Optimal strategy recommendation method and device, equipment and storage medium

Abstract

The invention belongs to the technical field of computer software, is applied to the field of medical health and the field of financial science and technology, and discloses an optimal strategy recommendation method, device and equipment and a storage medium. Analyzing the business document based on a pre-configured rule set, and generating a business calculation factor corresponding to the business document; obtaining customer portrait data associated with the business document; generating a business success probability of the business document according to the customer portrait data; and recommending an optimal processing strategy set of the business document to the target user based on the business calculation factor and the business success probability. The technical problem that in the prior art, it cannot be guaranteed that the selection rate of a customer for business receipts is high and the business target value corresponding to the business receipts is high at the same time is solved.

Description

Technical Field

[0001] The present invention belongs to the field of computer software technology and is applied to the fields of medical health and financial technology, and in particular relates to a method, device, equipment and storage medium for recommending an optimal strategy. Background Art

[0002] The insurance industry has experienced rapid growth in recent years. To attract more customers to insurance, agents must first be motivated. Therefore, when agents recommend insurance to clients, they earn commissions corresponding to the successful recommendations. Naturally, the higher the commissions earned, the higher the agent's work enthusiasm, which translates into more insurance purchases from clients, and ultimately, better sustainable growth for the insurance company.

[0003] With diverse commission strategies, balancing incentives and costs presents a challenge. Simply increasing commissions for a single agent increases the insurance company's financial burden, part of which is transferred to clients' insurance costs, thereby reducing their purchase rate. To address this, insurance companies can adopt a high-volume sales strategy, recommending insurance plans that clients are more likely to accept and purchase. However, the commissions for these plans are not guaranteed and may be low. This means that even after helping clients handle a large number of insurance cases, agents still may not receive a commission commensurate with their workload, significantly dampening their work enthusiasm.

[0004] Therefore, the prior art cannot simultaneously ensure that the customer selection rate of the business document is high and the business target value (such as agent commission) corresponding to the business document is high. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for recommending an optimal strategy to solve the technical problem that the existing technology cannot simultaneously ensure a high customer selection rate for a business document and a high business target value corresponding to the business document.

[0006] In a first aspect, the present invention provides a method for recommending an optimal strategy, comprising:

[0007] Obtain the business documents associated with the target user;

[0008] Parsing the business document based on a preconfigured rule set to generate a business calculation factor corresponding to the business document;

[0009] Obtaining customer profile data associated with the business document;

[0010] Generate a business success probability of the business document based on the customer profile data;

[0011] Based on the business calculation factor and the business success probability, an optimal processing strategy set for the business document is recommended to the target user.

[0012] In a second aspect, the present invention provides an optimal strategy recommendation device, comprising:

[0013] The first acquisition module is used to obtain the business documents associated with the target user;

[0014] A first generating module, configured to parse the business document based on a preconfigured rule set and generate a business calculation factor corresponding to the business document;

[0015] A second acquisition module is used to obtain customer portrait data associated with the business document;

[0016] A second generating module is used to generate a business success probability of the business document based on the customer portrait data;

[0017] A recommendation module is used to recommend an optimal processing strategy set for the business document to the target user based on the business calculation factor and the business success probability.

[0018] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned optimal strategy recommendation method when executing the computer program.

[0019] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned optimal strategy recommendation method are implemented.

[0020] The solution implemented by the aforementioned optimal strategy recommendation method, apparatus, device, and storage medium analyzes and calculates specific business calculation factors for a business document, thereby calculating the target value of the service corresponding to the business document based on the business calculation factors. Furthermore, the solution can calculate the service success probability for each business document. Thus, based on the target value and success probability of the service for a business document, a business document with both a high target value and a high success probability can be recommended to the target user. This ensures that when the target user connects the business document to a customer, the target value of the business document is high and the customer selection rate for the business document is high.

[0021] In summary, this solution can solve the problem in the prior art of simultaneously ensuring a high customer selection rate for business documents and a high business target value for business documents. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1 This is a flow chart of a method for recommending an optimal commission strategy in one embodiment of the present invention;

[0024] Figure 2 yes Figure 1 A flow chart of step S140;

[0025] Figure 3 yes Figure 1 A flow chart of step S150;

[0026] Figure 4 is another flow chart of a method for recommending an optimal commission strategy in one embodiment of the present invention;

[0027] Figure 5 This is another flowchart of a method for recommending an optimal commission strategy in one embodiment of the present invention;

[0028] Figure 6 This is a schematic structural diagram of a device for recommending an optimal commission strategy in one embodiment of the present invention;

[0029] Figure 7 is a structural diagram of a computer device in one embodiment of the present invention;

[0030] Figure 8 FIG. 2 is another structural diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0032] Figure 1 A flowchart of a method for recommending an optimal commission strategy according to an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method for generating interface test cases provided by the embodiment of the present invention includes the following steps.

[0033] Step S110: Acquire the business document associated with the target user.

[0034] It should be noted that the target user in step S110 is a person related to the business document. For example, in the insurance field, the target user may be an individual responsible for providing insurance services to associated customers. For example, the target user may refer to an institution or individual that collects commissions from the insurer (i.e., the agent's associated customer) based on the entrustment and handles insurance business on behalf of the insurer within the scope of the insurer's authorization. The business document in step S110 may be a business document in any field. For example, a business document may be an insurance business that the insurance agent is responsible for that is renewed by the associated customer in the future. As a specific example, for example, in a medical and health insurance scenario, the policy data to be renewed may be commercial medical insurance, major disease insurance, or nursing insurance, etc. In a financial insurance scenario, the policy data to be renewed may be term life insurance, whole life insurance, or annuity insurance, etc.

[0035] It should be noted that if the business document obtained in step S110 is pending policy data, then any feasible method may be used to obtain the pending policy data for the agent's associated clients. For example, a database may be pre-stored with information about agents, their associated clients, the pending policy data for the associated clients, and the relationships between them. Thus, after a target agent is identified, the database may be used to extract the client data associated with the target agent and the pending policy data for the associated clients.

[0036] Step S120: parsing the business document based on a preconfigured rule set to generate a business calculation factor corresponding to the business document.

[0037] It should be noted that in this step, the business calculation factor is ultimately used to calculate the target value of the business document. The target value here can be determined based on the specific needs of the business application. For example, in the insurance field, the business document may be the data of the pending policy, and the target value may be the commission corresponding to the pending policy data.

[0038] Specifically, in this step, the method for parsing business documents based on a preconfigured rule set can be any feasible method. For example, a rule configuration layer, a document parsing layer, a factor calculation layer, and a configuration management module can be provided. The rule configuration layer is used to store parsing rules, the document parsing layer is used to extract key data fields based on the rules, the factor calculation layer is used to execute calculation logic based on the extracted data, and the configuration management module is used to support the addition, deletion, modification, and version control of rules.

[0039] As a specific example, a preconfigured rule set can be obtained by building a knowledge graph for a relevant business domain. For example, in the insurance field, a preconfigured rule set can be a commission rule set, which can include a product classification rule set, a policy attribute determination rule set, and a fee annual rule set.

[0040] It is understood that different target values ​​are typically set for different business documents. As a specific example, an agent may charge different commissions for different renewal policy data. In this step, the target value for the business document varies based on the business calculation factor, and ultimately, different business calculation factors can distinguish different business documents. For example, the commission varies based on the commission calculation factor, and different commission calculation factors can distinguish different renewal policy data.

[0041] It is understandable that, in this step, as a specific example, when the commission rule set includes a product classification rule set, a policy attribute determination rule set, and a fee year rule set, the pending policy data is parsed according to the commission rule set, and the commission calculation factors corresponding to the generated pending policy data include the product classification corresponding to the pending policy data, the policy attributes corresponding to the pending policy data, and the fee year corresponding to the pending policy data. Specifically, the product classification of the pending policy data may include short-term insurance product classification and long-term insurance product classification. The policy attributes of the pending policy data may include orphan policies and active policies, where an orphan policy is a policy for which the original agent responsible has resigned, and an active policy is a policy for which the original agent responsible is still employed. The handling fee year may include the policy year, the guaranteed renewal year and the policy continuous payment year, where the policy year is the year in which the policy data to be renewed is located. For example, if the policy data to be renewed is in the fifth year since the insurance contract takes effect, then the policy year of the policy data to be renewed is the fifth policy year; the guaranteed renewal year is the annual time that the policy data to be renewed continues. For example, if the guaranteed renewal year of a policy data to be renewed is 5 years, then within the 5 years that the policy data to be renewed takes effect, the customer will enjoy the insurance corresponding to the policy data to be renewed; the continuous payment year refers to the year in which the customer has paid premiums continuously for the policy data to be renewed. For example, if the customer has paid premiums for the fifth consecutive year since the first payment of premium, then the continuous payment year is 5 years.

[0042] As a specific example, in the field of medical health insurance, assuming that the policy data to be renewed is critical illness insurance, its corresponding product category is the long-term insurance product category. The initial commission ratio corresponding to the long-term insurance product category is 30%, and the responsible agent is in office, so it is not an orphan policy. Therefore, the commission ratio corresponding to the long-term insurance product category will not be further changed. The policy year of the current policy data to be renewed is the fourth year, and the rule set of the fee annual rule set is that as the policy year increases, the policy commission will decrease at a rate of 2% per year. In this way, the commission ratio corresponding to the current fourth policy year is 24%. Therefore, it can be obtained that the commission finally obtained by the agent is the premium multiplied by 24%.

[0043] Step S130: Obtain the customer portrait data associated with the business document.

[0044] Specifically, in this step, customer profile data refers to customer information related to the business. For example, in the insurance business, customer profile data may include basic customer information (age, gender, occupation, income, etc.), consumption behavior, insurance preferences, and other multi-dimensional information.

[0045] Step S140: Generate a purchase success probability for the policy data to be renewed based on the customer portrait data of the associated customer.

[0046] In some embodiments of the present invention, Figure 2 As shown, step S140 includes the following steps.

[0047] Step S141: Acquire historical business documents of the customer associated with the business document.

[0048] Specifically, in this step, all historical business document records for the associated customer can be precisely filtered from the database based on the customer's unique identifier. For example, in the insurance sector, historical business documents can be historical insurance policy data. This historical policy data can include a wealth of information, including the policy purchase date, insurance type (such as critical illness insurance, life insurance, medical insurance, etc.), insured amount, premium payment status, whether a claim has been made, and the claim amount. For example, customer Zhang San has purchased three policies from the same insurance company since 2015. These include a critical illness insurance policy with a coverage of 500,000 yuan purchased in 2015, with an annual premium of 10,000 yuan. To date, premiums have been paid regularly and no claims have been made; a term life insurance policy with a coverage of 1 million yuan purchased in 2018, with an annual premium of 5,000 yuan. A claim was settled in 2020 due to the accidental death of the insured; and a medical insurance policy purchased in 2022, with an annual premium of 2,000 yuan, which is currently within the normal coverage period.

[0049] Step S142: Analyze and obtain the business target impact factors of the historical business documents.

[0050] Specifically, the business target influencing factor in this step is a factor that affects the target value of the business.

[0051] Specifically, in this step, data analysis and mining techniques can be used to identify factors that significantly impact the business's target value from massive amounts of historical business documents. For example, in the insurance sector, the target value might be the renewal rate of policy data. Analyzing and deriving the factors influencing the business target means identifying factors from the policy data that significantly impact renewal behavior. Factors that significantly impact renewal behavior may include:

[0052] Payment habits: Has the customer paid their premiums on time in the past? Do they pay in advance, on time, or frequently overdue? For example, customers who frequently pay on time may have a high degree of insurance acceptance and loyalty and be more likely to renew their policy. On the other hand, customers who frequently overdue their premiums may be less likely to renew.

[0053] Claims experience: If a customer has had claims experience in previous policies and the claims process went smoothly and they received satisfactory compensation, they may have stronger trust in the insurance company and thus increase their willingness to renew their policy. Conversely, if the claims process is cumbersome and the compensation amount is not ideal, the possibility of renewal may be reduced.

[0054] Reasonable combination of insurance types: Whether the different insurance types held by the customer form a reasonable combination of protection. For example, if a customer has both critical illness insurance to cover the risk of major illnesses and medical insurance to supplement medical expense reimbursement, the customer is likely to renew their insurance more easily. However, if the customer's insurance combination has obvious gaps, they may be prompted to adjust their insurance plan or even switch insurers when renewing.

[0055] Changes in customer age and family circumstances: As customers age, their insurance needs may shift. For example, while younger, they may be more interested in accident and medical insurance, as they age, their demand for critical illness and retirement insurance may increase. Changes in family circumstances, such as marriage, childbirth, and family illness, can also influence customers' insurance needs and renewal decisions.

[0056] Furthermore, the correlation between these factors and renewal behavior can be quantitatively analyzed through statistical analysis, association rule mining and other methods to determine the impact of each factor on renewal.

[0057] Step S143: Mark the renewal factor on the historical policy data to form sample data.

[0058] Specifically, after clarifying the factors influencing the business objectives, the specific information of these factors is annotated on the corresponding historical policy data. For example, for the critical illness insurance policy purchased by Zhang San in 2015, his payment habit is "payment on time", and his claim experience is "no claim". In terms of insurance type matching, this critical illness insurance is a good complement to the medical insurance purchased later. The customer was 30 years old at the time of purchase and his family status was single. These renewal influencing factor information are integrated with other basic information of the policy (such as policy number, purchase time, insurance type, etc.) to form a complete sample data. This annotation process is performed on the historical policy data of all related customers, thereby constructing a data set containing a large amount of sample data, which will be used to train the prediction model.

[0059] Step S144: input the sample data into a preset model to train the preset model.

[0060] Specifically, the preset model can be various types of machine learning models, such as logistic regression models, decision tree models, neural network models, etc. Taking the logistic regression model as an example, the sample data with the renewal influencing factors labeled are input into the model. The model adjusts the parameters of the model by continuously learning the relationship between the features in the sample data (i.e., renewal influencing factors) and the target variable (whether to renew). During the training process, the model calculates the error between the predicted result and the actual result (such as cross entropy loss) based on the sample data, and then continuously adjusts the model parameters through optimization algorithms (such as gradient descent method) to gradually reduce the error, thereby improving the model's prediction accuracy for renewal behavior. After repeated training on a large amount of sample data, the model gradually learned the inherent laws between the combination of different business goal influencing factors and the success probability of the business goal, and has the ability to predict the success probability of business goals for new data.

[0061] Step S145: extract the business objective influencing factors of the historical business documents in the customer portrait data.

[0062] As a specific example, as mentioned above, in the insurance sector, customer profile data is a comprehensive description of the customer, including basic information (age, gender, occupation, income, etc.), consumption behavior, insurance preferences, and other multi-dimensional information. From this rich customer profile data, target renewal influencing factors (i.e., business target influencing factors) related to the data of the pending renewal policy are extracted. For example, for a critical illness insurance policy that is about to expire and is pending renewal, it is necessary to extract target renewal influencing factors such as the customer's current age (because age changes may affect the demand for critical illness insurance), income level (income level affects premium payment ability), past critical illness insurance purchase history (such as whether there have been any claims, whether payments were made on time, etc.), and the customer's current health status (which is closely related to the willingness to renew critical illness insurance). These factors will serve as input data for the subsequent prediction of the successful purchase probability of the pending renewal policy through the trained model.

[0063] Step S146: Input the business target impact factor and the business document into the preset model to obtain the business success probability of the business document.

[0064] Specifically, the pre-set model analyzes and calculates input data based on previously learned patterns, ultimately outputting a numerical value representing the success probability of the business document. For example, the model calculates that the purchase probability of a expiring critical illness insurance policy is 0.7, indicating a 70% probability that the customer will renew the policy. This probability value provides important insights for insurance companies' business decisions. For example, for customers with a high purchase probability, more conventional renewal reminders can be implemented. For customers with a low purchase probability, further analysis can be conducted to develop personalized marketing strategies, such as offering discounted premiums and increased benefits, to increase customer renewal willingness.

[0065] Step S150 : recommending an optimal processing strategy set for the business document to the target user based on the business calculation factor and the business success probability.

[0066] Specifically, the optimal processing strategy set for a business document is one that ensures the target value of the business document meets expectations. As a specific example, when the business document is insurance policy data and the target value of the business document is commission, the optimal processing strategy set for the commission plan can be the pending insurance policy data with a high commission calculated by the commission calculation factor and a high purchase success probability. This higher standard can be set according to the specific needs of the application. For example, weights can be set for the commission and purchase success probability values ​​respectively, and then the weighted commission and purchase success probability values ​​can be sorted. Finally, the pending insurance policy data with the top five rankings will be used as the recommended strategy set for the commission plan.

[0067] It will be appreciated that the above solution can analyze and obtain specific commission calculation factors for calculating commissions, thereby calculating commissions based on the commission calculation factors. Furthermore, the above solution can calculate the customer's purchase success probability for each pending policy data item. Thus, based on the commission and purchase success probability for the pending policy data item, the pending policy data item with both high commissions and purchase success probabilities can be recommended to the agent. In this way, when the agent sells the pending policy data item to a client, they can ensure high commissions for the pending policy data item and a high customer purchase rate for the insurance business.

[0068] In summary, this solution can solve the problem in the prior art of simultaneously ensuring a high customer purchase rate for insurance business and a high agent commission.

[0069] In some embodiments of the present invention, Figure 3 As shown, step S150 includes the following steps.

[0070] Step S151 : Based on the values ​​of the business calculation factor and the business success probability, a multi-rule collaborative business trial calculation strategy is executed to recommend an optimal processing strategy set for the business document to the target user.

[0071] Specifically, in this step, the multi-rule collaborative business trial calculation strategy is a business trial calculation strategy that satisfies each rule in the pre-configured rule set and the logical relationship between each rule. Based on this business trial calculation strategy, the calculation method of the target value of the business can be obtained, and the target value of the business can be obtained. In this way, after obtaining the business target value and the success probability value of the business target, the optimal processing strategy set for the business document can naturally be recommended to the target user.

[0072] In some embodiments of the present invention, Figure 4 As shown, step S151 includes the following steps.

[0073] Step S1511, obtaining a business type ratio according to the business calculation factor and the multi-rule collaborative business trial calculation strategy;

[0074] Step S1512: Calculate the business target value of the business document based on the business type ratio and the business initial value;

[0075] Step S1513: Acquire the business document whose business target value is greater than a first preset value and whose business success probability is greater than a second preset value, and form an optimal processing strategy set for the business document;

[0076] Step S1514: recommending an optimal processing strategy set for the business document to the target user.

[0077] It is understandable that in step S1511, when calculating the target value of a business, the various business calculation factors may influence each other. Therefore, when obtaining the business calculation factors, it is necessary to confirm the relationship between the various business calculation factors when calculating the target value of the business based on the various rules in the preconfigured rule set and the logical connections between the rules. Therefore, the multi-rule collaborative business trial calculation strategy is a strategy that obtains the target value of the business based on the relationship between the various business calculation factors and the specific values ​​of the business calculation factors. This strategy is reflected in a specific feature, namely the business type ratio. The business type ratio is the calculated ratio of the target value of the business document corresponding to a certain business type. Therefore, in step S1512, based on the obtained business type ratio and the business initial value, the two can be multiplied to obtain the business target value of the business document. For example, in the insurance field, the business type ratio can be the insurance commission ratio, that is, the commission ratio of a certain insurance type, and the business initial value can be the premium of the aforementioned insurance type.

[0078] Specifically, in step S1513, the first preset value and the second preset value can be set according to specific needs of the application, and are not limited in detail here.

[0079] It can be understood that through steps S1511 to S1514, the business target value can be automatically calculated, and based on the business target value, the optimal processing strategy set for the business document can be further recommended to the target user. This can effectively save resources compared to calculating the target value of the business document through manual data analysis.

[0080] In some embodiments of the present invention, the commission calculation factor includes the business classification of the business document, the business attribute of the business document, and the business year corresponding to the business document;

[0081] The execution of the multi-rule collaborative business trial calculation strategy includes:

[0082] Determine the basic calculation ratio of the target value corresponding to the business classification according to the business classification rules;

[0083] Determining an attribute adjustment factor corresponding to the business attribute according to the business attribute rule;

[0084] Determine the time impact factor corresponding to the business year according to the business year rules;

[0085] The business type ratio is calculated according to the basic calculation ratio, the attribute adjustment factor and the time impact factor.

[0086] Specifically, the basic calculation ratio corresponding to the business classification of the business document can be determined according to specific business rules. For example, in the medical and health insurance application scenario, the initial commission ratio of long-term insurance (business classification) is 30%, so its corresponding basic calculation ratio is 30%. The attribute adjustment factor corresponding to the business attribute can be set according to specific business rules. For example, when the policy attribute (business attribute) is an orphan policy, since the orphan policy problem is caused by the resignation of the original agent, it will bring a bad user experience to the customer. Therefore, the commission ratio paid by the customer must be reduced to a certain extent. For this purpose, the attribute adjustment factor corresponding to the orphan policy can be set to 0.1. Multiplying the attribute adjustment factor with the basic commission ratio can obtain the adjusted commission ratio. Specifically, the time impact factor corresponding to the business year can be determined according to the specific business year rules. For example, for long-term insurance, the commission ratio will change with the policy year of the insurance purchased by the customer and will decrease year by year. For example, in the third year of the policy year, since the commission ratio of the policy year will decrease by 2%, the basic commission ratio will be reduced by 4% in the third year of the policy year, that is, from 30% to 26%.

[0087] In this way, it can be understood that, according to the set multi-rule collaborative business trial calculation strategy, various influencing factors of the business type ratio can be fully considered, so that the final business type ratio can be accurately obtained.

[0088] In some embodiments of the present invention, determining the attribute adjustment factor corresponding to the service attribute according to the service attribute rule includes:

[0089] determining, according to the association configuration between the service classification rule and the service attribute rule, an attribute influence factor of the service classification on the service attribute;

[0090] An attribute adjustment factor is obtained according to the attribute influencing factor and the service attribute.

[0091] Specifically, when business classification rules and business attribute rules are related, it is necessary to consider the impact between the specific business classification and the business attributes, specifically the impact of the business classification on the attribute adjustment factor. To this end, the attribute impact factor of the business classification on the business attributes can be determined. Specifically, historical business documents can be obtained and clustered based on the business classification to form multiple clusters. The attribute adjustment factor corresponding to each business attribute in each cluster is calculated. Different values ​​of the attribute adjustment factor corresponding to the same business attribute in different business classifications are determined. These different values ​​are then multiplied by different coefficients to normalize them. These different coefficients can then be used as the attribute impact factor of the business classification on the business attributes. As a specific example, if the business classification is life insurance, insurance policies with orphan attributes will automatically be transferred to the commission rate of active policies. As mentioned earlier, the commission rate of orphan policies will be reduced to 0.1 times the basic commission rate. However, when transferred to active policies, the commission rate will return to the original basic commission rate. Therefore, the attribute adjustment factor of 0.1 needs to be multiplied by the attribute impact factor of 10 to eliminate the impact of orphan policies on the basic commission rate.

[0092] It is understandable that based on the association configuration between the service classification rules and the service attribute rules, the attribute influence factor can be obtained, and thus a more accurate attribute adjustment factor can be obtained based on the attribute influence factor.

[0093] In some embodiments of the present invention, Figure 5 As shown, after step S150, the following steps are further included:

[0094] Step S160 : collecting the target user's selection operation data and parameter modification records for the solutions in the optimal processing strategy set.

[0095] Specifically, in step S160, to collect the target user's selection operation data and parameter modification records for the optimal processing strategy set, each recommended optimal processing strategy set can be displayed on the target user's terminal and editable on the target user's terminal, allowing the target user to select the desired strategy as the final processing strategy for the business document. The target user's parameter modification record for the strategy can be any desired strategy. For example, if a strategy in the optimal processing strategy set recommends that a customer purchase multiple related insurance policies simultaneously, the agent can remove one or more of the policies based on actual experience and evaluation, thereby making the customer more receptive.

[0096] Step S170: updating the optimal processing strategy set according to the selection operation data and the parameter modification record.

[0097] In this way, according to the modification of the above step S160, a modified optimal processing strategy set can be obtained, which is obviously more complete than the above automatically given optimal processing strategy set.

[0098] It should be understood that the order of execution of the steps in the above embodiments does not necessarily imply a specific order of execution. The order of execution of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The software tools or components not provided by our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0099] In one embodiment, a device for recommending an optimal commission strategy is provided, which corresponds to the method for recommending an optimal commission strategy in the above embodiment. Figure 6 As shown, the recommendation device includes a first acquisition module 610, a first generation module 620, a second acquisition module 630, a second generation module 640 and a recommendation module 650. The functional modules are described in detail as follows:

[0100] A first acquisition module 610 is used to acquire the business document associated with the target user;

[0101] A first generating module 620, configured to parse the business document based on a preconfigured rule set and generate a business calculation factor corresponding to the business document;

[0102] The second acquisition module 630 is used to obtain the customer portrait data associated with the business document;

[0103] A second generating module 640 is configured to generate a business success probability of the business document based on the customer profile data;

[0104] The recommendation module 650 is configured to recommend an optimal processing strategy set for the business document to the target user based on the business calculation factor and the business success probability.

[0105] In one embodiment, the generating module 640 is specifically configured to:

[0106] Obtaining historical business documents of the customer associated with the business document;

[0107] Analyze and obtain the business target influencing factors of historical business documents;

[0108] Marking the business target influencing factors on the historical business documents to form sample data;

[0109] Inputting the sample data into a preset model to train the preset model;

[0110] Extracting business objective influencing factors of the historical business documents in the customer portrait data;

[0111] The business objective influencing factor and the business document are input into the preset model to obtain the business success probability of the business document.

[0112] In one embodiment, the recommendation module 650 is specifically configured to:

[0113] Based on the values ​​of the business calculation factor and the business success probability, a multi-rule collaborative business trial calculation strategy is executed to recommend an optimal processing strategy set for the business document to the target user.

[0114] In one embodiment, the recommendation module 650 is further configured to:

[0115] Obtaining a business type ratio according to the business calculation factor and the multi-rule collaborative business trial calculation strategy;

[0116] Calculate the business target value of the business document according to the business type ratio and the business initial value;

[0117] Acquire the business document whose business target value is greater than a first preset value and whose business success probability value is greater than a second preset value, and form an optimal processing strategy set for the business document;

[0118] Recommend the optimal processing strategy set for the business document to the target user.

[0119] In one embodiment, the business calculation factor includes the business classification of the business document, the business attribute of the business document, and the business year corresponding to the business document;

[0120] The recommendation module 650 is further configured to:

[0121] The execution of the multi-rule collaborative business trial calculation strategy includes:

[0122] Determine the basic calculation ratio of the target value corresponding to the business classification according to the business classification rules;

[0123] Determining an attribute adjustment factor corresponding to the business attribute according to the business attribute rule;

[0124] Determine the time impact factor corresponding to the business year according to the business year rules;

[0125] The business type ratio is calculated according to the basic calculation ratio, the attribute adjustment factor and the time impact factor.

[0126] In one embodiment, the recommendation module 650 is further configured to:

[0127] determining, according to the association configuration between the service classification rule and the service attribute rule, an attribute influence factor of the service classification on the service attribute;

[0128] An attribute adjustment factor is obtained according to the attribute influencing factor and the service attribute.

[0129] In one embodiment, the recommendation module 650 is further configured to:

[0130] Collecting the target user's selection operation data and parameter modification records for the solutions in the optimal processing strategy set;

[0131] The optimal processing strategy set is updated according to the selection operation data and the parameter modification record.

[0132] The present invention provides an optimal strategy recommendation device that analyzes and obtains specific business calculation factors for a business document, thereby calculating the target value of the service corresponding to the business document based on the business calculation factors. Furthermore, this scheme can calculate the service success probability for each business document. Thus, based on the target value and success probability of the service in the business document, a business document with both a high target value and a high success probability can be recommended to a target user. This ensures that when the target user connects these business documents to their customers, the target value of the business document is high and the customer selection rate for the business document is high.

[0133] In summary, this solution can solve the problem in the prior art that it is impossible to simultaneously ensure a high customer selection rate for a business document and a high business target value for the business document.

[0134] The specific definitions of the optimal strategy recommendation device can be found in the definitions of the optimal strategy recommendation method described above and will not be repeated here. Each module in the optimal strategy recommendation device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the modules described above can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0135] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps of the service-side of a method for recommending an optimal strategy.

[0136] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, network interface, display screen, and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of the client side of a method for recommending an optimal strategy.

[0137] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0138] Obtain the business documents associated with the target user;

[0139] Parsing the business document based on a preconfigured rule set to generate a business calculation factor corresponding to the business document;

[0140] Obtaining customer profile data associated with the business document;

[0141] Generate a business success probability of the business document based on the customer profile data;

[0142] Based on the business calculation factor and the business success probability, an optimal processing strategy set for the business document is recommended to the target user.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0144] Obtain the business documents associated with the target user;

[0145] Parsing the business document based on a preconfigured rule set to generate a business calculation factor corresponding to the business document;

[0146] Obtaining customer profile data associated with the business document;

[0147] Generate a business success probability of the business document based on the customer profile data;

[0148] Based on the business calculation factor and the business success probability, an optimal processing strategy set for the business document is recommended to the target user.

[0149] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0150] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0151] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0152] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for recommending an optimal strategy, characterized in that: include: Obtain the business documents associated with the target user; Parsing the business document based on a preconfigured rule set to generate a business calculation factor corresponding to the business document; Obtaining customer profile data associated with the business document; Generate a business success probability of the business document based on the customer profile data; Based on the business calculation factor and the business success probability, an optimal processing strategy set for the business document is recommended to the target user.

2. The optimal strategy recommendation method according to claim 1, characterized in that: Generating the business success probability of the business document according to the customer profile data includes: Obtaining historical business documents of the customer associated with the business document; Analyze and obtain the business target influencing factors of historical business documents; Marking the business target influencing factors on the historical business documents to form sample data; Inputting the sample data into a preset model to train the preset model; Extracting business objective influencing factors of the historical business documents in the customer portrait data; The business objective influencing factor and the business document are input into the preset model to obtain the business success probability of the business document.

3. The optimal strategy recommendation method according to claim 1, characterized in that: The recommending an optimal processing strategy set for the business document to the target user based on the business calculation factor and the business success probability includes: Based on the values ​​of the business calculation factor and the business success probability, a multi-rule collaborative business trial calculation strategy is executed to recommend an optimal processing strategy set for the business document to the target user.

4. The optimal strategy recommendation method according to claim 3, characterized in that: The executing of a multi-rule collaborative business trial calculation strategy based on the business calculation factor and the business success probability to recommend an optimal processing strategy set for the business document to the target user includes: Obtaining a business type ratio according to the business calculation factor and the multi-rule collaborative business trial calculation strategy; Calculate the business target value of the business document according to the business type ratio and the business initial value; Acquire the business document whose business target value is greater than a first preset value and whose business success probability value is greater than a second preset value, and form an optimal processing strategy set for the business document; Recommend the optimal processing strategy set for the business document to the target user.

5. The optimal strategy recommendation method according to claim 4, characterized in that: The business calculation factor includes the business classification of the business document, the business attribute of the business document, and the business year corresponding to the business document; The execution of the multi-rule collaborative business trial calculation strategy includes: Determine the basic calculation ratio of the target value corresponding to the business classification according to the business classification rules; Determining an attribute adjustment factor corresponding to the business attribute according to the business attribute rule; Determine the time impact factor corresponding to the business year according to the business year rules; The business type ratio is calculated according to the basic calculation ratio, the attribute adjustment factor and the time impact factor.

6. The optimal strategy recommendation method according to claim 5, characterized in that: The determining, according to the service attribute rule, the attribute adjustment factor corresponding to the service attribute includes: determining, according to the association configuration between the service classification rule and the service attribute rule, an attribute influence factor of the service classification on the service attribute; An attribute adjustment factor is obtained according to the attribute influencing factor and the service attribute.

7. The optimal strategy recommendation method according to claim 1, characterized in that: After recommending the optimal processing strategy set of the service document to the target user based on the service calculation factor and the service success probability, the method further includes: Collecting the target user's selection operation data and parameter modification records for the solutions in the optimal processing strategy set; The optimal processing strategy set is updated according to the selection operation data and the parameter modification record.

8. An optimal strategy recommendation device, characterized in that: include: The first acquisition module is used to obtain the business documents associated with the target user; A first generating module, configured to parse the business document based on a preconfigured rule set and generate a business calculation factor corresponding to the business document; A second acquisition module is used to obtain customer portrait data associated with the business document; A second generating module is used to generate a business success probability of the business document based on the customer portrait data; A recommendation module is used to recommend an optimal processing strategy set for the business document to the target user based on the business calculation factor and the business success probability.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the optimal strategy recommendation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for recommending an optimal strategy according to any one of claims 1 to 7 are implemented.

Images