CN108734590B - Policy distribution method and terminal equipment - Google Patents
Policy distribution method and terminal equipment Download PDFInfo
- Publication number
- CN108734590B CN108734590B CN201810309425.9A CN201810309425A CN108734590B CN 108734590 B CN108734590 B CN 108734590B CN 201810309425 A CN201810309425 A CN 201810309425A CN 108734590 B CN108734590 B CN 108734590B
- Authority
- CN
- China
- Prior art keywords
- insurance
- policy
- units
- unit
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention is suitable for the technical field of artificial intelligence, and provides a policy distribution method and terminal equipment, wherein in the embodiment of the invention, policy information of a policy to be distributed and a cash release threshold of each insurance unit are obtained; calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to a cash threshold value as a cash ratio; classifying the insurance units with the paying-out proportion smaller than the preset proportion threshold value into a first acceptance group, and classifying the insurance units into a second acceptance group if the paying-out proportion is smaller than the preset proportion threshold value; determining the policy category of the policy to be allocated according to the policy information; if the insurance units of the insurance policy category of the insurance policy to be distributed are not processed in the first acceptance group, the insurance units of the insurance policy category of the insurance policy to be distributed processed in the second acceptance group are used as candidate units, and the insurance policy to be distributed is distributed to one insurance unit with the lowest deposit proportion in the candidate units, so that the reasonable degree and the automation degree of policy distribution are improved.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a policy distribution method and terminal equipment.
Background
Currently, after the customer completes the real name verification, the insurance company randomly distributes the customer's policy to the insurance branch company which can process the policy, and the insurance branch company performs subsequent operations on the policy, and pays money for the customer when the customer needs to pay.
But different insurance companies may have areas of their own tampering, if one policy is one insurance company not tampering, it may take longer to operate, which may result in a reduced user experience. On the other hand, if the amount of money paid by an insurance carrier has reached the warning line within a predetermined period of time, continuing to receive the policy may present a problem of excess money paid, which may make money turnover to the insurance carrier difficult.
Disclosure of Invention
In view of this, the embodiment of the invention provides a policy distribution method and terminal equipment, so as to solve the problem of excessive paying money possibly existing in the policy distribution in the prior art.
A first aspect of an embodiment of the present invention provides a policy allocation method, including:
acquiring policy information of a policy to be allocated and a cash release threshold of each insurance unit;
calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as a cash ratio;
Classifying the insurance units with the paying-out proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the paying-out proportion larger than or equal to the proportion threshold value into a second acceptance group;
determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm;
acquiring an operation record of an insurance unit in the first acceptance group, wherein the operation record is used for recording policy information of a policy processed by the insurance unit;
if the insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and distributing the insurance policy to be distributed to the insurance unit with the highest processing score;
and if the insurance units of the insurance policy category processed by the insurance policy to be distributed in the first acceptance group do not exist, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to the insurance units with the lowest deposit proportion in the candidate units.
A second aspect of an embodiment of the present invention provides a terminal device, including a memory and a processor, where the memory stores a computer program executable on the processor, and when the processor executes the computer program, the processor implements the following steps:
Acquiring policy information of a policy to be allocated and a cash release threshold of each insurance unit;
calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as a cash ratio;
classifying the insurance units with the paying-out proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the paying-out proportion larger than or equal to the proportion threshold value into a second acceptance group;
determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm;
acquiring an operation record of an insurance unit in the first acceptance group, wherein the operation record is used for recording policy information of a policy processed by the insurance unit;
if the insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and distributing the insurance policy to be distributed to the insurance unit with the highest processing score;
and if the insurance units of the insurance policy category processed by the insurance policy to be distributed in the first acceptance group do not exist, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to one insurance unit with the lowest deposit proportion in the candidate units.
A third aspect of the embodiments of the present invention provides a computer readable storage medium storing a computer program which when executed by a processor performs the steps of: acquiring policy information of a policy to be allocated and a cash release threshold of each insurance unit; calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as a cash ratio; classifying the insurance units with the paying-out proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the paying-out proportion larger than or equal to the proportion threshold value into a second acceptance group; determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm; acquiring an operation record of an insurance unit in the first acceptance group, wherein the operation record is used for recording policy information of a policy processed by the insurance unit; if the insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and distributing the insurance policy to be distributed to the insurance unit with the highest processing score; and if the insurance units of the insurance policy category processed by the insurance policy to be distributed in the first acceptance group do not exist, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to the insurance units with the lowest deposit proportion in the candidate units.
Further, before calculating the ratio of the accumulated payout amount of each insurance unit in the preset time period to the payout threshold value as the payout ratio, the method further includes: and taking the average time length required from the zero clearing of the accumulated cash amount of the first preset number of insurance units to the time when the cash proportion reaches the proportion threshold value as the preset time period.
Further, the determining, according to the policy information, the policy category of the policy to be allocated by a K nearest neighbor algorithm includes: acquiring policy information of a plurality of sample policies and class labels corresponding to the sample policies; converting the policy information of the policy to be allocated into a test matrix, converting the policy information of the sample policy into a training matrix, and establishing a corresponding relation between the training matrix and the class label based on the class label corresponding to the sample policy; calculating Manhattan distances from the test matrix to each training matrix; and taking a second preset number of class labels corresponding to training matrixes with minimum Manhattan distance of the test matrixes as candidate classes, and taking the candidate class with the highest occurrence proportion as a policy class of the policy to be allocated.
Further, the obtaining the operation record of the insurance unit in the first acceptance group includes:
acquiring a preset webpage database, and determining the correlation degree between each webpage in the preset webpage database and the insurance units; the determining the relevance between each webpage and the insurance entity in the preset webpage database comprises the following steps: word segmentation processing is carried out on the content of each webpage in the preset webpage database so as to generate a word set corresponding to each webpage; by the formula:
calculating probability parameters of the insurance units in each webpage, wherein the Y i Probability parameter in webpage i for insurance unit, n is as follows i Number of occurrences, k, of insurance units in the term set corresponding to webpage i i The term sum contained in the term set corresponding to the webpage i is the sum of the number of webpages contained in the webpage database, and b is the number of webpages containing the insurance units in the webpage database; and determining the correlation degree between the insurance units and each webpage according to the corresponding relation between the preset probability parameter interval and the correlation degree.
Capturing the content in the webpage with the correlation degree with the insurance units being greater than or equal to a preset correlation degree threshold value, generating a content database, and searching the operation records of the insurance units in the content database by adopting the depth priority order.
Further, the calculating a processing score of each insurance unit in the first acceptance group based on the operation record includes: if the insurance unit does not process the policy category of the policy to be allocated, setting the processing score of the insurance unit to 0; if the insurance unit processes the policy category of the policy to be allocated, the policy category is calculated by the formula: calculating a processing score of the insurance unit by s=1- (T/T) - (e+p), wherein S is the processing score of the insurance unit, T is the policy processing time of the insurance unit contained in the operation record, T is the policy processing average time of a third preset number of insurance units calculated according to the operation record, e is the processing error rate of the insurance unit contained in the operation record, and p is the conversion processing probability of the insurance unit contained in the operation record.
In the embodiment of the invention, the policy information of the policy to be distributed and the paying-off threshold value of each insurance unit are obtained; calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to a cash threshold value as a cash ratio; classifying the insurance units with the paying-out proportion smaller than the preset proportion threshold value into a first acceptance group, and classifying the insurance units into a second acceptance group if the paying-out proportion is smaller than the preset proportion threshold value; determining the policy category of the policy to be allocated according to the policy information; if the insurance units of the insurance policy category of the insurance policy to be distributed are not processed in the first acceptance group, the insurance units of the insurance policy category of the insurance policy to be distributed processed in the second acceptance group are used as candidate units, and the insurance policy to be distributed is distributed to one insurance unit with the lowest deposit proportion in the candidate units, so that the reasonable degree and the automation degree of policy distribution are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an implementation method of policy allocation provided in an embodiment of the present invention;
fig. 2 is a flowchart of a specific implementation of a policy allocation method S104 provided in an embodiment of the present invention;
fig. 3 is a flowchart of a specific implementation of a policy allocation method S105 provided in an embodiment of the present invention;
FIG. 4 is a block diagram of a policy distribution device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Fig. 1 shows a flow of implementation of a policy allocation method according to an embodiment of the present invention, where the flow of implementation includes steps S101 to S108. The specific implementation principle of each step is as follows.
S101: and acquiring policy information of the policy to be allocated and the paying-out threshold value of each insurance unit.
In the embodiment of the invention, each policy has corresponding policy information, and the policy information can be selected and filled by a user or formulated by an insurance unit. Optionally, the policy information includes: user assets, user credit ratings, user identity information, product information, and the like. It will be appreciated that policy information may be used to describe the user who purchased the insurance as well as the insurance product being purchased.
In the embodiment of the present invention, each insurance unit may be a branch or a subsidiary of an insurance company, or may be a plurality of independent insurance companies added to a federation, and it may be understood that each insurance unit has a corresponding payout maximum according to its operating condition and fund quota, and in the embodiment of the present invention, the payout maximum of an insurance unit is referred to as a payout threshold. In actual business, although multiple insurance units may be able to mutually invoke funds to address the issue of excess payouts, the best solution is for each insurance unit to ensure that its payouts do not exceed its payouts threshold under normal circumstances and to respond and pays as quickly as possible for the obtained policy.
S102: calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as the cash ratio.
For example, assume that the cumulative amount of money paid by insurance unit a is 1000 tens of thousands, the cumulative amount of money paid by insurance unit B is 2000 tens of thousands, the cumulative amount of money paid by insurance unit C is 1500 tens of thousands, the cumulative amount of money paid by insurance unit D is 2500 tens of thousands, and the cumulative amount of money paid by insurance unit E is 3000 tens of thousands. If the payoff thresholds for insurance entity A, B, C, D and E are both: 3000 ten thousand. The payoff ratio of A, B, C, D and E can be calculated as: 33%, 66%, 50%, 83% and 100%. It will be appreciated that in the above example, the payout thresholds of the 5 insurance units are the same, but the embodiment of the present invention may cope with the case where the payout thresholds of the plurality of insurance units are different, and the manner in which the payout ratio is calculated is unchanged.
Further, before calculating the ratio of the accumulated payout amount of each insurance unit in the preset time period to the payout threshold value as the payout ratio, the method further includes: and taking the average time length required from the zero clearing of the accumulated cash amount of the first preset number of insurance units to the time when the cash proportion reaches the proportion threshold value as the preset time period.
It can be appreciated that in the embodiment of the present invention, the preset time period is dynamically adjusted according to the actual payment situations of a plurality of insurance units, so that the whole calculation process is closer to the actual payment requirements.
It can be understood that the calculation process is automatically performed by a computer, and calculating the paying-off proportion of each insurance unit is beneficial to reasonably dividing different insurance units later, so that the insurance policy can be distributed more quickly and accurately.
S103, classifying the insurance units with the cash discharge proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the cash discharge proportion larger than or equal to the proportion threshold value into a second acceptance group.
In the embodiment of the invention, after the paying-out proportion of each insurance unit is determined, the insurance units are grouped based on the paying-out proportion. Illustratively, as described in the above examples, the payouts of insurance units A, B, C, D and E are respectively: 33%, 66%, 50%, 83%, and 100%, then assuming that the preset ratio threshold is 80%, insurance carrier A, B, C is classified into the first accepted group and insurance carrier E, D is classified into the second accepted group.
The meaning of the grouping is: in the subsequent policy assignment, first, consider the insurance units in the first acceptance group, and if the policy cannot be assigned to the insurance units in the first acceptance group, consider the policy to be assigned to the insurance units in the second acceptance group, and the assignment selection manner of the first acceptance group and the second acceptance group is not the same, and the specific assignment manner will be described in detail below.
S104: and determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm.
In the embodiment of the invention, considering that the policy categories of the different insurance units good for processing in actual situations are different, in the embodiment of the invention, the policy needs to be divided into different policy categories according to the policy information.
Optionally, the policy information of each policy includes: data such as user assets, user credit ratings, user identity information, and product information can be converted into a matrix form and classified into different policy categories according to a pattern classification algorithm. Alternatively, a KNN algorithm may be selected to categorize the policy information.
Notably, in order to facilitate the subsequent calculation process, the embodiment of the present invention adopts a supervised pattern classification algorithm, that is, the policy categories are already preset, and in the embodiment of the present invention, the policy category to which the policy to be allocated belongs is identified according to the policy information of the policies of other known policy categories.
As an embodiment of the present invention, as shown in fig. 2, the step S104 includes:
s1041: and acquiring the policy information of a plurality of sample policies and the class labels corresponding to the sample policies.
It can be understood that the sample policy is a policy of a known policy category, and in the embodiment of the present invention, the policy information of the sample policy and the category label corresponding to the sample policy can be used as training data for subsequent recognition.
S1042: and converting the policy information of the policy to be allocated into a test matrix, converting the policy information of the sample policy into a training matrix, and establishing a corresponding relation between the training matrix and the class label based on the class label corresponding to the sample policy.
Optionally, the policy information of the policy to be allocated is converted into the test matrix or the policy information of the sample policy is converted into the training matrix, and the data of different types can be stored in different preset corresponding positions in the matrix, if the data of a certain type is not a number, the data can be converted into the number according to the corresponding relation between the preset data and the number, and then stored in the preset positions of the matrix.
It can be understood that, after the policy information of the sample policy is converted into training matrices, the category labels need to be labeled for each training matrix according to the category labels corresponding to the sample policy.
S1043: and calculating Manhattan distances from the test matrix to each training matrix.
In the embodiment of the invention, the proximity degree of the policy to be distributed and each sample policy can be determined by calculating the Manhattan distance from the test matrix to each training matrix.
S1044, taking a second preset number of class labels corresponding to training matrixes with minimum Manhattan distance of the test matrixes as candidate classes, and taking the candidate class with the highest occurrence proportion as the policy class of the policy to be allocated.
It can be understood that, by converting the policy information of the policy to be allocated into a training matrix and then calculating the manhattan distance between the training matrix and the test matrix, the proximity degree of the policy to be allocated and the sample policy of each known policy class is determined, so that the class label with the highest occurrence proportion in the plurality of sample policies closest to the policy to be allocated is used as the policy class of the policy to be allocated.
S105: and acquiring an operation record of the insurance unit in the first acceptance group, wherein the operation record is used for recording the policy information of the policy processed by the insurance unit.
In the embodiment of the invention, the operation records related to the insurance units in the first acceptance group can be automatically grasped through a crawler technology, so that more comprehensive data guarantee is provided for subsequent analysis of the insurance units.
As an embodiment of the present invention, as shown in fig. 3, the step S105 includes:
s1051, acquiring a preset webpage database, and determining the correlation degree between each webpage in the preset webpage database and the insurance units.
In the embodiment of the present invention, a web database is preset, and mass web pages are stored in the web database, where the content in the web pages includes introduction of information of a policy processed by an insurance unit, and also includes processing data of the insurance unit for processing each policy, for example: processing time length, processing time, processing problems and other information. It will be appreciated that different insurance units may be aware of how different policies are processed by the different insurance units via the web pages.
Optionally, determining the relevance between each web page in the preset web page database and the insurance entity may be performed according to the following steps:
firstly, word segmentation processing is carried out on the content of each webpage in the preset webpage database, and a word set corresponding to each webpage is generated. In the embodiment of the invention, the content of each webpage in the webpage database is composed of a plurality of words, so that word segmentation processing is needed to be performed on the content of each webpage to generate a word set corresponding to each webpage.
Notably, the same word that repeatedly appears may be included in one word set, for example, 5 "insurance units a" appear in one first web page, and then there are 5 "insurance units a" in the word set corresponding to the first web page, that is, the "insurance units a" in the word set corresponding to the first web page may repeatedly appear 5 times, and the 5 "insurance units a" may not be combined into one word.
Subsequently, the formula is passed:
calculating probability parameters of a certain insurance unit in each webpage, wherein Y is as follows i Probability parameter in webpage i for insurance unit, n is as follows i Number of occurrences, k, of insurance units in the term set corresponding to webpage i i And b is the sum of words contained in the word set corresponding to the webpage i, wherein h is the sum of the number of webpages contained in the webpage database, and b is the number of webpages containing the insurance units in the webpage database. It will be appreciated that the probability parameter is not the probability of a simple insurance unit in each web page, but is a parameter that reflects how close an insurance unit is to one web page calculated in combination with 4 important parameters, namely the number of occurrences of the insurance unit in the word set corresponding to web page i, the word sum contained in the word set corresponding to web page i, the number of web pages contained in the web page database, and the number of insurance units contained in the web page database.
And finally, determining the correlation degree between the insurance units and each webpage according to the corresponding relation between the preset probability parameter interval and the correlation degree.
In the embodiment of the invention, the probability parameter of the insurance unit and each webpage is not the last correlation degree with each webpage, but the corresponding relation between the preset probability parameter interval and the correlation degree is required to be called, and the correlation degree corresponding to the probability parameter in the last step is calculated and used as the correlation degree of the insurance unit and each webpage.
S1052, capturing the content in the webpage with the correlation degree with the insurance units being greater than or equal to the preset correlation degree threshold value, generating a content database, and searching the operation records of the insurance units in the content database by adopting the depth priority order.
In the embodiment of the invention, a program for automatically extracting the web pages through the web crawlers is designed, and the program can extract and download the web pages meeting the requirements from a preset web page database. Optionally, the web crawler starts from the URL of one or more initial web pages, obtains the URL on the initial web page, and continuously extracts a new URL from the current web page and puts the new URL into the queue in the process of crawling the web page until the stopping condition of crawling of the web crawler is met.
In the embodiment of the invention, the web pages with highest correlation degree with the insurance units are grabbed from the web page with highest correlation degree with the insurance units, and the web pages are grabbed gradually from high to low according to the correlation degree with the insurance units, and the stopping conditions are as follows: and stopping grabbing when the correlation degree threshold value with the insurance unit is smaller than the preset correlation degree threshold value. The content in all web pages crawled by the web crawlers is stored by the system, creating a content database. It will be appreciated that the content database contains the content of a plurality of web pages, and that the content of these web pages is highly relevant to each insurance entity. As described above, the content of each web page in the content database may include an introduction to the policy processed by the insurance entity and an introduction to the processing of each policy by the insurance entity.
Optionally, in an embodiment of the present invention, the operation records of each insurance entity are searched in the content database using depth-first order. It can be understood that, in the present invention, depth first refers mainly to capturing the latest operation record corresponding to the name of an insurance unit in the network after the name of the insurance unit is obtained, then capturing the second new operation record corresponding to the name of the insurance unit, and so on, after capturing all operation records of the name of one insurance unit in a period of time, capturing the operation record corresponding to the name of another insurance unit. It can be appreciated that, due to the nature of the information to be acquired in the application, the depth-first search mode is directly adopted, which is beneficial to improving the efficiency of searching and grabbing operation records.
S106, judging whether insurance units of the policy category of the policy to be allocated are processed in the first acceptance group.
It can be appreciated that, since each insurance unit has the policy category processed and not processed, whether each insurance unit processes the policy category of the policy to be allocated can be automatically and respectively determined according to the operation record of each insurance unit.
And S107, if the insurance units of the insurance policy category of the insurance policy to be allocated exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and allocating the insurance policy to be allocated to the insurance unit with the highest processing score.
Optionally, in the embodiment of the present invention, if there are insurance units in the policy class that have processed the policy to be allocated in the first acceptance group, the processing score of each insurance unit is specifically determined by:
firstly, for an insurance unit of an insurance policy category of which the insurance policy to be allocated is not processed in a first acceptance group, setting a processing score of the insurance unit to 0 directly;
secondly, for the insurance units of the policy category of the policy to be allocated processed in the first acceptance group, the following formula is adopted: calculating a processing score of the insurance unit by s=1- (T/T) - (e+p), wherein S is the processing score of the insurance unit, T is the policy processing time of the insurance unit contained in the operation record, T is the policy processing average time of a third preset number of insurance units calculated according to the operation record, e is the processing error rate of the insurance unit contained in the operation record, and p is the conversion processing probability of the insurance unit contained in the operation record.
It can be understood that, since the policy category to which the policy to be allocated belongs has been determined in the previous step, in this step, after calculating the processing score of each policy category processed by each insurance unit, the policy to be allocated may be allocated to the insurance unit with the highest processing score for processing the policy category to which the policy to be allocated belongs in the first acceptance group.
And S108, if no insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to one insurance unit with the lowest deposit proportion in the candidate units.
In the embodiment of the present invention, as described above, the policy allocation method of the first acceptance group and the policy allocation method of the second acceptance group are different.
It can be understood that, because some insurance units with the paying-out proportion reaching the warning position are in the second accepting group, the insurance units in the second accepting group are not suitable for being distributed by processing scores, but are distributed by the paying-out proportion, and the insurance units to be distributed are automatically distributed to one insurance unit with the lowest paying-out proportion in the candidate units, so that the user experience can be considered, and the insurance units can be ensured to have the capability of processing the insurance units to the greatest extent.
Notably, the policy allocation modes according to the embodiments of the present invention can be automatically executed by a designed program, without manual intervention.
In the embodiment of the invention, the policy information of the policy to be distributed and the paying-off threshold value of each insurance unit are obtained; calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to a cash threshold value as a cash ratio; classifying the insurance units with the paying-out proportion smaller than the preset proportion threshold value into a first acceptance group, and classifying the insurance units into a second acceptance group if the paying-out proportion is smaller than the preset proportion threshold value; determining the policy category of the policy to be allocated according to the policy information; if the insurance units of the insurance policy category of the insurance policy to be distributed are not processed in the first acceptance group, the insurance units of the insurance policy category of the insurance policy to be distributed processed in the second acceptance group are used as candidate units, and the insurance policy to be distributed is distributed to one insurance unit with the lowest deposit proportion in the candidate units, so that the reasonable degree and the automation degree of policy distribution are improved.
Corresponding to the policy distribution method described in the above embodiment, fig. 4 shows a block diagram of a policy distribution device provided in the embodiment of the present invention, and for convenience of explanation, only the portion relevant to the embodiment of the present invention is shown.
Referring to fig. 4, the apparatus includes:
an obtaining module 401, configured to obtain policy information of a policy to be allocated and a payout threshold of each insurance unit;
a calculating module 402, configured to calculate, as a payout ratio, a ratio of an accumulated payout amount of each insurance unit in a preset time period to the payout threshold;
the identification module 404 is configured to determine, according to the policy information, a policy category of the policy to be allocated according to a K nearest neighbor algorithm;
a record obtaining module 405, configured to obtain an operation record of an insurance unit in the first acceptance group;
a first allocation module 406, configured to calculate, if, according to the operation record, an insurance unit of a policy class that has processed the policy to be allocated exists in the first acceptance group, a processing score of each insurance unit in the first acceptance group based on the operation record, and allocate the policy to be allocated to an insurance unit with the highest processing score;
and the second allocation module 407 is configured to, if no insurance units of the policy class that has processed the policy to be allocated exist in the first receiving group, take the insurance units of the policy class that has processed the policy to be allocated in the second receiving group as candidate units, and allocate the policy to be allocated to one insurance unit with the lowest deposit proportion in the candidate units.
Optionally, the apparatus further comprises:
the setting module is used for taking the average time length required from the start of zero clearing of the accumulated cash amount of the first preset number of insurance units to the time when the cash proportion reaches the proportion threshold value as the preset time period.
Optionally, the identifying module 404 includes:
and the sample acquisition sub-module is used for acquiring the policy information of the plurality of sample policies and the class labels corresponding to the sample policies.
The relation establishing sub-module is used for converting the policy information of the policy to be allocated into a test matrix, converting the policy information of the sample policy into a training matrix, and establishing the corresponding relation between the training matrix and the class label based on the class label corresponding to the sample policy;
the distance calculation sub-module is used for calculating Manhattan distances from the test matrix to each training matrix;
and the class determination submodule is used for taking a second preset number of class labels corresponding to training matrixes with minimum Manhattan distance of the test matrix as candidate classes, and taking the candidate class with the highest occurrence proportion as the policy class of the policy to be allocated.
Optionally, the record obtaining module 405 includes:
The correlation calculation submodule is used for acquiring a preset webpage database and determining the correlation between each webpage in the preset webpage database and the insurance unit.
And the grabbing sub-module is used for grabbing the content in the webpage with the correlation degree with the insurance units being greater than or equal to a preset correlation degree threshold value, generating a content database, and searching the operation record of the insurance units in the content database by adopting the depth priority order.
Optionally, the first allocation module includes:
the first evaluation sub-module is used for setting the processing score of the insurance unit to be 0 if the insurance unit does not process the policy category of the policy to be allocated;
the second evaluation sub-module is configured to, if the insurance unit processes the policy category of the policy to be allocated, pass the formula: calculating a processing score of the insurance unit by s=1- (T/T) - (e+p), wherein S is the processing score of the insurance unit, T is the policy processing time of the insurance unit contained in the operation record, T is the policy processing average time of a third preset number of insurance units calculated according to the operation record, e is the processing error rate of the insurance unit contained in the operation record, and p is the conversion processing probability of the insurance unit contained in the operation record.
In the embodiment of the invention, the policy information of the policy to be distributed and the paying-off threshold value of each insurance unit are obtained; calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to a cash threshold value as a cash ratio; classifying the insurance units with the paying-out proportion smaller than the preset proportion threshold value into a first acceptance group, and classifying the insurance units into a second acceptance group if the paying-out proportion is smaller than the preset proportion threshold value; determining the policy category of the policy to be allocated according to the policy information; if the insurance units of the insurance policy category of the insurance policy to be distributed are not processed in the first acceptance group, the insurance units of the insurance policy category of the insurance policy to be distributed processed in the second acceptance group are used as candidate units, and the insurance policy to be distributed is distributed to one insurance unit with the lowest deposit proportion in the candidate units, so that the reasonable degree and the automation degree of policy distribution are improved.
Fig. 5 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 5, the terminal device 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52, such as an allocation program of a policy, stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps of the respective policy allocation method embodiments described above, such as steps 101 to 108 shown in fig. 1. Alternatively, the processor 50, when executing the computer program 52, performs the functions of the modules/units of the apparatus embodiments described above, e.g. the functions of the units 401 to 407 shown in fig. 4.
By way of example, the computer program 52 may be partitioned into one or more modules/units that are stored in the memory 51 and executed by the processor 50 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 52 in the terminal device 5.
The terminal device 5 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the terminal device 5 and does not constitute a limitation of the terminal device 5, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the terminal device may further include an input-output device, a network access device, a bus, etc.
The processor 50 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 51 may be an external storage device of the terminal device 5, 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 terminal device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 51 is used for storing the computer program as well as other programs and data required by the terminal device. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. A method for distributing a policy, comprising:
acquiring policy information of a policy to be allocated and a cash release threshold of each insurance unit;
calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as a cash ratio;
classifying the insurance units with the paying-out proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the paying-out proportion larger than or equal to the proportion threshold value into a second acceptance group;
determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm;
acquiring an operation record of an insurance unit in the first acceptance group, wherein the operation record is used for recording policy information of a policy processed by the insurance unit;
if the insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and distributing the insurance policy to be distributed to the insurance unit with the highest processing score;
and if the insurance units of the insurance policy category processed by the insurance policy to be distributed in the first acceptance group do not exist, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to the insurance units with the lowest deposit proportion in the candidate units.
2. The method of claim 1, further comprising, prior to said calculating a ratio of the cumulative payout amount of each of said insurance units over a predetermined period of time to said payout threshold as a payout ratio:
and taking the average time length required from the zero clearing of the accumulated cash amount of the first preset number of insurance units to the time when the cash proportion reaches the proportion threshold value as the preset time period.
3. The policy allocation method according to claim 1, wherein said determining, according to said policy information, a policy category of said policy to be allocated by a K nearest neighbor algorithm includes:
acquiring policy information of a plurality of sample policies and class labels corresponding to the sample policies;
converting the policy information of the policy to be allocated into a test matrix, converting the policy information of the sample policy into a training matrix, and establishing a corresponding relation between the training matrix and the class label based on the class label corresponding to the sample policy;
calculating Manhattan distances from the test matrix to each training matrix;
and taking a second preset number of class labels corresponding to training matrixes with minimum Manhattan distance of the test matrixes as candidate classes, and taking the candidate class with the highest occurrence proportion as a policy class of the policy to be allocated.
4. The method for assigning policy of claim 1, wherein said obtaining an operation record of insurance units in said first acceptance group includes:
acquiring a preset webpage database, and determining the correlation degree between each webpage in the preset webpage database and the insurance units;
capturing the content in the webpage with the correlation degree with the insurance units being greater than or equal to a preset correlation degree threshold value, generating a content database, and searching the operation records of the insurance units in the content database by adopting a depth priority order;
the determining the relevance between each webpage and the insurance entity in the preset webpage database comprises the following steps:
word segmentation processing is carried out on the content of each webpage in the preset webpage database so as to generate a word set corresponding to each webpage;
by the formula:
calculating probability parameters of the insurance units in each webpage, wherein the Y i Probability parameter in webpage i for insurance unit, n is as follows i Number of occurrences, k, of insurance units in the term set corresponding to webpage i i The term sum contained in the term set corresponding to the webpage i is the sum of the number of webpages contained in the webpage database, and b is the number of webpages containing the insurance units in the webpage database;
And determining the correlation degree between the insurance units and each webpage according to the corresponding relation between the preset probability parameter interval and the correlation degree.
5. The policy distribution method according to claim 1, wherein said calculating a process score for each insurance entity in said first acceptance group based on said operation records comprises:
if the insurance unit does not process the policy category of the policy to be allocated, setting the processing score of the insurance unit to 0;
if the insurance unit processes the policy category of the policy to be allocated, the policy category is calculated by the formula: calculating a processing score of the insurance unit by s=1- (T/T) - (e+p), wherein S is the processing score of the insurance unit, T is the policy processing time of the insurance unit contained in the operation record, T is the policy processing average time of a third preset number of insurance units calculated according to the operation record, e is the processing error rate of the insurance unit contained in the operation record, and p is the conversion processing probability of the insurance unit contained in the operation record.
6. A terminal device comprising a memory and a processor, said memory storing a computer program executable on said processor, characterized in that said processor, when executing said computer program, performs the steps of:
Acquiring policy information of a policy to be allocated and a cash release threshold of each insurance unit;
calculating the ratio of the accumulated cash amount of each insurance unit in a preset time period to the cash threshold value as a cash ratio;
classifying the insurance units with the paying-out proportion smaller than a preset proportion threshold value into a first acceptance group, and classifying the insurance units with the paying-out proportion larger than or equal to the proportion threshold value into a second acceptance group;
determining the policy category of the policy to be allocated according to the policy information through a K nearest neighbor algorithm;
acquiring an operation record of an insurance unit in the first acceptance group, wherein the operation record is used for recording policy information of a policy processed by the insurance unit;
if the insurance units of the insurance policy category processed by the insurance policy to be distributed exist in the first acceptance group according to the operation record, calculating the processing scores of the insurance units in the first acceptance group based on the operation record, and distributing the insurance policy to be distributed to the insurance unit with the highest processing score;
and if the insurance units of the insurance policy category processed by the insurance policy to be distributed in the first acceptance group do not exist, taking the insurance units of the insurance policy category processed by the insurance policy to be distributed in the second acceptance group as candidate units, and distributing the insurance policy to be distributed to the insurance units with the lowest deposit proportion in the candidate units.
7. The terminal device of claim 6, further comprising, prior to said calculating a ratio of the cumulative payout amount of each of said insurance units over a preset time period to said payout threshold as a payout ratio:
and taking the average time length required from the zero clearing of the accumulated cash amount of the first preset number of insurance units to the time when the cash proportion reaches the proportion threshold value as the preset time period.
8. The terminal device of claim 6, wherein the determining, according to the policy information, the policy category of the policy to be allocated by a K nearest neighbor algorithm includes:
acquiring policy information of a plurality of sample policies and class labels corresponding to the sample policies;
converting the policy information of the policy to be allocated into a test matrix, converting the policy information of the sample policy into a training matrix, and establishing a corresponding relation between the training matrix and the class label based on the class label corresponding to the sample policy;
calculating Manhattan distances from the test matrix to each training matrix;
and taking a second preset number of class labels corresponding to training matrixes with minimum Manhattan distance of the test matrixes as candidate classes, and taking the candidate class with the highest occurrence proportion as a policy class of the policy to be allocated.
9. The terminal device of claim 6, wherein the computing a process score for each insurance entity in the first acceptance group based on the operation records comprises:
if the insurance unit does not process the policy category of the policy to be allocated, setting the processing score of the insurance unit to 0;
if the insurance unit processes the policy category of the policy to be allocated, the policy category is calculated by the formula: calculating a processing score of the insurance unit by s=1- (T/T) - (e+p), wherein S is the processing score of the insurance unit, T is the policy processing time of the insurance unit contained in the operation record, T is the policy processing average time of a third preset number of insurance units calculated according to the operation record, e is the processing error rate of the insurance unit contained in the operation record, and p is the conversion processing probability of the insurance unit contained in the operation record.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810309425.9A CN108734590B (en) | 2018-04-09 | 2018-04-09 | Policy distribution method and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810309425.9A CN108734590B (en) | 2018-04-09 | 2018-04-09 | Policy distribution method and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108734590A CN108734590A (en) | 2018-11-02 |
| CN108734590B true CN108734590B (en) | 2023-04-28 |
Family
ID=63940647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810309425.9A Active CN108734590B (en) | 2018-04-09 | 2018-04-09 | Policy distribution method and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108734590B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112906998A (en) * | 2019-11-19 | 2021-06-04 | 泰康保险集团股份有限公司 | Data processing system and method for reassigning clerks to customers of an insurance company |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107688888A (en) * | 2017-06-13 | 2018-02-13 | 平安科技（深圳）有限公司 | Declaration form distribution method, device, storage medium and computer equipment |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
| CN107784590A (en) * | 2017-02-16 | 2018-03-09 | 平安科技（深圳）有限公司 | The appraisal procedure and device of a kind of claim reserve |
| CN107798592A (en) * | 2017-06-09 | 2018-03-13 | 平安科技（深圳）有限公司 | Calculate the method and apparatus of commission |
-
2018
- 2018-04-09 CN CN201810309425.9A patent/CN108734590B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784590A (en) * | 2017-02-16 | 2018-03-09 | 平安科技（深圳）有限公司 | The appraisal procedure and device of a kind of claim reserve |
| CN107798592A (en) * | 2017-06-09 | 2018-03-13 | 平安科技（深圳）有限公司 | Calculate the method and apparatus of commission |
| CN107688888A (en) * | 2017-06-13 | 2018-02-13 | 平安科技（深圳）有限公司 | Declaration form distribution method, device, storage medium and computer equipment |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108734590A (en) | 2018-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107945024B (en) | Method for identifying internet financial loan enterprise operation abnormity, terminal equipment and storage medium | |
| CN109961191B (en) | Coupon issuing method and device | |
| CN109543984A (en) | Risk control method, device, electronic equipment and medium | |
| CN111179066B (en) | Batch processing method and device for business data, server and storage medium | |
| JP7173332B2 (en) | Fraud detection device, fraud detection method, and fraud detection program | |
| CN110737917A (en) | Data sharing device and method based on privacy protection and readable storage medium | |
| CN108804564A (en) | The combined recommendation method and terminal device of financial product | |
| CN111598360A (en) | Service policy determination method and device and electronic equipment | |
| CN114896506A (en) | Product recommendation method, device, equipment and storage medium | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| CN108734590B (en) | Policy distribution method and terminal equipment | |
| CN114490692A (en) | Data checking method, device, equipment and storage medium | |
| CN114022264A (en) | Method, device, equipment and storage medium for generating certificate | |
| CN111242779B (en) | Financial data characteristic selection and prediction method, device, equipment and storage medium | |
| CN111695077A (en) | Asset information pushing method, terminal equipment and readable storage medium | |
| CN109446054B (en) | Processing method and terminal equipment for override operation request based on big data | |
| CN101770626A (en) | Method, device and system for identifying agents with card-laundering behavior | |
| WO2022057425A1 (en) | Identifying siem event types | |
| CN110264306B (en) | Big data-based product recommendation method, device, server and medium | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN109255698B (en) | Method for distributing refund amount based on big data and terminal equipment | |
| CN113487407A (en) | Data processing method and device and electronic equipment | |
| CN112116450A (en) | Risk early warning method and device | |
| CN111369370A (en) | Estimation table processing method, device, server and storage medium | |
| CN108876301A (en) | Data determination method, device, electronic equipment and computer readable 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 |