A customer service intelligent access method and device, an intelligent terminal and a storage medium

Abstract

This application discloses a customer service intelligent access method, device, intelligent terminal, and storage medium. The method includes: acquiring the conversation intent of a bank customer accessing a chatbot; determining the target business category the bank customer wants to inquire about; acquiring a business attribute analysis report of the bank customer and obtaining the weight value, basic score, and attention elements of the target business category; calculating a first score based on the weight value and basic score; acquiring and analyzing the conversation status and content between the bank customer and the chatbot in real time; obtaining key information based on the analysis results; matching the key information and attention elements; calculating a second score based on the matching results; using the sum of the first and second scores as the total score; and determining whether to transfer the customer to a human customer service representative based on a comparison of the total score with a preset threshold. Through this method, accurate identification, analysis, and decision-making regarding whether a consultation service needs to be transferred to a human customer service representative can be achieved.

Description

Technical Field

[0001] This application relates to the field of computer application technology, and in particular to a customer service intelligent access method, device, intelligent terminal and storage medium. Background Technology

[0002] With the development of the financial sector and the increasing demand for services, the banking industry has set up customer service access methods to better serve the public. This means that bank customers can access the bank's customer service through the bank's hotline to inquire about or conduct business.

[0003] Bank customer service includes chatbots and human agents. Currently, bank hotlines typically have a button to transfer to a human agent. However, this existing service model lacks a comprehensive analysis of customer attributes, historical behavior, and current inquiry intent to determine whether human assistance is needed. This reduces service efficiency and increases the workload of human agents. Summary of the Invention

[0004] This application provides a customer service intelligent access method, device, intelligent terminal, and storage medium to solve the problems in the background art.

[0005] In a first aspect, embodiments of this application provide a customer service intelligent access method, the method comprising:

[0006] Obtain the conversation intent of a bank customer when accessing the chatbot customer service, and determine the target business category that the bank customer wants to inquire about and handle based on the conversation intent;

[0007] Obtain the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period;

[0008] Based on the business attribute analysis report, the weight value, basic score and focus elements of the target business category are obtained, and the first score value is calculated based on the weight value and the basic score.

[0009] The system acquires and analyzes the conversation status and content between the bank customer and the robot customer service in real time. Based on the analysis results, it obtains key information, matches the key information with the focus elements, and calculates a second score based on the matching results.

[0010] The sum of the first score and the second score is taken as the total score. Based on the comparison between the total score and a preset threshold, it is determined whether to transfer the call to a human customer service representative.

[0011] In some embodiments, obtaining the business attribute analysis report of the bank customer, wherein the business attribute analysis report is a report pre-analyzed based on the bank customer's business operation behavior within a historical time period, includes:

[0012] The bank customer's business operation behavior within a historical time period is obtained, and the business operation behavior is classified into the corresponding business category.

[0013] The operational behaviors of each business category are analyzed, and based on the analysis results, the relevant elements for each business category are obtained.

[0014] In some embodiments, after analyzing the business operation behavior of each business category and obtaining the focus elements corresponding to each business category based on the analysis results, the method further includes:

[0015] Set management labels for each of the aforementioned key elements and their corresponding business categories;

[0016] A weight value is assigned to each of the aforementioned elements based on the number of times the business operation is performed, and the weight value is recorded in the corresponding management tag.

[0017] In some embodiments, the product of the base score and the weight value is the first score value.

[0018] In some embodiments, the preset threshold includes a first preset threshold and a second preset threshold, wherein the first preset threshold is greater than the second preset threshold.

[0019] In some embodiments, the step of using the sum of the first score and the second score as the total score, and determining whether to transfer the call to a live agent based on a comparison of the total score with a preset threshold, includes:

[0020] If the total score is greater than the first preset threshold, the call is transferred to a human customer service representative, and the description table of the bank customer and the robot customer service representative is forwarded to the target human customer service representative who has entered the session.

[0021] If the total score is less than the first preset threshold and the total score is greater than the second preset threshold, the bank customer may choose whether to transfer the call to a live customer service representative.

[0022] If the total score is less than the second preset threshold, the customer will not be transferred to a human customer service representative, and the chatbot will continue to serve the bank customer.

[0023] In some embodiments, the specific implementation method for generating the element description table is as follows:

[0024] Key information that matches the elements of interest is identified as target key information;

[0025] Based on the target key information, obtain historical session information associated with the target key information. The historical session information includes historical session content, historical session time, and customer status information.

[0026] Based on the target key information, the elements of interest, the historical session information, and the preset table generation mode, an element description table is generated.

[0027] Secondly, embodiments of this application also provide a customer service intelligent access device, the device comprising:

[0028] The first acquisition unit is used to acquire the conversation intent of a bank customer accessing the robot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about and handle.

[0029] The second acquisition unit is used to acquire the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period.

[0030] The first calculation unit is used to obtain the weight value, basic score and attention elements of the target business category based on the business attribute analysis report, and calculate the first score based on the weight value and the basic score.

[0031] The second calculation unit is used to acquire and analyze the conversation status and content between the bank customer and the robot customer service in real time, obtain key information based on the analysis results, match the key information with the focus elements, and calculate a second score based on the matching results.

[0032] The determining unit is used to take the sum of the first score and the second score as the total score, and determine whether to transfer the call to a human customer service representative based on the comparison result between the total score and a preset threshold.

[0033] Thirdly, embodiments of this application also provide a smart terminal, including a memory and a processor, wherein the memory is used to store instructions and data, and the processor is used to execute the customer service smart access method described above.

[0034] Fourthly, embodiments of this application also provide a storage medium storing a plurality of instructions, which are adapted to be loaded by a processor to execute the customer service intelligent access method described above.

[0035] The intelligent customer service access method in this application includes: acquiring the conversation intent of a bank customer accessing a robot customer service; determining the target business category the bank customer wants to inquire about based on the conversation intent; acquiring a business attribute analysis report of the bank customer, which is a report pre-analyzed based on the bank customer's business operation behavior within a historical time period; acquiring the weight value, basic score, and attention elements of the target business category based on the business attribute analysis report; calculating a first score based on the weight value and basic score; acquiring and analyzing the conversation status and content between the bank customer and the robot customer service in real time; obtaining key information based on the analysis results; matching the key information and attention elements; calculating a second score based on the matching results; using the sum of the first score and the second score as the total score; and determining whether to transfer the customer to a human customer service representative based on the comparison result of the total score and a preset threshold. In this application's embodiment, through the analysis and calculation of multiple aspects of information, the method accurately identifies, analyzes, and decides whether the current customer's consultation service should be provided by a robot or by a human. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of a customer service intelligent access method provided in an embodiment of this application.

[0038] Figure 2 This is a schematic diagram of the structure of a customer service intelligent access device provided in an embodiment of this application.

[0039] Figure 3 This is a schematic diagram of the structure of a smart terminal provided in an embodiment of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0042] To enable any person skilled in the art to implement and use this application, the following description is provided. In this description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known processes will not be described in detail to avoid obscuring the description of the embodiments of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in the embodiments of this application.

[0043] This application provides a customer service intelligent access method, device, intelligent terminal, and storage medium, which will be described in detail below.

[0044] Please see Figure 1 , Figure 1 A flowchart of a customer service intelligent access method provided in this application embodiment includes the following:

[0045] 101. Obtain the conversation intent of a bank customer accessing the chatbot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about.

[0046] In the embodiments of this application, bank customers can access the robot customer service through various means, including telephone access, text chat box access, or video access.

[0047] Taking telephone access as an example, it can be assumed that after a bank customer dials the bank's customer service hotline, they are first connected to the robot customer service. During the conversation between the bank customer and the robot customer service, a comprehensive analysis is conducted to determine whether it is necessary to transfer the customer to a human customer service representative. If so, the customer is transferred to a human customer service representative who will continue to provide services to the bank customer.

[0048] Correspondingly, after bank customers connect to the chatbot, they can input statements or text expressing their intentions via voice or text. The chatbot will automatically recognize the input to determine the customer's intent for the conversation.

[0049] By analyzing the conversation intent, the target service category that the bank customer wants to inquire about can be determined. The target service category is one of many service categories set by the bank, which may include wealth management services, credit card services, loan services, event services, account services, transaction services, and product services, etc.

[0050] 102. Obtain the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period.

[0051] Bank customer transactions over a historical period can include purchases, transfers, reviews, review content, successful and failed transactions, participation in activities, and marketing records. These transactions are analyzed and categorized according to business type to identify the relevant business categories and key elements for each category.

[0052] Regarding the key factors for a business category, for example, the key factors for a wealth management business category may include transaction records, product attributes, agreement signing, asset allocation, evaluation records, and complaints. Among these, transaction records may include purchase records, redemption records, and cancellation records, and product attributes may include product fees and product risks.

[0053] Regarding the key factors to consider for different business categories, for example, key factors for credit card business categories may include application processing, credit limit adjustment, credit card status inquiry and processing, installment payments, repayments, complaint evaluations, and browsing operation records.

[0054] Regarding the key factors for a business category, for example, the key factors for a loan business category may include customer funding needs, product attributes, the match between the customer and the consulting product, sales records and evaluations. Among these, product attributes may include loan interest rates and loan product risks.

[0055] The above-mentioned business categories are merely a few examples illustrating the embodiments of this application. It should be understood that all business categories involved by bank customers during historical periods should have corresponding business operation behaviors with their respective attention elements, which will not be elaborated here.

[0056] Optionally, after analyzing the bank customers' business operation behavior over a historical period to identify the key factors for each business category, a business attribute analysis report is generated according to preset report generation rules. This report then records the key factors that bank customers focused on for each business category over the historical period.

[0057] In addition to acquiring the business operation behavior of bank customers during historical time periods, the system also acquires historical conversation information between bank customers and the bank's chatbot customer service during those historical time periods, as well as the service operation behavior of the chatbot customer service during the service phase. By analyzing the service operation behavior and historical conversation information, the system obtains the service elements of the bank's chatbot customer service during the historical time periods. Service elements may include no recognized intent, unresolved issues, sensitive words, and emotional words, etc.

[0058] Optionally, after analyzing the bank customers' business operation behavior over a historical period to identify the key considerations for each business category and the service elements of the chatbot customer service, a business attribute analysis report is generated according to preset report generation rules. This report records the key considerations and corresponding service elements for each business category within the historical time period.

[0059] In some embodiments, this step includes: obtaining the business operation behavior of bank customers within a historical time period, classifying the business operation behavior into corresponding business categories, analyzing the business operation behavior of each business category, and obtaining the focus elements corresponding to each business category based on the analysis results.

[0060] For example, a bank may have already set up a report template according to a pre-defined file format and all the business categories it includes. This report template contains a record field for each business category and its corresponding element. After obtaining the bank's customers' business operations over a historical period, the bank categorizes these operations by business category, analyzes the operations within each category to identify the key elements for each category, and records them in the corresponding key record field of the business category within the report template.

[0061] In some embodiments, after analyzing the business operation behavior of each business category and obtaining the focus elements corresponding to each business category based on the analysis results, the method further includes: setting management tags for each focus element and its corresponding business category, setting weight values ​​for each focus element according to the number of operations of the business operation behavior, and recording the weight values ​​in the corresponding management tags.

[0062] Optionally, the more operations performed on a given element, the higher its weight; conversely, the fewer operations performed on a given element, the lower its weight. Besides setting weight values, priority levels can also be used.

[0063] In the embodiments of this application, in addition to setting a weight value for each element of interest, a weight value is also set for each business category. Furthermore, based on the weight values ​​and the preset basic score setting rules, a basic score for each business category and a basic score for each element of interest are set. This is so that relevant information in the subsequent conversation between the bank customer and the robot customer service can be analyzed, and the decision on whether to transfer the customer to a human customer service representative can be determined based on the score calculation.

[0064] Correspondingly, the weight value and basic score of each business category will be recorded in the business attribute analysis report of the bank customer, and the weight value and basic score of each focus element will also be recorded in the business attribute analysis report of the bank customer.

[0065] After parsing out the key features contained in each business category, a management tag is set for each business category and its key feature. A management tag is then assigned between each business category and one of its key features. Furthermore, after determining the weight value of the key feature, that weight value is recorded in the corresponding management tag. Therefore, each management tag can be understood as corresponding to a business category, a key feature, and a weight value.

[0066] 103. Based on the business attribute analysis report, obtain the weight value, basic score and attention elements of the target business category, and calculate the first score based on the weight value and the basic score.

[0067] 104. The conversation status and content of the bank customer and the robot customer service are obtained in real time and analyzed. Based on the analysis results, key information is obtained, and the key information is matched with the focus elements. Based on the matching results, a second score is calculated.

[0068] In embodiments of this application, the first score is the product of the weight value and the base score of the target business category. For example, if the weight value of the target business category is 'a' and its base score is 'b', then the value of 'a*b' is the first score of the target business category.

[0069] After obtaining the bank customer's conversation intent, the type of business the customer wants to inquire about can be determined, i.e., the target business category of the conversation can be identified. The weight value and base score corresponding to the target business category can then be obtained from the bank customer's business attribute analysis report. Based on the weight value and base score, the first score value for the target business category can be calculated.

[0070] In the embodiments of this application, the conversation state between the bank customer and the chatbot is obtained by parsing the text, voice, video, or images during the conversation. The conversation state reveals the bank customer's emotional state during the conversation, as well as the chatbot's ability to recognize the customer's questions, and so on.

[0071] After clarifying the bank customer's conversation intent, in addition to acquiring the conversation status of the bank customer and the chatbot in real time, the conversation content is also acquired in real time during the conversation. The conversation status and content are then analyzed to extract key information. Some of this key information may match the elements of interest contained in the target business category. By matching the key information with the elements of interest, the key information matching the elements of interest can be identified, that is, the elements of interest involved in the conversation can be determined from the elements of interest contained in the target business category.

[0072] For example, if the target business category is credit card business, its key considerations include application processing, credit limit adjustment, credit card status inquiry and processing, installment payments, repayments, complaint evaluations, and browsing activity logs. During a conversation, if the key information obtained from parsing a particular conversation is "credit card application," then matching this key information with the key considerations within the credit card business category will confirm that the matched key consideration is "application processing."

[0073] In the embodiments of this application, the second score is the sum of the scores of the attention elements that successfully match the key information during the session. This can be achieved by setting a timed calculation task, which acquires the key information in real time within the corresponding time period, matches the key information with the attention elements, and uses the sum of the scores of the attention elements that successfully match within the corresponding time period as the second score.

[0074] For example, if the timing time for a scheduled calculation task is set to 3 minutes, then the timing starts after the bank customer and the robot customer service connect to the conversation. The target business category corresponding to the conversation intent is determined, and key information is obtained in real time within 3 minutes. The sum of the scores of the focus elements in the target business category that match the key information obtained within 3 minutes is used as the second score.

[0075] Further, for example, if the target business category is the credit card business category, the concern elements it contains are application processing, credit limit adjustment, credit card status query and processing, installment, repayment, complaint evaluation, and browsing operation records. The concern elements that match the key information within 3 minutes include application processing, credit limit adjustment, and installment. Moreover, the weight values of these three concern elements are a1, a2, and a3 respectively, and the basic scores of these three concern elements are b1, b2, and b3. Then, the second score value of the conversation within 3 minutes is S = a1 * b1 + a2 * b2 + a3 * b3.

[0076] Optionally, in a conversation, multiple timing calculation tasks can be set, and the corresponding times of the timing calculation tasks can be set separately. After determining the concern elements that match the key information, the second score value is calculated through a summation formula.

[0077] 105. Use the sum of the first score value and the second score value as the total score value, and determine whether to transfer to a human customer service based on the comparison result between the total score value and a preset threshold.

[0078] In the embodiments of the present application, the preset threshold includes a first preset threshold and a second preset threshold, and the first preset threshold is greater than the second preset threshold.

[0079] For example, if the first score value is S1 and the second score value is S2, then the total score value is S = S1 + S2. The first preset threshold is Sa, and the second preset threshold is Sb.

[0080] In the embodiments of the present application, this step includes: if the total score value is greater than the first preset threshold, transfer to a human customer service and forward the element description form of the bank customer and the robot customer service to the target human customer service accessing the conversation; if the total score value is less than the first preset threshold and greater than the second preset threshold, let the bank customer choose whether to transfer to a human customer service; if the total score value is less than the second preset threshold, do not transfer to a human customer service, and let the robot customer service continue to serve the bank customer.

[0081] For example, in the first case L1: S ≥ Sa, it indicates that the bank customer's need for human service is very clear and urgent; in the second case L2: Sb ≤ S < Sa, it indicates that the bank customer may need timely human service, but not very urgently; in the third case L3: S < Sb, it indicates that the bank customer can complete the consultation and handling through the service of the robot customer service, and there is no need for human service intervention for the time.

[0082] Furthermore, based on the above examples, the system makes the following decisions: If it is the first case L1, the system immediately uses a human customer service representative to take over from the robot customer service representative and synchronizes the preset element description table to the human customer service representative; if it is the second case L2, the human intervention service entry is displayed in the most prominent position in the bank customer's system client, and if the bank customer chooses to enter human service, the preset element description table is synchronized to the human customer service representative; if it is the third case L3, the system continues to monitor the conversation status between the robot customer service representative and the bank customer, and the human intervention service entry is not displayed in the bank customer's system client.

[0083] In some embodiments, the specific implementation of generating the element description table is as follows: determining the key information matching the element of interest as the target key information; based on the target key information, obtaining the historical session information associated with the target key information, the historical session information including historical session content, historical session time and customer status information; and generating the element description table based on the target key information, the element of interest, the historical session information and the preset table generation mode.

[0084] The element description table provides detailed explanations of the elements of interest that match the key information. These explanations include not only relevant information obtained in the current session but also historical related information. By synchronizing the element description table with the assigned human customer service representative, the representative can access important information and historical data from the customer's conversation with the chatbot. This facilitates communication between the human and customer service representatives, speeds up the consultation process, and improves the efficiency of human customer service.

[0085] Optionally, the element description table may also record information such as the bank customer's session intent, session mood, and target business category when accessing the current session. There are no restrictions on the content recorded in the element description table.

[0086] The intelligent customer service access method of this application includes: acquiring the conversation intent of a bank customer accessing a robot customer service; determining the target business category the bank customer wants to inquire about based on the conversation intent; acquiring a business attribute analysis report of the bank customer, which is a report pre-analyzed based on the bank customer's business operation behavior within a historical time period; acquiring the weight value, basic score, and attention elements of the target business category based on the business attribute analysis report; calculating a first score value based on the weight value and basic score; acquiring and analyzing the conversation status and content between the bank customer and the robot customer service in real time; obtaining key information based on the analysis results; matching the key information and attention elements; calculating a second score value based on the matching results; using the sum of the first score value and the second score value as the total score value; and determining whether to transfer the customer to a human customer service representative based on the comparison result of the total score value and a preset threshold. This intelligent customer service access method of this application, through the analysis and calculation of multiple aspects of information, accurately identifies, analyzes, and decides whether the current customer's consultation service should be provided by a robot or by a human, thereby improving customer service efficiency and reducing the workload of human customer service representatives while effectively and quickly serving customers.

[0087] Please see Figure 2 , Figure 2 This application provides a schematic diagram of the structure of a customer service intelligent access device 200, which includes the following units:

[0088] The first acquisition unit 201 is used to acquire the conversation intent of a bank customer accessing the robot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about.

[0089] The second acquisition unit 202 is used to acquire the business attribute analysis report of the bank customer. The business attribute analysis report is a report obtained in advance based on the bank customer's business operation behavior in a historical time period.

[0090] The first calculation unit 203 is used to obtain the weight value, basic score and attention elements of the target business category based on the business attribute analysis report, and calculate the first score based on the weight value and basic score.

[0091] The second calculation unit 204 is used to acquire and analyze the conversation status and content of bank customers and robot customer service in real time, obtain key information based on the analysis results, match the key information with the elements of interest, and calculate the second score based on the matching results.

[0092] The determining unit 205 is used to take the sum of the first score and the second score as the total score, and determine whether to transfer the call to a human customer service representative based on the comparison result between the total score and a preset threshold.

[0093] Optionally, the second acquisition unit 202 described above may include the following sub-units:

[0094] The category division sub-unit is used to obtain the business operation behavior of bank customers within a historical time period and classify the operation behavior into the corresponding business category.

[0095] The element acquisition subunit is used to analyze the operational behavior of each business category and, based on the analysis results, acquire the relevant elements for each business category.

[0096] The label setting sub-unit is used to set management labels for each element of interest and its corresponding business category.

[0097] The recording sub-unit is used to set a weight value for each element of interest based on the number of times the operation is performed, and to record the weight value in the corresponding management tag.

[0098] Optionally, the preset thresholds include a first preset threshold and a second preset threshold. The first preset threshold is the product of a first proportional coefficient and the total score, and the second preset threshold is the product of a second proportional coefficient and the total score. The first proportional coefficient is greater than the second proportional coefficient. Therefore, the determining unit 205 described above may include the following sub-units:

[0099] The judgment subunit is used to transfer the customer to a human customer service representative if the total score is greater than a first preset threshold, and forward the element description table of the bank customer and the robot customer service representative to the target human customer service representative in the access session; if the total score is less than the first preset threshold and greater than a second preset threshold, the bank customer can choose whether to transfer the customer to a human customer service representative; if the total score is less than the second preset threshold, the customer is not transferred to a human customer service representative, and the robot customer service representative continues to serve the bank customer.

[0100] Optionally, the customer service intelligent access device 200 in this application embodiment also includes other units and sub-units, which will not be described in detail here.

[0101] The customer service intelligent access device 200 of this application embodiment includes a first acquisition unit 201, used to acquire the conversation intent of a bank customer accessing the robot customer service, and determine the target business category that the bank customer wants to inquire about based on the conversation intent; a second acquisition unit 202, used to acquire the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period; a first calculation unit 203, used to acquire the weight value, basic score and attention elements of the target business category based on the business attribute analysis report, and calculate a first score value based on the weight value and basic score; a second calculation unit 204, used to acquire and analyze the conversation status and conversation content of the bank customer and the robot customer service in real time, acquire key information based on the analysis results, match the key information and attention elements, and calculate a second score value based on the matching results; and a determination unit 205, used to take the sum of the first score value and the second score value as the total score value, and determine whether to transfer to human customer service based on the comparison result of the total score value and a preset threshold. The customer service intelligent access device 200 of this application embodiment accurately identifies, analyzes, and decides whether the current customer's consultation service is provided by a robot or by human intervention through the analysis and calculation of various information. While achieving effective and fast customer service, it improves customer service efficiency and reduces the workload of human customer service representatives.

[0102] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a smart terminal provided in an embodiment of this application. The smart terminal 300 can be a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other smart terminal device. The smart terminal 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a computer program stored on the memory 302 and executable on the processor 301. The processor 301 and the memory 302 are electrically connected. Those skilled in the art will understand that the smart terminal structure shown in the figure does not constitute a limitation on the smart terminal; it may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0103] The processor 301 is the control center of the smart terminal 300. It connects various parts of the smart terminal 300 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the smart terminal 300 and processes data, thereby performing overall monitoring of the smart terminal 300.

[0104] In this embodiment, the processor 301 in the smart terminal 300 loads the instructions corresponding to the processes of one or more applications into the memory 302 according to the following steps, and the processor 301 runs the applications stored in the memory 302 to achieve various functions:

[0105] Obtain the conversation intent of bank customers when they connect to the chatbot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about and handle.

[0106] Obtain business attribute analysis reports from bank customers. These reports are pre-analyzed based on the bank customers' business operation behavior over a historical period.

[0107] Based on the business attribute analysis report, obtain the weight value, basic score and key elements of the target business category, and calculate the first score based on the weight value and basic score.

[0108] The system acquires and analyzes the conversation status and content of bank customers and chatbot customer service in real time. Based on the analysis results, it obtains key information, matches the key information with the elements of interest, and calculates the second score based on the matching results.

[0109] The sum of the first and second scores is used as the total score. Based on the comparison between the total score and a preset threshold, it is determined whether to transfer the call to a human customer service representative.

[0110] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0111] Optionally, the smart terminal 300 also includes a touch display screen 303, an input unit 304, and a power supply 305, wherein the processor 301 is electrically connected to the touch display screen 303, the input unit 304, and the power supply 305. Those skilled in the art will understand that... Figure 3 The smart terminal structure shown does not constitute a limitation on the smart terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0112] The touch display screen 303 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The touch display screen 303 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the computer device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar devices. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), and generate corresponding operation commands, which then execute the corresponding program. Optionally, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 301. It can also receive and execute commands from the processor 301. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 301 to determine the type of touch event. Subsequently, the processor 301 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the touch display screen 303 to achieve input and output functions. However, in some embodiments, the touch panel and the touch display screen 303 can be implemented as two independent components to achieve input and output functions. That is, the touch display screen 303 can also be used as part of the input unit 304 to achieve input functions.

[0113] The input unit 304 can be used to receive input numbers, characters, or user characteristic information (such as fingerprints, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0114] Power supply 305 is used to power the various components of smart terminal 300. Optionally, power supply 305 can be logically connected to processor 301 through power management system, thereby enabling functions such as charging, discharging, and power consumption management through power management system. Power supply 305 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0115] although Figure 3As not shown in the diagram, the smart terminal 300 may also include sensors and radio frequency modules, which will not be elaborated here.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0117] As can be seen from the above, the smart terminal 300 provided in this embodiment obtains the conversation intent of a bank customer accessing the robot customer service, and determines the target business category that the bank customer wants to inquire about based on the conversation intent; obtains the bank customer's business attribute analysis report, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period; obtains the weight value, basic score, and attention elements of the target business category based on the business attribute analysis report, and calculates a first score based on the weight value and basic score; obtains and analyzes the conversation status and conversation content between the bank customer and the robot customer service in real time, obtains key information based on the analysis results, matches the key information and attention elements, and calculates a second score based on the matching results; uses the sum of the first score and the second score as the total score, and determines whether to transfer to human customer service based on the comparison result of the total score and a preset threshold.

[0118] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0119] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs that can be loaded by a processor to execute steps in any of the customer service intelligent access methods provided in embodiments of this application. For example, the computer program can execute the following steps:

[0120] Obtain the conversation intent of bank customers when they connect to the chatbot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about and handle.

[0121] Obtain business attribute analysis reports from bank customers. These reports are pre-analyzed based on the bank customers' business operation behavior over a historical period.

[0122] Based on the business attribute analysis report, obtain the weight value, basic score and key elements of the target business category, and calculate the first score based on the weight value and basic score.

[0123] The system acquires and analyzes the conversation status and content of bank customers and chatbot customer service in real time. Based on the analysis results, it obtains key information, matches the key information with the elements of interest, and calculates the second score based on the matching results.

[0124] The sum of the first and second scores is used as the total score. Based on the comparison between the total score and a preset threshold, it is determined whether to transfer the call to a human customer service representative.

[0125] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0126] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0127] Since the computer program stored in the storage medium can execute the steps in any of the intelligent customer service access methods provided in the embodiments of this application, the beneficial effects that any of the intelligent customer service access methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0128] The above provides a detailed description of a customer service intelligent access method, device, intelligent terminal, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for intelligent customer service access, characterized in that, The method includes: Obtain the conversation intent of a bank customer when accessing the chatbot customer service, and determine the target business category that the bank customer wants to inquire about and handle based on the conversation intent; Obtain the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period; Based on the business attribute analysis report, the weight value, basic score and focus elements of the target business category are obtained, and the first score value is calculated based on the weight value and the basic score. The system acquires and analyzes the conversation status and content between the bank customer and the robot customer service in real time. Based on the analysis results, it obtains key information, matches the key information with the focus elements, and calculates a second score based on the matching results. The sum of the first score and the second score is taken as the total score. Based on the comparison between the total score and a preset threshold, it is determined whether to transfer the call to a human customer service representative.

2. The intelligent customer service access method according to claim 1, characterized in that, The step of obtaining the bank customer's business attribute analysis report, which is a report pre-analyzed based on the bank customer's business operation behavior over a historical period, includes: The bank customer's business operation behavior within a historical time period is obtained, and the business operation behavior is classified into the corresponding business category. The operational behaviors of each business category are analyzed, and based on the analysis results, the relevant elements for each business category are obtained.

3. The intelligent customer service access method according to claim 2, characterized in that, After analyzing the business operation behavior of each business category and obtaining the relevant elements for each business category based on the analysis results, the method further includes: Set management labels for each of the aforementioned key elements and their corresponding business categories; A weight value is assigned to each of the aforementioned elements based on the number of times the business operation is performed, and the weight value is recorded in the corresponding management tag.

4. The intelligent customer service access method according to claim 1, characterized in that, The product of the base score and the weight value is the first score value.

5. The intelligent customer service access method according to claim 1, characterized in that, The preset threshold includes a first preset threshold and a second preset threshold, wherein the first preset threshold is greater than the second preset threshold.

6. The intelligent customer service access method according to claim 5, characterized in that, The step of using the sum of the first score and the second score as the total score, and determining whether to transfer the call to a human customer service representative based on a comparison of the total score with a preset threshold, includes: If the total score is greater than the first preset threshold, the call is transferred to a human customer service representative, and the description table of the bank customer and the robot customer service representative is forwarded to the target human customer service representative who has entered the session. If the total score is less than the first preset threshold and the total score is greater than the second preset threshold, the bank customer may choose whether to transfer the call to a live customer service representative. If the total score is less than the second preset threshold, the customer will not be transferred to a human customer service representative, and the chatbot will continue to serve the bank customer.

7. The intelligent customer service access method according to claim 6, characterized in that, The specific implementation method for generating the element description table is as follows: Key information that matches the elements of interest is identified as target key information; Based on the target key information, obtain historical session information associated with the target key information. The historical session information includes historical session content, historical session time, and customer status information. Based on the target key information, the elements of interest, the historical session information, and the preset table generation mode, an element description table is generated.

8. A customer service intelligent access device, characterized in that, The device includes: The first acquisition unit is used to acquire the conversation intent of a bank customer accessing the robot customer service, and based on the conversation intent, determine the target business category that the bank customer wants to inquire about and handle. The second acquisition unit is used to acquire the business attribute analysis report of the bank customer, which is a report obtained in advance based on the bank customer's business operation behavior in a historical time period. The first calculation unit is used to obtain the weight value, basic score and attention elements of the target business category based on the business attribute analysis report, and calculate the first score based on the weight value and the basic score. The second calculation unit is used to acquire and analyze the conversation status and content between the bank customer and the robot customer service in real time, obtain key information based on the analysis results, match the key information with the focus elements, and calculate a second score based on the matching results. The determining unit is used to take the sum of the first score and the second score as the total score, and determine whether to transfer the call to a human customer service representative based on the comparison result of the total score and a preset threshold.

9. A smart terminal, characterized in that, It includes a memory and a processor, the memory being used to store instructions and data, and the processor being used to execute the customer service intelligent access method according to any one of claims 1-7.

10. A storage medium, characterized in that, The storage medium stores multiple instructions, which are adapted to be loaded by a processor to execute the customer service intelligent access method according to any one of claims 1-7.

Images