Method, device and storage medium for matching a collection scheme

Abstract

The application discloses a collection scheme matching method, device and equipment and a storage medium, which can be widely applied to the field of artificial intelligence technology. The method comprises the following steps: obtaining policy fee information corresponding to a plurality of target policies; performing data mining on the policy fee information corresponding to the plurality of target policies to obtain a policy value, a repayment probability and an estimated payment period corresponding to the target policies; performing classification processing on the target policies according to the policy value and the repayment probability to obtain classified policies; dividing a policy period corresponding to the classified policies into at least one collection time period, wherein each collection time period corresponds to an estimated payment period; and when the estimated payment period corresponding to the collection time period meets a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified policy. The embodiment of the application can effectively improve the collection efficiency.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a collection scheme matching method and device, equipment and a storage medium. BACKGROUND

[0002] In recent years, as people's insurance awareness continues to increase, more and more people buy insurance. Usually, when the insurance is about to expire, the user needs to be reminded to pay the premium. In related technologies, due to different payment habits of different users, such as the habit of paying early or the habit of paying late, the insurance company still adopts the way of constantly reminding the user to pay the premium to realize the collection process for the above-mentioned users, resulting in a large number of invalid collection of insurance policies, and thus low collection efficiency. SUMMARY

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] The main purpose of the embodiments of the present application is to provide a collection scheme matching method, device, equipment and storage medium, which can effectively improve the collection efficiency.

[0005] To achieve the above-mentioned purpose, in a first aspect, the embodiments of the present application provide a collection scheme matching method, comprising:

[0006] obtaining insurance premium information corresponding to a plurality of target insurance policies;

[0007] data mining the insurance premium information corresponding to the plurality of target insurance policies to obtain insurance value, repayment probability and estimated premium payment period corresponding to the target insurance policies;

[0008] classifying the target insurance policies according to the insurance value and the repayment probability to obtain classified insurance policies;

[0009] dividing the insurance period corresponding to the classified insurance policies into at least one collection time period, wherein each collection time period corresponds to the estimated premium payment period;

[0010] When the estimated premium payment period corresponding to the collection time period meets a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified insurance policies.

[0011] In some embodiments, the obtaining of the insurance premium information corresponding to the plurality of target insurance policies comprises:

[0012] obtaining the insurance premium information corresponding to the plurality of target insurance policies in a preset premium payment date;

[0013] The policy premium information includes at least one of policy amount information, cumulative payment times, and historical payment information.

[0014] In some embodiments, the dividing the policy period corresponding to the classified policy into at least one collection time period comprises:

[0015] The policy period corresponding to the classified policy is divided into four collection time periods in a time dimension;

[0016] The collection time period includes a preliminary collection time period, an intermediate collection time period, a later collection time period, and a final collection time period.

[0017] In some embodiments, the collection time period includes the preliminary collection time period, and the collection scheme includes:

[0018] When the current date reaches a preset payment date, collection information is sent, wherein the preliminary collection time period is provided with the preset payment date.

[0019] In some embodiments, the collection time period includes the intermediate collection time period or the later collection time period, and the collection scheme includes one of the following:

[0020] A collection suggestion date is obtained, and when the current date reaches the collection suggestion date, collection information is sent, wherein the collection suggestion date is obtained by a preset prediction model, or the collection suggestion date is obtained by a marking process; or

[0021] The estimated payment time period corresponding to the classified policy is taken as the collection suggestion date, and collection information is sent according to the collection suggestion date.

[0022] In some embodiments, the collection time period includes the final collection time period, and the collection scheme includes:

[0023] The collection suggestion date is obtained by analyzing the policy value.

[0024] When the current date reaches the collection suggestion date, collection information is sent.

[0025] In some embodiments, the estimated payment time period corresponding to the collection time period satisfies a preset collection condition, including:

[0026] The payment time period corresponding to the classified policy is obtained.

[0027] In a case where the estimated payment time period corresponding to the collection time period does not correspond to the payment time period, the preset collection condition is satisfied.

[0028] In a second aspect, the embodiments of the present application provide a collection device, comprising:

[0029] a data acquisition module configured to acquire policy expense information corresponding to a plurality of target policies;

[0030] a data mining module configured to perform data mining on the policy expense information corresponding to the plurality of target policies to obtain policy values, repayment probabilities, and estimated payment time periods corresponding to the target policies;

[0031] a classification processing module configured to perform classification processing on the target policies according to the policy values and the repayment probabilities to obtain classified policies;

[0032] a period division module configured to divide policy periods corresponding to the classified policies into at least one collection time period, wherein each of the collection time periods corresponds to the estimated payment time period;

[0033] a data matching module configured to, when the estimated payment time period corresponding to the collection time period satisfies a preset collection condition, match a corresponding collection scheme according to the collection time period corresponding to the classified policy.

[0034] In a third aspect, an embodiment of the present application provides a collection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the matching method of the collection scheme of the foregoing embodiment when executing the computer program.

[0035] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium storing a computer executable program, and the computer executable program is used to execute the matching method of the collection scheme of the foregoing embodiment.

[0036] The beneficial effects of the embodiments of the present application include: acquiring policy expense information corresponding to a plurality of target policies; performing data mining on the policy expense information corresponding to the plurality of target policies to obtain policy values, repayment probabilities, and estimated payment time periods corresponding to the target policies; performing classification processing on the target policies according to the policy values and the repayment probabilities to obtain classified policies; dividing policy periods corresponding to the classified policies into at least one collection time period, wherein each of the collection time periods corresponds to the estimated payment time period; and when the estimated payment time period corresponding to the collection time period satisfies a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified policy. According to the embodiments of the present application, the target policies are classified according to the policy values and the repayment probabilities to obtain classified policies, so that the target policies are distinguished, and a corresponding collection scheme is matched according to the collection time period corresponding to the classified policy, and the classified policies are collected through the collection scheme. Compared with related technologies, the embodiments of the present application can effectively improve the collection efficiency.

[0037] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structure particularly pointed out in the description and appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings are included to provide a further understanding of the technical solution of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the technical solution of the present application, and do not constitute a limitation on the technical solution of the present application.

[0039] Figure 1 Flowchart of the matching method of the collection scheme of the embodiment of the present application;

[0040] Figure 2 Flowchart of the pre-collection time period of the embodiment of the present application;

[0041] Figure 3 Flowchart of the mid-collection time period of the embodiment of the present application;

[0042] Figure 4 Flowchart of the end-collection time period of the embodiment of the present application;

[0043] Figure 5 Structural schematic diagram of the collection device of the embodiment of the present application;

[0044] Figure 6 Hardware structural schematic diagram of the collection equipment of the embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0046] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0048] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the

[0049] The block diagrams in the drawings show only the functionality and the relation between the functional entities, and not necessarily the physical arrangement of the entities. That is, the functional entities can be implemented in software, or in hardware, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0050] The flow diagrams shown in the drawings are merely examples of possible flow diagrams, and are not necessarily meant to include all of the steps or operations, nor are the steps or operations necessarily meant to be performed in the order shown. For example, some steps or operations can be broken down further, while some steps or operations can be combined or partially combined, and thus the actual order of execution can vary from what is described.

[0051] First, some terms involved in the present application are analyzed:

[0052] Artificial Intelligence (AI): is a new technical science that studies, develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; Artificial intelligence is a branch of computer science, and artificial intelligence aims to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. The research in this field includes robots, language recognition, image recognition, natural language processing and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also the theory, method, technology and application system of using digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, to perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0053] Automatic Speech Recognition (ASR): is a technology that converts human speech into text. Speech recognition is a multidisciplinary field closely related to acoustics, phonetics, linguistics, digital signal processing theory, information theory, computer science and many other disciplines. Due to the diversity and complexity of speech signals, speech recognition systems can only achieve satisfactory performance under certain restrictions, or can only be applied to certain specific situations.

[0054] Natural Language Processing (NLP): is a discipline that studies the language problem of human-computer interaction. According to the difficulty of technical implementation, such systems can be divided into three types: simple matching type, fuzzy matching type and paragraph understanding type. The simple matching type tutoring and answering system mainly realizes the matching of the question raised by the student and the relevant answer item in the answer library through simple keyword matching technology, so as to automatically answer the question or carry out relevant tutoring. The fuzzy matching type tutoring and answering system increases the matching of synonyms and antonyms on this basis. In this way, even if the question raised by the student cannot find a direct matching answer in the answer library according to the original keyword, but if the synonym or antonym of the keyword can be matched, the relevant answer item can still be found in the answer library. The paragraph understanding type tutoring and answering system is the most ideal and truly intelligent tutoring and answering system (strictly speaking, the simple matching type and the fuzzy matching type can only be called "automatic tutoring and answering system" rather than "intelligent tutoring and answering system").

[0055] At present, based on mature ASR / NLP technology, combined with big data mining technology, suitable collection opportunities can be identified in the collection scene, which can be used to guide the collection work.

[0056] In recent years, with the continuous enhancement of people's insurance consciousness, more and more people purchase insurance. Usually, when the insurance is about to expire, the user needs to be reminded to pay the premium. In the related art, due to different users having different payment habits, such as being used to paying the premium early or being used to paying the premium late, and the insurance company still adopts the way of continuously reminding the user to pay the premium to realize the collection process for the above users, for example, the way of non-discriminatory collection is adopted in the collection process, resulting in a large number of invalid collection of insurance policies, and thus leading to low collection efficiency, high collection cost and affecting user satisfaction.

[0057] Based on this, the embodiment of the application provides a collection scheme matching method, device and equipment and a storage medium. The collection scheme matching method comprises the following steps: obtaining policy fee information corresponding to a plurality of target policies; performing data mining on the policy fee information corresponding to the plurality of target policies to obtain a policy value, a repayment probability and an estimated payment period corresponding to the target policies; performing classification processing on the target policies according to the policy value and the repayment probability to obtain classified policies; dividing a policy period corresponding to the classified policies into at least one collection time period, wherein each collection time period corresponds to an estimated payment period; and when the estimated payment period corresponding to the collection time period meets a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified policies. The embodiment of the application classifies the target policies according to the policy value and the repayment probability to obtain the classified policies, thereby distinguishing the target policies, matching the corresponding collection scheme according to the collection time period corresponding to the classified policies, and collecting the classified policies through the collection scheme. Compared with related technologies, the embodiment of the application can effectively improve the collection efficiency, reduce the collection cost and ensure the user satisfaction.

[0058] The embodiment of the application provides a collection scheme matching method, device, equipment and storage medium. The collection scheme matching method is described in the following embodiment. First, the collection scheme matching method in the embodiment of the application is described.

[0059] The embodiment of the application can acquire and process related data such as original data of the embodiment of the application based on artificial intelligence technology. The artificial intelligence is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain optimal results.

[0060] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics and the like. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology and machine learning / deep learning and the like.

[0061] The application provides a method for matching a collection scheme, and relates to the technical field of artificial intelligence. The method for matching the collection scheme can be applied to a terminal, a server end, or software running in the terminal or the server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, or the like; the server end can be configured as a separate physical server, a server cluster composed of multiple physical servers, or a distributed system, and can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and big data and artificial intelligence platforms; and the software can be an application for implementing the method for matching the collection scheme, but is not limited to the above forms.

[0062] Specifically, the terminal / device can obtain the policy fee information corresponding to the target policy. The terminal / device can be a mobile terminal device or a non-mobile terminal device. The mobile terminal device can be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a palmtop computer, an ultra-mobile personal computer (UMPC), a wearable device, a netbook, a personal digital assistant (PDA), an augmented reality (AR) / virtual reality (VR) device, or the like. The non-mobile terminal device can be a personal computer, a teller machine, or a self-service machine, and the application does not make specific limitations.

[0063] The embodiments of the application can be used in many general or special computer system environments or configurations. For example, personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0064] Specifically, refer to Figure 1The embodiment of the present application provides a matching method of a collection scheme, including but not limited to the following steps S100 to S500:

[0065] Step S100, obtaining policy fee information corresponding to a plurality of target policies;

[0066] Step S200, data mining is performed on the policy fee information corresponding to the plurality of target policies, to obtain a policy value, a repayment probability and an estimated payment period corresponding to the target policy;

[0067] Step S300, performing classification processing on the target policy according to the policy value and the repayment probability, to obtain a classified policy;

[0068] Step S400, dividing a policy period corresponding to the classified policy into at least one collection time period, wherein each collection time period corresponds to an estimated payment period;

[0069] Step S500, when the estimated payment period corresponding to the collection time period meets a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified policy.

[0070] Exemplarily, the matching method of the collection scheme of the embodiment of the present application can be applied to a policy collection scene, for example, a collection scheme matching method is realized through a policy collection platform.

[0071] In some embodiments of the present application, the policy fee information corresponding to the plurality of target policies is obtained, for example, the policy fee information can include at least one of policy amount information, cumulative payment times, and historical payment information. The policy amount information refers to the amount of money to be collected for the policy; the historical payment information can be a historical payment habit, for example, a habit of early payment, a habit of late payment, a habit of irregular payment, etc.

[0072] In some embodiments of the present application, the policy value, the repayment probability and the estimated payment period corresponding to the target policy are obtained by data mining on the policy fee information corresponding to the plurality of target policies, for example, the policy amount information, the cumulative payment times and the historical payment information. Exemplarily, after data mining, the obtained policy value can have multiple categories, such as high policy value, medium policy value, and low policy value. In some embodiments, the policy value can be a collection value. That is, after data mining, the policy value corresponding to each target policy can be obtained, for example, a target policy with high policy value, a target policy with medium policy value, and a target policy with low policy value. Exemplarily, the policy values corresponding to all target policies are graded, the first 30% of the target policies are defined as high policy value, the 30% to 70% of the target policies are defined as medium policy value, and the last 30% of the target policies are defined as low policy value.

[0073] Exemplarily, after data mining, the repayment probability can also have multiple categories, such as high repayment probability, uncertain repayment probability, and low repayment probability. In some embodiments, the repayment probability represents the repayment willingness. That is, after data mining, the repayment probability corresponding to each target policy can be obtained, such as a target policy with high repayment probability, a target policy with uncertain repayment probability, and a target policy with low repayment probability.

[0074] It should be noted that the estimated payment period refers to a period in which the user, for example, an insurance user, is likely to generate a policy payment behavior.

[0075] Then, the target policies are classified according to the policy value and the repayment probability to obtain classified policies. Specifically, after data mining, the policy value and the repayment probability corresponding to each target policy can be obtained, and the policy value and the repayment probability are used as classification conditions to classify all target policies to obtain classified policies. In some embodiments, a target policy corresponding to a high policy value and a high repayment probability can be used as a kind of classified policy; or a target policy corresponding to a medium policy value and a high repayment probability can be used as a kind of classified policy; or a target policy corresponding to a low policy value and uncertain repayment probability can be used as a kind of classified policy; and so on. Nine different classified policies can be obtained. It should be noted that the categories corresponding to the policy value and the repayment probability are only one embodiment of the present application, and the present application is not limited thereto.

[0076] In some embodiments of the present application, the policy period corresponding to the classified policy is divided into at least one collection time period, for example, the policy period corresponding to the classified policy is divided into one collection time period, at which time the policy period is the collection time period; or the policy period corresponding to the classified policy is divided into two collection time periods; or the policy period corresponding to the classified policy is divided into four collection time periods, which are not limited by the embodiments of the present application. In some embodiments, the policy period corresponding to the classified policy is sequentially divided into at least one collection time period according to the time dimension, that is, at least one collection time period constitutes the policy period. By such a setting, a corresponding collection scheme is formed in each collection time period, and each collection time period corresponds to an estimated payment period. Exemplarily, the classified policy can correspond to an estimated payment period.

[0077] In the embodiments of the present application, when the estimated payment period corresponding to the collection time period satisfies the preset collection condition, the corresponding collection scheme is matched according to the collection time period corresponding to the classified policy. The preset collection condition can be that the estimated payment period corresponding to the collection time period does not correspond to a payment time period, that is, no policy payment behavior is generated.

[0078] Exemplarily, the payment time period is a time period in which the user generates a policy payment behavior.

[0079] It can be understood that the estimated payment period corresponding to the collection time period meets the preset collection condition, including: obtaining the payment time period corresponding to the classified policy; in the case that the estimated payment period corresponding to the collection time period does not correspond to the payment time period, the preset collection condition is met.

[0080] That is, the embodiment of the present application can predict the estimated payment period corresponding to the collection time period of the classified policy. When the estimated payment period corresponding to the collection time period does not correspond to the payment time period, that is, the estimated payment period does not generate the payment time period, it represents that the user does not generate the policy payment behavior, and at this time, the preset collection condition is met.

[0081] When the estimated payment period corresponding to each collection time period meets the preset collection condition that there is no corresponding payment time period, that is, no policy payment behavior is generated, according to each collection time period corresponding to the classified policy, the collection scheme corresponding to each collection time period is matched.

[0082] The beneficial effects of the embodiment of the present application include: obtaining policy fee information corresponding to a plurality of target policies; performing data mining on the policy fee information corresponding to the plurality of target policies to obtain policy values, repayment probabilities, and estimated payment periods corresponding to the target policies; classifying the target policies according to the policy values and the repayment probabilities to obtain classified policies; dividing a policy period corresponding to the classified policies into at least one collection time period, wherein each collection time period corresponds to an estimated payment period; when the estimated payment period corresponding to the collection time period meets the preset collection condition, matching the corresponding collection scheme according to the collection time period corresponding to the classified policy. According to the policy values and the repayment probabilities, the embodiment of the present application classifies the target policies to distinguish the target policies, so as to further match the corresponding collection scheme according to the collection time period corresponding to the classified policy. Through the collection scheme, the collection of the classified policy is realized, which can facilitate the matching of different collection schemes according to different classified policies. Compared with the non-discriminatory collection method of related technologies, the embodiment of the present application can effectively improve the collection efficiency.

[0083] In some embodiments, the policy value represents the loss value corresponding to the non-payment of the user, specifically, the policy value = premium * non-payment probability * payment frequency coefficient; wherein the payment frequency coefficient can be updated monthly, for example, the payment frequency coefficient can be: the coefficient of twice payment is 1.2, the coefficient of three times payment is 1.1, and the coefficient of four times and above payment = 1-n*0.01 (wherein n is the cumulative payment frequency).

[0084] In some embodiments, the repayment probability is obtained according to the payment probability model, artificial marking, or payment estimation state.

[0085] The target policy is input into the premium payment probability model to obtain the repayment probability corresponding to the target policy. Exemplarily, the repayment probabilities corresponding to all target policies are classified, the first 30% of target policies are defined as high repayment probability, 30% to 70% of target policies are defined as uncertain repayment probability, and the last 30% of target policies are defined as low repayment probability.

[0086] For example, the target policy with a repayment probability of 30% or less is defined as low repayment probability, the target policy with a repayment probability of 30% to 70% is defined as uncertain repayment probability, and the target policy with a repayment probability of 70% or more is defined as high repayment probability.

[0087] Exemplarily, the repayment probability corresponding to the target policy can also be classified according to the premium estimation state (manual labeling). The target policy with low repayment probability is defined as unrecoverable state, the target policy with uncertain repayment probability is defined as uncertain state, and the target policy with high repayment probability is defined as recoverable state.

[0088] The premium payment probability model is obtained by modeling a plurality of feature data, and the feature data includes at least one of the following: total premium of the policy, total premium of the policy, number of premium payments, small category of insurance, total annual standard premium, number of days from the date of the salesperson's regular date to today, total period premium, number of invalid policies under the name of the policyholder, invalid amount of policies under the name of the policyholder, number of invalid policies under the name of the policyholder, and the like.

[0089] It can be understood that the premium information corresponding to the plurality of target policies is obtained, including: obtaining the premium information corresponding to the plurality of target policies in the preset premium payment date; wherein the premium information includes at least one of the policy amount information, the cumulative number of premium payments, and the historical premium information.

[0090] Specifically, for each target policy, a preset premium payment date is set, which represents the policy payment date. When the current date reaches the policy payment date (payment date), the premium information corresponding to the plurality of target policies is obtained.

[0091] It can be understood that the preset premium payment date is set in the policy period corresponding to the target policy.

[0092] It can be understood that the policy period corresponding to the classified policy is divided into at least one collection time period, including: dividing the policy period corresponding to the classified policy in the time dimension to obtain four collection time periods, wherein the collection time period includes the early collection time period, the middle collection time period, the late collection time period and the end collection time period.

[0093] The policy period corresponding to the classified policy is divided into time periods to obtain four collection time periods, so that the collection scheme corresponding to the four collection time periods is matched according to the four collection time periods corresponding to the classified policy.

[0094] Exemplarily, the policy period corresponding to the classified policy can also be divided into time periods to obtain three collection time periods, wherein the collection time period includes an early collection time period, a middle collection time period, and a late collection time period, which are not limited by the present application.

[0095] Referring to Figure 2 It can be understood that the collection time period includes an early collection time period, and the collection scheme includes but is not limited to the following step S501.

[0096] In step S501, when the current date reaches the preset payment date, collection information is sent, wherein the early collection time period is provided with the preset payment date.

[0097] The embodiment of the present application divides the policy period corresponding to the classified policy into time periods to obtain four collection time periods, and each collection time period corresponds to a predicted payment period.

[0098] The classified policy does not correspond to a payment time period in the early collection time period (for example, T-T10, wherein T represents the preset payment date, and T10 represents the 10 days after the preset payment date), that is, no policy payment behavior is generated, that is, the predicted payment period corresponding to the early collection time period meets the preset collection condition, and the corresponding collection scheme is matched according to the early collection time period corresponding to the classified policy. The collection scheme is: when the current date reaches the preset payment date, for example, reaches T, collection information is sent.

[0099] The classified policy of the embodiment of the present application needs to be collected once on the preset payment date (the due date), so the collection is performed on the fixed collection time, that is, the preset payment date.

[0100] Referring to Figure 3 It can be understood that the collection time period includes a middle collection time period or a late collection time period, and the collection scheme includes one of the following:

[0101] In step S502, a collection suggestion date is obtained, and when the current date reaches the collection suggestion date, collection information is sent, wherein the collection suggestion date is predicted by a preset prediction model, or the collection suggestion date is obtained by a marking process; or,

[0102] In step S503, the predicted payment period corresponding to the classified policy is taken as the collection suggestion date, and the collection information is sent according to the collection suggestion date.

[0103] The classified policy of the embodiment of the present application corresponds to no payment time period in the middle period collection time period (for example, T10-T30, wherein T10 represents 10 days after the preset payment date, and T30 represents 30 days after the preset payment date) and the late collection time period (for example, T30-T45, wherein T45 represents 45 days after the preset payment date), that is, the estimated payment time period corresponding to the middle period collection time period or the late collection time period satisfies the preset collection condition, and the corresponding collection scheme is matched according to the middle period collection time period or the late collection time period corresponding to the classified policy. The collection scheme is as follows: an collection suggestion date is obtained, wherein the collection suggestion date is obtained by a preset prediction model, or the collection suggestion date is obtained by a marking process; when the current date reaches the collection suggestion date, collection information is sent, or the estimated payment time period corresponding to the classified policy is taken as the collection suggestion date, and the collection information is sent according to the collection suggestion date.

[0104] Exemplarily, the collection scheme of the embodiment of the present application can be that the collection suggestion date is obtained according to the preset prediction model and the marking process. The collection suggestion date represents a suitable collection opportunity.

[0105] Specifically, in the case that the collection suggestion date is an estimated payment time period obtained by the preset prediction model, or the collection suggestion date is a suggestion collection time point obtained by the marking process, for example, artificial marking, the collection is performed according to the marking process collection suggestion date>the estimated payment time period obtained by the preset prediction model.

[0106] In some embodiments, for the classified policy with high policy value and difficulty, the investment time is long, and the collection should be performed as early as possible; for the classified policy with low policy value and easy recovery, the investment time is small, and the collection can be performed late. In summary, the opportunity can be judged according to the collection principle in Table 1 as follows.

[0107] Exemplarily, the classified policy with high policy value and difficulty is collected as early as possible, and the classified policy with low policy value and easy recovery is collected late. Exemplarily, the collection can be realized by a telephone, an email, a short message and the like, so as to realize the sending of the collection information.

[0108] Table 1

[0109]

[0110] According to Table 1, the estimated payment period corresponding to the classified policy is the collection suggestion date. For example, the classified policy corresponding to the high repayment probability and the high or medium or low policy value, the corresponding collection suggestion date is T20-T30; the classified policy corresponding to the uncertain repayment probability and the high or medium policy value, the corresponding collection suggestion date is T10-T20. Illustratively, by classifying the target policy according to the policy value and the repayment probability, different estimated payment periods correspond to different classified policies. When there is no manually marked collection suggestion date and the preset prediction model predicts the estimated payment period in the medium-term or late-term collection period, the estimated payment period corresponding to the classified policy is used as the collection suggestion date.

[0111] Illustratively, the collection scheme corresponding to the medium-term or late-term collection period can be specifically:

[0112] Determine whether there is a next collection time marked by processing (i.e., personal marking / artificial marking), i.e., the collection suggestion date. When there is a marked collection suggestion date (i.e., personal marking / artificial marking), collection is performed according to the 'next collection time', i.e., the collection suggestion date.

[0113] When there is no marked collection suggestion date (i.e., personal marking / artificial marking), it is determined whether there is an estimated payment period T10 predicted by the preset prediction model, i.e., the collection suggestion date. But the classified policy does not pay after T10, i.e., the collection suggestion date, i.e., the estimated payment period predicted by the preset prediction model does not correspond to a payment period, i.e., no policy payment behavior is generated. When there is an estimated payment period predicted by the preset prediction model, i.e., the collection suggestion date, the collection information is sent according to the collection suggestion date, i.e., output 'T10-T20'.

[0114] When there is no collection suggestion date predicted by the preset prediction model, the estimated payment period corresponding to the classified policy is matched according to the policy value and the repayment probability. The estimated payment period corresponding to the classified policy is used as the collection suggestion date, and the collection information is sent according to the collection suggestion date.

[0115] It should be noted that the preset prediction model can predict the estimated payment period, which can be directly used as the collection suggestion date. For example, when the estimated payment period is (T, T10) period payment of the insurance user, the (T, T10) period is used as the collection suggestion date.

[0116] Illustratively, according to the payment rules of the insurance user, there are insurance users who habitually pay early. By analyzing the target policy corresponding to such insurance users, 49 characteristic data such as the user's payment habit, the user's lag days under the same agent, and the continuation rate under the same agent can be obtained.

[0117] Modeling learning is performed according to the above feature data to identify the habit of early payment of the insurance user, for example, the insurance user who is expected to pay in the (T, T10) period.

[0118] Referring to Figure 4 It can be understood that the collection time period includes the end collection time period, and the collection scheme includes but is not limited to the following steps S504 to S505:

[0119] In step S504, a collection suggestion date is analyzed according to the policy value.

[0120] In step S505, when the current date reaches the collection suggestion date, collection information is sent.

[0121] The classified policy of the embodiment of the present application does not correspond to a premium payment time period in the end collection time period (for example, T45-T60, where T45 represents 45 days after the preset premium payment date, and T60 represents 60 days after the preset premium payment date), that is, no premium payment behavior is generated in the end collection time period, that is, the estimated payment time period corresponding to the end collection time period meets the preset collection condition, and according to the end collection time period corresponding to the classified policy, a corresponding collection scheme is matched. The collection scheme is: according to the policy value, a collection suggestion date is analyzed, and when the current date reaches the collection suggestion date, collection information is sent.

[0122] It should be noted that since the premium payment time of the classified policy at this time has reached the end, it must be a difficult collection item, and therefore, a suitable collection opportunity is analyzed according to the policy value, that is, a collection suggestion date is analyzed.

[0123] The embodiment of the present application recommends suitable collection time periods to human and AI external calls for daily output. The insurance company arranges suitable collection efforts for human or AI external calls for the collection time period. For example, when the collection time period is the early collection time period, for example, (0, 10) days, the key collection is arranged 10 days after the preset premium payment date, that is, the human can collect 10 days later.

[0124] When the collection time period is the middle collection time period, for example, (10, 30) days, no collection is arranged at (0, 10) days. Thus, the collection cost can be greatly reduced and the collection efficiency can be improved on the basis of ensuring the same collection effect.

[0125] The matching method of the collection scheme in the embodiment of the application, by obtaining the policy fee information corresponding to a plurality of target policies; performing data mining on the policy fee information corresponding to the plurality of target policies to obtain the policy value, the repayment probability and the estimated payment period corresponding to the target policy; classifying the target policy according to the policy value and the repayment probability to obtain a classified policy; dividing the policy period corresponding to the classified policy into at least one collection time period, wherein each collection time period corresponds to an estimated payment period; and when the estimated payment period corresponding to the collection time period meets a preset collection condition, matching the corresponding collection scheme according to the collection time period corresponding to the classified policy. According to the policy value and the repayment probability, the embodiment of the application classifies the target policy to obtain a classified policy, thereby distinguishing the target policy, so as to further match the corresponding collection scheme according to the collection time period corresponding to the classified policy, and to realize the collection of the classified policy through the collection scheme, which can facilitate the matching of different collection schemes according to different classified policies. Compared with the non-discriminatory collection method of the related art, the embodiment of the application can effectively improve the collection efficiency.

[0126] It should be noted that in each specific embodiment of the application, when it is necessary to process related data related to the identity or characteristics of the user, such as user information (for example, policy fee information), user behavior data (for example, cumulative payment times), user historical data (for example, historical payment information) and user location information, the user's permission or consent will be obtained first, and the collection, use and processing of these data will comply with the relevant laws, regulations and standards of the country and region. In addition, when the embodiment of the application needs to obtain sensitive personal information of the user, the user's separate permission or separate consent will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for the normal operation of the embodiment of the application will be obtained.

[0127] Referring to Figure 5 An embodiment of the application further provides a collection device which can realize the matching method of the collection scheme, and the collection device includes but is not limited to the following modules:

[0128] The data acquisition module 100 is configured to obtain the policy fee information corresponding to a plurality of target policies;

[0129] The data mining module 200 is configured to perform data mining on the policy fee information corresponding to the plurality of target policies to obtain the policy value, the repayment probability and the estimated payment period corresponding to the target policy;

[0130] The classification processing module 300 is configured to classify the target policy according to the policy value and the repayment probability to obtain a classified policy;

[0131] The period division module 400 divides the policy period corresponding to the classified policy into at least one collection time period, wherein each collection time period corresponds to a predicted payment period;

[0132] The data matching module 500 is configured to match a corresponding collection scheme according to the collection time period corresponding to the classified policy when the predicted payment period corresponding to the collection time period meets a preset collection condition.

[0133] It should be noted that the contents of the method embodiments of the present application are applicable to the device embodiments, the device embodiments specifically implement the same functions as the above-mentioned method embodiments, and achieve the same beneficial effects as the above-mentioned method, which will not be described here.

[0134] The present application also provides a collection device, which comprises a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing the connection and communication between the processor and the memory, and the program is executed by the processor to realize the matching method of the above-mentioned collection scheme. The collection device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0135] It should be noted that the collection device in the present embodiment can be applied to the matching method of the collection scheme of the above-mentioned embodiments, and the collection device in the present embodiment and the matching method of the collection scheme of the above-mentioned embodiments have the same inventive concept, so these embodiments have the same implementation principle and technical effects, which will not be described in detail here.

[0136] Please refer to Figure 6 , Figure 6 The hardware structure of the collection device will be described in detail. The collection device comprises a processor 801, a memory 802, an input / output interface 803, a communication interface 804 and a bus 805.

[0137] The processor 801 can be implemented by a general CPU (Central Processing Unit, central processor), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute related programs to realize the technical scheme provided by the present application.

[0138] The memory 802 can be implemented in the form of a read only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM), etc. The memory 802 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 802 and are called and executed by the processor 801 to implement the matching method of the collection scheme provided by the embodiments of the present application;

[0139] The input / output interface 803 is configured to realize information input and output.

[0140] The communication interface 804 is configured to realize the communication interaction between the device and other devices, and the communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0141] The bus 805 is configured to transmit information between various components (for example, the processor 801, the memory 802, the input / output interface 803 and the communication interface 804) of the device.

[0142] The processor 801, the memory 802, the input / output interface 803 and the communication interface 804 are connected to each other through the bus 805 to realize the communication connection between the devices.

[0143] The above-described collection device embodiments are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the present embodiment.

[0144] The embodiments of the present application also provide a computer readable storage medium for computer readable storage, and the computer readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the matching method of the above collection scheme.

[0145] The memory is a non-transitory computer readable storage medium, which can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0146] The application embodiment provides a matching method, device and equipment of a collection scheme and a storage medium. The matching method comprises the following steps: obtaining policy fee information corresponding to a plurality of target policies; performing data mining on the policy fee information corresponding to the plurality of target policies to obtain policy values, repayment probabilities and estimated payment time periods corresponding to the target policies; performing classification processing on the target policies according to the policy values and the repayment probabilities to obtain classified policies; dividing a policy period corresponding to the classified policies into at least one collection time period, wherein each collection time period corresponds to an estimated payment time period; and when the estimated payment time period corresponding to the collection time period meets a preset collection condition, matching a corresponding collection scheme according to the collection time period corresponding to the classified policy. According to the application embodiment, the target policies are classified according to the policy values and the repayment probabilities to obtain the classified policies, so that the target policies are distinguished, and then the corresponding collection scheme is matched according to the collection time period corresponding to the classified policy, and the classified policy is collected through the collection scheme. Compared with the related art, the application embodiment can effectively improve the collection efficiency.

[0147] The embodiments described in the application embodiment are used to more clearly illustrate the technical solutions of the application embodiment, and do not constitute a limitation on the technical solutions provided by the application embodiment. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the application embodiment are also applicable to similar technical problems.

[0148] Those skilled in the art can understand that, Figures 1-4 The technical solutions shown in the above description do not constitute a limitation on the application embodiment, and can include more or fewer steps, or combine some steps, or different steps.

[0149] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0150] Those skilled in the art can understand that all or some steps in the above disclosed method, the functions of the modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0151] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of this application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of orderly or chronological mundane operation, reverse order operation, based on circuitry availability, based on stated preference or the like, and that "default" or other orderings are thus permissible. Further, the terms "comprise", "comprising", "include", "including", and the like, are specifically intended to be open-ended. That is, references to individual steps and the like do not suhstantially exclude the presence of two or more of a given step or its integral presence in the process, method, system, article, or apparatus having been made with a wider scope. The use of notation such as "first", "second", "third", etc. does not generally limit the areas, but is used to connect between similar objects.

[0152] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the relationship between the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and back associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0153] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the above-mentioned units is only a logical functional division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0154] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0155] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0156] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0157] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above-mentioned embodiments. Those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for matching collection schemes, characterized in that, include: Obtain policy fee information for multiple target policies, including: Within a preset payment date, obtain policy fee information corresponding to multiple target policies; wherein, the policy fee information includes at least one of policy amount information, cumulative number of payments, and historical payment information; Data mining is performed on the policy fee information corresponding to multiple target policies to obtain the policy value, repayment probability, and estimated payment period of the target policies; The target policies are classified according to the policy value and the repayment probability to obtain classified policies; The policy periods corresponding to the aforementioned categorized policies are divided into at least one collection period, including: The policy period corresponding to the classified policies is divided into four collection periods in the time dimension; each collection period corresponds to the estimated payment period, and the collection period includes the early collection period, the middle collection period, the late collection period and the final collection period. When the estimated payment period corresponding to the collection period meets the preset collection conditions, the corresponding collection plan is matched according to the collection period corresponding to the category of insurance policy.

2. The matching method for collection schemes according to claim 1, characterized in that, The collection period includes the initial collection period, and the collection plan includes: When the current date reaches the preset payment date, a collection reminder message is sent, wherein the preset payment date is set in the early collection period.

3. The matching method for collection schemes according to claim 1, characterized in that, The collection period includes the mid-term collection period or the late-term collection period, and the collection plan includes one of the following: Obtain a suggested collection date; when the current date reaches the suggested collection date, send collection information. The suggested collection date is either predicted by a preset prediction model or obtained through tagging. The estimated payment period corresponding to the classified policies is used as the collection suggestion date, and collection information is sent according to the collection suggestion date.

4. The matching method for collection schemes according to claim 1, characterized in that, The collection period includes the final collection period, and the collection plan includes: Based on the policy value, a suggested collection date is determined. When the current date reaches the suggested collection date, a collection message is sent.

5. The matching method for collection schemes according to any one of claims 1 to 4, characterized in that, The estimated payment period corresponding to the collection period meets the preset collection conditions, including: Obtain the payment period corresponding to the aforementioned policy category; If the estimated payment period corresponding to the collection period does not correspond to the payment period, the preset collection conditions are met.

6. A collection device, characterized in that, include: The data acquisition module is used to obtain policy expense information for multiple target policies, including: Within a preset payment date, obtain policy fee information corresponding to multiple target policies; wherein, the policy fee information includes at least one of policy amount information, cumulative number of payments, and historical payment information; The data mining module is used to perform data mining on the policy fee information corresponding to multiple target policies to obtain the policy value, repayment probability and estimated payment period of the target policies. The classification processing module is used to classify the target insurance policy according to the policy value and the repayment probability to obtain classified insurance policies; The period segmentation module is used to divide the policy period corresponding to the categorized policies into at least one collection period, including: The policy period corresponding to the classified policies is divided into four collection periods in the time dimension; each collection period corresponds to the estimated payment period, and the collection period includes the early collection period, the middle collection period, the late collection period and the final collection period. The data matching module is used to match the corresponding collection plan according to the collection period corresponding to the category of insurance policies when the estimated payment period corresponding to the collection period meets the preset collection conditions.

7. A collection device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements a matching method for collection schemes as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The system contains a computer-executable program for performing a matching method for a collection scheme according to any one of claims 1 to 5.

Images