the first standard problem, the maintenance process in the standard knowledge base is as follows:
1. collecting and sorting standard questions-answer sets, namely standard questions: what are the old activity gifts with new activities? And (3) answer: 1) area A: presenting a 500 yuan shopping card; 2) and (B) area: giving 300 yuan of telephone charge.
2. Two dimensions are generated according to the answers, namely an area A and an area B.
3. The answer "present 500 yuan purchase card" is related to the dimension of area a, and the answer "present 300 yuan telephone charge" is related to the dimension of area B.
4. The standard question one is split into "what the old activity gift with the new activity is".
5. The generated word sequence 'what is a new gift old' is stored in association with the standard question one.
For the second standard problem, the maintenance process in the standard knowledge base is the same as the first standard problem, and details are not repeated here.
Based on the second embodiment, in a third embodiment, as shown in fig. 5, the step S2 specifically includes the following sub-steps:
s21, extracting key words in each standard question in the standard knowledge base;
s22, forming a keyword set by all the keywords and carrying out de-duplication processing to obtain a standard word set;
s23, sequentially extracting the standard words in the standard word set, collecting at least one similar meaning word similar to the meaning of the standard words, and associating the similar meaning word with the standard words to form a word group for storage.
In this embodiment, the keywords in the standard problem are determined as the standard words, and then each standard word is associated with a plurality of similar meaning words, so that when the customer uses the words according to their habits, the system can replace the non-standard words with the standard words, and thus when the customer problem is matched with the standard problem, a better matching effect can be achieved, and the matching accuracy is improved.
In the above example, the maintenance process of the thesaurus is as follows:
1. extract standard questions-what are the old active gifts with new activities? "the key word in" what old and new gifts are; extract standard question two "old self-service process with new activities? The ' middle key word ' old with new self-help handling flow '.
2. The keyword of 'old with new' is deduplicated to obtain a standard word set 'what self-service handling process of the old with new gift'.
3. Firstly, collecting new similar meaning words of old customers, such as 'the old customers introduce new customers', 'the old customers bring new customers' and the like, and storing the new similar meaning words of 'the old customers introduce new customers', 'the old customers bring new customers' and the like as old new word groups in a related manner; the composition of other keyword word groups is the same as that of the old new word group.
Based on the third embodiment, in the fourth embodiment, as shown in fig. 6, step S4 specifically includes the following sub-steps:
s41, segmenting words, and utilizing a word segmentation tool to split the content of the customer service conversation into a word sequence consisting of a plurality of words;
s42, extracting target keywords, and generating a simplified word sequence only consisting of the keywords by removing stop words in the word sequence;
s43, judging whether the keywords in the simplified word sequence belong to standard words in a synonym library, if not, replacing the keywords in the simplified word sequence with the standard words in the synonym library to generate a target word sequence only containing the standard words;
and S44, outputting the target word sequence.
Taking the example above, suppose there is a customer incoming line asking for new activities in old zone, the question is "ask me to introduce me friend into new activities in old zone, what gift i can get? "this is taken as an example to specifically explain the flow of session analysis:
1. the question of the client "ask me to introduce me friend to take part in the new activities of old belt, what prize me can get? The word sequence is split into a word sequence of asking me to introduce what gifts can be obtained by me friends participating in old and new activities.
2. The keyword 'old with new prize' in the word sequence is extracted.
3. And replacing the prizes in the simplified word sequence with gifts to generate a standard word sequence of 'what gifts are new and old'.
4. And outputting a standard word sequence of 'what gift is new with old'.
Based on the fourth embodiment, in the fifth embodiment, as shown in fig. 7, the substep S43 specifically includes the following substeps:
s431, obtaining keywords in the simplified word sequence;
s432, comparing the acquired keywords with standard words in a synonym library one by one;
s433, judging whether the synonym library has a standard word matched with the keyword, if so, executing a step S435, otherwise, executing a step S434;
s434, comparing the keyword with the similar synonyms in the synonym library one by one, finding out the synonym same as the keyword, and replacing the position of the keyword in the simplified word sequence with the standard word associated with the synonym;
s435, judging whether the keyword is the last word in the simplified word sequence, if so, executing a step S436, otherwise, executing a step S431;
and S436, generating a target word sequence only containing the standard words.
In the following example, the replacement process is specifically described by taking the synonym for replacing the simplified word sequence "what new prize is given for the old" as an example:
1. acquiring a first keyword 'old with new' in a simplified word sequence 'old with new' and 'what prize';
2. comparing the keyword 'old with new' with the standard words in the synonym library to find the same word 'old with new';
3. judging that the keyword 'old with new' is not the last word in the simplified word sequence 'old with new prize';
4. acquiring a second keyword 'what' in a simplified word sequence 'old with new prize';
5. comparing the keyword 'what' with the standard words in the synonym library to find the same word 'what';
6. judging whether the keyword 'what' is not the last word in the simplified word sequence 'old with new prize';
7. acquiring a third keyword ' prize ' in a simplified word sequence ' what new prize ' is brought by old words ';
8. comparing the keyword 'prize' with the standard words in the synonym library, and finding out the same words;
9. comparing the keyword 'prize' with the similar words in the synonym library to find the same word 'prize', and replacing the keyword 'prize' in the simplified word sequence with the standard word 'gift' associated with the word 'prize';
10. judging that the keyword ' prize ' is the last word in the simplified word sequence ' which prize is new after the old word;
11. the standard word sequence "what gift is new with old" is generated.
Based on the fifth embodiment, in the sixth embodiment, as shown in fig. 8, step S5 specifically includes the following sub-steps:
s51, matching the target word sequence with a standard word sequence in a standard knowledge base, and finding out a standard word sequence matched with the target word sequence;
s52, judging whether the number of answers related to the standard question stored in association with the found standard word sequence is more than 1, if so, executing the step S6, and if so, skipping the step S6 and directly outputting the answer.
In the previous example, the standard word sequence 'which gift is new in the old' is matched with the word sequence in the standard knowledge base;
1. the standard word sequence 'what new gift is brought old' is matched with the word sequence 'what new gift is brought old' in the standard knowledge base;
2. the word sequence "what the old new gift was" in the standard knowledge base "has the associated standard problem of" what the old new active gift was? ", it is determined that the standard question corresponds to two answers.
Based on the sixth embodiment, in the seventh embodiment, as shown in fig. 9, step S6 specifically includes the following sub-steps:
s61, judging whether the dimensionality of the answers related to the standard question can be acquired through automatic detection, if so, outputting the dimensionality and executing a step S64, and otherwise, executing a step S62;
s62, pushing questions to the client according to the question-chasing rule to question the dimensionality of the answers;
s63, receiving the answer of the client, extracting dimensions from the answer and outputting the dimensions;
and S64, pushing answers related to the standard questions in the dimension according to the output dimension.
Taking the example above, to push the standard question "what are the active gifts for old and new activities" to the customer in area a? "the answer is an example to specifically explain the process of answer positioning and pushing:
1. the dimensions of the standard problem are area A and area B, which cannot be automatically obtained by the system;
2. asking the customer about where he belongs, and since the number of answers is 2, an enumerated question can be used, such as asking the customer about "ask you about whether you are in area a or area B? "
3. Receiving a client answer 'I live in area A', extracting and outputting a keyword 'area A' in the client answer;
4. push standard question to client "what is an active gift of old and new activities? "answer in dimension of area a, i.e. push answer" give away 500-yuan purchase card ".
It should be noted that, in this embodiment, in order to make the answer of the client match the keyword in the standard answer as much as possible, the following question-following rule may be adopted: when the number of answers exceeds 3, open questioning is adopted; when the number of answers is less than or equal to 3, an enumerated question is asked. Since the number of answers corresponding to the standard question in the above example is only 2, it is recommended to use an enumerated question.
Furthermore, the present invention relates to a computer-readable storage medium, in which an intelligent customer service system 20 is stored, and when the intelligent customer service system 20 is executed by one or more processors, the operations of the intelligent customer service method or the electronic device are implemented.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (7)
1. An intelligent customer service method is characterized by comprising the following steps:
s1, constructing a standard knowledge base, storing a plurality of standard questions, associating corresponding answers of the standard questions on one or more dimensions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
s2, constructing a synonym library, and storing a plurality of word groups formed by associating standard words with similar words of the standard words, wherein the standard words are keywords in the standard problem, and the standard words are associated with the similar words for storage;
s3, receiving a service session request of a client and creating a client service session with the client;
s4, analyzing the content of the customer service session to obtain the analysis result of the customer service session; the method specifically comprises the following steps:
s41, segmenting words, and utilizing a word segmentation tool to split the content of the customer service conversation into a word sequence consisting of a plurality of words;
s42, extracting target keywords, and generating a simplified word sequence only consisting of the keywords by removing stop words in the word sequence;
s43, judging whether the keywords in the simplified word sequence belong to standard words in a synonym library, if not, generating a target word sequence only containing the standard words in the synonym library;
s44, outputting the target word sequence;
s5, searching a standard problem matched with the analysis result from the standard knowledge base according to the analysis result; the method specifically comprises the following steps:
s51, matching the target sequence with a standard word sequence in a standard knowledge base, and finding out a standard word sequence matched with the target word sequence;
s52, judging whether the number of answers associated with the standard questions stored in association with the found word sequences is more than 1, if so, executing a step S6, and if so, skipping the step S6 and directly outputting the answers;
s6, positioning the dimension of the answer associated with the standard question, and pushing the answer associated with the standard question in the dimension, wherein the dimension is three dimensions of android, IOS and IE, and the answer is the operation flow description associated with each dimension; step S6 specifically includes the following substeps:
s61, judging whether the dimensionality of the answers related to the standard question can be acquired through automatic detection, if so, outputting the dimensionality and executing a step S64, and otherwise, executing a step S62;
s62, pushing questions to the client according to the question-chasing rule to question the dimensionality of the answers;
s63, receiving the answer of the client, extracting dimensions from the answer and outputting the dimensions;
and S64, pushing answers related to the standard questions in the dimension according to the output dimension.
2. The intelligent customer service method according to claim 1, wherein step S1 specifically comprises the following substeps:
s11, collecting and sorting the question and at least one answer matched with the question;
s12, generating dimensionality according to the answer;
s13, associating answers corresponding to the dimensions to the questions in one or more dimensions, and generating a standard question-answer set;
s14, splitting the standard problem into a word sequence consisting of a plurality of words through a word segmentation tool;
and S15, removing stop words in the word sequence, generating a standard word sequence consisting of a plurality of key words, and storing the standard word sequence in association with the standard question.
3. The intelligent customer service method according to claim 1, wherein step S2 specifically comprises the following substeps:
s21, extracting key words in each standard question in the standard knowledge base;
s22, forming a keyword set by all the keywords and carrying out de-duplication processing to obtain a standard word set;
s23, sequentially extracting the standard words in the standard word set, collecting at least one similar meaning word similar to the meaning of the standard words, and associating the similar meaning word with the standard words to form a word group for storage.
4. The intelligent customer service method according to claim 1, wherein the substep S43 specifically comprises the following substeps:
s431, obtaining keywords in the simplified word sequence;
s432, comparing the acquired keywords with standard words in a synonym library one by one;
s433, judging whether the synonym library has a standard word matched with the keyword, if so, executing a step S435, otherwise, executing a step S434;
s434, comparing the keyword with the similar synonyms in the synonym library one by one, finding out the synonym same as the keyword, and replacing the position of the keyword in the simplified word sequence with the standard word associated with the synonym;
s435, judging whether the keyword is the last word in the simplified word sequence, if so, executing a step S436, otherwise, executing a step S431;
and S436, generating a target word sequence only containing the standard words.
5. The intelligent customer service method according to claim 1, wherein the question-chasing rules are specifically:
when the number of answers exceeds 3, open questioning is adopted;
when the number of answers is less than or equal to 3, an enumerated question is asked.
6. An electronic device comprising a memory and a processor, wherein the memory has stored thereon an intelligent customer service system executable by the processor, the intelligent customer service system comprising:
the standard knowledge base is used for storing a plurality of standard questions, associating corresponding answers on one or more dimensions of the standard questions to form a standard question-answer set, and splitting the standard questions into standard word sequences consisting of a plurality of key words and storing the standard word sequences in association with the standard questions;
the synonym library is used for storing a plurality of word groups formed by associating standard words with the similar meaning words of the standard words, the standard words are the key words in the standard questions, and the standard words and the similar meaning words are stored in an associated manner;
the session connection module is used for receiving a service session request of a client and creating a client service session with the client;
the session analysis module is used for analyzing the content of the customer service session to obtain an analysis result of the customer service session; the session analysis process comprises:
segmenting words, namely segmenting the content of the customer service conversation into a word sequence consisting of a plurality of words by utilizing a word segmentation tool; extracting target keywords, and generating a simplified word sequence only consisting of the keywords by removing stop words in the word sequence; judging whether the keywords in the simplified word sequence belong to standard words in a synonym library, if not, replacing the keywords in the simplified word sequence with the standard words in the synonym library to generate a target word sequence only containing the standard words; outputting the target word sequence;
the matching module is used for searching out a standard problem matched with the analysis result from the standard knowledge base according to the analysis result; the matching process comprises: matching the target word sequence with a standard word sequence in a standard knowledge base to find out a standard word sequence matched with the target word sequence;
the positioning and pushing module is used for positioning the dimension of the answer associated with the standard question and pushing the answer associated with the standard question in the dimension, wherein the dimension is three dimensions of android, IOS and IE, and the answer is an operation flow description associated with each dimension; the process of locating the dimension of the answer associated with the standard question comprises the following steps: judging whether the dimensionality of the answers associated with the standard questions can be obtained through automatic detection, if so, outputting the dimensionality and pushing the answers associated with the standard questions in the dimensionality according to the output dimensionality, and if not, pushing the questions to the client according to a question-chasing rule so as to question the dimensionality of the answers; receiving the answer of the client, extracting dimensions from the answer and outputting the dimensions; and then according to the output dimension, pushing the answer associated with the standard question in the dimension.
7. A computer-readable storage medium, having stored thereon an intelligent customer service system, the intelligent customer service system being executable by at least one processor to cause the at least one processor to perform the steps of the intelligent customer service method according to any one of claims 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710932603.9A CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
| PCT/CN2018/083081 WO2019062078A1 (en) | 2017-09-30 | 2018-04-13 | Smart customer service method, electronic apparatus and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710932603.9A CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107807960A CN107807960A (en) | 2018-03-16 |
| CN107807960B true CN107807960B (en) | 2020-05-12 |
Family
ID=61584874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710932603.9A Active CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107807960B (en) |
| WO (1) | WO2019062078A1 (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107807960B (en) * | 2017-09-30 | 2020-05-12 | 平安科技（深圳）有限公司 | Intelligent customer service method, electronic device and computer readable storage medium |
| CN108197963A (en) * | 2018-03-28 | 2018-06-22 | 广州市菲玛尔咨询服务有限公司 | A kind of intelligent customer service manages system |
| CN110399469B (en) * | 2018-04-23 | 2022-02-15 | 中国电信股份有限公司 | Customer service robot understanding performance detection fusion method and device |
| CN108984777B (en) * | 2018-07-25 | 2021-04-30 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer-readable storage medium |
| CN109685628A (en) * | 2018-12-27 | 2019-04-26 | 北京百佑科技有限公司 | Information sharing apparatus and system |
| CN109684461A (en) * | 2018-12-30 | 2019-04-26 | 联想(北京)有限公司 | A kind of data processing method and device |
| CN110472024A (en) * | 2019-07-11 | 2019-11-19 | 北京云迹科技有限公司 | For the configuration of the customized question and answer of robot, processing method and device, robot |
| CN111078832A (en) * | 2019-11-08 | 2020-04-28 | 杭州九阳小家电有限公司 | Auxiliary response method and system for intelligent customer service |
| CN111159372A (en) * | 2019-12-24 | 2020-05-15 | 合肥凌极西雅电子科技有限公司 | Question-answering system applied to pragmatic education |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130073277A1 (en) * | 2011-09-21 | 2013-03-21 | Pket Llc | Methods and systems for compiling communication fragments and creating effective communication |
| CN104933204A (en) * | 2015-07-15 | 2015-09-23 | 武汉杰宇天成文化咨询服务有限公司 | Intelligent network response method and device |
| CN105117387B (en) * | 2015-09-21 | 2018-06-12 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent robot interactive system |
| CN105893465B (en) * | 2016-03-28 | 2019-12-27 | 北京京东尚科信息技术有限公司 | Automatic question answering method and device |
| CN109753560B (en) * | 2016-11-04 | 2020-08-07 | 上海智臻智能网络科技股份有限公司 | Information processing method and device of intelligent question-answering system |
| CN107807960B (en) * | 2017-09-30 | 2020-05-12 | 平安科技（深圳）有限公司 | Intelligent customer service method, electronic device and computer readable storage medium |
-
2017
- 2017-09-30 CN CN201710932603.9A patent/CN107807960B/en active Active
-
2018
- 2018-04-13 WO PCT/CN2018/083081 patent/WO2019062078A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107807960A (en) | 2018-03-16 |
| WO2019062078A1 (en) | 2019-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807960B (en) | Intelligent customer service method, electronic device and computer readable storage medium | |
| CN110502608B (en) | Man-machine conversation method and man-machine conversation device based on knowledge graph | |
| US10777207B2 (en) | Method and apparatus for verifying information | |
| WO2019062001A1 (en) | Intelligent robotic customer service method, electronic device and computer readable storage medium | |
| CN107832291B (en) | Man-machine cooperation customer service method, electronic device and storage medium | |
| WO2019062010A1 (en) | Semantic recognition method, electronic device and computer readable storage medium | |
| CN108388558B (en) | Question matching method and device, customer service robot and storage medium | |
| CN107864301B (en) | Client label management method, system, computer equipment and storage medium | |
| EP3540612A1 (en) | Cluster processing method and device for questions in automatic question and answering system | |
| WO2019062012A1 (en) | Question association push method, electronic device and computer readable storage medium | |
| CN106294505B (en) | Answer feedback method and device | |
| CN111353014B (en) | Position keyword extraction and position demand updating method and device | |
| CN109766422A (en) | Information processing method, apparatus and system, storage medium, terminal | |
| CN113127621A (en) | Dialogue module pushing method, device, equipment and storage medium | |
| CN110990541A (en) | Method and device for realizing question answering | |
| CN109165286A (en) | Automatic question-answering method, device and computer readable storage medium | |
| US11361032B2 (en) | Computer driven question identification and understanding within a commercial tender document for automated bid processing for rapid bid submission and win rate enhancement | |
| WO2019080419A1 (en) | Method for building standard knowledge base, electronic device, and storage medium | |
| CN112765450A (en) | Recommended content determining method, recommended content determining device and storage medium | |
| CN110390083A (en) | Method for pushing, device, computer equipment and the storage medium of approximate case | |
| CN110062112A (en) | Data processing method, device, equipment and computer readable storage medium | |
| EP3962073A1 (en) | Online interview method and system | |
| CN113254624A (en) | Intelligent question-answering processing method, device, equipment and medium based on artificial intelligence | |
| CN110851517A (en) | Source data extraction method, device and equipment and computer storage medium | |
| CN113722432B (en) | Method and device for associating news with stocks |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |