CN117909590A

CN117909590A - Service organization recommendation method, device, equipment, medium and program product

Info

Publication number: CN117909590A
Application number: CN202410102073.5A
Authority: CN
Inventors: 余磊; 姜文玲
Original assignee: Chongqing Ant Consumer Finance Co ltd
Current assignee: Chongqing Ant Consumer Finance Co ltd
Priority date: 2024-01-24
Filing date: 2024-01-24
Publication date: 2024-04-19

Abstract

The embodiment of the specification discloses a service mechanism recommendation method, device, equipment, medium and product. Wherein the method comprises the following steps: acquiring target characteristic indexes of target users and preference configuration information corresponding to each of a plurality of service mechanisms in the affiliated mechanism; respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service mechanisms, and determining at least one service mechanism to be recommended, which is matched with the target user, in the plurality of service mechanisms; predicting a target prediction index between a target user and a service mechanism to be recommended based on the target characteristic index, wherein the target prediction index is used for predicting a future relationship between the target user and the service mechanism to be recommended; and determining the target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

Description

Service organization recommendation method, device, equipment, medium and program product

Technical Field

The present disclosure relates to the field of intelligent recommendation technologies, and in particular, to a service mechanism recommendation method, device, equipment, medium, and program product.

Background

In the consumer finance scenario, there are two modes of service, camping and affiliated. In the affiliated mode, aiming at the credit application of the user, the affiliated mechanism needs to be ensured to have a high passing rate so as to improve the user experience, and the preference of the affiliated mechanism needs to be considered to meet the requirements of the affiliated mechanism.

Therefore, there is a need for a service organization recommendation method that can comprehensively consider user experience and affiliate organization service preference limitations to select a most suitable service organization from multiple affiliates for service to a user.

Disclosure of Invention

The embodiment of the specification provides a service organization recommending method, device, equipment, medium and program product, which greatly reduce the rejection rate of a service organization in a service application (e.g. a credit application) stage and improve the success rate of the recommended target service organization in a user service request stage (e.g. a credit application stage) by predicting a target prediction index for predicting the future relationship between the service organization and a target user. The technical scheme is as follows:

in a first aspect, an embodiment of the present disclosure provides a service organization recommendation method, where the method includes:

Acquiring target characteristic indexes of target users and preference configuration information corresponding to each of a plurality of service mechanisms in the affiliated mechanism;

respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service institutions, and determining at least one service institution to be recommended, which is matched with the target user, in the plurality of service institutions;

predicting a target prediction index between the target user and the service mechanism to be recommended based on the target characteristic index; the target prediction index is used for predicting the future relation between the target user and the service mechanism to be recommended;

And determining the target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

In one possible implementation manner, the determining, based on the target prediction index corresponding to the at least one service to be recommended, the target service recommended for the target user includes:

Evaluating the real-time state score of the service mechanism to be recommended based on the interaction log information corresponding to the service mechanism to be recommended;

Determining the recommendation priority corresponding to each of the at least one service mechanism to be recommended based on the target prediction index corresponding to each of the at least one service mechanism to be recommended;

Weighting calculation is carried out on the recommendation priority corresponding to each of the at least one service mechanism to be recommended and the real-time state score to obtain the target recommendation priority corresponding to each of the at least one service mechanism to be recommended;

And determining the target service mechanism recommended for the target user based on the target recommendation priority corresponding to each of the at least one service mechanism to be recommended.

In one possible implementation manner, the interaction log information includes a current response duration and a current response success rate of the service mechanism to be recommended;

the evaluating the real-time status score of the service organization to be recommended based on the interaction log information corresponding to the service organization to be recommended includes:

and carrying out weighted evaluation on the current response time length and the current response success rate to obtain the real-time state score of the service institution to be recommended.

In one possible implementation manner, the predicting the target prediction index between the target user and the service to be recommended based on the target feature index includes:

Inputting the target characteristic index into an index prediction model corresponding to the service mechanism to be recommended, and outputting a target prediction index between the target user and the service mechanism to be recommended; the index prediction model is obtained by training based on characteristic indexes of a plurality of users known to be corresponding to the prediction indexes of the service mechanism to be recommended; the target prediction index includes at least one of the following: target passing rate index, target risk index, target utilization rate index, and target repayment capability index.

In one possible implementation manner, the obtaining the target feature index of the target user includes:

Acquiring target user data of the target user; the target user data comprise target basic data provided by the target user and target external data obtained after the authorization of the target user;

And processing the target user data based on the timeliness of the target user data to obtain target characteristic indexes corresponding to the target users.

In one possible implementation, the preference configuration information includes information of at least one of the following preset mechanism dimensions: basic information, regional information, age requirement information, and risk preference information;

The obtaining the preference configuration information corresponding to each of the plurality of service institutions in the affiliated institution includes:

and acquiring preference configuration information set by a manager corresponding to each of the plurality of service institutions in the affiliated institution based on the preset institution dimension.

after receiving a target service request of a target user, acquiring a target characteristic index of the target user;

After determining the target service organization recommended for the target user based on the target prediction index corresponding to the at least one service organization to be recommended, the method further includes:

And forwarding the target service request to the target service mechanism so that the target service mechanism determines corresponding target service response information based on the target service request.

In a second aspect, embodiments of the present disclosure provide a service organization recommendation apparatus, where the apparatus includes:

the first acquisition module is used for acquiring target characteristic indexes of target users;

The second acquisition module is used for acquiring preference configuration information corresponding to each of the plurality of service mechanisms in the affiliated mechanism;

The preference configuration matching module is used for respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service mechanisms and determining at least one service mechanism to be recommended, which is matched with the target user, in the plurality of service mechanisms;

The index prediction module is used for predicting a target prediction index between the target user and the service mechanism to be recommended based on the target characteristic index; the target prediction index is used for predicting the future relation between the target user and the service mechanism to be recommended;

and the service mechanism recommending module is used for determining a target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

In one possible implementation manner, the service organization recommendation module includes:

the mechanism state evaluation unit is used for evaluating the real-time state score of the service mechanism to be recommended based on the interaction log information corresponding to the service mechanism to be recommended;

A recommendation priority determining unit, configured to determine a recommendation priority corresponding to each of the at least one service to be recommended, based on the target prediction indicator corresponding to each of the at least one service to be recommended;

the weighting calculation unit is used for carrying out weighting calculation on the recommendation priority corresponding to each of the at least one service mechanism to be recommended and the real-time state score to obtain the target recommendation priority corresponding to each of the at least one service mechanism to be recommended;

And the service mechanism recommending unit is used for determining a target service mechanism recommended for the target user based on the target recommendation priority corresponding to each of the at least one service mechanism to be recommended.

the mechanism state evaluation unit is specifically configured to:

In one possible implementation manner, the index prediction module is specifically configured to:

In one possible implementation manner, the first obtaining module includes:

An acquisition unit configured to acquire target user data of the target user; the target user data comprise target basic data provided by the target user and target external data obtained after the authorization of the target user;

And the processing unit is used for processing the target user data based on the timeliness of the target user data to obtain target characteristic indexes corresponding to the target users.

The second obtaining module is specifically configured to:

In one possible implementation manner, the first obtaining module is specifically configured to:

the service organization recommending apparatus further includes:

And the service request forwarding module is used for forwarding the target service request to the target service mechanism so that the target service mechanism determines corresponding target service response information based on the target service request.

In a third aspect, embodiments of the present disclosure provide an electronic device, including: a processor and a memory;

the processor is connected with the memory;

the memory is used for storing executable program codes;

The processor executes a program corresponding to the executable program code stored in the memory by reading the executable program code for performing the method provided by the first aspect of the embodiments of the present specification or any one of the possible implementations of the first aspect.

In a fourth aspect, embodiments of the present specification provide a computer storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to carry out the method provided by the first aspect of embodiments of the present specification or any one of the possible implementations of the first aspect.

In a fifth aspect, embodiments of the present description provide a computer program product comprising instructions which, when run on a computer or a processor, cause the computer or the processor to perform the method provided by the first aspect of embodiments of the present description or any one of the possible implementations of the first aspect.

In the embodiment of the specification, acquiring a target characteristic index of a target user and acquiring preference configuration information corresponding to each of a plurality of service mechanisms in a affiliated mechanism; respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service institutions, and determining at least one service institution to be recommended, which is matched with the target user, in the plurality of service institutions; predicting a target prediction index between the target user and the service organization to be recommended based on the target feature index, wherein the target prediction index is used for predicting a future relationship between the target user and the service organization to be recommended; the target service mechanism recommended by the target user is determined based on the target prediction index corresponding to the at least one service mechanism to be recommended, so that the rejection rate of the service mechanism in the service application (e.g. credit application) stage is greatly reduced by predicting the target prediction index for predicting the future relationship between the service mechanism and the target user, the problem that the target service mechanism recommended by the target user refuses to provide service for the target user due to the hard rule caused by the fact that the hard rule is directly subjected to the cyclic matching judgment of the rules of the affiliated mechanism such as regions, ages and the like is avoided, and the success rate of the recommended target service mechanism in the user service request stage (e.g. credit application stage) is improved, the service experience of the user can be guaranteed, and the service preference limitation and the service appeal of the affiliated mechanism can be considered.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present description, the drawings that are required in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present description, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic architecture diagram of a service organization recommendation system according to an exemplary embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating a service organization recommendation method according to an exemplary embodiment of the present disclosure;

FIG. 3 is a schematic diagram of an implementation flow of a target service mechanism for determining a recommendation for a target user according to an exemplary embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating an implementation process of a service organization recommendation method according to an exemplary embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of a service organization recommendation device according to an exemplary embodiment of the present disclosure;

Fig. 6 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification.

The terms first, second, third and the like in the description and in the claims and in the above drawings, are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

It should be noted that, information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals according to the embodiments of the present disclosure are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of relevant data is required to comply with relevant laws and regulations and standards of relevant countries and regions. For example, the target user data, preference configuration information, and the like referred to in this specification are all acquired with sufficient authorization.

First, terms according to the embodiments of the present application will be described.

A joint organization: in the affiliated mode, all of the service institutions (e.g., without limitation, banks or financial institutions, etc.) participating in the service (e.g., without limitation, loan service, etc.).

Joint service: a person, project or business is served by two or more service institutions together. Such as, but not limited to, a joint loan service, i.e., a loan provided by two or more banks/financial institutions together to a person, project, or business.

Pulling head row: in the affiliated mode, aiming at the joint service business, the organization is responsible for implementing and coordinating other service organizations to carry out service work and leading the service work task. For example, in a consumer financial credit scenario, in a affiliated mode, for joint loan officials, banks or financial institutions responsible for organizing, coordinating other bank/financial institution loan tasks, leading loan work tasks.

Credit application: trust refers to the act of a bank/financial institution providing funds support directly to a customer or guaranteeing a third party for the customer's credit in an associated economic activity. The credit application refers to the application behavior that a customer obtains credit from a bank or a financial institution.

In the related art, in the affiliated mode, aiming at the credit application of the user, as the lead line of the combined service, either a service mechanism is randomly selected from the affiliated mechanism list to carry out the credit application, or the hard rules of the affiliated mechanism, such as the area, the age and the like, are subjected to the rule circulation matching judgment with the user information, so as to find the user meeting the requirements of the service mechanism. However, because of the diversified combination distribution of the areas, the expenses, the professions, the credit levels and the like of the users, the financial institutions have different requirements on the area restrictions, the client preferences, the risk bearing capacity and the like of the users, the system capacity of the financial institutions is also uneven, the service institutions selected in a random manner often cause the failure of the credit application, the user experience is hurt on one hand, and a large number of users are lost on the other hand. The service mechanism selected by the hard rule circular matching mode does not consider the risk of the user at all, namely, whether the service relationship exists between the user and the service mechanism in the future under the condition of no risk or smaller risk is not predicted, so that the situation that the selected service mechanism refuses to provide service for the user due to higher risk of the user easily occurs.

Based on this, the embodiments of the present disclosure provide a service mechanism recommendation method, apparatus, device, medium, and program product, which greatly reduce the rejection rate of a service mechanism in a service application (e.g., a credit application) stage by predicting a target prediction index for predicting a future relationship between the service mechanism and a target user, improve the success rate of the recommended target service mechanism in the user service request stage (e.g., the credit application stage), and not only ensure the service experience of the user, but also consider the service preference limitation and service appeal of the affiliated mechanism.

Next, please refer to fig. 1, which is a schematic diagram illustrating an architecture of a service organization recommendation system according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the service organization recommendation system includes: a client 110, a lead 120, and a service organization. Wherein:

The user terminal 110 may be a terminal corresponding to a user who needs to apply for services such as trust, and the user terminal 110 may be installed with target service software, and the user may, but is not limited to, send a target service request to the service organization or the affiliated organization by applying for the target service software. The user terminal 110 may interact with the lead 120 and the service mechanism through the network to receive a target service request from the target service mechanism recommended by the lead 120 or send a target service request of a target user to the lead 120, or receive target service response information determined by the target service mechanism according to the target service request, etc. The client 110 may be hardware or software. When the user terminal 110 is hardware, it may be various electronic devices including, but not limited to, a smart watch, a smart phone, a tablet computer, a laptop portable computer, a desktop computer, and the like. When the client 110 is software, it may be installed in the above-listed electronic device, and may be implemented as a plurality of software or software modules (for example, to provide distributed services), or may be implemented as a single software or software module, which is not specifically limited herein.

The lead lines 120 may be organization-specific servers that are capable of providing various service organization recommendations in the affiliated mode. The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (for example, to provide a distributed service), or may be implemented as a single software or software module, which is not specifically limited herein. The servers may be, but are not limited to, hardware servers, virtual servers, cloud servers, and the like.

In the embodiment of the present disclosure, the lead line 120 may first obtain the target feature index of the target user and the preference configuration information corresponding to each of the multiple service mechanisms in the affiliated mechanism; then, matching the target characteristic index with preference configuration information corresponding to each of the plurality of service mechanisms respectively, and determining at least one service mechanism to be recommended, which is matched with the target user, in the plurality of service mechanisms; predicting a target prediction index between a target user and a service mechanism to be recommended based on the target characteristic index, wherein the target prediction index is used for predicting a future relationship between the target user and the service mechanism to be recommended; and finally, determining the target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

The service institutions may be servers corresponding to all service institutions (e.g., without limitation, banks or financial institutions, etc.) participating in a service (e.g., without limitation, loan service, etc.) in the affiliated mode, such as, without limitation, including service institution 130a, service institution 130b, service institution 130c, etc. Any service organization may interact with the lead line 120 through a network, for example, receive a target service request of a target user forwarded by the lead line 120, and send target service response information corresponding to the target service request to the lead line 120.

The network may be a medium that provides a communication link between the client 110 and the lead 120, between the lead 120 and any service mechanism, or between the client 110 and any service mechanism, or may be the internet that includes network devices and transmission media, but is not limited thereto. The transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic and digital subscriber lines (digital subscriber line, DSL), etc., or a wireless link, such as, but not limited to, wireless internet (WIRELESS FIDELITY, WIFI), hypertext transfer protocol (Hypertext Transfer Protocol, HTTP), bluetooth, and mobile device networks, etc.

It will be appreciated that the number of clients 110, lead lines 120, and service institutions in the service institution recommendation system shown in FIG. 1 is by way of example only, and that any number of clients 110, lead lines 120, and service institutions may be included in the service institution recommendation system in a particular implementation.

Next, referring to fig. 1, taking the lead line to execute service mechanism recommendation as an example, a service mechanism recommendation method provided in an exemplary embodiment of the present disclosure is described. As shown in fig. 2, the service organization recommending method includes the following steps:

S202, obtaining target characteristic indexes of target users.

Specifically, the target feature index is a quantization index for describing and measuring features of various aspects of the target user, and is used for analyzing information of various aspects of behavior, requirements, preferences and the like of the target user. The target characteristic index may include, but is not limited to, characteristic indexes of the target user in various aspects such as region, occupation, education level, balance level, consumption habit and the like.

Further, when the target user wants to apply for the target service, the corresponding target service request can be sent to the lead through the user terminal. After receiving the target service request of the target user, the lead can acquire the target characteristic index of the target user according to the target user identifier carried by the target service request, so as to recommend a more suitable target service mechanism for the target user according to the target characteristic index of the target user for the target service request of the target user. The target service request can carry information of target service applied by the target user besides the target user identifier of the target user, for example, when the target user applies for loan, the target service request can carry loan amount of loan service applied by the target user, so that a target service mechanism can be accurately recommended for the target user according to the information of the target service applied by the target user, and the passing rate of the target user service application is improved.

Optionally, in S202 above, acquiring the target feature index of the target user may include: the method comprises the steps of firstly obtaining target user data of a target user, and then processing the target user data based on timeliness of the target user data to obtain target characteristic indexes corresponding to the target user. The target user data may include, but is not limited to, target basic data provided by the target user and target external data of the target user obtained by querying an external institution after authorization of the target user. The target basic data may include, but is not limited to, age, name, native and the like of the target user, and the target external data may include, but is not limited to, school information of the target user queried from the credit network, expense information of the target user queried from the banking institution and the like, consumption information of the target user queried from the consumption software and the like after the authorization of the target user. The processing of the target user data based on the timeliness of the target user data to obtain the target feature index corresponding to the target user may, but is not limited to, offline processing (e.g., but not limited to, feature extraction and/or model classification of the target user data obtained by history with low timeliness requirements) the target user data with low timeliness requirements, such as the student status information and the hometown information of the target user, and online real-time processing (e.g., but not limited to, real-time feature extraction and/or model classification of the target user data obtained by real-time acquisition of the target user data with high timeliness requirements) the target user data with high timeliness requirements, such as the age of the target user.

According to the embodiment of the specification, after the target user data of the target user are obtained, the target user data are processed based on timeliness of the target user data to obtain the target feature indexes corresponding to the target user, so that the target user data with low timeliness requirements can be processed in an efficient and rapid off-line manner, the obtaining efficiency of the target feature indexes is ensured, the real-time on-line processing of the target user data with high timeliness requirements is also performed, the accuracy of the target feature indexes with high timeliness requirements is ensured, and further, the follow-up recommendation of a more accurate service mechanism can be realized according to the accurate target feature indexes.

It may be understood that, in the embodiment of the present disclosure, the target feature indexes required to be obtained may include one or more feature indexes of the target user to be extracted, which are preset according to the recommended requirement of the actual service institution, and this disclosure is not limited in particular.

Next, please refer to fig. 2, as shown in fig. 2, the step S202, after obtaining the target feature index of the target user, further includes:

S204, obtaining preference configuration information corresponding to each of the plurality of service institutions in the affiliated institution.

Specifically, the above-mentioned preference configuration information is information for characterizing various aspects of policies, users, means, etc. that are preferred when the service organization provides the service, and may, but is not limited to, information including at least one of the following preset organization dimensions: basic information, regional information, age requirement information, and risk preference information.

Optionally, when the lead needs to make service mechanism recommendation, the preference configuration information set by the manager corresponding to each of the plurality of service mechanisms in the affiliated mechanism based on the preset mechanism dimension may be obtained directly, for example, but not limited to, sending a preference configuration request of the preset mechanism dimension to the manager corresponding to each of the plurality of service mechanisms, receiving preference configuration information set by the manager corresponding to each of the plurality of service mechanisms based on the preset mechanism dimension and the like returned by the manager corresponding to each of the plurality of service mechanisms.

S206, matching the target characteristic index with preference configuration information corresponding to each of the plurality of service institutions, and determining at least one service institution to be recommended, which is matched with the target user, in the plurality of service institutions.

Specifically, after the target feature index of the target user and the preference configuration information corresponding to each of the plurality of service institutions are obtained, the target feature index and the preference configuration information corresponding to each of the plurality of service institutions may be respectively matched, whether the target feature index of the target user completely hits the preference (for example, risk preference, age preference, guest group preference, such as preference white collar or blue collar, etc.) in the preference configuration information of the service institutions is seen, if the target feature index of the target user completely hits, the service institutions are matched with the target user, if the target user applies for services to the service institutions, the service institutions cannot be refused due to strong rule matching of the service institutions, and if the application passing rate of the target user is guaranteed to a certain extent, the service institutions may be determined as service institutions to be recommended in the affiliated institutions.

S208, predicting target prediction indexes between the target user and the service institution to be recommended based on the target characteristic indexes.

Specifically, the target prediction index is used for predicting a future relationship (for example, predicting whether a service relationship exists in the future) between the target user and the service organization to be recommended, that is, whether the service organization to be recommended will agree to provide the target service for the target user after receiving the target service request of the target user.

Specifically, after the target characteristic index of the target user is obtained, the target characteristic index can be directly input into an index prediction model corresponding to the service mechanism to be recommended, the target prediction index between the target user and the service mechanism to be recommended is output, and the index prediction model is obtained by training the characteristic indexes of a plurality of users which know the prediction indexes corresponding to the service mechanism to be recommended. The portion of the target prediction index that can be limited to include at least one of: target passing rate index, target risk index, target utilization rate index, and target repayment capability index. The target passing rate index is used for representing the probability that a target user applies for target service to a service mechanism to be recommended, the target risk index is used for representing the probability that the target user may risk after the service mechanism to be recommended provides target service for the target user or the risk degree corresponding to the target user, the target tariff rate index is used for representing the proportion of total funds which the target user may need to use funds to provide target service for the target user after the service mechanism to be recommended provides target service for the target user, and the target repayment capability index is used for representing repayment capability of the target user.

It may be understood that the target feature indexes of the target users focused by the index prediction models of different service institutions to be recommended may be the same or different, which is not limited in the embodiment of the present disclosure.

S210, determining a target service mechanism recommended for the target user based on target prediction indexes corresponding to at least one service mechanism to be recommended.

Specifically, after predicting the target prediction index between the target user and the service to be recommended based on the target feature index, the recommendation priority of at least one service to be recommended may be ordered according to the target prediction index corresponding to at least one service to be recommended, for example, but not limited to, the higher the target passing rate index is, the higher the recommendation priority corresponding to the service to be recommended is, the lower the recommendation priority corresponding to the service to be recommended is, and then the service to be recommended with the highest recommendation priority among the at least one service to be recommended is determined as the target service recommended by the target user.

It may be understood that, when the service organization to be recommended corresponds to a plurality of different target predictors, the recommendation priority of the service organization to be recommended may be determined comprehensively according to weights corresponding to the target predictors, and weights corresponding to the same target predictors of different service organizations to be recommended may be the same or different.

In some possible embodiments, after the lead receives the target service request of the target user, the target feature index of the target user may be obtained, and the target service mechanism recommended for the target user is determined by the service mechanism recommendation method described in the embodiments of the present specification. And then, forwarding the target service request to the target service mechanism so that the target service mechanism determines corresponding target service response information based on the target service request, for example, but not limited to, inquiring corresponding target user data according to a target user identifier carried by the target service request, performing risk assessment based on the target user data to obtain a corresponding target risk assessment result, determining whether to provide target service for the target user according to the target risk assessment result, and the like.

In some possible embodiments, as shown in fig. 3, in S210, the implementation procedure of determining, based on the target prediction index corresponding to the at least one service entity to be recommended, the target service entity recommended for the target user may include:

s302, evaluating real-time state scores of the service institutions to be recommended based on the interaction log information corresponding to the service institutions to be recommended.

Specifically, the interaction log information may include, but is not limited to, a current response duration and a current response success rate of the service institution to be recommended. The current response time may be, but is not limited to, a time between a request time when the lead transmits the interactive test request to the service to be recommended and a response time when the service to be recommended receives a test response to the interactive test request. The current response success rate may be, but is not limited to, the success rate of waiting for the recommended service organization to respond to the user to apply for the service for the current time period (e.g., but not limited to, within 1 day, within 1 month, etc.).

Optionally, after determining at least one service mechanism to be recommended, interaction log information corresponding to each service mechanism to be recommended may be obtained first, and then the interaction log information corresponding to the service mechanism to be recommended is input into the real-time state evaluation model, and a real-time state score of the service mechanism to be recommended is output. The real-time state evaluation model may be, but is not limited to, obtained by training based on interaction log information corresponding to each of a plurality of service institutions with known real-time state scores.

Optionally, after the current response time length, the current response success rate and other interaction log information of the service mechanism to be recommended are obtained, the current response time length and the current response success rate can be weighted and evaluated to obtain a real-time state score of the service mechanism to be recommended. The weighting weights corresponding to the current response time length and the current response success rate may be the same or different, which is not limited in this specification.

It can be understood that, under the condition that the current response success rate is the same, the current response time length is different, or the range of the current response time length is different, the real-time state scores of the corresponding service institutions to be recommended are different; under the condition that the current response time length is the same, the current response success rate is different, or the range of the current response success rate is different, and the real-time state scores of the corresponding service institutions to be recommended are different. The shorter the current response time length is, the higher the current response success rate is, and the higher the real-time state score of the service institution to be recommended is.

S304, determining the recommendation priority corresponding to each of the at least one service mechanism to be recommended based on the target prediction index corresponding to each of the at least one service mechanism to be recommended.

Specifically, the determining manner of the recommendation priority of each of the at least one service mechanism to be recommended in S304 is consistent with the determining manner of the recommendation priority of the service mechanism to be recommended in the specific description of S210, which is not described herein.

S306, weighting calculation is carried out on the recommendation priority and the real-time state score corresponding to the at least one service mechanism to be recommended, and the target recommendation priority corresponding to the at least one service mechanism to be recommended is obtained.

Specifically, after determining the recommendation priority and the real-time status score corresponding to each of the at least one service mechanism to be recommended, the recommendation priority and the real-time status score corresponding to each of the service mechanisms to be recommended may be weighted, so as to obtain the target recommendation priority corresponding to each of the service mechanisms to be recommended.

It can be understood that when the real-time status score of the service mechanism to be recommended is 0, which indicates that the system of the service mechanism to be recommended fails or is offline, and the target service cannot be provided for the target user currently, it can be determined that the target recommendation priority of the service mechanism to be recommended is 0. In order to ensure accuracy and response success rate of service institution recommendation, only recommendation priority of service institutions to be recommended and real-time status scores meeting preset service requirements can be weighted, and institutions to be recommended which do not meet preset service requirements, for example, real-time status scores of 0 or less than preset scores, are screened out from calculation which does not participate in subsequent target recommendation priority and determined recommendation of target service institutions.

S308, determining a target service mechanism recommended for the target user based on the target recommendation priority corresponding to each of the at least one service mechanism to be recommended.

Specifically, but not limited to, determining a service mechanism to be recommended with the highest target recommendation priority in at least one service mechanism to be recommended as a target service mechanism recommended by a target user, so that real-time state scoring of a service mechanism system is performed by sensing system indexes such as a service mechanism response state (such as a current response success rate and the like) and a current response time length in real time, and weighting and sorting are performed according to the real-time state scoring in combination with target prediction indexes of the service mechanisms to be recommended, so that a most suitable target service mechanism is selected, a scene that a target user is refused due to the system reason of the service mechanism in a trust application stage (namely, a service request stage) is avoided, and service experience of the user is further ensured while service preference limitation and service appeal of the affiliated mechanism are considered.

Referring next to fig. 4, as shown in fig. 4, the service recommendation lead or other device in the embodiment of the present disclosure may include, but is not limited to, a user data acquisition module, a mechanism preference configuration module, a model prediction module, a mechanism state evaluation module, a loading module, a service recommendation policy execution module, and the like. Wherein:

and the user data acquisition module is used for acquiring target basic data submitted by the target user and target external data of the target user inquired after the target user authorization passes. After the user data acquisition module acquires the target basic data and the target external data, the data can be processed offline or calculated in real time to obtain the target characteristic index corresponding to the target user.

The institution preference configuration module is used for configuring preference configuration information of preset institution dimensions such as basic information, regional information, age requirements, risk preferences and the like of the affiliated institutions.

The model prediction module can predict target prediction indexes such as target passing rate indexes, target risk indexes, target utilization rate indexes, target repayment capacity indexes and the like of target users by combining historical big data of a service mechanism through an artificial intelligence algorithm.

The mechanism state evaluation module is used for analyzing the obtained real-time interaction log information such as the current response time length and the current response success rate of the service mechanism and evaluating the real-time state scores of the service mechanisms in the linkage mechanism.

The loading module is used for loading contents such as target characteristic indexes, preference configuration information, target prediction indexes, real-time state scores and the like on which the service mechanism recommendation depends into the program memory for use when the service mechanism recommendation policy execution module carries out service mechanism recommendation.

The service mechanism recommendation policy execution module is used for firstly matching the target characteristic index of the target user with preference configuration information of each service mechanism in the affiliated mechanism to determine at least one service mechanism to be recommended; and then sequencing the recommendation priority of at least one service mechanism to be recommended according to the target prediction index between the at least one service mechanism to be recommended and the target user, finally carrying out weighted calculation by combining the real-time state scores of the service mechanisms to be recommended to determine the final target recommendation priority of the service mechanisms to be recommended, and selecting the service mechanism to be recommended with the highest target recommendation priority as the target service mechanism which is finally recommended for the target user.

Next, please refer to fig. 5, which is a schematic diagram illustrating a service organization recommendation device according to an exemplary embodiment of the present disclosure. As shown in fig. 5, the service organization recommendation device 500 includes:

A first obtaining module 510, configured to obtain a target feature index of a target user;

a second obtaining module 520, configured to obtain preference configuration information corresponding to each of the plurality of service institutions in the affiliated institution;

A preference configuration matching module 530, configured to match the target feature index with preference configuration information corresponding to each of the plurality of service mechanisms, and determine at least one service mechanism to be recommended that matches the target user in the plurality of service mechanisms;

An index prediction module 540, configured to predict a target prediction index between the target user and the service to be recommended based on the target feature index; the target prediction index is used for predicting the future relation between the target user and the service mechanism to be recommended;

And a service mechanism recommending module 550, configured to determine a target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

In one possible implementation, the service organization recommendation module 550 includes:

the mechanism state evaluation unit is specifically configured to:

In one possible implementation, the index prediction module 540 is specifically configured to:

In one possible implementation manner, the first obtaining module 510 includes:

the second obtaining module 520 is specifically configured to:

In one possible implementation manner, the first obtaining module 510 is specifically configured to:

the service organization recommendation device 500 further includes:

The division of the modules in the service recommendation device is only used for illustration, and in other embodiments, the service recommendation device may be divided into different modules as required to complete all or part of the functions of the service recommendation device. The implementation of each module in the service organization recommendation apparatus provided in the embodiments of the present specification may be in the form of a computer program. The computer program may run on a terminal or a server. Program modules of the computer program may be stored in the memory of the terminal or server. The computer program, when executed by a processor, implements all or part of the steps of the service organization recommendation method described in the embodiments of the present specification.

Next, please refer to fig. 6, which is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. As shown in fig. 6, the electronic device 600 may include: at least one processor 610, at least one communication bus 620, a user interface 630, at least one network interface 640, a memory 650.

Wherein the communication bus 620 may be used to enable the connection communication of the various components described above.

The user interface 630 may include a Display screen (Display) and a Camera (Camera), and the optional user interface may further include a standard wired interface and a wireless interface.

The network interface 640 may optionally include a bluetooth module, a Near Field Communication (NFC) module, a wireless fidelity (WIRELESS FIDELITY, wi-Fi) module, and the like, among others.

Wherein the processor 610 may include one or more processing cores. The processor 610 utilizes various interfaces and lines to connect various portions of the overall electronic device 600, perform various functions of the routing electronic device 600 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 650, and invoking data stored in the memory 650. Alternatively, the processor 610 may be implemented in at least one hardware form of digital signal processing (DIGITAL SIGNAL processing, DSP), field-programmable gate array (field-programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 610 may integrate one or a combination of several of a processor (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 610 and may be implemented by a single chip.

The memory 650 may include a random access memory (Random Access Memory, RAM) or a read-only memory (ROM). Optionally, the memory 650 includes a non-transitory computer readable medium. Memory 650 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 650 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as an index prediction function, a service organization recommendation function, a preference configuration matching function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data or the like referred to in the above respective method embodiments. Memory 650 may also optionally be at least one storage device located remotely from the aforementioned processor 610. As shown in fig. 6, an operating system, network communication modules, user interface modules, and program instructions may be included in memory 650, which is a type of computer storage medium.

In some possible embodiments, the electronic device 600 may be the service organization recommendation device described above, and the processor 610 may be configured to call the program instructions stored in the memory 650, and specifically perform the following operations: acquiring target characteristic indexes of target users and preference configuration information corresponding to each of a plurality of service mechanisms in the affiliated mechanism; respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service institutions, and determining at least one service institution to be recommended, which is matched with the target user, in the plurality of service institutions; predicting a target prediction index between the target user and the service mechanism to be recommended based on the target characteristic index; the target prediction index is used for predicting the future relation between the target user and the service mechanism to be recommended; and determining the target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

In some possible embodiments, when the processor 610 executes the target service recommended for the target user based on the target prediction index corresponding to the at least one service to be recommended, the method is specifically configured to execute: evaluating the real-time state score of the service mechanism to be recommended based on the interaction log information corresponding to the service mechanism to be recommended; determining the recommendation priority corresponding to each of the at least one service mechanism to be recommended based on the target prediction index corresponding to each of the at least one service mechanism to be recommended; weighting calculation is carried out on the recommendation priority corresponding to each of the at least one service mechanism to be recommended and the real-time state score to obtain the target recommendation priority corresponding to each of the at least one service mechanism to be recommended; and determining the target service mechanism recommended for the target user based on the target recommendation priority corresponding to each of the at least one service mechanism to be recommended.

In some possible embodiments, the interaction log information includes a current response duration and a current response success rate of the service mechanism to be recommended;

the processor 610 is specifically configured to execute when executing the evaluation of the real-time status score of the service organization to be recommended based on the interaction log information corresponding to the service organization to be recommended:

In some possible embodiments, when the processor 610 executes the target prediction index for predicting the target user and the service to be recommended based on the target feature index, the method specifically includes: inputting the target characteristic index into an index prediction model corresponding to the service mechanism to be recommended, and outputting a target prediction index between the target user and the service mechanism to be recommended; the index prediction model is obtained by training based on characteristic indexes of a plurality of users known to be corresponding to the prediction indexes of the service mechanism to be recommended; the target prediction index includes at least one of the following: target passing rate index, target risk index, target utilization rate index, and target repayment capability index.

In some possible embodiments, when the processor 610 executes the obtaining the target feature index of the target user, the method specifically is used to execute: acquiring target user data of the target user; the target user data comprise target basic data provided by the target user and target external data obtained after the authorization of the target user; and processing the target user data based on the timeliness of the target user data to obtain target characteristic indexes corresponding to the target users.

In some possible embodiments, the preference configuration information includes information of at least one of the following preset mechanism dimensions: basic information, regional information, age requirement information, and risk preference information;

The processor 610 is specifically configured to, when executing the obtaining the preference configuration information corresponding to each of the plurality of service institutions in the affiliated institution, execute: and acquiring preference configuration information set by a manager corresponding to each of the plurality of service institutions in the affiliated institution based on the preset institution dimension.

In some possible embodiments, when the processor 610 executes the obtaining the target feature index of the target user, the method specifically is used to execute:

And after receiving the target service request of the target user, acquiring the target characteristic index of the target user.

The processor 610 is further configured to execute, after executing the determining the target service recommended for the target user based on the target prediction index corresponding to the at least one service to be recommended, the following steps:

The present description also provides a computer-readable storage medium having instructions stored therein, which when executed on a computer or processor, cause the computer or processor to perform one or more steps of the above embodiments. The respective constituent modules of the service organization recommendation apparatus may be stored in the computer-readable storage medium if implemented in the form of software functional units and sold or used as independent products.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product described above includes one or more computer instructions. When the computer program instructions described above are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present specification are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted across a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (Digital Subscriber Line, DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage media may be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disk (DIGITAL VERSATILE DISC, DVD)), or a semiconductor medium (e.g., a Solid state disk (Solid STATE DISK, SSD)), or the like.

Those skilled in the art will appreciate that implementing all or part of the above-described embodiment methods may be accomplished by way of a computer program, which may be stored in a computer-readable storage medium, instructing relevant hardware, and which, when executed, may comprise the embodiment methods as described above. And the aforementioned storage medium includes: various media capable of storing program code, such as ROM, RAM, magnetic or optical disks. The technical features in the present examples and embodiments may be arbitrarily combined without conflict.

The above-described embodiments are merely preferred embodiments of the present disclosure, and do not limit the scope of the disclosure, and various modifications and improvements made by those skilled in the art to the technical solution of the disclosure should fall within the scope of protection defined by the claims.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims and description may be performed in an order different from that in the embodiments recited in the description and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A service organization recommendation method, the method comprising:

Respectively matching the target characteristic index with preference configuration information corresponding to each of the plurality of service mechanisms, and determining at least one service mechanism to be recommended, which is matched with the target user, in the plurality of service mechanisms;

Predicting a target prediction index between the target user and the service mechanism to be recommended based on the target characteristic index; the target prediction index is used for predicting a future relationship between the target user and the service mechanism to be recommended;

and determining a target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended.

2. The method of claim 1, wherein the determining, based on the target prediction index corresponding to the at least one service entity to be recommended, a target service entity recommended for the target user includes:

Determining recommendation priorities corresponding to the at least one service mechanism to be recommended respectively based on the target prediction indexes corresponding to the at least one service mechanism to be recommended respectively;

3. The method of claim 2, wherein the interaction log information includes a current response duration and a current response success rate of the service to be recommended;

and carrying out weighted evaluation on the current response time length and the current response success rate to obtain the real-time state score of the service mechanism to be recommended.

4. The method of claim 1, the predicting a target prediction index between the target user and the service to be recommended based on the target feature index, comprising:

Inputting the target characteristic index into an index prediction model corresponding to the service mechanism to be recommended, and outputting a target prediction index between the target user and the service mechanism to be recommended; the index prediction model is obtained by training based on the characteristic indexes of a plurality of users known to be corresponding to the prediction indexes of the service mechanism to be recommended; the target prediction index comprises at least one of the following: target passing rate index, target risk index, target utilization rate index, and target repayment capability index.

5. The method of claim 1, the obtaining the target feature indicator of the target user, comprising:

6. The method of claim 1, the preference configuration information comprising information of at least one of the following preset mechanism dimensions: basic information, regional information, age requirement information, and risk preference information;

the obtaining the preference configuration information corresponding to each of the plurality of service institutions in the affiliated institution comprises the following steps:

7. The method of claim 1, the obtaining the target feature indicator of the target user, comprising:

After determining the target service mechanism recommended for the target user based on the target prediction index corresponding to the at least one service mechanism to be recommended, the method further includes:

8. A service organization recommendation device, the device comprising:

the index prediction module is used for predicting a target prediction index between the target user and the service mechanism to be recommended based on the target characteristic index; the target prediction index is used for predicting a future relationship between the target user and the service mechanism to be recommended;

9. An electronic device, comprising: a processor and a memory;

The processor is connected with the memory; the memory is used for storing executable program codes; the processor runs a program corresponding to executable program code stored in the memory by reading the executable program code for performing the method according to any one of claims 1-7.

10. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any of claims 1-7.

11. A computer program product comprising instructions which, when run on a computer or a processor, cause the computer or the processor to perform the method of any of claims 1-7.