WO2019080420A1

WO2019080420A1 - Method for customer service of human-robot collaboration, electronic device, and storage medium

Info

Publication number: WO2019080420A1
Application number: PCT/CN2018/076507
Authority: WO
Inventors: 卢川; 高祎璠
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-10-26
Filing date: 2018-02-12
Publication date: 2019-05-02
Also published as: CN107832291B; CN107832291A

Abstract

A method for customer service of human-robot collaboration, relating to the technical field of intelligent customer service. The method for customer service of human-robot collaboration comprises the following steps: S1, building a standard knowledge base; S2, building a thesaurus; S3, obtaining and analyzing a question of a customer, and dividing the question of the customer into standard word sequences only comprising standard words; S4, matching the standard word sequences with word sequences in the standard knowledge base, and calculating, for each word sequence in the standard knowledge base, a corresponding matching value; S5, pushing an answer corresponding to a standard question associated with the word sequence having the highest matching value and displaying the answer in a dialog box of manual customer service; and S6, pushing a correct answer to the customer after the manual customer service makes a determination on the pushed content. After a customer selects the manual customer service, the intelligent customer service does not directly end the customer service, but helps the manual customer service to obtain the matched answer, and displays the answer in the dialog box of the manual customer service, so as to reduce the time consumed by the manual customer service in answer query and typing.

Description

Human-machine cooperation customer service method, electronic device and storage medium

This application claims the priority of the Chinese patent application filed on October 26, 2017, with the application number of 201711030638.X, entitled "Human-machine collaboration customer service method, electronic device and storage medium", the overall content of the Chinese patent application It is incorporated herein by reference.

Technical field

The application relates to the field of intelligent customer service technology, and relates to a human-machine cooperation customer service method, an electronic device and a storage medium.

Background technique

At present, common network customers are usually composed of intelligent customer service and manual customer service. Smart customer service can provide round-the-clock and day-to-day service, but it can't accurately understand customer's problems like manual customer service and give flexible answers. Manual customer service can accurately understand the customer's problem, but the answer query speed is slow, especially when manual customer service is required to manually input the answer to the dialog box.

Summary of the invention

The purpose of the application is to provide a human-machine cooperation customer service method, an electronic device and a storage medium. After switching to a manual customer service, the intelligent customer service changes the service object from the customer to the customer service personnel to help the customer service personnel provide possible answers.

The present application solves the above technical problems by the following technical solutions:

A human-machine collaborative customer service method includes the following steps: S1, constructing a standard knowledge base, storing a number of standard question-answer pairs for intelligent question and answer, and splitting the standard question into a sequence of words composed of several keywords. The standard problem is associated with saving; S2, constructing a thesaurus, storing a plurality of word groups consisting of standard words associated with the standard words, the standard words corresponding to keywords in the standard question; S3, obtaining the customer's problem and Perform analysis to split the customer's problem into a standard word sequence containing only standard words; S4, matching the standard word sequence with the word sequence in the standard knowledge base, and calculating corresponding to each word sequence in the standard knowledge base Corresponding matching value; S5, the answer corresponding to the standard question associated with the word sequence with the highest push matching value is displayed in the dialog box of the manual customer service; S6, the manual customer service judges the pushed content and pushes the correct answer to the customer.

An electronic device includes a memory and a processor, wherein the memory stores a human-machine cooperation customer system that can be executed by the processor, and the human-machine collaborative customer service system includes: a standard knowledge base for storing A number of standard question-answer pairs for intelligent question and answer, and splitting the standard question into a sequence of words consisting of several keywords associated with the standard question; a thesaurus for storing a number of standard words associated with the standard word a group of words composed of synonyms, the standard words correspond to keywords in a standard question; a session acquisition analysis module is used to acquire and analyze a customer's problem, and split the customer's question into standard words containing only standard words. a sequence matching method for matching a standard word sequence with a word sequence in a standard knowledge base, and calculating a corresponding matching value corresponding to each word sequence in the standard knowledge base; an automatic pushing module for pushing the matching value The answer to the standard question associated with the highest word sequence is displayed in the dialog box of the manual customer service; the manual push module is used for the manual guest. The service judges the content of the push and pushes the correct answer to the customer.

A computer readable storage medium storing a human-machine collaborative customer service system, the human-machine cooperative customer service system being executable by at least one processor to perform the following steps: S1, building a standard The knowledge base stores a number of standard question-answer pairs for intelligent question and answer, and splits the standard question into a sequence of words consisting of several keywords associated with the standard question; S2, builds a synonym database, and stores a number of standards. a word group consisting of a synonym of the standard word, the standard word corresponding to a keyword in a standard question; S3, obtaining a customer's problem and analyzing, and splitting the customer's question into a standard containing only standard words a sequence of words; S4, matching the sequence of standard words with the sequence of words in the standard knowledge base, and calculating corresponding matching values for each word sequence in the standard knowledge base; S5, pushing the standard of the word sequence with the highest matching value The answer corresponding to the question is displayed in the dialog box of the manual customer service; S6, the manual customer service judges the content of the push and pushes the correct answer to client.

The positive progress of the application is that: in the application, the intelligent customer service will help the manual customer service to match the answers after the customer selects the manual customer service, and display the answer in the manual customer service dialog box, thereby reducing the manual customer service query answer and typing. Time to improve service efficiency.

DRAWINGS

1 is a schematic diagram showing the hardware architecture of an embodiment of an electronic device of the present application;

2 is a schematic diagram showing a program module of an embodiment of a customer service system for human-machine cooperation in an electronic device of the present application;

3 is a flow chart showing a first embodiment of the customer service method of the applicant machine cooperation;

4 is a flow chart showing a second embodiment of the customer service cooperation method of the applicant machine;

FIG. 5 is a flow chart showing a second embodiment of the customer service method of the applicant machine cooperation;

6 is a flow chart showing a third embodiment of the customer service method of the applicant machine cooperation;

7 is a flow chart showing a fourth embodiment of the customer service method of the applicant machine cooperation;

8 is a flow chart showing a fifth embodiment of the customer service method of the applicant machine cooperation;

FIG. 9 is a flow chart showing a sixth embodiment of the customer service method of the applicant machine cooperation.

Detailed ways

The present application is further illustrated by the following examples, but is not intended to limit the scope of the embodiments.

First of all, the present application proposes an electronic device.

1 is a schematic diagram of a hardware architecture of an embodiment of an electronic device of the present application. In the embodiment, the electronic device 1 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance. For example, it can be a smartphone, a tablet, a laptop, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster composed of multiple servers). As shown, the electronic device 2 includes at least, but not limited to, a memory 21, a processor 22, a network interface 23, and a human-machine cooperative customer service system 20 that can communicate with each other via a system bus. among them:

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 (eg, SD or DX memory, etc.), a random access memory (RAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, and the like. In some embodiments, the memory 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 device 2, such as a plug-in hard disk equipped on the electronic device 2, a smart memory card (SMC), and a secure digital device. (Secure Digital, SD) card, flash card, etc. Of course, the memory 21 can also include both the internal storage unit of the electronic device 2 and its external storage device. In this embodiment, the memory 21 is generally used to store an operating system installed in the electronic device 2 and various application software, such as program code of the customer service system 20 of the human-machine cooperation. Further, the memory 21 can 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 typically used to control the overall operation of the electronic device 2, such as performing control and processing associated with data interaction or communication with the electronic device 2. In this embodiment, the processor 22 is configured to run program code or processing data stored in the memory 21, such as the customer service system 20 that runs the human-machine cooperation.

The network interface 23 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 2 and other electronic devices. For example, the network interface 23 is configured to connect the electronic device 2 to an external terminal through a network, establish a data transmission channel, a communication connection, and the like between the electronic device 2 and an external terminal. The network may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, or a 5G network. Wireless or wired networks such as network, Bluetooth, Wi-Fi, etc.

It is pointed out that FIG. 1 only shows the electronic device 2 with the components 21-23, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.

In this embodiment, the human-machine cooperative 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 may be Or multiple processors (this embodiment is processor 22) are executed to complete the application.

For example, FIG. 2 is a schematic diagram of a program module of an embodiment of the human-machine cooperation customer service system 20. In this embodiment, the human-machine cooperation customer service system 20 can be divided into a standard knowledge base 201 and a thesaurus 202. The session acquisition analysis module 203, the answer matching module 204, the automatic push module 205, and the manual push module 206. The following description will specifically describe the specific functions of the program modules 201-206.

The standard knowledge base 201 is configured to store a number of standard question-answer pairs for intelligent question and answer, and split the standard question into a sequence of words consisting of several keywords associated with the standard question; the thesaurus 202 is used to store a number of a word group consisting of a standard word associated with a synonym of the standard word, the standard word corresponding to a keyword in a standard question; the session acquisition analysis module 203 is configured to acquire a customer's problem and analyze the problem, and split the customer's question into A standard word sequence containing only standard words; the answer matching module 204 is configured to match the standard word sequence with the word sequence in the standard knowledge base, and calculate a corresponding matching value corresponding to each word sequence in the standard knowledge base; The answer corresponding to the standard question of the push module 205 for pushing the word sequence associated with the highest matching value is displayed in the dialog box of the manual customer service; the manual pushing module 206 is used to push the correct answer after the artificial customer service judges the pushed content. client.

In this embodiment, the human-machine cooperative customer service system 20 can continue to obtain the customer problem after the customer selects the manual customer service, analyze the query, and then send the answer to the manual customer service to save the time for the manual customer service to query the answer.

Secondly, the present application proposes a customer service method for human-machine collaboration.

In the first embodiment, as shown in FIG. 3, the human-machine cooperation customer service method includes the following steps:

S1. Build a standard knowledge base, store a number of standard question-answer pairs for intelligent question and answer, and split the standard question into a sequence of words consisting of several keywords to be associated with the standard question;

S2, constructing a synonym database, storing a plurality of word groups consisting of standard words associated with the standard words, the standard words corresponding to keywords in the standard question;

S3. Obtain the customer's problem and analyze it, and split the customer's problem into a standard word sequence containing only standard words;

S4, matching the standard word sequence with the word sequence in the standard knowledge base, and calculating corresponding matching values corresponding to each word sequence in the standard knowledge base;

S5. The answer corresponding to the standard question associated with the word sequence with the highest push matching value is displayed in the dialog box of the manual customer service;

S6. The manual customer service judges the pushed content and pushes the correct answer to the customer.

It should be noted that the build standard knowledge base in step S1 and the build synonym database in step S2 are pre-maintained in the system, and need not be maintained once every time, as long as the content needs to be updated, the maintenance mode can be maintained. It is manual maintenance, automatic maintenance after the system automatically captures information, or a combination of the two. In step S6, the answer of the manual customer service for the smart customer service push can be modified in the dialog box, and then the correct answer is sent to the client.

Based on the foregoing first embodiment, in the second embodiment, as shown in FIG. 4, the step S1 specifically includes the following sub-steps:

S11. Collect and organize the questions and the answers that match the questions, construct a standard question-answer pair and save;

S12. Splitting the standard question into a sequence of words consisting of several words through a word segmentation tool;

S13. The stop words in the word sequence are removed, and a sequence of words composed of a plurality of keywords is generated and stored in association with the standard question.

The following is a detailed description of the construction process of the standard knowledge base by taking the maintenance of the credit card as an example:

Assumption: Standard Question 1: How to apply for a credit card? Standard question 2: What should I do if my credit card auto repayment debit card balance is insufficient? Standard question 3: How to handle credit card loss reporting?

1. Find the corresponding answer for each of the three standard questions, and construct the answer and the three standard questions into standard question-answer pairs and save them in the standard knowledge base. 2. Split the three standard questions into word sequences, respectively: “How to apply for a credit card”, “How to do if the credit card automatic repayment debit card balance is insufficient” and “How to handle credit card loss reporting”. 3. Remove the stop words in the word sequence, and generate 3 sets of word sequences consisting of several keywords: “Apply for credit card”, “Insufficient credit card automatic repayment balance” and “Handling credit card loss”, respectively. Associated with the corresponding standard question is stored in the standard knowledge base.

Based on the foregoing second embodiment, in the third embodiment, as shown in FIG. 5, the step S2 specifically includes the following sub-steps:

S21. Extract keywords in each standard question in the standard knowledge base;

S22. Combine all keywords into a keyword set and perform deduplication processing to obtain a standard word set.

S23. Extract standard words in the standard word set in turn, collect at least one synonym similar to the standard word, and associate the synonyms with the standard words into a word group for preservation.

In this embodiment, the keywords in the standard question are determined as standard words, and then each standard word is associated with a number of synonyms, so that when the customer uses the words according to their respective habits, the system can replace the non-standard words with standard words to optimize the matching effect. Improve the correct rate of matching.

In the following example, the maintenance process of the thesaurus is as follows: 1. Extract the keywords “Apply for Credit Card”, “Insufficient Credit Card Auto Repayment Balance” and “Handle Credit Card Loss” in the three standard questions. 2. The keyword “credit card” is de-emphasized, and the standard word set “Apply for credit card automatic repayment balance is insufficient to report the loss”. 3. First find the synonym of “application”, which can be “sponsorship”, “request” or “handling”, etc., and save these words in association with the standard word “application” as the application group; the composition of other keyword groups is the same. The composition of the application group.

Based on the third embodiment described above, in the fourth embodiment, as shown in FIG. 6, step S3 specifically includes the following sub-steps:

S31. Obtaining a customer's problem;

S32, word segmentation, using the word segmentation tool to split the customer's problem into a sequence of words composed of several words;

S33. Extract a keyword, and generate a simplified word sequence composed only of keywords by removing the stop word in the word sequence;

S34, replacing the synonym, determining whether the keyword in the simplified word sequence belongs to the standard word in the synonym database, and if not, replacing the keyword with the standard word in the synonym database, and generating a standard word sequence containing only the standard word;

S35. Output a standard word sequence.

In the example above, suppose a customer enters the line to ask about the old activity. The question is “What should I do if there is not enough money in the credit card automatic repayment debit card?” The process of the session analysis is as follows: 1. Obtain the customer’s question “Credit card automatically What if the money in the debit card is not enough?". 2, the customer's problem is divided into the word sequence "credit card automatic repayment debit card, the money is not enough, how to do." 3. Extract the five keywords “credit card”, “automatic”, “repayment”, “money”, and “not enough” in the sequence of words, and generate a simplified word sequence “credit card automatic repayment is not enough”. 4. Replace “insufficient” in the aforementioned simplified word sequence with “insufficient” to generate a standard word sequence “Insufficient credit card automatic repayment”. 5, the output standard word sequence "credit card automatic repayment of insufficient money."

Based on the fourth embodiment described above, in the fifth embodiment, as shown in FIG. 7, the sub-step S33 specifically includes the following sub-steps:

S341. Acquire keywords in the simplified word sequence;

S342, comparing the obtained keywords with the standard words in the thesaurus;

S343, determining whether there is a standard word matching the keyword in the thesaurus, if yes, executing step S345, if otherwise, executing step S344;

S344, comparing the keyword with the synonym in the thesaurus, finding the same synonym as the keyword, and replacing the standard word associated with the synonym with the position of the keyword in the simplified word sequence. ;

S345, determining whether the keyword is the last word in the sequence of simplified words, if yes, executing step S346, if otherwise performing step S341;

S346. Generate a standard word sequence containing only standard words.

In the following example, the replacement process is described by replacing the synonym of the simplified word sequence "credit card automatic repayment is not enough" as an example: 1. Obtain the first keyword "credit card" in the simplified word sequence "credit card automatic repayment money is not enough" "2. Compare the keyword "credit card" with the standard words in the thesaurus to find the same word "credit card"; 3. Determine the keyword "credit card" is not a simplified word sequence "credit card automatic repayment is not enough" The last word; 4. Obtain the second keyword "automatic" in the simplified word sequence "credit card automatic repayment money is not enough", repeat the previous steps until the fourth keyword "money" in the simplified word sequence 5, to obtain the simplified keyword sequence "credit card automatic repayment, insufficient money" in the fifth keyword "not enough"; 6, the keyword "not enough" compared with the standard words in the thesaurus, did not find the same word 7. Compare the keyword "not enough" with the synonym in the thesaurus, find the same word "not enough", use the word "not enough The associated standard word "insufficient" replaces the keyword "not enough" in the simplified word sequence; 8. The judgment keyword "not enough" is the last word in the simplified word sequence "credit card automatic repayment money is not enough"; 9, generating standard words The sequence "credit card automatic repayment is insufficient".

Based on the fifth embodiment described above, in the sixth embodiment, as shown in FIG. 8, step S4 specifically includes the following sub-steps:

S41. Extract a sequence of words associated with a standard question from a standard knowledge base;

S42. Extract a standard word from the standard word sequence to match the keyword in the word sequence;

S43, it is determined whether the standard word matches the keyword in the word sequence, if yes, step S44 is performed, otherwise step S45 is performed;

S44. Accumulating corresponding scores according to a scoring rule;

S45, determining whether the standard word is the last standard word in the standard word sequence, if yes, executing step S46, if otherwise performing step S42;

S46. Output a cumulative total score, and then calculate a ratio between the total score and a total score of all keywords in the word sequence as a matching value for temporary storage;

S47, determining whether the word sequence is the last word sequence in the standard knowledge base, if yes, executing step S48, if otherwise, performing step S41;

S48. Sort all the temporarily stored matching values in descending order.

In the following example, the standard word sequence “Insufficient credit card automatic repayment amount” is matched with the word sequence in the standard knowledge base as an example to specify the calculation process of the matching value: 1. Extract a standard question from the standard knowledge base. “How do I apply for a credit card?” The associated word sequence “Apply for a credit card”; 2. Extract the key words of a standard word “credit card” and the word sequence “Apply for a credit card” from the standard word sequence “Insufficient credit card automatic repayment” The words are matched in order; 3. The standard word "credit card" matches the "credit card" of the word sequence "apply for credit card"; 4. the score is accumulated according to the scoring rule; 5; the standard word "credit card" is not a standard word sequence. The last standard word in the order, in turn, matches the standard words in the standard word sequence “Insufficient credit card automatic repayment” with the keywords in the word sequence “Apply for credit card”, and there are no other matching words; And output the accumulated total score of 5, the total score is 9, and the matching value is calculated to be 0.5. 6; 7, the word sequence "application for opening a credit card" is not the last word sequence in the standard knowledge base, so the second word sequence in the standard knowledge base "incorrect credit card automatic repayment balance" is sequentially extracted to calculate the matching value. 0.9, and then take out the second word sequence in the standard knowledge base "handling credit card loss reporting" to calculate the matching value of 0.56, and so on to calculate... 8. Here, only the above three matching values are arranged in descending order, respectively 0.9 , 0.56, 0.56.

In this example, the matching value is up to 0.9, and the corresponding word sequence is “Insufficient credit card automatic repayment balance”. The standard question associated with the word sequence is “What should I do if the credit card automatic repayment debit card balance is insufficient?” The answer to the standard question is pushed and displayed in the manual customer service dialog.

Based on the sixth embodiment, in the seventh embodiment, as shown in FIG. 9, step S6 specifically includes the following sub-steps: S61, the manual customer service determines the answer displayed in the dialog box, and if the answer is correct, step S63 is performed. If the answer is not correct, step S62 is performed; S62, the incorrect answer is modified; and S63, the answer is pushed to the client.

Connected to the example, to push the standard question "What should I do if the credit card automatic repayment debit card balance is insufficient?" The answer is given to the manual customer service as an example. The manual push process is specified: 1. The manual customer service judgment is displayed in the dialog box. The answer is the correct answer to the customer's question; 2. The answer is sent directly to the customer.

Assuming that the manual customer service determines that the answer displayed in the dialog box is incorrect or partially incorrect, the answer needs to be corrected and the corrected answer is sent to the client. For example, if the answer displayed in the dialog box is the answer to the standard question “How do I apply for a credit card?”, the manual customer service needs to clear the dialog box and re-enter the correct answer. Another example: the answer displayed in the dialog box is the answer to the standard question “What if the credit card automatic repayment debit card balance is insufficient?”, but some of the answers are not updated in time, then the manual customer service needs to update the answer. , then send the latest answer to the customer.

In addition, the present application is a computer readable storage medium storing a human-machine cooperation customer service system 20, which can be implemented by one or more processors to implement the above-mentioned person The customer service method of the machine cooperation or the operation of the electronic device.

While the embodiments of the present invention have been described above, it will be understood by those skilled in the art that the scope of the invention is defined by the appended claims. A person skilled in the art can make various changes or modifications to these embodiments without departing from the spirit and scope of the present application, and such changes and modifications fall within the scope of the present application.

Claims

A human-machine cooperation customer service method, characterized in that the method comprises the following steps:

S1. Build a standard knowledge base, store a number of standard question-answer pairs for intelligent question and answer, and split the standard question into a sequence of words consisting of several keywords to be associated with the standard question;

S2, constructing a synonym database, storing a plurality of word groups consisting of standard words associated with the standard words, the standard words corresponding to keywords in the standard question;

S3. Obtain the customer's problem and analyze it, and split the customer's problem into a standard word sequence containing only standard words;

S4, matching the standard word sequence with the word sequence in the standard knowledge base, and calculating corresponding matching values corresponding to each word sequence in the standard knowledge base;

S5. The answer corresponding to the standard question associated with the word sequence with the highest push matching value is displayed in the dialog box of the manual customer service;

S6. The manual customer service judges the pushed content and pushes the correct answer to the customer.
The customer service cooperation method of the human-machine cooperation according to claim 1, wherein the step S1 specifically comprises the following sub-steps:

S11. Collect and organize the questions and the answers that match the questions, construct a standard question-answer pair and save;

S12. Splitting the standard question into a sequence of words consisting of several words through a word segmentation tool;

S13. The stop words in the word sequence are removed, and a sequence of words composed of a plurality of keywords is generated and stored in association with the standard question.
The customer service cooperation method of the human-machine cooperation according to claim 2, wherein the step S2 comprises the following sub-steps:

S21. Extract keywords in each standard question in the standard knowledge base;

S22. Combine all keywords into a keyword set and perform deduplication processing to obtain a standard word set.

S23. Extract standard words in the standard word set in turn, collect at least one synonym similar to the standard word, and associate the synonyms with the standard words into a word group for preservation.
The customer service method for human-machine cooperation according to claim 3, wherein the step S3 specifically comprises the following sub-steps:

S31. Obtaining a customer's problem;

S32, word segmentation, using the word segmentation tool to split the customer's problem into a sequence of words composed of several words;

S33. Extract a keyword, and generate a simplified word sequence composed only of keywords by removing the stop word in the word sequence;

S34, replacing the synonym, determining whether the keyword in the simplified word sequence belongs to the standard word in the synonym database, and if not, replacing the keyword with the standard word in the synonym database, and generating a standard word sequence containing only the standard word;

S35. Output a standard word sequence.
The human-machine cooperation customer service method according to claim 4, wherein the sub-step S34 comprises the following sub-steps:

S341. Acquire keywords in the simplified word sequence;

S342, comparing the obtained keywords with the standard words in the thesaurus;

S343, determining whether there is a standard word matching the keyword in the thesaurus, if yes, executing step S345, if otherwise, executing step S344;

S344, comparing the keyword with the synonym in the thesaurus, finding the same synonym as the keyword, and replacing the standard word associated with the synonym with the position of the keyword in the simplified word sequence. ;

S345, determining whether the keyword is the last word in the sequence of simplified words, if yes, executing step S346, if otherwise performing step S341;

S346. Generate a standard word sequence containing only standard words.
The customer service cooperation method of the human-machine cooperation according to claim 5, wherein the step S4 specifically comprises the following sub-steps:

S41. Extract a sequence of words associated with a standard question from a standard knowledge base;

S42. Extract a standard word from the standard word sequence to match the keyword in the word sequence;

S43, it is determined whether the standard word matches the keyword in the word sequence, if yes, step S44 is performed, otherwise step S45 is performed;

S44. Accumulating corresponding scores according to a scoring rule;

S45, determining whether the standard word is the last standard word in the standard word sequence, if yes, executing step S46, if otherwise performing step S42;

S46. Output a cumulative total score, and then calculate a ratio between the total score and a total score of all keywords in the word sequence as a matching value for temporary storage;

S47, determining whether the word sequence is the last word sequence in the standard knowledge base, if yes, executing step S48, if otherwise, performing step S41;

S48. Sort all the temporarily stored matching values in descending order.
The customer service method for human-machine cooperation according to claim 6, wherein the step S6 specifically comprises the following sub-steps:

S61, the manual customer service determines the answer displayed in the dialog box, if the answer is correct, step S63 is performed, if the answer is not correct, step S62 is performed;

S62. Modify the incorrect answer;

S63. Push the answer to the customer.
An electronic device includes a memory and a processor, wherein the memory stores a customer service system capable of being executed by the processor, and the human-machine cooperation customer service system comprises:

a standard knowledge base for storing a number of standard question-answer pairs for intelligent question and answer, and splitting the standard question into a sequence of words consisting of several keywords associated with the standard question;

a synonym library for storing a plurality of word groups consisting of a synonym of a standard word associated with the standard word, the standard word corresponding to a keyword in a standard question;

The session acquisition analysis module is configured to acquire and analyze the customer's problem, and split the customer's problem into a standard word sequence containing only standard words;

An answer matching module, configured to match the standard word sequence with the word sequence in the standard knowledge base, and calculate a corresponding matching value corresponding to each word sequence in the standard knowledge base;

The automatic push module, which is used to push the standard question associated with the word sequence with the highest matching value, is displayed in the dialog box of the manual customer service;

The manual push module is used to push the correct answer to the customer after the manual customer service judges the pushed content.
A computer readable storage medium, wherein the computer readable storage medium stores a human machine cooperative customer service system, and the human machine cooperative customer service system can be executed by at least one processor to perform the following steps:

S1. Build a standard knowledge base, store a number of standard question-answer pairs for intelligent question and answer, and split the standard question into a sequence of words consisting of several keywords to be associated with the standard question;

S2, constructing a synonym database, storing a plurality of word groups consisting of standard words associated with the standard words, the standard words corresponding to keywords in the standard question;

S3. Obtain the customer's problem and analyze it, and split the customer's problem into a standard word sequence containing only standard words;

S4, matching the standard word sequence with the word sequence in the standard knowledge base, and calculating corresponding matching values corresponding to each word sequence in the standard knowledge base;

S5. The answer corresponding to the standard question associated with the word sequence with the highest push matching value is displayed in the dialog box of the manual customer service;

S6. The manual customer service judges the pushed content and pushes the correct answer to the customer.
The computer readable storage medium according to claim 9, wherein the step S1 comprises the following substeps:

S11. Collect and organize the questions and the answers that match the questions, construct a standard question-answer pair and save;

S12. Splitting the standard question into a sequence of words consisting of several words through a word segmentation tool;

S13. The stop words in the word sequence are removed, and a sequence of words composed of a plurality of keywords is generated and stored in association with the standard question.
The computer readable storage medium according to claim 10, wherein the step S2 comprises the following substeps:

S21. Extract keywords in each standard question in the standard knowledge base;

S22. Combine all keywords into a keyword set and perform deduplication processing to obtain a standard word set.

S23. Extract standard words in the standard word set in turn, collect at least one synonym similar to the standard word, and associate the synonyms with the standard words into a word group for preservation.
The computer readable storage medium according to claim 11, wherein the step S3 comprises the following substeps:

S31. Obtaining a customer's problem;

S32, word segmentation, using the word segmentation tool to split the customer's problem into a sequence of words composed of several words;

S33. Extract a keyword, and generate a simplified word sequence composed only of keywords by removing the stop word in the word sequence;

S34, replacing the synonym, determining whether the keyword in the simplified word sequence belongs to the standard word in the synonym database, and if not, replacing the keyword with the standard word in the synonym database, and generating a standard word sequence containing only the standard word;

S35. Output a standard word sequence.
The computer readable storage medium according to claim 12, wherein the substep S34 comprises the following substeps:

S341. Acquire keywords in the simplified word sequence;

S342, comparing the obtained keywords with the standard words in the thesaurus;

S343, determining whether there is a standard word matching the keyword in the thesaurus, if yes, executing step S345, if otherwise, executing step S344;

S344, comparing the keyword with the synonym in the thesaurus, finding the same synonym as the keyword, and replacing the standard word associated with the synonym with the position of the keyword in the simplified word sequence. ;

S345, determining whether the keyword is the last word in the sequence of simplified words, if yes, executing step S346, if otherwise performing step S341;

S346. Generate a standard word sequence containing only standard words;
The computer readable storage medium according to claim 13, wherein the step S4 comprises the following substeps:

S41. Extract a sequence of words associated with a standard question from a standard knowledge base;

S42. Extract a standard word from the standard word sequence to match the keyword in the word sequence;

S43, it is determined whether the standard word matches the keyword in the word sequence, if yes, step S44 is performed, otherwise step S45 is performed;

S44. Accumulating corresponding scores according to a scoring rule;

S45, determining whether the standard word is the last standard word in the standard word sequence, if yes, executing step S46, if otherwise performing step S42;

S46. Output a cumulative total score, and then calculate a ratio between the total score and a total score of all keywords in the word sequence as a matching value for temporary storage;

S47, determining whether the word sequence is the last word sequence in the standard knowledge base, if yes, executing step S48, if otherwise, performing step S41;

S48. Sort all the temporarily stored matching values in descending order.
The computer readable storage medium according to claim 14, wherein the step S6 comprises the following substeps:

S61, the manual customer service determines the answer displayed in the dialog box, if the answer is correct, step S63 is performed, if the answer is not correct, step S62 is performed;

S62. Modify the incorrect answer;

S63. Push the answer to the customer.