CN110349039B - Complaint risk assessment method, system, computer device and readable storage medium - Google Patents
Complaint risk assessment method, system, computer device and readable storage medium Download PDFInfo
- Publication number
- CN110349039B CN110349039B CN201910511934.4A CN201910511934A CN110349039B CN 110349039 B CN110349039 B CN 110349039B CN 201910511934 A CN201910511934 A CN 201910511934A CN 110349039 B CN110349039 B CN 110349039B
- Authority
- CN
- China
- Prior art keywords
- data
- complaint
- customer
- policy
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 238000012795 verification Methods 0.000 claims description 55
- 238000012549 training Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims 2
- 239000000758 substrate Substances 0.000 claims 1
- 238000013459 approach Methods 0.000 abstract description 2
- 238000003066 decision tree Methods 0.000 description 6
- 238000007477 logistic regression Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention provides a complaint risk assessment method based on big data, which comprises the following steps: receiving customer complaint data; judging whether the customer complaint data comprises basic information of a policy or not; if the customer complaint data comprises the basic information of the insurance policy, acquiring the associated data of the target case aimed at by the customer complaint data according to the basic information of the insurance policy; inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model; judging whether the complaint risk coefficient is larger than a preset threshold value or not; and determining to send the customer complaint data to the first electronic equipment or the second electronic equipment according to the complaint risk coefficient. The complaint risk of the customer complaint event can be evaluated through the associated data of different dimensions, and the solving approach is determined in advance according to the evaluation result.
Description
Technical Field
The embodiment of the invention relates to the field of computer data processing, in particular to a complaint risk assessment method, a system, computer equipment and a computer readable storage medium based on big data.
Background
With the increasing awareness of people's insurance, commercial insurance has become an important component of current social security systems. The number of policies for a portion of the insurance organization is on the order of tens of millions based on the referenceable data. In the process of the policy transaction, the situation that some service periods (such as new contracts, security, renewal, claims settlement and other service periods) are not enough can be avoided, so that customer complaints are caused.
The complaint causes of these complaint events are different from the content descriptions, and in order to cope with these complaint events, the current solution is: 1. a large number of seat personnel or mediation specialists are hired, and the complaint events are solved through a manual way; 2. these complaint events are addressed by intelligent voice robots.
It is easy to understand that the customer complaint event is solved by a large number of seat personnel or mediation specialists, and the labor cost is increased; the customer complaint event is solved by the intelligent voice robot, which may cause further deterioration of the complaint event, and further makes the customer complaint to an administrative department, such as complaint to China insurance supervision committee. Therefore, how to evaluate the complaint risk of each customer complaint event and determine the solving path in advance according to the evaluation result is one of the technical problems to be solved at present.
Disclosure of Invention
Accordingly, an object of the embodiments of the present invention is to provide a big data-based complaint risk assessment method, system, computer device and computer readable storage medium, which can determine a resolution approach in advance for each customer complaint event complaint risk according to the assessment result.
In order to achieve the above object, the embodiment of the present invention provides a complaint risk assessment method based on big data, including the following steps:
receiving customer complaint data;
judging whether the customer complaint data comprises the basic information of a policy, wherein the basic information of the policy comprises a policy number;
if the customer complaint data comprises the policy basic information, acquiring associated data of a target case aimed at by the customer complaint data according to the policy basic information, wherein the associated data comprises service personnel data, customer data, policy data and service data;
inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model;
judging whether the complaint risk coefficient is larger than a preset threshold value or not;
if the complaint risk coefficient is larger than the preset threshold value, the customer complaint data is sent to first electronic equipment; and
And if the complaint risk coefficient is not greater than the preset threshold value, sending the customer complaint data to second electronic equipment.
Preferably, if the customer complaint data includes the basic information of the policy, the step of basically acquiring the associated data of the target case for the customer complaint data according to the policy includes:
the method comprises the steps that a policy service source of a target case aimed at by customer complaint data is basically obtained according to the policy, and the policy service source is used for judging whether the customer complaint data is sent to the first electronic equipment or not;
if the policy service source of the target case is the target source, sending the customer complaint data to first electronic equipment; and
And if the policy service source of the target case is not the target source, basically acquiring the associated data of the target case aiming at the customer complaint data according to the policy.
Preferably, if the policy service source of the target case is not a target source, the step of basically acquiring the associated data of the target case for the customer complaint data according to the policy includes:
matching the customer complaint data with a plurality of target character strings;
When the customer complaint data is matched with at least one target character string in the target character strings, sending the customer complaint data to first electronic equipment;
when the customer complaint data is not matched with any one of the target character strings, the associated data of the target case aimed at by the customer complaint data is basically obtained according to the policy.
Preferably, the step of matching the customer complaint data with a plurality of target strings includes:
detecting whether a target character string in the customer complaint data is a target character string or not according to a rule character string;
the regular strings are configured according to a string set and regular expressions.
Preferably, the method further comprises:
obtaining a sample data set, wherein the sample data set comprises a first sample data set of high-risk customer complaints and a second sample data set of non-high-risk customer complaints;
analyzing correlation coefficients between each feature data in the sample data set and high-risk customer complaint events;
selecting a plurality of feature data with the correlation coefficient higher than a preset threshold according to the correlation coefficient between each feature data and the high-risk customer complaint event;
Judging whether the plurality of feature data comprise one or more policy service sources; and
If the plurality of feature data includes one or more policy service sources, the one or more policy service sources are determined to be the target sources.
Preferably, before the step of receiving customer complaint data, the method further includes:
acquiring a training data set of customer complaints, wherein the training data set comprises a plurality of case risk data corresponding to a plurality of complaint sample cases, and each case risk data comprises salesman data, customer data, policy data and business data; and
And training the complaint risk assessment model based on the training data set to obtain a trained complaint risk assessment model.
Preferably, between the step of obtaining the trained complaint risk assessment model and the step of receiving customer complaint data, there is included:
acquiring a first verification data set of high-risk customer complaints generated in a plurality of time intervals and a second verification data set of non-high-risk customer complaints;
mixing a plurality of verification samples of the first verification data set and a plurality of verification samples in the second verification data to obtain a cross-time verification set;
Inputting a plurality of verification data in the cross-time verification set into the complaint risk assessment model to obtain a complaint risk assessment result output by the complaint risk assessment model;
calculating the evaluation accuracy and stability coefficient of the complaint risk evaluation model according to the complaint risk evaluation result of the complaint risk evaluation model;
and determining whether the complaint risk assessment model is used for assessing the customer complaint data according to the assessment accuracy and the stability coefficient.
In order to achieve the above object, an embodiment of the present invention further provides a complaint risk assessment system based on big data, including:
the receiving module is used for receiving customer complaint data;
the first judging module is used for judging whether the customer complaint data comprises the basic information of the insurance policy or not, wherein the basic information of the insurance policy comprises the insurance policy number;
the first acquisition module is used for acquiring associated data of a target case for the customer complaint data according to the policy basic information if the customer complaint data comprises the policy basic information, wherein the associated data comprises salesman data, customer data, policy data and business data;
the second acquisition module is used for inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model;
The second judging module is used for judging whether the complaint risk coefficient is larger than a preset threshold value or not;
the diversion module is used for sending the customer complaint data to the first electronic equipment if the complaint risk coefficient is larger than the preset threshold value; and sending the customer complaint data to a second electronic device if the complaint risk coefficient is not greater than the preset threshold.
To achieve the above object, an embodiment of the present invention further provides a computer device, a memory of the computer device, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the big data based complaint risk assessment method as described above.
To achieve the above object, an embodiment of the present invention also provides a computer-readable storage medium having stored therein a computer program executable by at least one processor to cause the at least one processor to perform the steps of the big data based complaint risk assessment method as described above.
According to the complaint risk assessment method, system, computer equipment and computer readable storage medium based on big data, which are provided by the embodiment of the invention, the complaint risk of a customer complaint event is assessed through the associated data of the complaint cases by mining, and the solving way is determined in advance according to the assessment result.
Drawings
FIG. 1 is a flowchart of a first embodiment of a big data based complaint risk assessment method according to the present invention.
FIG. 2 is a flowchart of a second embodiment of a big data based complaint risk assessment method of the present invention.
FIG. 3 is a flowchart of a third embodiment of a big data based complaint risk assessment method of the present invention.
FIG. 4 is a block diagram illustrating a fourth embodiment of a big data-based complaint risk assessment system according to the present invention.
Fig. 5 is a schematic diagram of a hardware structure of a fifth embodiment of the computer device of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
The following embodiments will exemplarily describe taking the computer device 2 as an execution subject.
Example 1
Referring to fig. 1, a flowchart of a method for evaluating risk of complaints based on big data according to an embodiment of the present invention is shown. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. Specifically, the following is described.
Step S100, customer complaint data is received.
The customer complaint data includes text data and voice data.
And the text data, such as complaint information submitted by clients through a network complaint platform or complaint information submitted through a complaint mailbox.
The voice data, such as voice complaint information submitted by a customer through a complaint platform supporting voice input, or telephone complaint information. In the case of speech data, speech recognition is performed by the computer device to obtain text information.
Step S102, judging whether the customer complaint data comprises the basic information of the insurance policy, wherein the basic information of the insurance policy comprises the insurance policy number. If yes, go to step S104; otherwise, the process advances to step S110.
The policy basic information may include a policy number, a customer number, etc. The policy number refers to the number of the insurance contract which the insurance company has issued after the insurance applicant successfully applies to the insurance company. The customer number is an identity number configured by the insurer for each customer.
Step S104, obtaining the associated data of the target case for the customer complaint data according to the basic information of the policy. The next step goes to step S108.
For example, according to the policy number or the client number in the policy basic information, the associated data of the target case for which the client complaints case is aimed is searched from the database.
The associated data includes attendant data, customer data, policy data, and business data.
The salesman data refers to relevant information of a salesman transacting the target case, such as sex, age of a business, belonging channel, job level, institution, EPASS examination score, job reference before job entry, marital status, sales habit (number of clients, effective clients, number of insuring clients), commission promotion, product sales data, belonging team, etc.
The client data refers to relevant information of the client of the target case, such as the client gender, age, occupation, complaint records, etc.
The policy data refers to information related to the policy of the target case, such as policy status, policy property, premium, etc.
The business data refers to related information of the business of the target case, such as new contracts, castles, safeguards, claims and the like.
Step S106, inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model.
The complaint risk assessment model may be a logistic regression model, a combination model of a gradient-lifting decision tree and logistic regression, a combination model of a gradient-lifting decision tree and a factoring machine, or other models.
The complaint risk coefficient is used to quantify the degree of reflection of the customer, such as:
complaint risk factors are high, such as: complaint events that may be complaint by the customer to the administrative department;
complaints have low risk factors, such as: the complaint event which can be solved by only communicating the explanation can be caused by misunderstanding caused by asymmetric information.
Step S108, judging whether the complaint risk coefficient is larger than a preset threshold value. If the threshold is greater than the preset threshold, the process proceeds to step S110, otherwise, the process proceeds to step S112.
Step S110, the customer complaint data is sent to the first electronic equipment.
The first electronic device may be a desktop computer, a smart phone, a tablet computer, or a landline phone.
Specifically, the customer complaint data is sent to a desk computer and other devices of the seat personnel or the negotiating expert, and the seat personnel or the negotiating expert is prompted to solve the complaint event.
The target case aimed by the customer complaint data can be configured on a designated mobile phone or telephone, and customer complaints can be directly answered by seat personnel or negotiating specialists. This situation is particularly suitable for complaint scenarios where customers complain by telephone.
And step S112, the customer complaint data is sent to the second electronic equipment.
The second electronic equipment is internally provided with a pre-developed intelligent robot system, and the intelligent robot system is used for replying the customer in the form of voice or characters and the like according to the customer complaint data.
Example two
Referring to fig. 2, a flowchart of a complaint risk assessment method based on big data according to a second embodiment of the present invention is shown. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. Specifically, the following is described.
Step S200, customer complaint data is received.
The customer complaint data includes text data and voice data.
And the text data, such as complaint information submitted by clients through a network complaint platform or complaint information submitted through a complaint mailbox.
The voice data, such as voice complaint information submitted by a customer through a complaint platform supporting voice input, or telephone complaint information. In the case of speech data, speech recognition is performed by the computer device to obtain text information.
Step S202, judging whether the customer complaint data comprises the basic information of the insurance policy, wherein the basic information of the insurance policy comprises the insurance policy number. If yes, go to step S204, otherwise go to step S214.
The policy basic information may include a policy number, a customer number, etc. The policy number refers to the number of the insurance contract which the insurance company has issued after the insurance applicant successfully applies to the insurance company. The customer number is an identity number configured by the insurer for each customer.
Step S204, the policy service source of the target case aimed at by the customer complaint data is basically obtained according to the policy.
The policy service source is configured to determine whether to send the customer complaint data to a first electronic device. The policy service sources include network sales sources, telephone sales sources, salesman face-to-face sales sources, bank insurance sources, and the like.
Step S206, judging whether the policy service source of the target case is a target source. If yes, go to step S214; otherwise, the process advances to step S208.
How to determine which of the policy service sources belong to a target source may be as follows:
first, determining a target source through user definition;
Second, the target source is determined by sample data analysis, specifically as follows:
1.1, acquiring a sample data set, wherein the sample data set comprises a first sample data set of high-risk customer complaints and a second sample data set of non-high-risk customer complaints;
first sample data set of high risk customer complaints: for example, a sample set of multiple samples that are both user-defined and complained to an administrative organization;
a second sample data set of non-high risk customer complaints: for example, a sample set of multiple samples that have not been complained to an administrative organization.
1.2, analyzing correlation coefficients between each characteristic data in the sample data set and high-risk customer complaint events;
the characteristic data is sub-data in the associated data, such as explained by taking gender "male" as an example, and the male ratio of the first sample data set and the male ratio of the second sample data set are counted, if the male ratio of the first sample data set and the male ratio of the second sample data set are approximately the same, the gender correlation is considered to be low, otherwise the gender correlation is considered to be high. The degree of correlation can be quantified by a correlation coefficient, for example, the absolute value of the difference of the duty ratio or the absolute value is taken as the correlation coefficient.
1.3, selecting a plurality of feature data with the correlation coefficient higher than a preset threshold according to the correlation coefficient between each feature data and the high-risk customer complaint event;
1.4, judging whether the plurality of feature data comprise one or more policy service sources;
1.5, if the plurality of feature data includes one or more policy service sources, determining the one or more policy service sources as the target source.
For example, "telemarketing" and "online marketing" are determined as target sources.
It will be understood that if the policy service source queried in step S204 is "telemarketing", it is indicated that the policy source of the target case is the target source.
Step S208, obtaining the associated data of the target case for the customer complaint data according to the basic information of the policy. The next step goes to step S210.
For example, according to the policy number or the client number in the policy basic information, the associated data of the target case for which the client complaints case is aimed is searched from the database.
The associated data includes attendant data, customer data, policy data, and business data.
The salesman data refers to information about a salesman handling the target case, such as sex, age of a business, sales habits, commission proposal, product sales data, affiliated team, etc.
The client data refers to relevant information of the client of the target case, such as the client gender, age, occupation, complaint records, etc.
The policy data refers to information related to the policy of the target case, such as policy status, policy property, premium, etc.
The business data refers to related information of the business of the target case, such as new contracts, castles, safeguards, claims and the like.
Step S210, inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model.
The complaint risk assessment model may be a logistic regression model, a combination model of a gradient-lifting decision tree and logistic regression, a combination model of a gradient-lifting decision tree and a factoring machine, or other models.
The complaint risk coefficient is used to quantify the degree of reflection of the customer, such as:
complaint risk factors are high, such as: complaint events that may be complaint by the customer to the administrative department;
complaints have low risk factors, such as: the complaint event which can be solved by only communicating the explanation can be caused by misunderstanding caused by asymmetric information.
Step S212, judging whether the complaint risk coefficient is larger than a preset threshold value. If the threshold value is greater than the preset threshold value, the step S214 is entered; otherwise, the process advances to step S216.
Step S214, the customer complaint data is sent to the first electronic equipment.
The first electronic device may be a desktop computer, a smart phone, a tablet computer, or a landline phone.
Specifically, the customer complaint data is sent to a desk computer and other devices of the seat personnel or the negotiating expert, and the seat personnel or the negotiating expert is prompted to solve the complaint event.
The target case aimed by the customer complaint data can be configured on a designated mobile phone or telephone, and customer complaints can be directly answered by seat personnel or negotiating specialists. This situation is particularly suitable for complaint scenarios where customers complain by telephone.
Step S216, the customer complaint data is sent to a second electronic device.
The second electronic equipment is internally provided with a pre-developed intelligent robot system, and the intelligent robot system is used for replying the customer in the form of voice or characters and the like according to the customer complaint data.
Example III
Referring to fig. 3, a flowchart illustrating steps of a complaint risk assessment method based on big data according to a third embodiment of the present invention is shown. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. Specifically, the following is described.
Step S300, customer complaint data is received.
Step S302, judging whether the customer complaint data comprises the basic information of the insurance policy, wherein the basic information of the insurance policy comprises the insurance policy number. If yes, go to step S304; otherwise, the process advances to step S318.
The policy basic information may include a policy number, a customer number, etc. The policy number refers to the number of the insurance contract which the insurance company has issued after the insurance applicant successfully applies to the insurance company. The customer number is an identity number configured by the insurer for each customer.
Step S304, the policy service source of the target case aimed at by the customer complaint data is basically obtained according to the policy.
The policy service source is configured to determine whether to send the customer complaint data to a first electronic device. The policy service sources include network sales sources, telephone sales sources, salesman face-to-face sales sources, bank insurance sources, and the like.
Step S306, judging whether the policy service source of the target case is a target source. If yes, go to step S318; otherwise, the process advances to step S108.
How to determine which of the policy service sources belong to a target source may be as follows: determining a target source through user definition; the target source is determined by sample data analysis.
Step S308, matching the customer complaint data with a plurality of target character strings.
Specifically, whether the target character string in the customer complaint data is detected according to the rule character string. The regular strings are configured according to a string set and regular expressions.
Step S310, determining whether the target character string matches at least one target character string of the target character strings. If yes, go to step S318; otherwise, the process advances to step S312.
Step S312, obtaining the associated data of the target case for the customer complaint data according to the basic information of the policy. The next step goes to step S314.
For example, according to the policy number or the client number in the policy basic information, the associated data of the target case for which the client complaints case is aimed is searched from the database.
The associated data includes attendant data, customer data, policy data, and business data.
Step S314, inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model.
The complaint risk assessment model may be a logistic regression model, a combination model of a gradient-lifting decision tree and logistic regression, a combination model of a gradient-lifting decision tree and a factoring machine, or other models.
Step S316, judging whether the complaint risk coefficient is larger than a preset threshold value. If the threshold is greater than the preset threshold, the process proceeds to step S318, otherwise, the process proceeds to step S320.
Step S318, the customer complaint data is sent to the first electronic device.
Step S320, the customer complaint data is sent to a second electronic device.
In one embodiment:
before step S300, the method further includes the step of training the complaint risk assessment model:
1.1, acquiring a training data set of customer complaints, wherein the training data set comprises a plurality of case risk data corresponding to a plurality of complaint sample cases, and each case risk data comprises salesman data, customer data, policy data and business data; and
And 1.2, training the complaint risk assessment model based on the training data set to obtain a trained complaint risk assessment model.
In one embodiment:
step S300 is preceded by a step of verifying the trained complaint risk assessment model:
2.1, acquiring a first verification data set of high-risk customer complaints generated in a plurality of time intervals and a second verification data set of non-high-risk customer complaints.
2.2, mixing a plurality of verification samples of the first verification data set and a plurality of verification samples in the second verification data to obtain a cross-time verification set.
2.3, inputting a plurality of verification data in the cross-time verification set into the complaint risk assessment model to obtain a complaint risk assessment result output by the complaint risk assessment model.
2.4, calculating the evaluation accuracy and stability coefficient of the complaint risk evaluation model according to the complaint risk evaluation result of the complaint risk evaluation model.
And counting the verified correct rates of the high-risk verification samples and the non-high-risk verification samples according to the risk coefficient of each high-risk verification sample and the risk coefficient of each non-high-risk verification sample in the cross-time verification set. For example, taking 0.7 as a risk coefficient threshold, when the risk coefficient of a certain high-risk verification sample is greater than 0.7, indicating that the verification is correct, otherwise, the verification fails; and when the risk coefficient of a certain non-high risk verification sample is not more than 0.7, the verification is correct, otherwise, the verification fails.
Further, the stability factor of the complaint risk assessment model may also be calculated from the risk factor of each high risk verification sample and the risk factor of each non-high risk verification sample in the cross-time verification set. Further, the stability factor may be obtained by a standard deviation formula, for example, calculating a first stability factor of the plurality of high risk verification samples and a second stability factor of the plurality of non-high risk verification samples, respectively, so as to obtain a stability factor of the complaint insurance risk assessment model.
And 2.5, determining whether the complaint risk assessment model is used for assessing the customer complaint data according to the assessment accuracy and the stability coefficient.
Example IV
With continued reference to fig. 4, a schematic program module of a fourth embodiment of the big data-based complaint risk assessment system of the present invention is shown. In this embodiment, big data based complaint risk assessment system 20 may include or be partitioned into one or more program modules, which are stored in a storage medium and executed by one or more processors to complete the present invention and may implement the big data based complaint risk assessment method described above. Program modules in accordance with embodiments of the present invention are directed to a series of computer program instruction segments capable of performing particular functions, and are more suited to describing the execution of big data based complaint risk assessment system 20 on a storage medium than the program itself. The following description will specifically describe functions of each program module of the present embodiment:
and a receiving module 200 for receiving customer complaint data.
A first determining module 202, configured to determine whether the customer complaint data includes policy basic information, where the policy basic information includes a policy number.
The first obtaining module 204 is configured to obtain, if the customer complaint data includes the policy basic information, associated data of a target case for which the customer complaint data is aimed according to the policy basic information, where the associated data includes service person data, customer data, policy data and service data.
And a second obtaining module 206, configured to input the associated data into a complaint risk assessment model, and obtain a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model.
A second determining module 208, configured to determine whether the complaint risk coefficient is greater than a preset threshold.
A diversion module 210, configured to send the customer complaint data to a first electronic device if the complaint risk coefficient is greater than the preset threshold; and if the complaint risk coefficient is not greater than the preset threshold, sending the customer complaint data to a second electronic device.
In an exemplary embodiment, the first acquisition module 204 is further configured to: and basically acquiring a policy service source of a target case for the customer complaint data according to the policy, wherein the policy service source is used for judging whether to send the customer complaint data to the first electronic equipment. And if the policy service source of the target case is the target source, sending the customer complaint data to the first electronic device through the diversion module 210. And if the policy service source of the target case is not the target source, basically acquiring the associated data of the target case aiming at the customer complaint data according to the policy.
In an exemplary embodiment, if the policy service source of the target case is not a target source, the first obtaining module 204 is further configured to: matching the customer complaint data with a plurality of target character strings; when the customer complaint data matches at least one of the plurality of target strings, the customer complaint data is sent to a first electronic device by the diversion module 210. When the customer complaint data is not matched with any one of the target character strings, the associated data of the target case aimed at by the customer complaint data is basically obtained according to the policy.
The step of matching the customer complaint data with a plurality of target character strings comprises the following steps: and detecting whether a target character string is in the customer complaint data according to the rule character string. The regular strings are configured according to a string set and regular expressions.
In the exemplary embodiment, training module 212 is also included to train the complaint risk assessment model. The training module 212 is configured to:
obtaining a sample data set, wherein the sample data set comprises a first sample data set of high-risk customer complaints and a second sample data set of non-high-risk customer complaints; analyzing correlation coefficients between each feature data in the sample data set and high-risk customer complaint events; selecting a plurality of feature data with the correlation coefficient higher than a preset threshold according to the correlation coefficient between each feature data and the high-risk customer complaint event; judging whether the plurality of feature data comprise one or more policy service sources; and if the plurality of feature data includes one or more policy service sources, determining the one or more policy service sources as the target source.
In the exemplary embodiment, data collection module 214 is also includes a collection of training data for training the complaint risk assessment model. The data collection model 214 is used to:
acquiring a training data set of customer complaints, wherein the training data set comprises a plurality of case risk data corresponding to a plurality of complaint sample cases, and each case risk data comprises salesman data, customer data, policy data and business data; and training the complaint risk assessment model based on the training data set to obtain a trained complaint risk assessment model.
In the exemplary embodiment, verification module 216 is also included to verify the complaint risk assessment model. The verification module 216 is configured to:
acquiring a first verification data set of high-risk customer complaints generated in a plurality of time intervals and a second verification data set of non-high-risk customer complaints; mixing a plurality of verification samples of the first verification data set and a plurality of verification samples in the second verification data to obtain a cross-time verification set; inputting a plurality of verification data in the cross-time verification set into the complaint risk assessment model to obtain a complaint risk assessment result output by the complaint risk assessment model; calculating the evaluation accuracy and stability coefficient of the complaint risk evaluation model according to the complaint risk evaluation result of the complaint risk evaluation model; and determining whether the complaint risk assessment model is used for assessing the customer complaint data according to the assessment accuracy and the stability coefficient.
Example five
Fig. 5 is a schematic hardware architecture of a computer device according to a fifth embodiment of the present invention. In this embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction. The computer device 2 may be a personal computer, a rack-mounted server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster composed of a plurality of servers), or the like. As shown, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a big data based complaint risk assessment system 20 that are communicatively coupled to each other via a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the computer device 20. Of course, the memory 21 may also include both internal storage units of the computer device 2 and external storage devices. In this embodiment, the memory 21 is generally used to store an operating system installed on the computer device 2 and various types of application software, such as program codes of the complaint risk assessment system 20 based on big data in the fifth embodiment. Further, the memory 21 may be used to temporarily store various types of data that have been output or are to be output.
The processor 22 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is configured to execute the program code stored in the memory 21 or process data, for example, execute the complaint risk assessment system 10 based on big data, so as to implement the complaint risk assessment method based on big data of the first, second or third embodiment.
The network interface 23 may comprise a wireless network interface or a wired network interface, which network interface 23 is typically used for establishing a communication connection between the computer device 2 and other electronic devices. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or other wireless or wired network.
It is noted that fig. 5 only shows a computer device 2 having components 20-23, but it is understood that not all of the illustrated components are required to be implemented, and that more or fewer components may alternatively be implemented.
In the present embodiment, the big data based complaint risk assessment system 20 stored in the memory 21 may also be divided into one or more program modules, which are stored in the memory 21 and executed by one or more processors (the processor 22 in the present embodiment) to complete the present invention.
For example, FIG. 4 shows a schematic diagram of program modules for implementing a fourth embodiment of big data based complaint risk assessment system 20, where big data based complaint risk assessment system 20 can be divided into a receiving module 200, a first determining module 202, a first obtaining module 204, a second obtaining module 206, a second determining module 208, a diversion module 210, a training module 212, a data collecting module 214, and a verification module 216. Program modules depicted herein, being understood to mean a series of computer program instruction segments capable of performing a particular function, are more suited to describing the execution of big data based complaint risk assessment system 20 on computer device 2 than programs. The specific functions of the program modules 200-216 are described in detail in the fourth embodiment, and are not described herein.
Example six
The present embodiment also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs the corresponding functions. The computer readable storage medium of the present embodiment is used to store big data based complaint risk assessment system 20, which when executed by a processor implements big data based complaint risk assessment methods of embodiment one, two or three.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. A complaint case processing method based on big data, the method comprising:
receiving customer complaint data;
judging whether the customer complaint data comprises the basic information of a policy, wherein the basic information of the policy comprises a policy number;
if the customer complaint data comprises the policy basic information, acquiring associated data of a target case aimed at by the customer complaint data according to the policy basic information, wherein the associated data comprises service personnel data, customer data, policy data and service data; the salesman data refers to relevant information of a salesman handling the target case;
inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model;
judging whether the complaint risk coefficient is larger than a preset threshold value or not;
if the complaint risk coefficient is larger than the preset threshold value, the customer complaint data is sent to first electronic equipment; and
If the complaint risk coefficient is not greater than the preset threshold, sending the customer complaint data to a second electronic device;
if the customer complaint data includes the basic information of the policy, the step of basically acquiring the associated data of the target case for the customer complaint data according to the policy includes:
The method comprises the steps that a policy service source of a target case aimed at by customer complaint data is basically obtained according to the policy, and the policy service source is used for judging whether the customer complaint data is sent to the first electronic equipment or not;
if the policy service source of the target case is the target source, sending the customer complaint data to first electronic equipment; and
If the policy service source of the target case is not the target source, basically acquiring the associated data of the target case aimed at by the customer complaint data according to the policy;
if the policy service source of the target case is not the target source, the step of basically acquiring the associated data of the target case for the customer complaint data according to the policy includes:
matching the customer complaint data with a plurality of target character strings;
when the customer complaint data is matched with at least one target character string in the target character strings, sending the customer complaint data to first electronic equipment;
when the customer complaint data is not matched with any one of the target character strings, the associated data of the target case aimed at by the customer complaint data is basically obtained according to the policy.
2. The big data based complaint case processing method as claimed in claim 1, wherein,
the step of matching the customer complaint data with a plurality of target strings comprises:
detecting whether a target character string in the customer complaint data is a target character string or not according to a rule character string;
the regular strings are configured according to a string set and regular expressions.
3. The method according to any one of claims 1-2, further comprising:
obtaining a sample data set, wherein the sample data set comprises a first sample data set of high-risk customer complaints and a second sample data set of non-high-risk customer complaints;
analyzing correlation coefficients between each feature data in the sample data set and high-risk customer complaint events;
selecting a plurality of feature data with the correlation coefficient higher than a preset threshold according to the correlation coefficient between each feature data and the high-risk customer complaint event;
judging whether the plurality of feature data comprise one or more policy service sources; and
If the plurality of feature data includes one or more policy service sources, the one or more policy service sources are determined to be the target sources.
4. The method of claim 1, wherein the step of determining the position of the substrate comprises,
before the step of receiving customer complaint data, the method further comprises:
acquiring a training data set of customer complaints, wherein the training data set comprises a plurality of case risk data corresponding to a plurality of complaint sample cases, and each case risk data comprises salesman data, customer data, policy data and business data; and
And training the complaint risk assessment model based on the training data set to obtain a trained complaint risk assessment model.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the method comprises the following steps of obtaining a trained complaint risk assessment model and receiving customer complaint data:
acquiring a first verification data set of high-risk customer complaints generated in a plurality of time intervals and a second verification data set of non-high-risk customer complaints;
mixing a plurality of verification samples of the first verification data set and a plurality of verification samples in the second verification data to obtain a cross-time verification set;
inputting a plurality of verification data in the cross-time verification set into the complaint risk assessment model to obtain a complaint risk assessment result output by the complaint risk assessment model;
Calculating the evaluation accuracy and stability coefficient of the complaint risk evaluation model according to the complaint risk evaluation result of the complaint risk evaluation model;
and determining whether the complaint risk assessment model is used for assessing the customer complaint data according to the assessment accuracy and the stability coefficient.
6. A big data based complaint risk assessment system according to any one of claims 1 to 5, comprising:
the receiving module is used for receiving customer complaint data;
the first judging module is used for judging whether the customer complaint data comprises the basic information of the insurance policy or not, wherein the basic information of the insurance policy comprises the insurance policy number;
the first acquisition module is used for acquiring associated data of a target case for the customer complaint data according to the policy basic information if the customer complaint data comprises the policy basic information, wherein the associated data comprises salesman data, customer data, policy data and business data;
the second acquisition module is used for inputting the associated data into a complaint risk assessment model, and acquiring a complaint risk coefficient corresponding to the customer complaint data through the complaint risk assessment model;
The second judging module is used for judging whether the complaint risk coefficient is larger than a preset threshold value or not;
the diversion module is used for sending the customer complaint data to the first electronic equipment if the complaint risk coefficient is larger than the preset threshold value; and sending the customer complaint data to a second electronic device if the complaint risk coefficient is not greater than the preset threshold.
7. A computer device memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the method of any of claims 1 to 5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program executable by at least one processor to cause the at least one processor to perform the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910511934.4A CN110349039B (en) | 2019-06-13 | 2019-06-13 | Complaint risk assessment method, system, computer device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910511934.4A CN110349039B (en) | 2019-06-13 | 2019-06-13 | Complaint risk assessment method, system, computer device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110349039A CN110349039A (en) | 2019-10-18 |
| CN110349039B true CN110349039B (en) | 2024-03-05 |
Family
ID=68182027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910511934.4A Active CN110349039B (en) | 2019-06-13 | 2019-06-13 | Complaint risk assessment method, system, computer device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349039B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126783A (en) * | 2019-11-29 | 2020-05-08 | 广东电网有限责任公司 | Customer complaint risk rating method and device based on big data |
| CN112330468B (en) * | 2020-11-03 | 2023-10-27 | 中国平安财产保险股份有限公司 | Method, device, equipment and storage medium for identifying risk clients |
| CN112651635A (en) * | 2020-12-28 | 2021-04-13 | 长沙市到家悠享网络科技有限公司 | Risk identification method and device, electronic equipment and storage medium |
| CN112927091B (en) * | 2021-04-08 | 2023-11-10 | 泰康保险集团股份有限公司 | Complaint early warning method and device for annual gold insurance, computer equipment and medium |
| CN113592315B (en) * | 2021-08-04 | 2024-08-16 | 北京沃东天骏信息技术有限公司 | Method and device for processing dispute sheets |
| CN115564332B (en) * | 2022-10-08 | 2023-04-21 | 深圳中科保泰科技有限公司 | Government risk analysis method and system based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530127A (en) * | 2016-11-09 | 2017-03-22 | 国网江苏省电力公司南京供电公司 | Complaint early warning and monitoring analysis system based on text mining |
| CN108108352A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of enterprise's complaint risk method for early warning based on machine learning Text Mining Technology |
| CN109816399A (en) * | 2019-01-07 | 2019-05-28 | 平安科技（深圳）有限公司 | Complain management method, device, computer equipment and the storage medium of part |
| CN109858702A (en) * | 2019-02-14 | 2019-06-07 | 中国联合网络通信集团有限公司 | Client upgrades prediction technique, device, equipment and the readable storage medium storing program for executing complained |
| CN109872162A (en) * | 2018-11-21 | 2019-06-11 | 阿里巴巴集团控股有限公司 | A kind of air control classifying identification method and system handling customer complaint information |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120035977A1 (en) * | 2010-08-03 | 2012-02-09 | Bank Of America Corporation | Enterprise Consumer Complaints Program |
| US10453122B2 (en) * | 2010-08-18 | 2019-10-22 | The Western Union Company | Systems and methods for assessing fraud risk |
| US20120259673A1 (en) * | 2011-04-08 | 2012-10-11 | Welch Allyn, Inc. | Risk-Based Complaint Management System |
-
2019
- 2019-06-13 CN CN201910511934.4A patent/CN110349039B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530127A (en) * | 2016-11-09 | 2017-03-22 | 国网江苏省电力公司南京供电公司 | Complaint early warning and monitoring analysis system based on text mining |
| CN108108352A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of enterprise's complaint risk method for early warning based on machine learning Text Mining Technology |
| CN109872162A (en) * | 2018-11-21 | 2019-06-11 | 阿里巴巴集团控股有限公司 | A kind of air control classifying identification method and system handling customer complaint information |
| CN109816399A (en) * | 2019-01-07 | 2019-05-28 | 平安科技（深圳）有限公司 | Complain management method, device, computer equipment and the storage medium of part |
| CN109858702A (en) * | 2019-02-14 | 2019-06-07 | 中国联合网络通信集团有限公司 | Client upgrades prediction technique, device, equipment and the readable storage medium storing program for executing complained |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110349039A (en) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349039B (en) | Complaint risk assessment method, system, computer device and readable storage medium | |
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN109242261B (en) | Method for evaluating security risk based on big data and terminal equipment | |
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| CN110610431B (en) | Intelligent claim settlement method and intelligent claim settlement system based on big data | |
| WO2019019636A1 (en) | User identification method, electronic device, and computer readable storage medium | |
| CN109345417B (en) | Online assessment method and terminal equipment for business personnel based on identity authentication | |
| CN110704730A (en) | Product data pushing method and system based on big data and computer equipment | |
| CN113627566A (en) | Early warning method and device for phishing and computer equipment | |
| CN110008979A (en) | Abnormal data prediction technique, device, electronic equipment and computer storage medium | |
| CN112950359B (en) | User identification method and device | |
| CN108090831A (en) | Credit Risk Assessment method, application server and computer readable storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN111382944A (en) | Job behavior risk identification method and device, computer equipment and storage medium | |
| CN114219664A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN110795466A (en) | Anti-fraud method based on big data processing, server and computer-readable storage medium | |
| CN112232656A (en) | Monitoring and early warning method, device, terminal and readable medium for business data | |
| CN115879819A (en) | Enterprise credit evaluation method and device | |
| CN107545347B (en) | Attribute determination method and device for risk prevention and control and server | |
| CN115640486A (en) | Network news media influence evaluation method and device based on multi-source data fusion | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113743435B (en) | Training of service data classification model, and service data classification method and device | |
| CN111222923B (en) | Method and device for judging potential clients, electronic equipment and storage medium | |
| CN111640502B (en) | Method and device for detecting health state of delivery object | |
| CN112686702A (en) | Wool party identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |