Complaint risk determination method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a complaint risk determination method and device, equipment and a storage medium, and the method comprises the steps: aiming at a current customer, determining a complaint risk of the current customer according to historical customer behaviors which are counted at regular time, current-day customer behaviors which are counted in real time, a preset customer emotion influence degree score adding rule and a preset customer emotion influence degree score reducing rule; determining a customer emotion influence degree value; determining a target emotion value corresponding to the current customer according to a customer emotion basic score set for the current customer in advance and the determined customer emotion influence degree value; and determining the complaint risk level of the current customer according to the target emotion value.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and particularly to a method, apparatus, device, and storage medium for determining complaint risks. Background Art

[0002] In the insurance industry, the quality of customer service is crucial for the sustainable development of enterprises. The service personnel directly facing customers in insurance companies are mainly customer service agents. However, the service capabilities and business levels of the agents vary.

[0003] Currently, the method for evaluating customer emotions mainly relies on the subjective judgment of the agents. However, the experience, emotional state, and personal cognitive differences of the agents will greatly affect the accuracy of judging customer emotions. Different agents may have completely different interpretations of the emotions of the same customer, lacking a unified standard and objective basis, and being unable to accurately evaluate customer emotions, resulting in the inability to timely discover and resolve potential complaint risks of customers, and thus triggering customer complaints. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for determining complaint risks to solve the problem in the related art that due to mainly relying on the subjective judgment of agents to judge customer emotions, the customer emotions cannot be accurately evaluated, and thus the potential complaint risks of customers cannot be timely discovered and resolved, triggering customer complaints.

[0005] In a first aspect, embodiments of the present disclosure provide a method for determining complaint risks, the method including: For a current customer, determine a customer emotion influence degree value according to the historically counted customer behaviors at regular intervals, the customer behaviors counted in real time on the current day, a preset customer emotion influence degree bonus rule, and a preset customer emotion influence degree deduction rule; wherein, the customer behaviors at least include one of the following: evaluation behavior, call behavior, and insurance application behavior; the preset customer emotion influence degree bonus rule includes the specified bonus customer behaviors set in advance and the corresponding bonus scores for each specified bonus customer behavior; the preset customer emotion influence degree deduction rule includes the specified deduction customer behaviors set in advance and the corresponding deduction scores for each specified deduction customer behavior; Determine a target emotion value corresponding to the current customer according to the customer emotion base score set in advance for the current customer and the determined customer emotion influence degree value; Determine the complaint risk level of the current customer according to the target emotion value.

[0006] In a second aspect, embodiments of the present disclosure provide a device for determining complaint risks, the device including: A first determination module, configured to determine a customer emotion influence degree value for a current customer according to the historically statistically customer behaviors counted at regular intervals, the customer behaviors statistically in real time on the current day, a preset customer emotion influence degree bonus rule, and a preset customer emotion influence degree deduction rule; wherein the customer behaviors include at least one of the following: evaluation behavior, call behavior, and insurance application behavior; the preset customer emotion influence degree bonus rule includes preset specified bonus customer behaviors and the corresponding bonus scores for each specified bonus customer behavior; the preset customer emotion influence degree deduction rule includes preset specified deduction customer behaviors and the corresponding deduction scores for each specified deduction customer behavior; A second determination module, configured to determine a target emotion value corresponding to the current customer according to the customer emotion base score preset for the current customer and the determined customer emotion influence degree value; A third determination module, configured to determine a complaint risk level of the current customer according to the target emotion value.

[0007] In a third aspect, an embodiment of the present disclosure provides a device for determining a complaint risk, including: a processor; and a memory configured to store computer-executable instructions, and when the computer-executable instructions are executed, the processor implements the steps of the method described in the first aspect above.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the method described in the first aspect above are implemented.

[0009] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0010] The above at least one technical solution provided by the embodiments of the present invention can achieve the following technical effects: In the embodiments of the present invention, for a current customer, the customer emotion influence degree value can be determined according to the historically statistically customer behaviors counted at regular intervals, the customer behaviors statistically in real time on the current day, a preset customer emotion influence degree bonus rule, and a preset customer emotion influence degree deduction rule. Wherein, the customer behaviors may include evaluation behavior, call behavior, and insurance application behavior. The preset customer emotion influence degree bonus rule and deduction rule respectively include preset specified bonus customer behaviors and specified deduction customer behaviors, and the corresponding bonus scores and deduction scores. After determining the customer emotion influence degree value, the target emotion value corresponding to the current customer can be determined according to the customer emotion base score preset for the current customer and the determined customer emotion influence degree value, so as to determine the complaint risk level of the current customer according to the target emotion value.

[0011] Embodiments of the present invention can determine the customer emotion influence degree value by integrating the historical customer behaviors statistically timed and the current-day customer behaviors statistically in real time, determine the target emotion value by combining with the preset customer emotion base score according to the preset plus and minus rules covering various customer behaviors, and then determine the complaint risk level. Therefore, embodiments of the present invention can comprehensively consider various types of customer behaviors in history and at present to comprehensively, dynamically and accurately evaluate customer emotions, so as to timely discover potential customer complaint risks, take corresponding measures in time, effectively reduce customer complaints, optimize the service process, improve the overall service level and customer satisfaction, and effectively solve the problem in related technologies that due to mainly relying on the subjective judgment of seat personnel on customer emotions, it is impossible to accurately evaluate customer emotions, and thus it is impossible to timely discover and resolve potential customer complaint risks, resulting in customer complaints. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in one or more embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings. Figure 1 It is a schematic flowchart of a method for determining complaint risk provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the module composition of a device 200 for determining complaint risk provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the hardware structure of a device for determining complaint risk provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of the present disclosure, to make the purpose, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in combination with the specific embodiments and corresponding drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0014] The following will detail the technical solutions provided by each embodiment of the present invention in combination with the drawings.

[0015] Please refer to Figure 1 , Figure 1A flowchart of a method for determining complaint risk provided by an embodiment of the present invention is shown as Figure 1 follows. The method includes the following steps: Step 102: For the current customer, determine the customer emotion influence degree value according to the regularly counted historical customer behaviors, the contemporaneously counted same-day customer behaviors, the preset customer emotion influence degree bonus rules, and the preset customer emotion influence degree deduction rules. Among them, the customer behaviors include at least one of the following: evaluation behavior, call behavior, and insurance application behavior. The preset customer emotion influence degree bonus rules include the designated bonus customer behaviors set in advance and the corresponding bonus scores for each designated bonus customer behavior. The preset customer emotion influence degree deduction rules include the designated deduction customer behaviors set in advance and the corresponding deduction scores for each designated deduction customer behavior.

[0016] Step 104: Determine the target emotion value corresponding to the current customer according to the customer emotion base score set in advance for the current customer and the determined customer emotion influence degree value.

[0017] Step 106: Determine the complaint risk level of the current customer according to the target emotion value.

[0018] In an embodiment of the present invention, when a customer accesses the customer service seat, the emotion of the current customer can be evaluated to judge the complaint risk of the customer according to the emotion evaluation result.

[0019] When evaluating the emotion of the current customer, the historical customer behaviors of the current customer can be obtained according to the customer information of the current customer, such as the customer name, customer mobile phone number, customer identity identifier, such as ID card, etc., and the obtained historical customer behaviors are regularly counted. According to the regularly counted historical customer behaviors, the contemporaneously counted same-day customer behaviors, the preset customer emotion influence degree bonus rules, and the preset customer emotion influence degree deduction rules, the customer emotion influence degree value is determined. Among them, the customer behaviors include at least one of the following: evaluation behavior, call behavior, and insurance application behavior.

[0020] In an embodiment of the present invention, based on the principle that customer emotion is the positive and negative feedback on the historical service results of the insurance company, the customer emotion influence degree bonus items and the customer emotion influence degree deduction items can be formed according to the key events that can trigger positive and negative feedbacks frequently occurring between the insurance company and the customer. These addition and deduction items can be obtained by regularly counting the behavior of the existing customers (i.e., historical customer behaviors) and contemporaneously obtaining the behavior of the incremental customers (i.e., same-day customer behaviors).

[0021] In one embodiment, a bonus rule for the influence degree of customer emotion can be preset. The preset bonus rule for the influence degree of customer emotion can include presetting specified bonus-eligible customer behaviors and the corresponding bonus scores for each specified bonus-eligible customer behavior. The corresponding bonus scores for different specified bonus-eligible customer behaviors can be the same or different. The bonus score corresponding to a specified bonus-eligible customer behavior is a positive number. A bonus-eligible customer behavior refers to a customer behavior that can represent the positive emotion of a customer.

[0022] In one example, the preset specified bonus-eligible customer behaviors can include at least one of the following: The customer has no complaints within a specified time period. For example, the customer has no complaints within 6 months; The customer has a specified insurance purchase behavior within a specified time period. For example, the customer has a continuous insurance purchase behavior within 2 years; The customer has no regulatory complaints within a specified time period. For example, the customer has no regulatory complaints within 1 year; The customer has no negative NPS (Net Promoter Score) satisfaction evaluation within a specified time period. For example, the customer has no negative NPS satisfaction evaluation within 1 year; The customer has a specified positive evaluation behavior on the same day. For example, the customer has a positive satisfaction evaluation after a call on the same day, such as very satisfied, etc.; The customer has a specified positive call behavior on the same day. For example, the tone of the customer's call on the same day represents that the customer's emotion on the same day is a positive emotion, such as happy, etc.

[0023] In this example, for the specified bonus-eligible customer behaviors within a specified time period, a timing statistic method can be used to obtain them; while for the specified bonus-eligible customer behaviors on the same day, a real-time acquisition method can be used to obtain them.

[0024] In this example, different bonus scores can be set for different specified bonus-eligible customer behaviors. Generally, the more a specified bonus-eligible customer behavior can represent the positive emotion of a customer, the higher the corresponding bonus score. For example, the bonus score corresponding to the customer having no complaints within 6 months can be higher than the bonus score corresponding to the customer having a specified positive call behavior on the same day. In addition, the more a specified bonus-eligible customer behavior can represent the customer's recognition of the product, the higher the corresponding bonus score. For example, the bonus score corresponding to the customer having a continuous insurance purchase within 2 years can be higher than the bonus score corresponding to the customer having no complaints within 6 months. Therefore, when the bonus score corresponding to the customer having a continuous insurance purchase within 2 years is 10, the bonus score corresponding to the customer having no complaints within 6 months can be 5, and the bonus score corresponding to the customer having a specified positive call behavior on the same day can be 2.

[0025] In one embodiment, a deduction rule for the impact of customer sentiment can be preset. The preset deduction rule for the impact of customer sentiment may include presetting specified customer behavior for deduction and the corresponding deduction scores for each specified customer behavior for deduction. The deduction scores corresponding to different specified customer behaviors for deduction may be the same or different. The deduction score corresponding to the specified customer behavior for deduction is negative. The customer behavior for deduction refers to the customer behavior that can represent the negative sentiment of the customer.

[0026] In one example, the preset specified customer behavior for deduction may at least include one of the following: the customer has more than a specified number of complaints within a specified time period and more than a specified number of incoming call times. For example, the customer has more than 2 complaints within 1 month and the incoming call times exceed 10 times; the customer has more than a specified number of complaints within a specified time period and each return visit evaluation is unsatisfactory. For example, the customer has more than 2 complaints within 3 months and each return visit evaluation is unsatisfactory, where the return visit may include daily return visits and return visits for complaints; the customer has more than a specified number of regulatory complaints within a specified time period. For example, the customer has more than 2 regulatory complaints within 3 months; the customer has more than a specified number of negative NPS satisfaction evaluations within a specified time period. For example, the customer has more than 2 negative NPS satisfaction evaluations within 6 months; the customer has more than a specified number of incoming calls on the same day. For example, the customer has more than 3 incoming calls on the same day; the customer has specified negative call behaviors on the same day, where the specified negative call behaviors may include behaviors actively made by the customer during the call, such as the customer actively interrupting the other party; it may also include the customer's tone, intonation, and call content that can represent the customer's sentiment; the customer has specified negative evaluation behaviors on the same day. For example, the customer has a negative satisfaction rating after the call on the same day, such as unsatisfactory, etc.

[0027] In this example, for the specified customer behavior for deduction within a specified time period, a timed statistical method can be used to obtain it; while for the specified customer behavior for deduction on the same day, a real-time acquisition method can be used to obtain it.

[0028] In this example, different deduction scores can be set for different specified customer behaviors that result in score deductions. Generally, the higher the absolute value of the deduction score corresponding to a specified customer behavior that can better reflect the customer's negative emotions. For example, the absolute value of the deduction score corresponding to a customer having more than 2 complaints and more than 10 calls within 1 month can be higher than the absolute value of the deduction score corresponding to a customer having more than 2 complaints and all return visit evaluations being unsatisfactory within 3 months. In addition, since previous customer behaviors that result in score deductions can leave a bad impression on the customer and are more likely to trigger the customer's negative emotions, the absolute value of the deduction score corresponding to the historical specified customer behaviors that are regularly counted can be higher than the absolute value of the deduction score corresponding to the specified customer behaviors on the current day obtained in real time. For example, the absolute value of the deduction score corresponding to a customer having more than 2 complaints and all return visit evaluations being unsatisfactory within 3 months can be higher than the absolute value of the deduction score corresponding to a customer having a specified negative evaluation behavior on the current day. Therefore, when the deduction score corresponding to a customer having more than 2 complaints and more than 10 calls within 1 month is -15, the deduction score corresponding to a customer having more than 2 complaints and all return visit evaluations being unsatisfactory within 3 months can be -12, and the deduction score corresponding to a customer having a specified negative evaluation behavior on the current day can be -2.

[0029] In an embodiment of the present invention, the value of the customer emotion impact degree addition score can be determined according to the historical evaluation behaviors and insurance application behaviors counted regularly, the evaluation behaviors and call behaviors on the current day counted in real time, and the preset customer emotion impact degree addition rule. And the original value of the customer emotion impact degree deduction score can be determined according to the historical evaluation behaviors counted regularly, the call behaviors and evaluation behaviors on the current day counted in real time, and the preset customer emotion impact degree deduction rule. Considering that a good user experience will leave a good impression in the customer's mind, thereby enhancing the customer's tolerance for the company's services, while a bad user experience will deepen the customer's prejudice against the company and reduce the tolerance level during subsequent service processes. Therefore, the enhancement of negative emotions is more crucial for the impact on customer emotions. So, in order to more reasonably measure the customer's potential emotional state, a negative emotion enhancement coefficient is introduced to amplify the impact degree of the customer emotion impact degree deduction item, making the data more in line with the actual situation.

[0030] Therefore, in the embodiment of the present invention, the negative emotion enhancement coefficient can be determined according to the historical evaluation behaviors counted regularly and the preset negative emotion enhancement rule. Among them, the preset negative emotion enhancement rule can include the pre-set specified enhanced negative evaluation behaviors and the corresponding negative emotion enhancement coefficient values for each specified enhanced negative evaluation behavior. The specified enhanced negative evaluation behaviors can include having more than a specified number of complaints or regulatory complaints within a specified time period.

[0031] In one example, specifying an enhanced negative evaluation behavior can be that the customer has more than 5 complaints or more than 3 regulatory complaints within 3 months. Different negative emotion enhancement coefficient values can be set for different specified enhanced negative evaluation behaviors in this example. Among them, the greater the specified enhanced negative evaluation behavior that can increase the customer's negative emotion, the larger the corresponding negative emotion enhancement coefficient value. For example, the negative emotion enhancement coefficient value corresponding to the customer having more than 3 complaints or more than 2 regulatory complaints within 1 month can be greater than the negative emotion enhancement coefficient value corresponding to the customer having more than 5 complaints or more than 3 regulatory complaints within 3 months. When the negative emotion enhancement coefficient value corresponding to the customer having more than 5 complaints or more than 3 regulatory complaints within 3 months is 1.3, the negative emotion enhancement coefficient value corresponding to the customer having more than 3 complaints or more than 2 regulatory complaints within 1 month can be 1.8.

[0032] In another embodiment of the present invention, in order to more reasonably measure the potential emotional state of the customer, a negative emotion attenuation coefficient is also introduced to reduce the influence degree of the customer emotion impact reduction item, making the data closer to the actual situation.

[0033] In the embodiment of the present invention, the negative emotion attenuation coefficient can be determined according to the regularly counted historical evaluation behaviors and call behaviors, as well as the preset negative emotion attenuation rules. The preset negative emotion attenuation rules can include the specified attenuation negative evaluation behaviors set in advance, and the corresponding negative emotion attenuation coefficient values for each specified attenuation negative evaluation behavior. The specified attenuation negative evaluation behaviors can include no complaints within the specified first time period, no calls within the second time period, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory.

[0034] In one example, the specified attenuation negative evaluation behavior can be that the customer has no complaints within 3 months, no calls within 1 month, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory. Different negative emotion attenuation coefficient values can be set for different specified attenuation negative evaluation behaviors in this example. Among them, the greater the specified attenuation negative evaluation behavior that can reduce the customer's negative emotion, the larger the corresponding negative emotion attenuation coefficient value. For example, the negative emotion attenuation coefficient value corresponding to the customer having no complaints within 3 months, no calls within 1 month, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory can be greater than the negative emotion attenuation coefficient value corresponding to the customer having no complaints within 6 months, no calls within 3 months, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory. When the negative emotion attenuation coefficient value corresponding to the customer having no complaints within 3 months, no calls within 1 month, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory is 0.8, the negative emotion attenuation coefficient value corresponding to the customer having no complaints within 6 months, no calls within 3 months, all historical complaints have been successfully resolved and the return visit evaluation is satisfactory can be 0.7.

[0035] After determining the negative emotion enhancement coefficient and the negative emotion attenuation coefficient, the target customer emotion impact degree subtraction value can be determined based on the negative emotion enhancement coefficient, the negative emotion attenuation coefficient, and the above-mentioned original customer emotion impact degree subtraction value. Then, based on the target customer emotion impact degree subtraction value and the determined customer emotion impact degree addition value, the customer emotion impact degree value can be determined.

[0036] After determining the customer emotion impact degree value, the target emotion value corresponding to the current customer can be determined based on the pre-set customer emotion base score for the current customer and the determined customer emotion impact degree value.

[0037] In an embodiment of the present invention, considering that different customers have different business values for the company, a key customer coefficient KUC is introduced. This coefficient can represent the importance of the customer. The more important the customer is, the higher the sensitivity of the company to evaluate the customer's emotion, that is, for key customers, the company attaches more importance to the emotion impact degree of such customers.

[0038] In an example, the key customer coefficient can be divided into four levels: high (KUC can be 1.5), medium (KUC can be 1.2), low (KUC can be 1), and negative (KUC can be 0.8).

[0039] When determining the target emotion value corresponding to the current customer based on the pre-set customer emotion base score for the current customer and the determined customer emotion impact degree value, the pre-set key customer coefficient corresponding to the current customer can be obtained first. Then, based on the pre-set customer emotion base score for the current customer, the pre-set key customer coefficient corresponding to the current customer, and the determined customer emotion impact degree value, the target emotion value corresponding to the current customer can be determined.

[0040] In an example, the key customer coefficient KUC, the customer emotion impact degree addition value, the original customer emotion impact degree subtraction value, the negative emotion enhancement coefficient NNR, and the negative emotion attenuation coefficient NDR corresponding to the current customer can be obtained according to the above embodiment. Then the target emotion value can be: Target emotion value = customer emotion base score / KUC + customer emotion impact degree addition value + original customer emotion impact degree subtraction value × NNR × NDR In this example, the same customer emotion base score can be set for all customers. For example, the customer emotion base score can be set to 60.

[0041] After determining the target emotion value, the complaint risk level of the current customer can be determined based on the target emotion value. Among them, the lower the target emotion value is, the more negative the customer emotion is, and the worse the emotional stability of the customer is. At this time, the complaint risk level of the current customer is higher.

[0042] In an embodiment of the present invention, different complaint risk levels can be set for different target emotion values. For example, when the target emotion value is from 50 to 70 (including 50 but not including 70), the complaint risk level is set as medium; when the target emotion value is less than 50, the complaint risk level is set as high; when the target emotion value is not less than 70, the complaint risk level is set as low.

[0043] When the determined complaint risk level is high, it can be determined that there is a complaint risk. At this time, a customer complaint response mechanism can be triggered to resolve the customer's negative emotion to a certain extent and avoid customer complaints; when the determined complaint risk levels are medium and low, it can be determined that there is no complaint risk.

[0044] In an embodiment of the present invention, for the current customer, the customer emotion influence degree value can be determined according to the historically statistically timed customer behaviors, the currently statistically timed customer behaviors on the same day, as well as a preset customer emotion influence degree bonus rule and a preset customer emotion influence degree deduction rule. Among them, customer behaviors can include evaluation behaviors, call behaviors, and insurance application behaviors. The preset customer emotion influence degree bonus rule and deduction rule respectively include preset specified bonus customer behaviors and specified deduction customer behaviors, as well as corresponding bonus scores and deduction scores. After determining the customer emotion influence degree value, the target emotion value corresponding to the current customer can be determined according to the customer emotion base score preset for the current customer and the determined customer emotion influence degree value, so as to determine the complaint risk level of the current customer according to the target emotion value.

[0045] The embodiment of the present invention can integrate the historically statistically timed customer behaviors and the currently statistically timed customer behaviors on the same day, determine the customer emotion influence degree value according to the preset bonus and deduction rules covering various customer behaviors, then combine with the preset customer emotion base score to obtain the target emotion value, and further determine the complaint risk level. Therefore, the embodiment of the present invention can comprehensively evaluate the customer emotion by comprehensively considering various types of customer behaviors in history and at present, so as to timely discover the potential complaint risks of customers, take response measures in time, effectively reduce customer complaints, optimize the service process, improve the overall service level and customer satisfaction, and effectively solve the problem in the related technology that due to mainly relying on the subjective judgment of the seat personnel on the customer emotion, the customer emotion cannot be accurately evaluated, and thus the potential complaint risks of customers cannot be timely discovered and resolved, resulting in customer complaints.

[0046] Corresponding to the above method for determining the complaint risk, the embodiment of the present invention further provides a device for determining the complaint risk. Figure 2 It is a schematic diagram of the module composition of the device 200 for determining the complaint risk provided by the embodiment of the present invention, as Figure 2 shown. The device 200 for determining the complaint risk includes: The first determination module 201 is configured to determine the customer sentiment impact value for the current customer according to the historically timed customer behaviors, the current-day customer behaviors statistically in real time, the preset customer sentiment impact addition rules, and the preset customer sentiment impact subtraction rules; wherein, the customer behaviors include at least one of the following: evaluation behavior, call behavior, and insurance application behavior; the preset customer sentiment impact addition rules include the designated addition customer behaviors set in advance and the corresponding addition scores for each designated addition customer behavior; the preset customer sentiment impact subtraction rules include the designated subtraction customer behaviors set in advance and the corresponding subtraction scores for each designated subtraction customer behavior; The second determination module 202 is configured to determine the target sentiment value corresponding to the current customer according to the customer sentiment base score preset for the current customer and the determined customer sentiment impact value; The third determination module 203 is configured to determine the complaint risk level of the current customer according to the target sentiment value.

[0047] Optionally, the preset designated subtraction customer behaviors include at least one of the following: The customer has more than a specified number of complaints and more than a specified number of call times within a specified time period; The customer has more than a specified number of complaints and each return visit evaluation is unsatisfactory within a specified time period; The customer has more than a specified number of regulatory complaints within a specified time period; The customer has more than a specified number of negative Net Promoter Score (NPS) satisfaction evaluations within a specified time period; The customer has more than a specified number of call times on the current day; The customer has specified negative call behaviors on the current day; The customer has specified negative evaluation behaviors on the current day.

[0048] Optionally, the preset designated addition customer behaviors include at least one of the following: The customer has no complaints within a specified time period; The customer has specified insurance application behaviors within a specified time period; The customer has no regulatory complaints within a specified time period; The customer has no negative NPS satisfaction evaluations within a specified time period; The customer has specified positive evaluation behaviors on the current day; The customer has specified positive call behaviors on the current day.

[0049] Optionally, there is one or more candidate claim information parsing sub-rules, and the candidate claim parsing sub-rules corresponding to claim materials of different image types are the same, or the candidate claim parsing sub-rules corresponding to claim materials of different image types are different; The first determination module 201 is configured to: Determine the added value of customer sentiment impact according to the historically counted evaluation behaviors and insurance purchase behaviors, the currently counted same-day evaluation behaviors and same-day call behaviors, and a preset customer sentiment impact degree addition rule; Determine the original subtracted value of customer sentiment impact according to the historically counted evaluation behaviors, the currently counted same-day call behaviors and evaluation behaviors, and a preset customer sentiment impact degree subtraction rule; Determine a negative sentiment enhancement coefficient according to the historically counted evaluation behaviors and a preset negative sentiment enhancement rule; the preset negative sentiment enhancement rule includes a preset specified enhanced negative evaluation behavior and a corresponding negative sentiment enhancement coefficient value for each specified enhanced negative evaluation behavior; the specified enhanced negative evaluation behavior includes having more than a specified number of complaints or regulatory complaints within a specified time period; Determine the target subtracted value of customer sentiment impact according to the negative sentiment enhancement coefficient and the original subtracted value of customer sentiment impact; Determine the customer sentiment impact degree value according to the added value of customer sentiment impact and the target subtracted value of customer sentiment impact.

[0050] Optionally, the first module 201 is configured to: Determine a negative sentiment attenuation coefficient according to the historically counted evaluation behaviors and call behaviors and a preset negative sentiment attenuation rule; the preset negative sentiment attenuation rule includes a preset specified attenuated negative evaluation behavior and a corresponding negative sentiment attenuation coefficient value for each specified attenuated negative evaluation behavior; the specified attenuated negative evaluation behavior includes having no complaints within a specified first time period, no incoming calls within a second time period, all historical complaints being successfully resolved and the return visit evaluation being satisfactory; Determine the target subtracted value of customer sentiment impact according to the negative sentiment enhancement coefficient, the negative sentiment attenuation coefficient, and the original subtracted value of customer sentiment impact.

[0051] Optionally, the second determination module 202 is configured to: Obtain a preset key customer coefficient corresponding to the current customer; the key customer coefficient is used to identify the importance of the customer; Determine the target sentiment value corresponding to the current customer according to the customer sentiment base score preset for the current customer, the preset key customer coefficient corresponding to the current customer, and the determined customer sentiment impact degree value.

[0052] Based on the historical customer behaviors statistically analyzed at regular intervals and the same-day customer behaviors statistically analyzed in real time, as well as the preset rules for adding points and subtracting points for the impact of customer sentiment, the value of the impact of customer sentiment is determined. Among them, customer behaviors may include evaluation behaviors, call behaviors, and insurance application behaviors. The preset rules for adding points and subtracting points for the impact of customer sentiment respectively include the preset specified customer behaviors for adding points and subtracting points, as well as the corresponding point-adding values and point-subtracting values. After determining the value of the impact of customer sentiment, based on the preset basic sentiment score for the current customer and the determined value of the impact of customer sentiment, the target sentiment value corresponding to the current customer is determined, and based on this target sentiment value, the complaint risk level of the current customer is determined.

[0053] In the embodiment of the present invention, the historical customer behaviors statistically analyzed at regular intervals and the same-day customer behaviors statistically analyzed in real time can be integrated. According to the preset rules for adding and subtracting points covering various customer behaviors, the value of the impact of customer sentiment is determined. Then, in combination with the preset basic sentiment score, the target sentiment value is obtained, and further the complaint risk level is determined. Therefore, the embodiment of the present invention can comprehensively consider various types of customer behaviors in history and at present to comprehensively, dynamically and accurately evaluate customer sentiment, so as to timely discover potential customer complaint risks, take corresponding measures in time, effectively reduce customer complaints, optimize the service process, improve the overall service level and customer satisfaction, and effectively solve the problem in the related technology that due to mainly relying on the subjective judgment of seat personnel on customer sentiment, the customer sentiment cannot be accurately evaluated, and thus the potential complaint risks of customers cannot be timely discovered and resolved, resulting in customer complaints.

[0054] Corresponding to the above method for determining the complaint risk, the embodiment of the present invention further provides a device for determining the complaint risk. Figure 3 It is a schematic diagram of the hardware structure of the device for determining the complaint risk provided by an embodiment of the present invention.

[0055] The device for determining the complaint risk may be the terminal device or server provided in the above embodiment for determining the complaint risk, etc.

[0056] The equipment for determining complaint risks may vary significantly due to different configurations or performances, and may include one or more processors 301 and a memory 302. One or more stored application programs or data may be stored in the memory 302. Among them, the memory 302 may be transient storage or persistent storage. The application programs stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the equipment for determining complaint risks. Further, the processor 301 may be set to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the equipment for determining complaint risks. The equipment for determining complaint risks may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0057] Specifically, in this embodiment, the equipment for determining complaint risks includes a memory and one or more programs, where one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in the equipment for determining complaint risks and is configured to be executed by one or more processors in the above embodiment.

[0058] And the daily customer behaviors of real-time statistics, as well as the preset rules for adding points and subtracting points for the influence degree of customer emotions, to determine the value of the influence degree of customer emotions. Among them, customer behaviors may include evaluation behaviors, call behaviors, and insurance application behaviors. The preset rules for adding points and subtracting points for the influence degree of customer emotions respectively include the preset specified customer behaviors for adding points and subtracting points, as well as the corresponding point-adding values and point-subtracting values. After determining the value of the influence degree of customer emotions, the target emotion value corresponding to the current customer can be determined according to the preset basic emotion value of the current customer and the determined value of the influence degree of customer emotions, so as to determine the complaint risk level of the current customer according to the target emotion value.

[0059] In an embodiment of the present invention, by integrating historical customer behaviors statistically counted at regular intervals and the current day's customer behaviors statistically counted in real time, a customer sentiment impact value can be determined according to preset bonus and deduction rules covering various customer behaviors. Then, combined with a preset basic customer sentiment score, a target sentiment value can be obtained, and further the complaint risk level can be determined. Therefore, the embodiment of the present invention can comprehensively, dynamically and accurately evaluate customer sentiment by comprehensively considering various types of historical and current customer behaviors, so as to timely discover potential customer complaint risks, take corresponding measures in a timely manner, effectively reduce customer complaints, optimize the service process, improve the overall service level and customer satisfaction, and effectively solve the problem in the related art that due to mainly relying on the subjective judgment of seat personnel on customer sentiment, it is impossible to accurately evaluate customer sentiment, and thus it is impossible to timely discover and resolve potential customer complaint risks, resulting in customer complaints.

[0060] Another embodiment of the present disclosure also provides a computer-readable storage medium for storing computer-executable instructions, and the computer-executable instructions, when executed by a processor, implement the above process.

[0061] The storage medium in the embodiment of the present disclosure can implement each process of the above-described method embodiment for determining complaint risk and achieve the same effects and functions, which will not be repeated here.

[0062] Another embodiment of the present disclosure also provides a computer program product, the computer program product includes a computer program, and the computer program, when executed by a processor, implements the above process.

[0063] The computer program product in the embodiment of the present disclosure can implement each process of the above-described method embodiment for determining complaint risk and achieve the same effects and functions, which will not be repeated here.

[0064] In each embodiment of the present disclosure, the computer-readable storage medium includes a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk or an optical disc, etc.

[0065] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structures of diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method flows into the hardware circuits. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logical function is determined by a customer programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one type of HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0066] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0067] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0068] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of the present disclosure, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0069] Those skilled in the art should understand that one or more embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0070] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0071] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0073] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, commodity or device including the said element.

[0074] One or more embodiments of the present disclosure may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present disclosure may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0075] Each embodiment in the present disclosure is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For related parts, reference can be made to the description of the method embodiments.

[0076] The above description is only for the embodiments of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, various changes and modifications can be made to the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included within the scope of the claims of the present disclosure.

Claims

1. A method for determining complaint risk, characterized in that: The method comprises: For the current customer, the customer emotion impact value is determined based on the historical customer behaviors collected at regular intervals and the customer behaviors collected on the same day collected in real time, as well as the preset customer emotion impact score addition rule and the preset customer emotion impact score reduction rule; wherein the customer behaviors include at least one of the following: evaluation behaviors, call behaviors, and insurance behaviors; the preset customer emotion impact score addition rule includes preset designated customer behaviors that add points, and the score addition value corresponding to each designated customer behavior that adds points; the preset customer emotion impact score reduction rule includes preset designated customer behaviors that reduce points, and the score reduction value corresponding to each designated customer behavior that reduces points; Determine a target emotion value corresponding to the current customer based on a customer emotion basic score pre-set for the current customer and the determined customer emotion influence value; The complaint risk level of the current customer is determined based on the target sentiment value.

2. The method according to claim 1, characterized in that The pre-set designated customer behavior for deducting points includes at least one of the following: The customer has more than a specified number of complaints and more than a specified number of calls within a specified time period; The customer has made more than a specified number of complaints within a specified time period, and each follow-up evaluation is unsatisfactory; The customer has more than a specified number of regulatory complaints within a specified time period; The customer has more than a specified number of negative Net Promoter Score (NPS) satisfaction reviews within a specified time period; The customer has called more than the specified number of times on the day; The customer has specified negative calling behavior on that day; The customer has specified negative evaluation behavior on that day.

3. The method according to claim 1, characterized in that The pre-set designated bonus customer behavior includes at least one of the following: The customer has no complaints within a specified period of time; The customer has a specified insurance behavior within a specified time period; The client has no regulatory complaints within a specified time period; The customer has no negative NPS satisfaction ratings within the specified time period; The customer has specified positive evaluation behavior on that day; The customer has a designated positive call behavior on that day.

4. The method according to claim 1, characterized in that: The determining of the customer emotion impact value according to the historical customer behaviors counted at regular intervals and the customer behaviors counted on the same day in real time, as well as the preset customer emotion impact score adding rule and the preset customer emotion impact score subtracting rule, includes: Determine the customer emotion impact score numerator based on the historical evaluation and insurance behavior collected in timed statistics, the evaluation and call behavior collected in real time on the same day, and the preset customer emotion impact score rules; Determine the original customer emotion impact deduction numerator based on the historical evaluation behaviors collected at regular intervals, the call behaviors and evaluation behaviors collected on the same day collected in real time, and the preset customer emotion impact deduction rules; Determine the negative emotion enhancement coefficient based on the historical evaluation behaviors collected at regular intervals and the preset negative emotion enhancement rules; the preset negative emotion enhancement rules include preset designated enhanced negative evaluation behaviors and the negative emotion enhancement coefficient values ​​corresponding to each designated enhanced negative evaluation behavior; the designated enhanced negative evaluation behaviors include complaints or regulatory complaints exceeding a specified number within a specified time period; Determine the target customer emotion impact degree minus numerator value according to the negative emotion enhancement coefficient and the original customer emotion impact degree minus numerator value; The customer emotion impact value is determined according to the customer emotion impact plus numerator value and the target customer emotion impact minus numerator value.

5. The method according to claim 1, characterized in that The step of determining the target customer emotion impact deduction numerator value according to the negative emotion enhancement coefficient and the original customer emotion impact deduction numerator value comprises: Determine the negative emotion attenuation coefficient based on the historical evaluation behaviors and call behaviors collected at regular intervals, and the preset negative emotion attenuation rules; the preset negative emotion attenuation rules include pre-set designated attenuation negative evaluation behaviors, and the negative emotion attenuation coefficient values ​​corresponding to each designated attenuation negative evaluation behavior; the designated attenuation negative evaluation behaviors include no complaints within a specified first time period, no calls within a second time period, all historical complaints are successfully resolved, and the follow-up evaluation is satisfactory; The target customer emotion impact degree minus numerator value is determined according to the negative emotion enhancement coefficient, the negative emotion attenuation coefficient, and the original customer emotion impact degree minus numerator value.

6. The method according to any one of claims 1 to 5, characterized in that: Determining the target emotion value corresponding to the current customer according to the customer emotion basic score pre-set for the current customer and the determined customer emotion influence value includes: Obtaining a preset key customer coefficient corresponding to the current customer; the key customer coefficient is used to identify the importance of the customer; The target emotion value corresponding to the current customer is determined according to the customer emotion basic score pre-set for the current customer, the preset key customer coefficient corresponding to the current customer, and the determined customer emotion influence value.

7. A device for determining complaint risk, characterized in that: The device comprises: The first determination module is used to determine the customer emotion impact value for the current customer based on the historical customer behaviors collected by timed statistics and the customer behaviors collected by real-time statistics on the day, as well as the preset customer emotion impact score addition rule and the preset customer emotion impact score reduction rule; wherein the customer behaviors include at least one of the following: evaluation behaviors, call behaviors, and insurance behaviors; the preset customer emotion impact score addition rule includes preset designated customer behaviors that add points, and the score addition value corresponding to each designated customer behavior that adds points; the preset customer emotion impact score reduction rule includes preset designated customer behaviors that reduce points, and the score reduction value corresponding to each designated customer behavior that reduces points; A second determination module is used to determine a target emotion value corresponding to the current customer based on a customer emotion basic score pre-set for the current customer and the determined customer emotion influence value; The third determination module is used to determine the complaint risk level of the current customer according to the target emotion value.

8. A device for determining complaint risk, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images