CN117033789A - Method and device for determining service recommendation scheme, processor and electronic equipment - Google Patents

Abstract

The application discloses a method and a device for determining a service recommendation scheme, a processor and electronic equipment. Relates to the field of financial science and technology, and the method comprises the following steps: extracting service information of a target service, and constructing a triple structure by the service information, wherein the triple structure represents a framework among entity information, relationship information and attribute information in the service information; performing cluster analysis on the entity information, the relation information and the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result; and extracting the target mechanism and the target client from the target attribute information, and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client so as to complete the target service. The application solves the problem of low success rate of service recommendation by using the recommendation scheme in the related technology.

Description

Method and device for determining service recommendation scheme, processor and electronic equipment

Technical Field

The application relates to the field of financial science and technology, in particular to a method and device for determining a business recommendation scheme, a processor and electronic equipment.

Background

When a financial institution carries out product recommendation, a common recommendation method is to negotiate with a target charging institution through a business person, and further recommend a charging service of the institution to the institution, wherein the charging service can comprise an internal or external charging service for helping the charging institution to carry out, for example, a charging service such as water and electricity gas charge, service charge, property charge and the like, and further comprises a service for helping the institution to carry out bill management, user charging service, charging detail query, refund, reconciliation and the like.

Before making service recommendations, the service personnel need to select the appropriate institution from the existing institution customer list, but this method has many problems: because the mechanism in the mechanism customer list is too many, if the mechanism is screened by using a manual mode, a great amount of time cost and labor cost are consumed in the screening process, and in addition, if the service personnel conduct manual screening, a lower recommendation success rate can be caused due to insufficient cognition of different mechanisms.

Aiming at the problem of low success rate of service recommendation by using a recommendation scheme in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The application mainly aims to provide a method, a device, a processor and electronic equipment for determining a service recommendation scheme, so as to solve the problem of low success rate of service recommendation by using the recommendation scheme in the related technology.

In order to achieve the above object, according to one aspect of the present application, there is provided a method for determining a service recommendation scheme. The method comprises the following steps: extracting service information of a target service, and constructing a triple structure by the service information, wherein the triple structure represents a framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to receipt and payment relation information related to the target service, the receipt and payment relation refers to receipt and payment relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client; performing cluster analysis on the entity information, the relation information and the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result; and extracting the target mechanism and the target client from the target attribute information, and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client so as to complete the target service.

Optionally, performing cluster analysis on the entity information, the relationship information and the attribute information by using a cluster algorithm, and obtaining a cluster result includes: performing numerical value assignment on the entity information, the relation information and the attribute information according to the information assignment table to obtain A entity data, B relation data and C attribute data, wherein A, B, C is a positive integer; carrying out data aggregation on the A entity data, the B relation data and the C attribute data through a clustering model to obtain M clusters, and extracting attribute features from each cluster to obtain M candidate features, wherein M is a positive integer, M is smaller than A, M and smaller than B, and M is smaller than C; generating N feature matrixes according to the M candidate features, wherein each feature matrix comprises mechanism attribute features and customer attribute features, N is a positive integer, and N is smaller than M.

Optionally, generating N feature matrices from the M candidate features includes: and carrying out feature aggregation treatment on the features belonging to the same service type in the M candidate features to obtain N feature matrixes.

Optionally, determining the target attribute information according to the clustering result includes: calculating similarity data between the mechanism attribute features and the client attribute features in each feature matrix to obtain N similarity data; judging whether similarity data smaller than a preset threshold exists in the N pieces of similarity data; and under the condition that target similarity data smaller than a preset threshold exists in the N pieces of similarity data, taking a feature matrix associated with the target similarity data as target attribute information.

Optionally, after determining whether there is similarity data smaller than a preset threshold value in the N pieces of similarity data, the method further includes: under the condition that target similarity data smaller than a preset threshold value does not exist in the N pieces of similarity data, model parameters in the clustering model are adjusted, and an updated clustering model is obtained; and carrying out data aggregation processing on the A entity data, the B relation data and the C attribute data through the updated cluster model again to obtain updated clusters, and determining a feature matrix from the updated clusters until similarity data associated with at least one feature matrix is smaller than a preset threshold value.

Optionally, extracting the service information of the target service includes: obtaining information remarks of candidate service information stored in a database, wherein the information remarks at least comprise one of the following: service type information associated with the candidate service information, receipt relation information associated with the candidate service information, mechanism attribute information associated with the candidate service information and customer information associated with the candidate service information; and determining target information remarks according to the target service, and screening the candidate service information according to the target information remarks to obtain service information.

Optionally, in the case that the recommended solution includes a plurality of recommended solutions, after extracting the target organization and the target client from the target attribute information, the method further includes: pushing target recommended schemes in the plurality of recommended schemes to the clients, and receiving scoring data of the clients on the target recommended schemes; and pushing other recommended schemes to the client under the condition that the scoring data is smaller than the scoring threshold value, wherein the other recommended schemes are recommended schemes other than the target recommended scheme in the plurality of recommended schemes.

In order to achieve the above object, according to another aspect of the present application, there is provided a service recommendation scheme determining apparatus. The device comprises: the first extraction unit is used for extracting service information of the target service and constructing a triplet structure by the service information, wherein the triplet structure represents a framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to collecting relation information related to the target service, the collecting relation refers to collecting relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client; the analysis unit is used for carrying out cluster analysis on the entity information, the relation information and the attribute information by utilizing a cluster algorithm to obtain a cluster result, and determining target attribute information according to the cluster result; and the second extraction unit is used for extracting the target mechanism and the target client from the target attribute information and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client so as to complete the target service.

According to another aspect of the embodiment of the present application, there is further provided a processor, configured to execute a program, where the program controls, when running, a device in which a nonvolatile storage medium is located to execute a method for determining a service recommendation scheme.

According to another aspect of embodiments of the present application, there is also provided an electronic device including one or more processors and a memory; the memory has stored therein computer readable instructions for executing the computer readable instructions, wherein the computer readable instructions when executed perform a method of determining a business recommendation.

According to the application, the following steps are adopted: extracting service information of a target service, and constructing a triple structure by the service information, wherein the triple structure represents a framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to receipt and payment relation information related to the target service, the receipt and payment relation refers to receipt and payment relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client; performing cluster analysis on the entity information, the relation information and the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result; extracting a target mechanism and a target client from target attribute information to generate a recommendation scheme of target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client to finish the target service, the problem of low success rate of service recommendation by using the recommendation scheme in the related technology is solved, a triplet structure is obtained by extracting service information of the target service and constructing the service information, a clustering result is obtained by carrying out clustering analysis on the triplet structure by using a clustering algorithm, and the recommendation scheme of the target service is generated by using the clustering result, so that the effect of improving the success rate of pushing by using the recommendation scheme is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

fig. 1 is a flowchart of a method for determining a service recommendation scheme according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a method for determining target attribute information according to an embodiment of the present application;

fig. 3 is a schematic diagram of a determining device of a service recommendation scheme according to an embodiment of the present application;

fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party.

The present application will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for determining a service recommendation scheme according to an embodiment of the present application, as shown in fig. 1, where the method includes the following steps:

Step S101, extracting service information of a target service, and constructing a triple structure by the service information, wherein the triple structure represents a framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to collecting relation information related to the target service, the collecting relation refers to collecting relation between an organization providing the target service and a client, and the attribute information comprises information of organization attributes of the organization and client attributes of the client.

Specifically, the target service refers to a service that a financial institution needs to recommend to a different institution or a different customer, and may be a service for paying by the financial institution, a service for bill management by the financial institution, a business loan service, and the like. The service information refers to related information generated when the target service is performed, for example, when the target service is a payment service, the service information may be a fee and a fund detail of the payment, and the service information may include a customer group of the payment, a mechanism of the fee, a payment mode, a payment purpose, and the like.

Because the financial institutions need to conduct business negotiations with institutions of different industries and develop business cooperation in daily transactions, in the cooperation process, the financial institutions push recommendation schemes of related businesses to the institutions, and the institutions conduct processing of the related businesses through the recommendation schemes, so that win-win purposes are achieved. However, before negotiating with the institution and achieving win-win cooperation, the institution with a proper cooperation success rate is required to be screened from the existing institution client list, and then a dedicated service recommendation scheme is formulated for the institution.

The triplet structure is obtained by processing service information by RDF architecture (RDF: resource Description Framework, which is a framework for describing resources), so that in order to realize accurate recommendation, firstly, service information associated with target service of a financial institution needs to be acquired, and proper service information is selected from the service information to construct the triplet structure.

It should be noted that, the triplet structure refers to a basic unit in the knowledge graph, including an entity, a relationship and an attribute, that is, including entity information, relationship information and attribute information, where the entity represents an individual, in this embodiment, the entity information may be service type information of a target service that needs to be pushed by a financial institution, for example, the entity information may be information of a fuel industry, etc.; the relationship represents connection or association between entities, and in this embodiment, the relationship information is information of a fund flow direction relationship between a charging mechanism and a paying client, for example, the relationship information may be information of water charge collection between a certain water plant and residents in a certain cell; the attribute represents a feature or attribute of an entity, and in this embodiment, the attribute information may refer to information of a property of an organization and a property of a customer, for example, attribute information of one organization may be a water supply organization, and attribute information of some residents may be a population living in a certain district and aged over 40 years. By constructing and analyzing triples, relationships and attributes between entities can be revealed, thereby providing assistance in determining recommendations.

Step S102, performing cluster analysis on the entity information, the relation information and the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result.

It should be noted that, the clustering algorithm refers to an unsupervised learning algorithm, which is used for dividing samples in a data set into a plurality of categories or clusters, so that the similarity of samples in the same category or cluster is higher, and the similarity of samples in different categories or clusters is lower.

Specifically, after determining the triple structure according to the service information, performing cluster analysis on the information contained in the triple structure by using a clustering algorithm, namely calculating similarity data between different mechanism attribute features and different client attribute features in the triple structure by using the clustering algorithm, and obtaining a clustering result containing target attribute information according to the similarity data, thereby obtaining the mechanism attribute features and the client attribute features from the target attribute information, wherein the target attribute information refers to attribute information of a mechanism and a client which can cooperate with a service recommendation scheme.

Step S103, extracting the target mechanism and the target client from the target attribute information, and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client so as to complete the target service.

Specifically, after the target attribute information is obtained through cluster analysis, the mechanism attribute information representing the mechanism attribute is extracted from the target attribute information, namely, the target mechanism is extracted from the target attribute information, and then the client attribute information representing the client attribute is extracted, namely, the target client is obtained.

Further, the target mechanism and the target client are determined to be the party to be negotiated, a recommended scheme of the operation business of the mechanism is designed according to the industry information of the target mechanism, and the designed recommended scheme is pushed to the target client or the target mechanism.

According to the method for determining the service recommendation scheme, provided by the embodiment of the application, the service information of the target service is extracted, and a triple structure is constructed by the service information, wherein the triple structure represents the framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to receipt and payment relation information related to the target service, the receipt and payment relation refers to receipt and payment relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client; performing cluster analysis on the entity information, the relation information and the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result; extracting a target mechanism and a target client from target attribute information to generate a recommendation scheme of target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client to finish the target service, the problem of low success rate of service recommendation by using the recommendation scheme in the related technology is solved, a triplet structure is obtained by extracting service information of the target service and constructing the service information, a clustering result is obtained by carrying out clustering analysis on the triplet structure by using a clustering algorithm, and the recommendation scheme of the target service is generated by using the clustering result, so that the effect of improving the success rate of pushing by using the recommendation scheme is achieved.

In order to obtain a clustering result, a triplet structure needs to be processed, optionally, in the method for determining a service recommendation scheme provided by the embodiment of the present application, clustering analysis is performed on entity information, relationship information and attribute information by using a clustering algorithm, and obtaining the clustering result includes: performing numerical value assignment on the entity information, the relation information and the attribute information according to the information assignment table to obtain A entity data, B relation data and C attribute data, wherein A, B, C is a positive integer; carrying out data aggregation on the A entity data, the B relation data and the C attribute data through a clustering model to obtain M clusters, and extracting attribute features from each cluster to obtain M candidate features, wherein M is a positive integer, M is smaller than A, M and smaller than B, and M is smaller than C; generating N feature matrixes according to the M candidate features, wherein each feature matrix comprises mechanism attribute features and customer attribute features, N is a positive integer, and N is smaller than M.

Before the information contained in the triple structure is subjected to cluster analysis by using a clustering algorithm, the information contained in the triple structure needs to be processed, specifically, related information needs to be acquired, characteristic selection and characteristic extraction processing are performed on the information, and because entity information, relation information and attribute information contained in the triple structure are character type information, numerical conversion is required for the cluster analysis, namely, numerical values representing the entity information, the relation information and the attribute information are acquired through an information assignment table, and numerical conversion is performed on a plurality of pieces of information in the triple structure obtained by service information according to the numerical values, so that the obtained entity data, relation data and attribute data are obtained.

Further, since the entity information includes a large amount of information of service types and the attribute information includes a large amount of information of mechanism attributes and client attributes, it is necessary to perform preliminary data aggregation on a plurality of entity data, a plurality of relationship data and a plurality of attribute data, for example, if the attribute information includes information of different enterprises such as water fee payment, electric fee payment and gas payment, the enterprises of water fee payment, electric fee payment and gas payment are combined, collectively referred to as enterprises related to life payment, and by performing data aggregation on the data, more service information can be obtained, thereby laying a foundation for determining the subsequent target attribute information. And extracting attribute characteristics related to the attribute information from clusters obtained by preliminary data aggregation processing, and obtaining candidate characteristics from the attribute characteristics, wherein each cluster can comprise entity characteristics obtained by processing entity data, relationship characteristics obtained by processing relationship data and attribute characteristics obtained by processing the attribute data.

Furthermore, in order to obtain the target organization and the target enterprise more accurately, the candidate features need to be processed again, and the processed candidate features are represented in a vectorized form, so that a feature matrix is obtained. According to the method, the device and the system, the information contained in the triple structure is subjected to numerical value assignment, data aggregation and feature aggregation in sequence, so that the feature matrix taking the information of the mechanism attribute and the information of the client attribute as elements can be obtained, and a foundation is laid for obtaining the target attribute information through cluster analysis.

Optionally, in the method for determining a service recommendation scheme provided by the embodiment of the present application, generating N feature matrices according to M candidate features includes: and carrying out feature aggregation treatment on the features belonging to the same service type in the M candidate features to obtain N feature matrixes.

Specifically, after a plurality of candidate features obtained from the cluster are obtained, the candidate features are subjected to service type judgment, and features belonging to the same service type are selected as the features of aggregation processing, for example, when the candidate features are subjected to service type judgment, a group of customer attribute features and mechanism attribute features related to life payment are obtained, so that feature aggregation processing can be performed according to the group of customer attribute features and mechanism attribute features, namely, the customer attribute features and the mechanism attribute features are used as elements of a matrix to obtain a feature matrix.

After determining that the service type can be used to perform feature aggregation processing on a plurality of candidate features, a matrix generation model based on a machine learning model can be constructed by using the principle, a feature matrix can be directly obtained according to the matrix generation model, specifically, the candidate features obtained after performing data aggregation processing are input into the machine learning model, the matrix generation model performs permutation and combination of different candidate features according to the service type, and a plurality of feature matrices are obtained, wherein each feature matrix comprises a client attribute feature and a mechanism attribute feature, for example, the mechanism attribute feature related to the mechanism attribute comprises an A feature, a B feature and a C feature, the client attribute feature related to the client attribute is X, and three feature matrices can be obtained by the matrix generation model, wherein elements contained in the feature matrices can be AX, BX and CX. In the embodiment, the candidate features are used for determining the feature matrix, so that a foundation is laid for the subsequent clustering analysis by using the feature matrix.

Fig. 2 is a schematic diagram of a method for determining target attribute information according to an embodiment of the present application, as shown in fig. 2, optionally, in a method for determining a service recommendation scheme according to an embodiment of the present application, determining target attribute information according to a clustering result includes:

step S201, calculating similarity data between the mechanism attribute features and the client attribute features in each feature matrix to obtain N pieces of similarity data.

Step S202, judging whether similarity data smaller than a preset threshold exists in the N pieces of similarity data.

In step S203, in the case where there is target similarity data smaller than the preset threshold value in the N similarity data, the feature matrix associated with the target similarity data is used as the target attribute information.

Specifically, after a plurality of feature matrices are acquired, similarity data of elements in the feature matrices, that is, similarity data between the attribute features of the computing mechanism and the attribute features of the client, may be calculated by using a similarity function.

Further, after the similarity data corresponding to each feature matrix is obtained, the size relation between each similarity data and a preset threshold value is judged, when target similarity data smaller than the preset threshold value exists in the similarity data, the fact that the correlation between the mechanism attribute features and the client attribute features in the feature matrix associated with the similarity data is higher is indicated, namely, obvious supply-demand relation exists between the mechanism and the client obtained by the mechanism attribute features and the client attribute features, and at the moment, the target attribute information can be determined by the target similarity data smaller than the preset threshold value.

Specifically, the feature matrix associated with each object similarity data is determined, the mechanism attribute features and the client attribute features in the associated feature matrices can be obtained, the mechanism attribute information and the client attribute information are determined by the mechanism attribute features and the client attribute features, and the mechanism attribute information and the client attribute information are determined as object attribute information. According to the method, the target attribute information is determined by calculating the similarity data of the feature matrix and utilizing the similarity data, the target attribute information can be obtained simply and conveniently, and time cost and labor cost are saved for the establishment of a recommendation scheme.

Optionally, in the method for determining a service recommendation scheme provided by the embodiment of the present application, after determining whether there is similarity data smaller than a preset threshold value in the N similarity data, the method further includes: under the condition that target similarity data smaller than a preset threshold value does not exist in the N pieces of similarity data, model parameters in the clustering model are adjusted, and an updated clustering model is obtained; and carrying out data aggregation processing on the A entity data, the B relation data and the C attribute data through the updated cluster model again to obtain updated clusters, and determining a feature matrix from the updated clusters until similarity data associated with at least one feature matrix is smaller than a preset threshold value.

Specifically, if similarity data is calculated from each obtained feature matrix, and the relationship between the similarity data and a preset threshold is determined, all the obtained similarity data are larger than the preset threshold, which indicates that the correlation between the mechanism attribute feature and the client attribute feature in each feature matrix is lower, and the supply-demand relationship between the mechanism and the client is not obvious, so that new mechanism attribute feature and client attribute feature need to be searched again.

Specifically, when the clustering algorithm is used for carrying out clustering analysis, a clustering model can be constructed by the clustering algorithm, then the clustering model is used for obtaining similarity data, and when the similarity data obtained by the clustering model is larger than a preset threshold value, the model parameters in the model are not matched with the target service, so that the data aggregation processing and the feature aggregation processing can be carried out on the data after the numerical conversion obtained by the triple structure of the target service by adjusting the model parameters and then using the adjusted clustering model until an updated feature matrix with the similarity data smaller than the preset threshold value is obtained, and the target attribute information is obtained by the similarity data of the feature matrix. According to the embodiment, the model parameters of the clustering model are adjusted, the triple structure associated with the feature matrix with the similarity data larger than the preset threshold value is subjected to re-aggregation treatment by using the model, so that the feature matrix meeting the requirements is obtained, the target attribute information is determined by the feature matrix, and the time is saved for re-formulating the recommended scheme.

Before the related service information is subjected to cluster analysis by using a clustering algorithm, the service information needs to be screened and extracted, and optionally, in the method for determining the service recommendation scheme provided by the embodiment of the application, the service information of the target service is extracted, which comprises the following steps: obtaining information remarks of candidate service information stored in a database, wherein the information remarks at least comprise one of the following: service type information associated with the candidate service information, receipt relation information associated with the candidate service information, mechanism attribute information associated with the candidate service information and customer information associated with the candidate service information; and determining target information remarks according to the target service, and screening the candidate service information according to the target information remarks to obtain service information.

Specifically, since the database associated with the financial institution contains a huge amount of business information, if each piece of data in each piece of business information is judged, and time waste is caused when the business information of the target business is determined according to the judgment result, in order to reduce analysis time and analysis cost, judgment can be performed according to each remark of information when the business information is generated.

Specifically, the information remarks include service type information, receipt relation information, mechanism attribute information and customer information of each service, so that after the target service is determined, the service type, receipt relation, mechanism attribute and customer attribute of the target service are determined according to the target service, and further service information related to the target service is screened out from massive candidate service information according to the service type, receipt relation, mechanism attribute and customer attribute. According to the embodiment, the service information of the target service is determined by utilizing the information remarks of the service information, so that a foundation is laid for the establishment of a recommendation scheme of the target service.

In order to provide better services for clients, optionally, in the method for determining a service recommendation scheme provided by the embodiment of the present application, when the recommendation scheme includes a plurality of target institutions and target clients, after extracting target institutions and target clients from target attribute information, the method further includes: pushing target recommended schemes in the plurality of recommended schemes to the clients, and receiving scoring data of the clients on the target recommended schemes; and pushing other recommended schemes to the client under the condition that the scoring data is smaller than the scoring threshold value, wherein the other recommended schemes are recommended schemes other than the target recommended scheme in the plurality of recommended schemes.

Specifically, in order to perfect a recommendation strategy and better experience for a client, after a target recommendation scheme determined by target attribute information obtained by a clustering algorithm is recommended to the client, the target recommendation scheme can be adjusted by collecting scoring data about the target recommendation scheme fed back by the client, and when the scoring data fed back by the client is higher than a preset threshold value, the client is indicated to have higher satisfaction degree on the target recommendation scheme, and subsequent service can be directly performed according to the target recommendation scheme; if the scoring data fed back by the client is lower than a preset threshold value, indicating that the target recommendation scheme is not suitable for the mechanism service of the client, recommending other recommendation schemes to the client, wherein the other recommendation schemes are determined by other feature matrixes obtained after the same feature aggregation processing as the target recommendation scheme.

It should be noted that, after recommending other recommended schemes to the client, the scoring data of the client related to the recommended scheme may still be collected, and the satisfaction degree of the client may be determined according to the scoring data until the satisfaction degree of the client related to the recommended scheme is higher than a preset requirement, that is, the scoring data is higher than a preset threshold. According to the embodiment, the scoring data fed back to the client after the recommendation scheme is pushed to the client is collected, the advantages and disadvantages of the recommendation scheme are determined according to the scoring data, and other recommendation schemes are pushed under the condition that the scoring data is lower than the preset threshold value, so that the satisfaction degree of the client can be improved, and a hint can be provided for the establishment of the follow-up recommendation scheme.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a device for determining the service recommendation scheme, and the device for determining the service recommendation scheme can be used for executing the method for determining the service recommendation scheme provided by the embodiment of the application. The following describes a device for determining a service recommendation scheme provided by the embodiment of the application.

Fig. 3 is a schematic diagram of a determining device of a service recommendation scheme according to an embodiment of the present application, where, as shown in fig. 3, the device includes: a first extraction unit 30, an analysis unit 31, a second extraction unit 32.

The first extracting unit 30 is configured to extract service information of a target service, and construct a triplet structure from the service information, where the triplet structure characterizes a framework among entity information, relationship information and attribute information in the service information, the entity information is service type information of the target service, the relationship information is receipt relationship information related to the target service, the receipt relationship is a receipt relationship between a mechanism providing the target service and a client, and the attribute information includes information of mechanism attributes of the mechanism and client attributes of the client;

the analysis unit 31 is configured to perform cluster analysis on the entity information, the relationship information, and the attribute information by using a clustering algorithm, obtain a clustering result, and determine target attribute information according to the clustering result;

the second extracting unit 32 is configured to extract the target organization and the target customer from the target attribute information, and generate a recommendation scheme of the target service, where the recommendation scheme is used to recommend to the target customer that the target customer pay in the target organization to complete the target service.

Optionally, in the determining device for a service recommendation scheme provided in the embodiment of the present application, the analyzing unit 31 includes: the assignment module is used for carrying out numerical assignment on the entity information, the relation information and the attribute information according to the information assignment table to obtain A entity data, B relation data and C attribute data, wherein A, B, C is a positive integer; the first processing module is used for carrying out data aggregation processing on the A entity data, the B relation data and the C attribute data through the clustering model to obtain M clusters, extracting attribute features from each cluster to obtain M candidate features, wherein M is a positive integer, M is smaller than A, M and smaller than B, and M is smaller than C; the generating module is used for generating N feature matrixes according to the M candidate features, wherein each feature matrix comprises mechanism attribute features and client attribute features, N is a positive integer, and N is smaller than M.

Optionally, in the determining device for a service recommendation scheme provided in the embodiment of the present application, the analyzing unit 31 includes: and the second processing module is used for carrying out feature aggregation processing on the features belonging to the same service type in the M candidate features to obtain N feature matrixes.

Optionally, in the determining device for a service recommendation scheme provided in the embodiment of the present application, the analyzing unit 31 includes: the computing module is used for computing similarity data between the mechanism attribute characteristics and the client attribute characteristics in each feature matrix to obtain N similarity data; the judging module is used for judging whether the similarity data smaller than a preset threshold value exists in the N pieces of similarity data; the first determining module is used for taking the characteristic matrix associated with the target similarity data as target attribute information when the target similarity data smaller than a preset threshold exists in the N pieces of similarity data.

Optionally, in the device for determining a service recommendation scheme provided by the embodiment of the present application, the device further includes: the adjusting unit is used for adjusting model parameters in the clustering model to obtain an updated clustering model under the condition that target similarity data smaller than a preset threshold value does not exist in the N pieces of similarity data after judging whether the similarity data smaller than the preset threshold value exist in the N pieces of similarity data; and the processing unit is used for carrying out data aggregation processing on the A entity data, the B relation data and the C attribute data again through the updated cluster model to obtain updated clusters, and determining the feature matrix from the updated clusters until the similarity data of at least one feature matrix association is smaller than a preset threshold value.

Optionally, in the determining device for a service recommendation scheme provided in the embodiment of the present application, the first extracting unit 30 includes: the acquisition module is used for acquiring the information remarks of the candidate service information stored in the database, wherein the information remarks at least comprise one of the following: service type information associated with the candidate service information, receipt relation information associated with the candidate service information, mechanism attribute information associated with the candidate service information and customer information associated with the candidate service information; and the second determining module is used for determining target information remarks according to the target service and screening the candidate service information according to the target information remarks to obtain the service information.

Optionally, in the device for determining a service recommendation scheme provided by the embodiment of the present application, the device further includes: a first pushing unit configured to, in a case where the recommended solution includes a plurality of target institutions and target clients, push target recommended solutions among the plurality of recommended solutions to the clients after the recommended solution of the target service is generated by extracting the target institutions and the target clients from the target attribute information, and receive scoring data of the target recommended solutions by the clients; and the second pushing unit is used for pushing other recommended schemes to the client under the condition that the scoring data is smaller than the scoring threshold value, wherein the other recommended schemes are recommended schemes other than the target recommended scheme in the plurality of recommended schemes.

The determining device of the service recommendation scheme provided by the embodiment of the application is used for extracting service information of a target service through the first extracting unit 30 and constructing a triple structure by the service information, wherein the triple structure represents architecture among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to receipt and payment relation information related to the target service, the receipt and payment relation refers to receipt and payment relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client; the analysis unit 31 is configured to perform cluster analysis on the entity information, the relationship information, and the attribute information by using a clustering algorithm, obtain a clustering result, and determine target attribute information according to the clustering result; the second extracting unit 32 is configured to extract the target mechanism and the target client from the target attribute information, and generate a recommendation scheme of the target service, where the recommendation scheme is used to recommend to the target client that the target service is completed by paying in the target mechanism, so as to solve the problem of low success rate of service recommendation using the recommendation scheme in the related art.

The determining device of the service recommendation scheme includes a processor and a memory, the first extracting unit 30, the analyzing unit 31, the second extracting unit 32, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the problem of low success rate of service recommendation by using a recommendation scheme in the related technology is solved by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a computer readable storage medium, on which a program is stored, which when executed by a processor, implements a method for determining a service recommendation scheme.

The embodiment of the application provides a processor, which is used for running a program, wherein the program runs to execute a method for determining a service recommendation scheme.

Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 4, an embodiment of the present application provides an electronic device, where an electronic device 40 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor is configured to execute computer readable instructions, where the computer readable instructions execute a method for determining a service recommendation scheme when executed. The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform a method of determining a service recommendation scheme when executed on a data processing device.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims (10)

1. The method for determining the service recommendation scheme is characterized by comprising the following steps of:

extracting service information of a target service, and constructing a triplet structure by the service information, wherein the triplet structure represents a framework among entity information, relation information and attribute information in the service information, the entity information is service type information of the target service, the relation information is collection relation information related to the target service, the collection relation is collection relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client;

Performing cluster analysis on the entity information and the relation information by using a clustering algorithm according to the attribute information to obtain a clustering result, and determining target attribute information according to the clustering result;

and extracting a target mechanism and a target client from the target attribute information, and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending payment in the target mechanism to the target client so as to complete the target service.

2. The method of claim 1, wherein performing a clustering analysis on the entity information and the relationship information with the attribute information using a clustering algorithm to obtain a clustering result comprises:

performing numerical value assignment on the entity information and the relation information according to an information assignment table by using the attribute information to obtain A entity data, B relation data and C attribute data, wherein A, B, C is a positive integer;

performing data aggregation processing on the A entity data, the B relation data and the C attribute data through a clustering model to obtain M clusters, and extracting attribute features from each cluster to obtain M candidate features, wherein M is a positive integer, M is smaller than A, M and smaller than B, and M is smaller than C;

Generating N feature matrixes according to the M candidate features, wherein each feature matrix comprises mechanism attribute features and client attribute features, N is a positive integer, and N is smaller than M.

3. The method of claim 2, wherein generating N feature matrices from the M candidate features comprises:

and carrying out feature aggregation processing on the features belonging to the same service type in the M candidate features to obtain N feature matrixes.

4. The method of claim 2, wherein determining target attribute information from the clustering result comprises:

calculating similarity data between the mechanism attribute features and the client attribute features in each feature matrix to obtain N similarity data;

judging whether similarity data smaller than a preset threshold exists in the N pieces of similarity data;

and under the condition that target similarity data smaller than the preset threshold exists in the N pieces of similarity data, taking a feature matrix associated with the target similarity data as the target attribute information.

5. The method of claim 4, wherein after determining whether there is similarity data less than a preset threshold among the N similarity data, the method further comprises:

Under the condition that target similarity data smaller than the preset threshold value does not exist in the N pieces of similarity data, model parameters in the clustering model are adjusted, and an updated clustering model is obtained;

and carrying out data aggregation processing on the A entity data, the B relation data and the C attribute data again through the updated cluster model to obtain updated clusters, and determining a feature matrix from the updated clusters until the similarity data of at least one feature matrix association is smaller than a preset threshold value.

6. The method of claim 1, wherein extracting service information of the target service comprises:

obtaining information remarks of candidate service information stored in a database, wherein the information remarks at least comprise one of the following: the service type information associated with the candidate service information, the collection relation information associated with the candidate service information, the organization attribute information associated with the candidate service information and the customer information associated with the candidate service information;

and determining target information remarks according to the target service, and screening the candidate service information according to the target information remarks to obtain the service information.

7. The method according to claim 1, wherein in the case where the recommended plan includes a plurality, after extracting a target organization and a target customer from the target attribute information, the method further comprises:

pushing a target recommended scheme in a plurality of recommended schemes to the client, and receiving grading data of the client on the target recommended scheme;

and pushing other recommended schemes to the client under the condition that the scoring data is smaller than a scoring threshold value, wherein the other recommended schemes are recommended schemes other than the target recommended scheme in the plurality of recommended schemes.

8. A service recommendation scheme determining apparatus, comprising:

the system comprises a first extraction unit, a second extraction unit and a third extraction unit, wherein the first extraction unit is used for extracting service information of a target service, and constructing a triplet structure by the service information, the triplet structure represents a framework among entity information, relation information and attribute information in the service information, the entity information refers to service type information of the target service, the relation information refers to collection relation information related to the target service, the collection relation refers to collection relation between a mechanism for providing the target service and a client, and the attribute information comprises mechanism attribute of the mechanism and client attribute information of the client;

The analysis unit is used for carrying out cluster analysis on the entity information and the relation information by using the attribute information by using a clustering algorithm to obtain a clustering result, and determining target attribute information according to the clustering result;

and the second extraction unit is used for extracting a target mechanism and a target client from the target attribute information and generating a recommendation scheme of the target service, wherein the recommendation scheme is used for recommending the target client to pay in the target mechanism so as to complete the target service.

9. A processor, characterized in that the processor is configured to run a program, wherein the program, when run, performs the method of determining a service recommendation according to any one of claims 1 to 7.

10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining a business recommendation of any of claims 1 to 7.