A method, apparatus, equipment, and medium for evaluating business conversion rates.

Abstract

This application relates to the field of artificial intelligence technology and discloses a method, apparatus, device, and medium for evaluating business conversion rates. The method includes: acquiring the identity information and pending business types of multiple target users within a preset time period, and forming a first user set by combining all the target users; determining preset business access conditions based on the pending business types, and removing target users in the first user set that do not meet the preset business access conditions to obtain a second user set; generating order information based on the identity information and corresponding pending business types of the target users in the second user set to interact with the corresponding target users; determining the final number of target users for loan disbursement based on the interaction results, and determining the business conversion rate based on the final number of target users for loan disbursement and the first user set. This application can improve the accuracy of business conversion rate tracking.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence technology and natural language processing technology, and in particular to a method, apparatus, device and medium for evaluating business conversion rate. Background Technology

[0002] The funnel conversion model has a long history and is a well-established analytical model in the marketing and advertising industry. Users enter from the top of the funnel, and some drop-off occurs at each step. The overall conversion rate is equal to the product of the conversion rates at each step. Therefore, to improve the final conversion rate, improving the conversion rate at each step is essential. From an overall operational perspective, improving order conversion rate means that businesses can obtain higher profits at lower costs.

[0003] While there are well-established funnel models available, each company has its own specific definition based on its unique business needs. Current conversion rate logic fails to consider the uniqueness of the same user across different business scenarios, nor does it track the actual conversions of the same user. It mechanically applies conversion rate formulas, resulting in conversion rate data that doesn't accurately reflect user retention and is therefore frequently questioned. Summary of the Invention

[0004] This application provides a business conversion rate assessment method, apparatus, equipment, and medium to address the problem that existing conversion rate analyses are unable to accurately reflect user retention.

[0005] Firstly, a business conversion rate evaluation method is provided, including:

[0006] Obtain the identity information and pending business types of multiple target users within a preset time period, and combine all the target users into a first user set;

[0007] Based on the type of pending business, preset business access conditions are determined, and target users in the first user set who do not meet the preset business access conditions are removed to obtain a second user set.

[0008] Based on the identity information of the target users in the second user set and the corresponding pending business types, order information is generated and interacted with the corresponding target users to determine the final number of target users for loan disbursement;

[0009] The business conversion rate is determined based on the target number of users for the final loan disbursement and the first user set.

[0010] Secondly, a business conversion rate assessment device is provided, including:

[0011] The target acquisition module is used to acquire the identity information and pending business types of multiple target users within a preset time period, and to form a first user set by combining all the target users.

[0012] The access module is used to determine preset access conditions based on the type of pending business, and remove target users in the first user set who do not meet the preset access conditions to obtain a second user set.

[0013] The order interaction module is used to generate order information based on the identity information of the target user in the second user set and the corresponding pending business type, so as to interact with the corresponding target user and obtain the interaction result;

[0014] The conversion rate evaluation module is used to determine the target number of users for final loan disbursement based on the interaction results, and to determine the business conversion rate based on the target number of users for final loan disbursement and the first user set.

[0015] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described business conversion rate evaluation method.

[0016] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-mentioned business conversion rate method.

[0017] In the above-mentioned business conversion rate evaluation method, device, equipment, and medium, the following steps are taken: First, the identity information and pending business types of multiple target users within a preset time period are acquired, and all target users are grouped into a first user set. Preset business access conditions are determined based on the pending business types, and target users in the first user set that do not meet the preset business access conditions are removed, resulting in a second user set. Order information is generated based on the identity information and corresponding pending business types of the target users in the second user set to interact with the corresponding target users, obtaining interaction results. The final number of target users for loan disbursement is determined based on the interaction results, and the business conversion rate is determined based on the final number of target users for loan disbursement and the first user set. By using the first user set as the target set and the identity information of the target users in the final target set, the conversion rate of the next step reflects the retention of the target users in the previous step. By filtering target users through access conditions and order information interaction, user quality is ensured while obtaining more accurate business conversion rate information, facilitating targeted business decisions and improving data accuracy and reliability. Attached Figure Description

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0019] Figure 1 is a schematic diagram of an application environment of a service conversion rate evaluation method in an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a flow of a service conversion rate evaluation method in an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a flow of access screening of a first user set in an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a structure of a service conversion rate evaluation device in an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a structure of a computer device in an embodiment of the present application;

[0024] Figure 6 is another schematic diagram of a structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions of the embodiments of the present application will be described clearly and completely in the following with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort belong to the scope of protection of the present application.

[0026] The service conversion rate evaluation method provided by the embodiments of the present application can be applied in, for example, Figure 1In an application environment, a client communicates with a server through a network. The server can receive identity information and a to-be-handled business type input by a user through the client, obtain identity information and a to-be-handled business type of a plurality of target users in a preset time, form a first user set with all the target users, determine a preset business access condition according to the to-be-handled business type, eliminate a target user in the first user set who does not meet the preset business access condition, obtain a second user set, generate order information according to identity information of a target user in the second user set and a corresponding to-be-handled business type to interact with the corresponding target user, obtain an interaction result, determine a target user number of final loans according to the interaction result, and determine a business conversion rate according to the target user number of final loans and the first user set. In this application, for complex business scenarios such as automobile financing and leasing, order information can be marked with a vehicle identification number (VIN), and when a user uses multiple VINs to place orders, the VIN can be used to correspond the VIN to the user, avoiding errors in user number statistics and interference with conversion rate calculation. In addition, risk control and approval can be added to identify target users with hidden risks and ensure the quality of users for evaluating the conversion rate. The client can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The application will be described in detail through specific embodiments.

[0027] Referring to Figure 2 , as shown in Figure 2 , a flowchart of a business conversion rate evaluation method provided by an embodiment of the application includes the following steps.

[0028] Step 20, obtaining identity information and a to-be-handled business type of a plurality of target users in a preset time, and forming a first user set with all the target users.

[0029] In an embodiment of the application, the preset time can be one week, one month, or one quarter, and the business conversion rate is evaluated according to the preset time period. The specific preset time can be adjusted according to actual application requirements, which is not limited here. Users who have the intention to handle the business in the preset time period are regarded as target users and are included in the first user set. Based on the first user set, the uniqueness of the user in the conversion rate evaluation process is determined based on the target user identity information, and whether the user is a user retained in the previous step. A one-to-one correspondence between the target user identity information and the to-be-handled business type in the first user set is established.

[0030] In an embodiment, obtaining identity information and a to-be-handled business type of a plurality of target users in a preset time includes the following steps:

[0031] In step S201, text information corresponding to voice information of the user is obtained, the text information is compared with a preset user intention, a target intention is obtained, and the user with the target intention is taken as a target user.

[0032] In an embodiment, a service personnel or an intelligent robot can have a dialogue with the user and record voice information in the dialogue process of the user, and convert the voice information into text information. The conversion of voice into text can adopt a recognition model such as a Markov model, which is not limited here.

[0033] In an embodiment, a user intention database corresponding to each service type can be established in advance. The user intention database can be obtained by collecting frequently used questions of historical users, extracting named entities in the questions, or being set by a manager according to experience. After the text information is obtained, a network model such as a recurrent neural network or a cyclic neural network can be used to extract features of the text information, the extracted features are compared with preset user intentions in the user intention database in terms of similarity, a matched user intention is taken as a target intention of the user, and then the user with the target intention is taken as a target user.

[0034] In step S202, a first interaction interface is matched according to the target intention, and identity information and a to-be-handled service type of the target user are obtained through the first interaction interface.

[0035] In an embodiment, an interaction interface template can be set in advance, and the content in the interaction interface template can be obtained by matching the target intention. The target intention of the user often reflects the service demand of the user, the service type options with a similarity to the target intention reaching a set threshold are used to fill the interaction interface template based on matching the service type options based on the target intention, and the first interaction interface is generated. In another embodiment, the content of the first interaction interface can also be directly preset, the first interaction interface can establish a mapping relationship with multiple user intentions, and the corresponding first interaction interface can be directly matched after the target intention is determined based on the mapping relationship. The first interaction interface is output to a terminal corresponding to the user, the first interaction interface is displayed on the terminal, and the target user fills in the identity information and the to-be-handled service type in the first interaction interface. The identity information can include a contact number, an account number, a certificate number, and the like. The to-be-handled service type can also be selected and determined through the service type options provided by the first interaction interface.

[0036] As can be seen from the above scheme, the user with the intention to handle the service is classified into the first user set through voice recognition, information collection and service type confirmation are performed based on the user intention, the accuracy of user information collection can be ensured, the user experience is enhanced, the intention dialogue can be completed through the intelligent terminal, the dependence on manual work is reduced, and the automation level is improved.

[0037] Step S30, determining the preset business access condition according to the type of the to-be-handled business, and removing the target user in the first user set that does not meet the preset business access condition to obtain a second user set.

[0038] In an embodiment, in order to ensure the quality of the user handling the business, the target user in the first user set needs to be screened. The target user with a large risk, such as having a bad loan record, poor credit, and behaviors of overdue and non-repayment, is removed.

[0039] Referring to Figure 3 , Figure 3 is a flowchart of the process of screening the first user set in an embodiment of the present application. In an embodiment, the preset business access condition is determined according to the type of the to-be-handled business, and the target user in the first user set that does not meet the preset business access condition is removed, including the following steps:

[0040] Step S301, determining the business department to which the target user belongs according to the type of the to-be-handled business, and comparing the to-be-handled business type with the business condition in the preset business condition library of the business department to obtain the matched business condition as the preset business access condition.

[0041] In an embodiment, in order to better evaluate the conversion rate and effectively guide the business development and decision-making according to the evaluation result, the target user can be classified by business department to avoid data interference between different types of businesses handled by the same user. Therefore, the business department corresponding to the to-be-handled business type needs to be determined, and then the business department corresponding to the target user is determined. The business department can pre-set the business access condition corresponding to the business type for the business type it provides, and store the business access condition in the preset business condition library. After the type of the to-be-handled business of the target user is determined, the matched business access condition can be retrieved from the business condition library according to the type of the to-be-handled business. Exemplarily, the condition retrieval can be performed in the manner of Elasticsearch, and the specific retrieval manner is not limited here.

[0042] Step S302, obtaining the first user information associated with the identity information in the preset user database according to the identity information of each target user corresponding to the to-be-handled business type.

[0043] In an embodiment, the existing database can be queried based on the identity information such as the user certificate number to obtain the associated information of the public user identity information, such as user credit information, user loan record, etc. The associated information obtained by the query is used as the first user information of the corresponding target user. The user database can also be the local storage of the user historical data record, and the historical data record is obtained according to the identity information for access qualification verification, and the historical data record includes blacklist, whitelist, etc., and the specific data is not limited here.

[0044] Step S303, comparing the first user information with the preset service access condition, and performing an elimination operation on the target user in the first user set according to the comparison result.

[0045] In an embodiment, the user features in the first user information can be extracted by a neural network such as a recurrent neural network, and the user features can be converted into a feature vector. Exemplarily, the feature vector can be represented by one-hot encoding. The feature vector is compared with the service access condition in terms of similarity, and according to the comparison result, it is determined whether the target user meets the service access condition. If not, the corresponding target user is removed from the first user set. After the removal operation, the second user set is obtained.

[0046] As can be seen from the above scheme, the target user identity information is used as the user uniqueness confirmation parameter, and after confirming the user intention, the user credit information is automatically extracted and screened, so as to ensure the quality of the service access users. The automatic access screening process can complete data screening without feeling, and improves the processing efficiency.

[0047] Step S40, generating order information according to the identity information of the target user in the second user set and the corresponding to-be-performed business type, and interacting with the corresponding target user to determine the number of target users for final lending.

[0048] In an embodiment, after the target users with risks are removed through the identity information, the second user set obtained can meet the basic risk control requirements, but there is still a possibility of hidden risks. It is difficult to completely avoid hidden risks by screening only through the identity information, so more user information needs to be obtained for more detailed risk assessment. Therefore, order information corresponding to the target user in the second user set can be generated, and more user information can be obtained by interacting with the target user through the order information.

[0049] In an embodiment, generating order information according to the identity information of the target user in the second user set and the corresponding to-be-performed business type, and interacting with the corresponding target user, includes the following steps:

[0050] Step S401, calling a preset order template of the corresponding business according to the to-be-performed business type, the preset order template including business-related information collection items, and obtaining order information by marking the order template through the identity information.

[0051] In an embodiment, the order template corresponding to the business type stored on the server side can be invoked according to the business type corresponding to each target user in the second user set. The business association information collection items corresponding to the business type can be pre-set in the order template, such as whether the related business has been handled, whether there is other loan history, etc., which are only exemplary and should not be regarded as a limitation on the present application. The specific collection items can be set according to the actual business needs. Further, the called order template can be marked by the identity information of the target user to ensure that the generated order information is associated with the target user, facilitating subsequent unique tracking of the user according to the order information.

[0052] In step S402, the order information is output to a preset second interactive interface, and the second user information of the target user is obtained according to the business association information collection items.

[0053] In an embodiment, during the order interaction with the target user, the order presentation can be performed through the second interactive interface, and the order business association information input by the target user can be obtained. During the order confirmation process of the target user, information can be entered according to the business association information collection items. The input information of the target user is fed back to the server side as the second user information.

[0054] In an embodiment, after obtaining the second user information of the target user according to the business association information collection items, the following steps are further included:

[0055] In step S403, the second user information is identified according to a preset risk control model, and the risk score of the target user is output.

[0056] In an embodiment, a risk control model can be pre-trained, which performs risk scoring based on the input user information to further screen out target users with hidden risks. The risk control model can adopt a lightweight neural network type Resnet or a long short-term memory neural network model architecture.

[0057] In an embodiment, the interaction result is identified according to the preset risk control model, and the risk score of the target user is output, including the following steps:

[0058] In step S431, one or more key features in the interaction result are obtained.

[0059] In an embodiment, the interaction result includes the second user information, and the second user information corresponds to the content of the plurality of business association information collection items. The content collected by each business association information collection item can correspond to at least one key feature. Each key feature can be generated into a corresponding feature vector by one-hot encoding. In another embodiment, the first user information and the second user information can be combined to obtain more rich key features, thereby improving the risk control accuracy.

[0060] Step S432, input the key features into the risk control model to compare the similarity with the preset risk control indicators, and obtain the matched risk control indicators.

[0061] In an embodiment, the feature vector is input into the pre-trained risk control model. The risk control model is mainly used to calculate the similarity of the feature vector and the preset risk control indicators. The risk control indicators with a similarity to the feature vector reaching a set threshold are taken as the risk control indicators matched with the corresponding target user. The index library corresponding to the risk control indicators can be established in advance, and a weight is assigned to each risk control indicator. The risk control indicators can include, for example, overdue rate, bad rate, suspected fraud rate, etc. The specific indicator settings can be adjusted according to actual business needs, which are not limited here.

[0062] Step S433, taking the weight corresponding to the matched risk control indicator as the weight of the corresponding key feature.

[0063] In an embodiment, since one key feature can correspond to multiple matched risk control indicators, or multiple key features can correspond to the same matched risk control indicator, after identification by the risk control model, the key features and the matched risk control indicators can be merged, and only a set of corresponding relationships between the key features and the corresponding risk control indicators are retained. After determining the corresponding relationship, the preset weight corresponding to the matched risk control indicator is taken as the weight of the key feature.

[0064] Step S434, determining the risk score according to the key features contained in the second user information and the weights of the key features.

[0065] In an embodiment, after determining the weights of the key features according to the foregoing steps, the key features are weighted and averaged, and the weighted result is normalized so that the result is between 0 and 1. The result is taken as the risk score.

[0066] Step S404, screening the target users in the second user set according to the risk score to obtain a third user set.

[0067] In an embodiment, a risk score threshold can be set in advance. When the risk score of the second user information is higher than the risk score threshold, it is considered that the target user has hidden risks, and the target user is excluded from the second user set.

[0068] Step S405, associating the business object identifier corresponding to the to-be-done business type with the order information. If the order information of the target user in the third user set contains the corresponding business object identifier, it is confirmed that the order is completed, and the target user completing the order is determined as the target user for final loan.

[0069] In an embodiment, since there are cases where a target user adopts multiple business objects to place an order, the business object identifier can be associated with the order information when interacting with the target object through the order information. Taking car financing lease as an example, a user can place an order using multiple vehicle frame numbers, and when counting the number of users who place an order, it is often counted by the number of orders, which will lead to inaccurate user number statistics. By recording the vehicle frame number, one order can correspond to multiple vehicle frame numbers, and when counting the number of users who place an order, the orders can be combined based on the vehicle frame number to obtain accurate user number statistics.

[0070] As can be seen from the above scheme, by screening the target users with hidden risks, the quality of the users can be further guaranteed, and by associating the business object identifier with the order, more accurate user number can be determined, and the accuracy of the business conversion rate evaluation can be improved. In each link, the average conversion time of the target user can also be counted to provide reliable data support for subsequent business decision-making.

[0071] Step S50, determining a business conversion rate according to the target user number of the final loan and the first user set, comprising:

[0072] determining a first conversion rate according to the second user set and the first user set;

[0073] determining a second conversion rate according to the third set and the second set;

[0074] determining a third conversion rate according to the target user number of the final loan and the third set;

[0075] determining a business conversion rate according to the first conversion rate, the second conversion rate and the third conversion rate.

[0076] In an embodiment, still taking the car financing lease business scenario as an example, after determining the first user set, entering the pre-examination and approval link, it is necessary to confirm whether the target user's reserved information can pass the risk control approval in this link. The conversion rate generated in this step is: V1 = pre-examination and approval passed customer number / pre-examination and approval entered customer number.

[0077] In an embodiment, under the premise of guaranteeing the quality of the users, when the target user further clarifies the financing intention, the order link will be entered. At this time, the customer will store more information in the system. In this link, it is necessary to guarantee the uniqueness of the user identity information and the business department attribution of the order. The conversion rate generated in this step is: V2 = order placed user number / pre-examination and approval passed user number;

[0078] In an embodiment, after the target user completes the order placement operation, entering the order examination and approval link, more detailed risk control approval will be carried out in this link to eliminate users with hidden risks;

[0079] The conversion rate of this link is: V3 = order passed user number / order placed user number;

[0080] After the order link is audited, the user enters a loan link. Due to the particularity of the business, the same user may use different frame numbers to place orders (a small amount), so the frame number information is reserved at this time; the conversion rate of this link is: V4 = the number of users in the loan link / the number of users in the order link;

[0081] After entering the rental link, after a series of loan audits and file completion, the user enters the loan link. At this time, a complete business conversion process is completed. The conversion rate generated in this link is: V5 = the number of users in the loan link / the number of users in the loan link.

[0082] The product of the conversion rates of the above links is the final true business conversion rate, that is, the number of users in the loan link / the number of users in the pre-audit link = V1xV2xV3xV4xV5.

[0083] As can be seen from the above scheme, the improved conversion rate evaluation logic can more accurately reflect the true conversion scene of the specific business according to the user identity information following the conversion process, and can accurately calculate the average conversion time of the customer when the tracking time reaches a certain value and the sample size is sufficient. It can provide accurate data reference for enterprises to improve business conversion rate and promote more measures to improve conversion rate from the operation point of view; when the business index is assigned, the conversion rate can be evaluated to assign the target of each link, ensure the achievement of the performance of the department or enterprise, and provide more accurate decision basis for the enterprise or department.

[0084] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0085] In an embodiment, a business conversion rate evaluation device is provided, which corresponds to the business conversion rate evaluation method in the above embodiment. As shown in the figure, the business conversion rate evaluation device includes a target acquisition module 101, an access module 102, an order interaction module 103, and a conversion rate evaluation module 104. The function modules are described in detail as follows: Figure 4

[0086] The target acquisition module 101 is used to acquire the identity information of a plurality of target users and the type of to-be-performed business within a preset time, and groups all target users into a first user set;

[0087] The access module 102 is used to determine a preset business access condition according to the type of to-be-performed business, and removes target users in the first user set who do not meet the preset business access condition to obtain a second user set;

[0088] ​The order interaction module 103 is configured to interact with the target users in the second user set according to the identity information of the target users and the corresponding to-be-handled business types, and determine the number of target users of the final loan.

[0089] The conversion rate evaluation module 104 is configured to determine a business conversion rate according to the number of target users of the final loan and the first user set.

[0090] In an embodiment, the target acquisition module 101 is specifically configured to:

[0091] acquire identity information and to-be-handled business types of a plurality of target users within a preset time, including:

[0092] acquire text information corresponding to the voice information of the user, compare the text information with a preset user intent, obtain a target intent, and take the user with the target intent as a target user;

[0093] match a preset first interaction interface according to the target intent, and acquire the identity information and the to-be-handled business types of the target user through the first interaction interface.

[0094] In an embodiment, the access module 102 is specifically configured to:

[0095] determine a preset business access condition according to the to-be-handled business type, and exclude target users in the first user set that do not meet the preset business access condition, including:

[0096] determine a business department to which the target user belongs according to the to-be-handled business type, and compare the to-be-handled business type with a business condition in a preset business condition library of the business department to obtain a matched business condition as the preset business access condition;

[0097] acquire first user information associated with the identity information in a preset user database according to the identity information of each target user corresponding to the to-be-handled business type;

[0098] compare the first user information with the preset business access condition, and perform an exclusion operation on the target users in the first user set according to a comparison result.

[0099] In an embodiment, the order interaction module 103 is further configured to:

[0100] generate order information and interact with the target users in the second user set according to the identity information of the target users and the corresponding to-be-handled business types, including:

[0101] call a preset order template of the corresponding business according to the to-be-handled business type, the preset order template including a business-associated information collection item, and obtain the order information by marking the order template through the identity information;

[0102] output the order information to a preset second interactive interface, and acquire second user information of the target user according to the business association information collection item.

[0103] In an embodiment, the order interaction module 103 is further configured to:

[0104] After acquiring the second user information of the target user according to the business association information collection item, the method further includes:

[0105] identifying the second user information according to a preset risk control model, and outputting a risk score of the target user;

[0106] screening the target user in the second user set according to the risk score, and obtaining a third user set;

[0107] associating the business object identifier corresponding to the to-be-handled business type with the order information, if the order information of the target user in the third user set contains the corresponding business object identifier, confirming that the order is completed, and determining the target user of the final loan according to the target user of the completed order.

[0108] In an embodiment, the order interaction module 103 is further configured to:

[0109] identifying the second user information according to a preset risk control model, and outputting a risk score of the target user, including:

[0110] acquiring one or more key features in the second user information;

[0111] inputting the key features into the risk control model to compare the key features with preset risk control indicators, and obtaining matched risk control indicators;

[0112] taking the weight corresponding to the matched risk control indicators as the weight of the corresponding key features;

[0113] determining the risk score according to the key features contained in the second user information and the weight of the key features.

[0114] In an embodiment, the conversion rate evaluation module 104 is configured to:

[0115] determining a business conversion rate according to the number of target users of the final loan and the first user set, including:

[0116] determining a first conversion rate according to the second user set and the first user set;

[0117] determining a second conversion rate according to the third set and the second set;

[0118] determining a third conversion rate according to the number of target users of the final loan and the third set;

[0119] The business conversion rate is determined according to the first conversion rate, the second conversion rate and the third conversion rate.

[0120] The business conversion rate evaluation device provided in the application takes a first user set as a target set, confirms the next step conversion rate by identity information of a target user in a final target set, and reflects retention of the last step target user. The target user is screened through access conditions and order information interaction, so that more accurate business conversion rate information is obtained while the quality of the user is ensured, targeted business decisions are facilitated, and data accuracy and reliability are improved. On the one hand, the business conversion rate can be improved for the enterprise to provide accurate reference, and more measures for improving the business conversion rate are promoted from the perspective of business operation. On the other hand, since the conversion rate can be basically estimated, when the company issues business indicators, the targets of each link can be accurately estimated, so as to ensure the achievement of enterprise performance and provide more accurate decision basis for the enterprise.

[0121] The specific limitations of the business conversion rate evaluation device can be referred to the limitations of the business conversion rate evaluation method in the above, and will not be repeated here. Each module in the above business conversion rate evaluation device can be realized by software, hardware and combinations thereof in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0122] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 5 The computer device includes a processor, a memory, a network interface and a database connected through 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, 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 operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external client through the network connection. The computer program is executed by the processor to implement the functions or steps of the business conversion rate evaluation method server side.

[0123] In one embodiment, a computer device is provided, which can be a client, and an internal structure diagram thereof can be as shown in Figure 6As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, 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, an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is used to communicate with the external server through the network connection. The computer program is executed by the processor to realize the functions or steps of the business conversion rate evaluation method client side

[0124] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the following steps:

[0125] Obtain the identity information of a plurality of target users and the type of the to-be-handled business within a preset time, and group all target users into a first user set;

[0126] Determine a preset business access condition according to the type of the to-be-handled business, eliminate target users in the first user set who do not meet the preset business access condition, and obtain a second user set;

[0127] Generate order information according to the identity information of the target users in the second user set and the corresponding type of the to-be-handled business to interact with the corresponding target users, and obtain an interaction result;

[0128] Determine the number of target users for final loan according to the interaction result, and determine the business conversion rate according to the number of target users for final loan and the first user set.

[0129] In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, the computer program being executed by a processor to implement the following steps:

[0130] Obtain the identity information of a plurality of target users and the type of the to-be-handled business within a preset time, and group all target users into a first user set;

[0131] Determine a preset business access condition according to the type of the to-be-handled business, eliminate target users in the first user set who do not meet the preset business access condition, and obtain a second user set;

[0132] Generate order information according to the identity information of the target users in the second user set and the corresponding type of the to-be-handled business to interact with the corresponding target users, and obtain an interaction result;

[0133] The target number of users of the final loan is determined according to the interaction result, and the business conversion rate is determined according to the target number of users of the final loan and the first user set.

[0134] It should be noted that the functions or steps described above with respect to the computer-readable storage medium or the computer device can correspond to the related descriptions of the server side and the client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0135] A person of ordinary skill in the art can understand that all or part of the processes in the foregoing method embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a nonvolatile computer readable storage medium. When the computer program is executed, the processes of the foregoing embodiments of the method can be included. In each embodiment provided in the present application, any reference to a memory, storage, database or other medium can include a nonvolatile and / or volatile memory. The nonvolatile memory can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM) or a flash memory. The volatile memory can include a random access memory (RAM) or an external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), 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), etc.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified. In actual applications, the above functions can be completed by different functional units or modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of evaluating business conversion rate, characterized by, The method comprises the following steps: acquiring identity information and a to-be-handled business type of a plurality of target users within a preset time, and grouping all the target users into a first user set; determining a preset business access condition according to the to-be-handled business type, and removing target users in the first user set that do not meet the preset business access condition to obtain a second user set; generating order information according to the identity information and the corresponding to-be-handled business type of the target users in the second user set, and interacting with the corresponding target users to determine a number of target users for final lending; generating order information according to the identity information and the corresponding to-be-handled business type of the target users in the second user set, and interacting with the corresponding target users, comprising: calling a preset order template of a corresponding business according to the to-be-handled business type, wherein the preset order template comprises a business-related information collection item, and the order information is obtained by marking the order template according to the identity information; and outputting the order information to a preset second interaction interface, and acquiring second user information of the target users according to the business-related information collection item; determining a business conversion rate according to the number of target users for final lending and the first user set.

2. The service conversion rate evaluation method according to claim 1, characterized by, acquiring identity information and a to-be-handled business type of a plurality of target users within a preset time, comprising: acquiring text information corresponding to voice information of a user, comparing the text information with a preset user intent to obtain a target intent, and taking the user with the target intent as the target user; matching a preset first interaction interface according to the target intent, and acquiring the identity information and the to-be-handled business type of the target user through the first interaction interface.

3. The service conversion rate evaluation method according to claim 1, characterized by, determining a preset business access condition according to the to-be-handled business type, and removing target users in the first user set that do not meet the preset business access condition, comprising: determining a business department to which a corresponding target user belongs according to the to-be-handled business type, and comparing the to-be-handled business type with a business condition in a preset business condition library of the business department to obtain a matched business condition as the preset business access condition; acquiring first user information associated with the identity information in a preset user database according to the identity information of each target user corresponding to the to-be-handled business type; comparing the first user information with the preset business access condition, and performing a removal operation on the target users in the first user set according to the comparison result.

4. The service conversion rate evaluation method according to claim 1, characterized by, After acquiring the second user information of the target user according to the business-related information collection item, the method further comprises the following steps: identifying the second user information according to a preset risk control model, and outputting a risk score of the target user; screening the target users in the second user set according to the risk score to obtain a third user set; associating a business object identifier corresponding to the to-be-handled business type with the order information, and if the order information of a target user in the third user set contains a corresponding business object identifier, it is determined that the target user has completed the order, and the target user who has completed the order is determined as a target user for final lending.

5. The service conversion rate evaluation method according to claim 4, characterized by, According to the preset risk control model, the second user information is identified, and a risk score of the target user is output, including: Obtaining one or more key features in the second user information; Input the key features into the risk control model to compare the similarity with the preset risk control indicators, and obtain the matched risk control indicators; The weight corresponding to the matched risk control indicators is used as the weight of the corresponding key features; According to the key features contained in the second user information and the weight of the key features, the risk score is determined.

6. The service conversion rate evaluation method according to claim 4 or 5, characterized by, According to the target user number of the final loan and the first user set, the business conversion rate is determined, including: According to the second user set and the first user set, a first conversion rate is determined; According to the third user set and the second user set, a second conversion rate is determined; According to the target user number of the final loan and the third user set, a third conversion rate is determined; According to the first conversion rate, the second conversion rate and the third conversion rate, the business conversion rate is determined.

7. A service conversion rate evaluation apparatus characterized by comprising: Including: The target acquisition module is used for acquiring the identity information of a plurality of target users in a preset time and the to-be-done business type, and all the target users are grouped into a first user set; The access module is used for determining a preset business access condition according to the to-be-done business type, removing the target users in the first user set who do not meet the preset business access condition, and obtaining a second user set; The order interaction module is used for generating order information according to the identity information of the target users in the second user set and the corresponding to-be-done business type, and interacting with the corresponding target users to determine the target user number of the final loan; According to the identity information of the target users in the second user set and the corresponding to-be-done business type, the order information is generated and the corresponding target users are interacted, including: according to the to-be-done business type, a preset order template of the corresponding business is called, the preset order template includes a business-related information collection item, and the order information is obtained by marking the order template through the identity information; the order information is output to a preset second interaction interface, and the second user information of the target user is obtained according to the business-related information collection item; The conversion rate evaluation module is used for determining the business conversion rate according to the target user number of the final loan and the first user set.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the business conversion rate evaluation method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to realize the steps of the business conversion rate evaluation method of any one of claims 1 to 6.

Images