CN118710474A - Government service recommendation method and device, electronic equipment and storage medium - Google Patents

Abstract

The invention provides a government service recommendation method, a government service recommendation device, electronic equipment and a storage medium, and relates to the technical field of service recommendation. The method comprises the following steps: determining a target government service which is finally transacted by a target user; determining target government affair service association relation data corresponding to the target government affair service from the government affair service association relation data set; determining at least one target associated government service associated with the target government service and a confidence level corresponding to each target associated government service based on the target government service association relationship data; and determining at least one government service to be recommended from at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended. The invention can improve the recommendation accuracy of the government affair service, thereby improving the recommendation effect of the government affair service.

Description

Government service recommendation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of service recommendation technologies, and in particular, to a government service recommendation method, apparatus, electronic device, and storage medium.

Background

With rapid development of technology, government service is gradually turned to intelligence. To meet the intelligent demands of government services, the government services need to be actively recommended to users. The government has the advantages that the quantity of government service provided by the government is continuously increased, the relationship among government service is increasingly complex, and the government service relates to a plurality of departments, levels and service objects on the social side, so that the government service has the characteristics of numerous classification, complicated content, involvement, and the like; based on this, it is very difficult to find a government service matching with its own demand for the user.

Currently, a user searching mode is mostly adopted to recommend government service associated with searched content to a user. However, some government service has high similarity, so too many government service may be recommended, or too many search information may be given for selection, so that the user still needs to manually filter the recommended government service or filter the search information repeatedly to find the government service meeting the actual requirement of the user. Therefore, the current government service recommendation method has low recommendation accuracy, which results in poor recommendation effect of government service.

Disclosure of Invention

The invention provides a government service recommendation method, a government service recommendation device, electronic equipment and a storage medium, which are used for solving the defect of poor government service recommendation effect in the prior art and realizing efficient and accurate government service recommendation.

The invention provides a government service recommendation method, which comprises the following steps:

determining a target government service which is finally transacted by a target user;

Determining target government service association relationship data corresponding to the target government service from a government service association relationship data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service;

Determining at least one target associated government service associated with the target government service and a confidence degree corresponding to each target associated government service based on the target government service association relationship data;

And determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended.

According to the government service recommendation method provided by the invention, the government service association relation data set is determined based on the following modes:

Acquiring a first user history handling government affair service data set; the first user history government affair service data set comprises first user history government affair service data of a plurality of users, and the first user history government affair service data of any user comprises identification data of a plurality of government affair services which are already handled by the user and the government affair service handling time of each government affair service;

Determining a user transacting government service transaction data set based on the first user history transacting government service data set and a preset time interval threshold; the user transacting government service transaction data set comprises user transacting government service transaction data subsets of the plurality of users, the user transacting government service transaction data subset of any user comprises at least one user transacting government service transaction data of the user, the user transacting government service transaction data of any user comprises identification data of a first government service transacted by the user and identification data of a second government service transacted by the user, the transacting time of the first government service is before the transacting time of the second government service, and the transacting time interval between the first government service and the second government service is smaller than the preset time interval threshold;

Based on the user transacting government affair service transaction data set and a preset minimum confidence threshold, carrying out association relation analysis between government affair services to obtain the government affair service association relation data set; and the confidence coefficient corresponding to the associated government service is larger than the preset minimum confidence coefficient threshold value.

According to the government service recommendation method provided by the invention, the association analysis between government service is performed based on the user transacted government service transaction data set and a preset minimum confidence threshold, and the government service association data set is obtained, which comprises the following steps:

Removing the user business transaction data with the occurrence frequency smaller than a preset occurrence frequency threshold value in the user business transaction data set, and obtaining a removed user business transaction data set; the occurrence frequency of any user transaction data included in the removed user transaction data set is greater than or equal to the preset occurrence frequency threshold;

And carrying out association relation analysis between government service based on the removed government service transaction data set and a preset minimum confidence threshold value to obtain the government service association relation data set.

According to the government service recommendation method provided by the invention, the analysis of the association relationship between government service is performed based on the removed government service transaction data set and a preset minimum confidence threshold, and the government service association relationship data set is obtained, which comprises the following steps:

performing association relation analysis between government service based on the removed government service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold to obtain the government service association relation data set;

The support degree corresponding to the associated government service is larger than the preset minimum support degree threshold; the support degree corresponding to the associated government service is used for representing the probability that the same user transacts the government service and transacts the associated government service.

According to the government affair service recommending method provided by the invention, the determining of the user transacting government affair service data set based on the first user history transacting government affair service data set and the preset time interval threshold value comprises the following steps:

determining a transacting moment of a plurality of transacted government services transacted by the plurality of users based on the first user history transacting government service data set;

Based on the transacted times of the transacted government service of the plurality of users, respectively sequencing the transacted government service of the plurality of users according to the front-back sequence of the transacted times to obtain sequencing results corresponding to the plurality of users; the sorting result corresponding to any user comprises a plurality of transacted government services which are sequentially sorted according to the sequence before and after the transacting time;

determining an initial user transaction government service transaction data subset of the plurality of users based on the ordering results corresponding to the plurality of users and the first user history transaction government service data of the plurality of users; any user transacting government service transaction data included in the initial user transacting government service transaction data subset of any user comprises identification data of third government service transacted by the user and identification data of fourth government service transacted by the user, wherein the transacting moment of the third government service is before the transacting moment of the fourth government service, and the third government service and the fourth government service are two adjacent transacted government services in a sequencing result corresponding to the user;

Determining minimum handling time intervals corresponding to the users respectively based on the initial user handling government service transaction data subsets of the users and handling moments of the handled government service handled by the users; the minimum processing time interval corresponding to any user is the minimum processing time interval in the processing time intervals corresponding to the business data of each user in the initial user processing business data subset of the user processing business services, and the processing time interval corresponding to the business data of any user processing business is determined based on the processing time of two business services represented by the business data of the user processing business services;

Screening an initial user transaction data subset of the plurality of users to obtain a user transaction data subset of the plurality of users to transact government service based on a preset time interval threshold and minimum transaction time intervals respectively corresponding to the plurality of users; the standard handling time interval between the first government service and the second government service is smaller than the preset time interval threshold, and the standard handling time interval between the first government service and the second government service is the difference value between the handling time interval between the first government service and the second government service and the minimum handling time interval corresponding to the user.

According to the government service recommendation method provided by the invention, the method further comprises the following steps:

Acquiring historical user business service handling data of the target user; the historical user transacting government affair service data comprises identification data of a plurality of historical government affair services transacted by the target user and transacting time of each historical government affair service;

Based on the handling time of each historical government service, constructing the identification data of the historical government service into time sequence data;

periodically analyzing the time sequence data to obtain the handling period of the government service;

iteratively training a seasonal differential autoregressive moving average model based on the transaction period and the time series data;

Predicting future government affair service based on the seasonal differential autoregressive moving average model after iterative training;

recommending the future government service to the target user.

According to the government service recommendation method provided by the invention, the method further comprises the following steps:

Determining a target association rule data subset corresponding to the target user characteristic data from an association rule data set based on the target user characteristic data of the target user; the association rule data set comprises association rule data subsets corresponding to a plurality of user characteristic data, and any one of the association rule data subsets comprises at least one association rule data; the association rule data corresponding to any user characteristic data comprises identification data of the centrally transacted government service and the centrally transacted time of the centrally transacted government service;

Determining at least one government service which is centrally transacted by the target user and a target centralized transacting time of each government service which is centrally transacted by the target user based on the target association rule data subset;

And determining the recommended time of each government service which is intensively transacted by the target user based on each target centralized transacting time.

The invention also provides a government service recommendation device, which comprises:

the service determining module is used for determining the last transacted target government service of the target user;

The data determining module is used for determining target government service association relation data corresponding to the target government service from the government service association relation data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service;

The confidence degree determining module is used for determining at least one target associated government service associated with the target government service and the confidence degree corresponding to each target associated government service based on the target government service association relation data;

The order determining module is used for determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation order of the at least one government service to be recommended.

The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the government affair service recommendation method according to any one of the above when executing the program.

The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a government service recommendation method as described in any of the above.

The invention provides a government service recommending method, a device, electronic equipment and a storage medium, which are used for determining a finally transacted target government service of a target user, so as to determine target government service association relation data corresponding to the target government service from a government service association relation data set, wherein the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, the government service association relation data corresponding to any government service comprises association relation data corresponding to at least one government service associated with the government service, the association relation data corresponding to any government service comprises identification data of the associated government service and confidence coefficient corresponding to the associated government service, the confidence coefficient corresponding to the associated government service is used for representing the probability of the associated government service of the same user, so that the government service corresponding to the target government service is determined based on the target government service association relation data, the government service corresponding to be recommended from at least one association relation data corresponding to the government service, the government service corresponding to the at least one government service corresponding to be associated with the target government service is determined, and the government service corresponding to the confidence coefficient corresponding to the target government service is further improved, and the government service corresponding to the target user can be recommended to the target government service after the government service is recommended to the target government service corresponding to the target user; determining the recommendation sequence of at least one government service to be recommended based on the confidence coefficient corresponding to each target associated government service, so as to recommend the at least one government service to be recommended to a target user based on the recommendation sequence, thereby further improving the recommendation effect of the government service; in addition, the embodiment of the invention can finish recommendation without manually screening any information by the target user, thereby improving the recommendation efficiency of the government service and further improving the recommendation effect of the government service.

Drawings

In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a government service recommendation method provided by the invention.

Fig. 2 is a second flow chart of the government service recommendation method provided by the invention.

Fig. 3 is a schematic structural diagram of a government service recommendation device provided by the invention.

Fig. 4 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In view of the above problems, the present invention proposes the following embodiments. The government service recommendation method of the present invention is described below with reference to fig. 1-2.

Fig. 1 is a schematic flow chart of a government service recommendation method provided by the invention, and as shown in fig. 1, the government service recommendation method includes the following steps 110, 120, 130 and 140.

Step 110, determining the last transacted target government service of the target user.

The execution main body of the government service recommendation method provided by the embodiment of the invention can be a server, such as a server corresponding to a government APP or a government applet; the embodiment of the present invention is not particularly limited, and may be a terminal device, such as a government office device and a smart phone.

It should be noted that, in the embodiment of the present invention, the use of user data may be involved, and in practical application, the user specific personal data may be used in the scenario described in text within the scope allowed by the applicable legal regulations under the condition of meeting the applicable legal regulations of the country (for example, the user definitely agrees, actually notifies the user, etc.).

Here, the target user is a user to be recommended for the government service. The target government service is the government service with the last transacting moment in all government services transacted by the target user.

In an embodiment, in a preset time period after the target user transacts the target government service, determining the target government service which the target user transacts last, wherein the preset time period is a shorter time period, so that the target user is recommended to transact the related government service in a shorter time after the target user transacts the target government service, namely, based on the recently transacted government service behaviors of the target user, predicting that the government service which the target user should transact in the future is recommended to the target user. For example, a resident transacting "out of business registration" government service should claim an out of business insurance fee to which "out of business insurance Jin Shenling" government service, i.e., a continuity office, can be recommended based on a front-to-back relationship between government services.

And 120, determining target government service association relation data corresponding to the target government service from the government service association relation data set.

The government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability that the same user handles the associated government service after handling the government service.

Here, the associated government service is a government service associated with the government service, and the associated government service should be a service transacted after transacting the government service; for example, the "out-of-business insurance Jin Shenling" government service is an associated government service of the "out-of-business registration" government service.

Here, the identification data of the associated government service is used to uniquely identify the associated government service.

Further, the association relationship data corresponding to any associated government service also comprises identification data of the government service. Namely, the association relationship data comprises identification data of the government service which is processed in advance, identification data of the government service which is processed in post processing and is to be recommended, and confidence corresponding to the government service which is processed in post processing.

It should be noted that, the associated government service associated with any government service may be one or more, and based on this, the government service associated relationship data corresponding to any government service includes associated relationship data corresponding to one or more associated government services.

In an embodiment, the government service association relation data set is determined by manually analyzing the relationship between government service, that is, the government service association relation data set is manually preset.

In another embodiment, the government service association relationship data set is determined by a data analysis tool after analyzing relationships between government services.

In another embodiment, the government service association relationship data set is determined based on the following: acquiring a first user history handling government affair service data set; the first user history government affair service data set comprises first user history government affair service data of a plurality of users, and the first user history government affair service data of any user comprises identification data of a plurality of government affair services which are already transacted by the user and the transacting time of each government affair service; determining a user transacting government service transaction data set based on the first user history transacting government service data set; the user transacting government service transaction data set comprises a user transacting government service transaction data subset of a plurality of users, the user transacting government service transaction data subset of any user comprises at least one user transacting government service transaction data of the user, the user transacting government service transaction data of any user comprises identification data of first government service transacted by the user and identification data of second government service transacted by the user, and the transacting moment of the first government service is before the transacting moment of the second government service; based on the user transacting government affair service transaction data set and a preset minimum confidence threshold, carrying out association relation analysis between government affair services to obtain a government affair service association relation data set; the confidence coefficient corresponding to the associated government service is larger than a preset minimum confidence coefficient threshold value.

Further, based on the user transacting government affair service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold, carrying out association relation analysis between government affair services to obtain a government affair service association relation data set; the support degree corresponding to the associated government service is larger than a preset minimum support degree threshold value; the corresponding support degree of the associated government affair service is used for representing the probability that the same user transacts the government affair service and transacts the associated government affair service.

And 130, determining at least one target associated government service associated with the target government service and the confidence degree corresponding to each target associated government service based on the target government service association relationship data.

Because the government affair service association relation data corresponding to any government affair service comprises association relation data corresponding to at least one associated government affair service associated with the government affair service, the association relation data corresponding to any associated government affair service comprises identification data of the associated government affair service and confidence coefficient corresponding to the associated government affair service; based on the target government service association relationship data, at least one target associated government service associated with the target government service and the confidence corresponding to each target associated government service can be determined.

And 140, determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended.

Specifically, determining at least one government service to be recommended from at least one target associated government service based on the confidence coefficient corresponding to each target associated government service; based on the confidence corresponding to the at least one government service to be recommended, determining a recommendation sequence (recommendation priority) of the at least one government service to be recommended, so as to recommend the at least one government service to be recommended to the target user based on the recommendation sequence.

In one embodiment, at least one target associated government service is determined to be a government service to be recommended.

In another embodiment, based on the sequencing result of the confidence degrees corresponding to the target associated government service from high to low according to the confidence degrees, a preset number of government service to be recommended with the highest confidence degrees is determined from at least one target associated government service.

In another embodiment, based on the sequencing result of the confidence degrees corresponding to the target associated government service from high to low according to the confidence degrees, determining the to-be-recommended government service with the highest confidence degree in the preset proportion from at least one target associated government service. For example, if the number of at least one target associated government service is 10 and the preset ratio is 0.2, there are 2 government services to be recommended.

In another embodiment, based on the confidence level corresponding to each target associated government service, determining the government service to be recommended with the confidence level greater than a preset confidence level threshold from at least one target associated government service.

In a specific embodiment, a recommendation sequence of at least one government service to be recommended is determined based on a sequencing result of the confidence level corresponding to the at least one government service to be recommended from high to low.

According to the government service recommending method provided by the embodiment of the invention, the last transacted target government service of a target user is determined, the target government service association relation data corresponding to the target government service is determined from the government service association relation data set, the government service association relation data set comprises a plurality of government service association relation data corresponding to the government service, the government service association relation data corresponding to each government service comprises the association relation data corresponding to at least one government service associated with the government service, the association relation data corresponding to each government service comprises identification data of the government service and the confidence level corresponding to the government service, the confidence level corresponding to the government service is used for representing the probability of transacting the government service after the government service is transacted by the same user, the government service is determined based on the government service association relation data of the target government service, the confidence level corresponding to each government service is determined, the government service is recommended from at least one government service associated with the target government service based on the confidence level corresponding to the government service, and the government service is recommended to the government service associated with the target government service, and the government service is further recommended to the user by the target user based on the confidence level corresponding to the government service, and the government service associated with the government service is further recommended to the actual user is recommended to the government service associated with the target government service; determining the recommendation sequence of at least one government service to be recommended based on the confidence coefficient corresponding to each target associated government service, so as to recommend the at least one government service to be recommended to a target user based on the recommendation sequence, thereby further improving the recommendation effect of the government service; in addition, the embodiment of the invention can finish recommendation without manually screening any information by the target user, thereby improving the recommendation efficiency of the government service and further improving the recommendation effect of the government service.

Based on any of the above embodiments, fig. 2 is a second flow chart of the government service recommendation method provided by the present invention, as shown in fig. 2, the government service association relationship data set is determined based on the following manner:

step 210, acquiring a first user history handling government service data set.

The first user history government service data set comprises first user history government service data of a plurality of users, and the first user history government service data of any user comprises identification data of a plurality of government services which are already handled by the user and the government service handling time of each government service.

In one embodiment, the first user history transacted government service data set may be obtained by collecting government service data transacted by a plurality of users on an online platform, offline window.

Here, the identification data of the transacted government service is used to uniquely identify the transacted government service. Further, the first user history of any user transacts government service data also includes user information for that user.

Step 220, determining a user transacting government service transaction data set based on the first user history transacting government service data set and a preset time interval threshold.

The user transacting government service transaction data set comprises user transacting government service transaction data subsets of the plurality of users, any user transacting government service transaction data subset of the users comprises at least one user transacting government service transaction data of the users, any user transacting government service transaction data of the users comprises identification data of first government service transacted by the users and identification data of second government service transacted by the users, the transacting time of the first government service is before the transacting time of the second government service, and the transacting time interval between the first government service and the second government service is smaller than the preset time interval threshold.

Here, the preset time interval threshold is a preset persistent office time interval. Specifically, according to the user and the handling time interval of two government affairs services, clustering the first user history handling government affair service data set to obtain a user handling government affair service transaction data subset of a plurality of clustered users.

Considering that two government services are relatively related, the handling time interval between the two government services should be smaller than the preset time interval threshold, and the preset time interval threshold is a short time period, so that the target user is recommended to handle related government services in a short time after the target user handles the target government service, namely, the future government service recommendation of the target user is predicted to be recommended to the target user based on the government service behaviors which the target user has recently handled. Specifically, the step 110 includes: and determining the last transacted target government service of the target user in a preset time period after the target user transacts the target government service, wherein the preset time period is a preset time interval threshold value.

Specifically, the first user history government service transaction data set is screened based on a preset time interval threshold, and the user government service transaction data set is reconstructed based on a screening result.

Further, the first user history government affair service data set is subjected to data preprocessing, so that the user government affair service transaction data set is determined based on the first user history government affair service data set after data preprocessing. The data preprocessing mode may include, but is not limited to, at least one of the following: cleaning user history government service data, converting user history government service data and processing user history government service data; the data cleaning is mainly used for removing noise, errors, repetition, invalid values or incomplete data in the first user history handling government service data set, and comprises the steps of processing missing values, abnormal values and the like; the data conversion mainly standardizes the user history handling government service data, such as converting handling time into standard time stamp; the processing of the data mainly processes and assembles the user history government service data according to rules, and processes the user history government service data into data calculated by a subsequent algorithm model.

And 230, performing association relation analysis between government affairs services based on the government affair service transaction data set handled by the user and a preset minimum confidence threshold value to obtain the government affair service association relation data set.

The confidence coefficient corresponding to the associated government service is larger than the preset minimum confidence coefficient threshold value.

Here, the algorithm of the association analysis may be set according to actual needs, and the embodiment of the present invention is illustrated by taking FP-Growth (Frequent Pattern Growth ) algorithm as an example. The association relation analysis algorithm is used for analyzing association, rules and trends between two government service in the government service transaction data of any user in the government service transaction data set, and mining frequent item sets, namely mining frequent government service association relation data, so as to obtain government service association relation data sets.

It should be appreciated that in the FP-Growth algorithm, any user in the user transacting government service transaction data set transacts government service transaction data as a set of items.

Further, based on the user transacting government affair service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold, carrying out association relation analysis between government affair services to obtain a government affair service association relation data set; the support degree corresponding to the associated government service is larger than a preset minimum support degree threshold value; the corresponding support degree of the associated government affair service is used for representing the probability that the same user transacts the government affair service and transacts the associated government affair service.

In a specific embodiment, a preset minimum confidence threshold and a preset minimum support threshold are obtained, and an FP-Growth algorithm model is built based on a user transacted government service transaction data set, the preset minimum confidence threshold and the preset minimum support threshold so as to obtain a government service association relationship data set based on the FP-Growth algorithm model. More specifically, based on a user transacting government affair data set, a preset minimum confidence threshold and a preset minimum support threshold, model training is carried out to obtain a government affair service association relation data set. Further, high-frequency service and low-frequency service are considered in government affair service, so that a preset minimum confidence threshold or a preset minimum support threshold is continuously adjusted, and an FP-Growth algorithm model is continuously updated by combining manual judgment, so that a more accurate government affair service association relation data set is obtained.

It can be understood that if the government service association relation data set is determined by manual analysis, a large amount of manpower and material resources are consumed, and the government service association relation data set is easily affected by subjective factors, so that the government service association relation data set is inaccurate, and the government service recommendation is inaccurate; based on the above, the method automatically analyzes the association relation between the government affair services, and can determine the confidence coefficient corresponding to the association government affair services, thereby improving the determination efficiency of the association relation data set of the government affair services, reducing the cost, namely efficiently mining the association relation between the government affair services, and accurately capturing the deep relation between the government affair services, thereby improving the determination accuracy of the association relation data set of the government affair services, namely accurately mining the association relation between the government affair services, and further improving the recommendation accuracy of the government affair services.

It can be appreciated that, considering that if the government service association relationship data set is determined by the data analysis tool, the current data analysis tool can only process simple data relationships, and has limited relation mining capability on complex government services, so that the government service association relationship data set is inaccurate, and further, the government service recommendation is inaccurate; based on the above, the method automatically analyzes the association relation between the government affair services, and can determine the corresponding confidence of the association government affair services, so that the determination efficiency of the association relation data set of the government affair services is improved, namely, the association relation between the government affair services is efficiently mined, and the deep relation between the government affair services can be accurately captured, so that the determination accuracy of the association relation data set of the government affair services is improved, namely, the association relation between the government affair services is accurately mined, and the recommendation accuracy of the government affair services is further improved.

According to the government service recommendation method provided by the embodiment of the invention, the association relation analysis between government services is automatically carried out in the mode, and the corresponding confidence level of the associated government service can be determined, so that the determination efficiency of the government service association relation data set is improved, the cost is reduced, namely the association relation between government services is efficiently mined, and the deep relation between government services can be accurately captured in the mode, so that the determination accuracy of the government service association relation data set is improved, namely the association relation between government services is accurately mined, and the recommendation accuracy of government service is further improved.

Based on any one of the above embodiments, the method further includes the step 230 of:

Removing the user business transaction data with the occurrence frequency smaller than a preset occurrence frequency threshold value in the user business transaction data set, and obtaining a removed user business transaction data set; the occurrence frequency of any user transaction data included in the removed user transaction data set is greater than or equal to the preset occurrence frequency threshold;

And carrying out association relation analysis between government service based on the removed government service transaction data set and a preset minimum confidence threshold value to obtain the government service association relation data set.

Here, the occurrence frequency of the user transacting the government service transaction data is the number of the same user transacting the government service transaction data. More specifically, the occurrence frequency of the user transacting government service transaction data is the number of the user transacting government service transaction data including the identification data of the same two government service, namely, the same user or different users transact the second government service after transacting the first government service, so that the transaction data of the plurality of users transacting government service can be obtained respectively, and the occurrence frequency of the plurality of users transacting government service transaction data is the same.

Here, the preset occurrence frequency threshold may be set according to actual needs, and is not specifically limited herein.

In one embodiment, the frequency of occurrence is in order of high to low, ordering the business data of the user handling government affairs in the business data set of the user handling government affairs to obtain an ordering result; and removing the user transaction data with the occurrence frequency smaller than the preset occurrence frequency threshold value in the sequencing result to obtain a removed user transaction data set with the user transaction government service.

According to the government service recommendation method provided by the embodiment of the invention, the user government service transaction data with the occurrence frequency smaller than the preset occurrence frequency threshold value in the user government service transaction data set is removed, and the removed user government service transaction data set is obtained, so that the user government service transaction data set is screened, the user government service transaction data with the occurrence frequency smaller than the preset occurrence frequency threshold value is removed, and the association relationship of two government services included in the user government service transaction data in the removed user government service transaction data set is ensured to be a stronger association relationship, so that the determination accuracy of the government service association relationship data set is improved, and the recommendation accuracy of government service is further improved.

Based on any one of the above embodiments, in the method, performing association analysis between government service based on the removed user transacted government service transaction data set and a preset minimum confidence threshold to obtain the government service association data set, including: and carrying out association relation analysis between government service based on the removed government service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold to obtain the government service association relation data set.

The support degree corresponding to the associated government service is larger than the preset minimum support degree threshold; the support degree corresponding to the associated government service is used for representing the probability that the same user transacts the government service and transacts the associated government service.

In a specific embodiment, a preset minimum confidence threshold and a preset minimum support threshold are obtained, and an FP-Growth algorithm model is built based on the removed user transacted government service transaction data set, the preset minimum confidence threshold and the preset minimum support threshold so as to obtain a government service association relationship data set based on the FP-Growth algorithm model. More specifically, model training is performed based on the removed user transacted government service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold, so as to obtain a government service association relationship data set.

According to the government service recommendation method provided by the embodiment of the invention, the association relation analysis between government services is automatically carried out in the mode, and the corresponding confidence level of the associated government service can be determined, so that the determination efficiency of the government service association relation data set is improved, the cost is reduced, namely the association relation between government services is efficiently mined, and the deep relation between government services can be accurately captured in the mode, so that the determination accuracy of the government service association relation data set is improved, namely the association relation between government services is accurately mined, and the recommendation accuracy of government service is further improved.

Based on any of the above embodiments, it is considered that the handling time intervals of two associated government services may vary from person to person, i.e., the same handling time intervals of two associated government services may differ for different users; based on this, the step 220 includes: step 221-step 225.

Step 221, determining the time of transacting the plurality of transacted government services transacted by the plurality of users based on the first user history transacted government service data set.

Since the first user history government service data set includes first user history government service data of a plurality of users, and the first user history government service data of any one user includes identification data of a plurality of government services which have been transacted by the user, and the transacting time of each government service, the transacting time of a plurality of government services which have been transacted by the plurality of users can be determined based on the first user history government service data set.

Step 222, based on the transacted times of the transacted government services of the users, respectively sequencing the transacted government services of the users according to the sequence of the transacted times to obtain sequencing results corresponding to the users; the sorting result corresponding to any user comprises a plurality of transacted government services which are sequentially sorted according to the sequence of the transacted time.

The ranking results corresponding to the users are obtained respectively, and the ranking results corresponding to any user are obtained by ranking the plurality of transacted government services transacted by the user according to the sequence of the transacted time based on the transacted time of the plurality of transacted government services transacted by the user.

Step 223, determining an initial user transaction service transaction data subset of the plurality of users based on the ordering results corresponding to the plurality of users and the first user history transaction service data of the plurality of users; any user transacting government affair service transaction data included in the initial user transacting government affair service transaction data subset of any user comprises identification data of third government affair service transacted by the user and identification data of fourth government affair service transacted by the user, the transacting time of the third government affair service is before the transacting time of the fourth government affair service, and the third government affair service and the fourth government affair service are two adjacent transacted government affair services in a sequencing result corresponding to the user.

Specifically, based on the sorting results corresponding to the plurality of users, reconstructing the first user history government affair service data set to obtain the user government affair service transaction data set. Because the ordering results corresponding to the users are obtained, two government service included in the government service transaction data of any user are two government service which are most adjacent at the transaction time, so that the user government service transaction data subset is conveniently obtained by subsequent screening.

Step 224, determining minimum handling time intervals corresponding to the multiple users respectively based on the initial user handling government service transaction data subsets of the multiple users and handling time of the multiple handled government services handled by the multiple users; the minimum processing time interval corresponding to any user is the minimum processing time interval in the processing time intervals corresponding to the business data of all the users in the initial user processing business data subset of the user processing business services, and the processing time interval corresponding to the business data of the user processing business services is determined based on the processing time of two business services represented by the business data of the user processing business services.

It should be noted that the minimum handling time interval is different for each user, and thus needs to be determined separately.

Step 225, screening an initial user transaction government affair data subset of the plurality of users based on a preset time interval threshold and minimum transaction time intervals corresponding to the plurality of users respectively to obtain a user transaction government affair data subset of the plurality of users; the standard handling time interval between the first government service and the second government service is smaller than the preset time interval threshold, and the standard handling time interval between the first government service and the second government service is the difference value between the handling time interval between the first government service and the second government service and the minimum handling time interval corresponding to the user.

Specifically, based on a preset time interval threshold, an initial user transacting government service transaction data subset of a plurality of users is screened, and based on screening results, the user transacting government service transaction data set is reconstructed.

In a specific embodiment, for any user, sorting a plurality of transacted government services transacted by the user in ascending order according to the transacted government service transacting time, calculating the transacted government service at this time and the transacted government service at last time, defaulting the transacted time interval of the first order to be 0, and obtaining an initial user transacted government service transaction data subset of the user; and traversing the initial user business data subset of the business service, comparing each business time interval with a preset time interval threshold, reserving the business data of the business service of the user which is greater than or equal to 0 and smaller than the preset time interval threshold, and discarding the data if the business data of the business service of the user which is less than or equal to 0 and smaller than the preset time interval threshold is traversed.

According to the government service recommendation method provided by the embodiment of the invention, the minimum handling time intervals respectively corresponding to the plurality of users are respectively determined in the mode, so that the initial user handling government service transaction data subsets of the plurality of users are screened based on the preset time interval threshold and the minimum handling time intervals respectively corresponding to the plurality of users, more accurate user handling government service transaction data subsets of the plurality of users are obtained, namely, the fact that the handling time intervals of the same two associated government service are different for different users is considered, standardization is carried out, the determination accuracy of the user handling government service transaction data sets is improved, the determination accuracy of the government service association relationship data sets is further improved, and finally the recommendation accuracy of government service is improved.

Based on any of the above embodiments, the method further comprises: steps 310 through 360.

Step 310, acquiring historical user business service data of the target user; the historical user transacting government affair service data comprises identification data of a plurality of historical government affair services transacted by the target user and transacting time of each historical government affair service.

In one embodiment, the historical user transacting government service data may be obtained by collecting government service data transacted by the target user on an online platform, offline window.

Here, the identification data of the history government service is used to uniquely identify the history government service. Further, the historical user transacting government service data also comprises user information of the target user.

Further, data preprocessing is performed on the government affair service data handled by the historical user. The data preprocessing mode may include, but is not limited to, at least one of the following: data cleaning, data conversion and data processing; data cleaning is mainly to remove noise, errors, duplicates, invalid values or incomplete data, and includes processing missing values, abnormal values and the like; data conversion mainly standardizes data, such as converting handling time into standard time stamps; the processing of the data mainly processes and assembles the data according to rules, and processes the data into data calculated by a subsequent algorithm model.

Step 320, based on the handling time of each historical government service, constructing the identification data of the historical government service into time series data.

Because the historical user transacting government affair service data comprises the identification data of a plurality of historical government affair services which are transacted by the target user and the transacting time of each historical government affair service, based on the identification data of the plurality of historical government affair services, the identification data of the plurality of historical government affair services can be constructed into time series data based on the transacting time of each historical government affair service.

And 330, periodically analyzing the time sequence data to obtain the handling period of the government service.

Here, the algorithm of the periodic analysis may be set according to actual needs, for example, the handling period of the government service is determined by an autocorrelation function (ACF, auto Correlation Function) algorithm, or the time series data is converted from the time domain to the frequency domain by using fourier transform according to a periodical chart (Periodogram) algorithm, so as to identify and analyze the period of the data, i.e. the handling period of the government service is obtained.

Step 340, iteratively training a seasonal differential autoregressive moving average model based on the transaction period and the time series data.

In one embodiment, the transaction period is used as the season (period length) of a seasonal differential autoregressive moving average model (SARIMA model), and the seasonal differential autoregressive moving average model is trained iteratively based on time series data. More specifically, a seasonal differential autoregressive moving average model is selected according to the data characteristics and the analysis result, model fitting is performed by using time sequence data, parameters of the model are estimated, prediction is performed by using the seasonal differential autoregressive moving average model, a prediction result is obtained, the prediction result is evaluated, and the difference between the prediction value and an actual value is compared, so that training is completed.

Further, the seasonal differential autoregressive moving average model is continuously optimized and adjusted. Because the selection and tuning of the model parameters are critical to the accuracy and stability of the prediction, the model is adjusted and optimized according to the evaluation result, different model parameters and orders are tried, and the model prediction is more accurate.

And 350, predicting future government service based on the seasonal differential autoregressive moving average model after iterative training.

Specifically, based on an optimal seasonal differential autoregressive moving average model, future government services are predicted. The future government service is a government service which is regularly transacted by the target user, such as a government service which is regularly transacted by the pension, namely, periodic office is realized.

Further, the above-mentioned transaction period of the government service has been determined, based on which, based on the seasonal differential autoregressive moving average model after the iterative training, the transaction time of the future government service can also be predicted, so as to determine the recommendation time of the future government service based on the transaction time of the future government service.

Step 360, recommending the future government service to the target user.

In a specific embodiment, future government services are recommended to the target user based on the recommended time of the future government services. The recommended time can be set according to actual needs before the future government service handling time.

According to the government service recommendation method provided by the embodiment of the invention, the historical user government service data of the target user are obtained, the historical user government service data comprise identification data of a plurality of historical government services which are already handled by the target user, and the government service handling moments of each historical government service are constructed into time sequence data based on the government service handling moments of each historical government service, the time sequence data are subjected to periodic analysis to obtain the government service handling period, the seasonal differential autoregressive moving average model is iteratively trained based on the government service handling period and the time sequence data, and future government service is predicted based on the seasonal differential autoregressive moving average model after iterative training, so that future government service can be recommended to the target user based on the government service handling data of the target user, namely, the government service which is periodically handled by the target user is recommended to the target user, the future government service is recommended to meet the actual demands of the user, and the government service recommendation accuracy is further improved; in addition, the embodiment of the invention can finish recommendation without manually screening any information by the target user, thereby improving the recommendation efficiency of the government service and further improving the recommendation effect of the government service.

Based on any of the above embodiments, the method further comprises: step 410-step 430.

Step 410, determining a target association rule data subset corresponding to the target user feature data from an association rule data set based on the target user feature data of the target user; the association rule data set comprises association rule data subsets corresponding to a plurality of user characteristic data, and any one of the association rule data subsets comprises at least one association rule data; the association rule data corresponding to any user characteristic data comprises identification data of the centrally transacted government service and the centrally transacted time of the centrally transacted government service.

Here, the centrally transacted government service is a government service which most users concentrate on transacting in one time period; for example, users between 30-40 years of age have a greater tendency to transact social security services in the afternoon of the workday, i.e., social security services are centrally transacted government services.

Here, the central processing time may be one time period or one time.

It should be noted that, the association rule data associated with any user feature data may be one or more.

In one embodiment, the association rule data set is determined by manually analyzing the relationship between government services, i.e., the association rule data set is manually preset.

In another embodiment, the association rule data set is determined by a data analysis tool after analyzing relationships between government services.

Step 420, determining at least one government service that is centrally handled by the target user and a target centralized handling time of each government service that is centrally handled by the target user based on the target association rule data subset.

Because any association rule data subset comprises at least one association rule data, and the association rule data corresponding to any user characteristic data comprises identification data of the centrally transacted government service and the centrally transacted time of the centrally transacted government service; based on this, at least one government service centrally transacted by the target user and a target central transacting time for each government service centrally transacted by the target user may be determined based on the target association rule data subset.

Step 430, determining a recommended time of each government service handled in the target user set based on each target set handling time.

Here, the recommended time may be before or during the corresponding target-set transaction time.

Further, based on the recommending time of each government service handled in the target user set, each government service handled in the target user set is respectively recommended to the target user.

According to the government service recommendation method provided by the embodiment of the invention, based on the target user characteristic data of the target user, a target association rule data subset corresponding to the target user characteristic data is determined from the association rule data set, the association rule data set comprises a plurality of association rule data subsets corresponding to the user characteristic data, each association rule data subset comprises at least one association rule data, the association rule data corresponding to each user characteristic data comprises identification data of the government service which is centrally processed and the centralized processing time of the government service which is centrally processed, so that at least one government service which is centrally processed by the target user and the target centralized processing time of each government service which is centrally processed by the target user are determined based on the target association rule data subset, and the recommendation time of each government service which is centrally processed by the target user is determined based on the target centralized processing time, thereby recommending the government service which is centrally processed by the target user to the target user based on the association rule data set, and further recommending the government service which is centrally processed by the target user to meet the actual requirements of the user, thereby improving the accuracy of the government service recommendation; in addition, the embodiment of the invention can finish recommendation without manually screening any information by the target user, thereby improving the recommendation efficiency of the government service and further improving the recommendation effect of the government service.

Based on any of the above embodiments, the association rule data set is determined based on a manner including steps 510-530.

Step 510, acquiring a second user history handling government service data set; the second user history government service data set comprises second user history government service data of a plurality of users, and any second user history government service data of the users comprises identification data of a plurality of government services which are already handled by the users, the processing time of each government service and user characteristic data of the users.

In one embodiment, the second user history transacted government service data set may be obtained by collecting government service data transacted by a plurality of users on an online platform, offline window.

Here, the identification data of the transacted government service is used to uniquely identify the transacted government service.

In one embodiment, the user characteristic data is determined based on user portrait data. Further, user portrait data for any user is determined based on the user's electronic license data. User characteristic data of any user is used to characterize attribute content of at least one attribute of the user. The user portrait data of a user is used for determining the user characteristic data of the user, namely, labeling classification is carried out on each user to form a characteristic user portrait.

In the government affair field, the electronic license data can be acquired, so that the user portrait data of the user is determined based on the electronic license data, the determination accuracy and the determination efficiency of the user characteristic data can be improved, and the recommendation accuracy and the recommendation efficiency of the government affair service are further improved.

The electronic license data may include, but is not limited to, at least one of: a household directory, a social security card, a driving license, a birth medical certificate, a real estate certificate, an academic certificate, a driving license, a wedding license, a disabled person license, a rural resident minimum life guarantee license, an urban and rural resident minimum life guarantee license, an employment and industry loss registration license and the like.

In a specific embodiment, a set of attribute feature values of a target user is determined based on user portrait data of the target user, the user portrait data of the target user including attribute contents of a plurality of attributes of the target user, the set of attribute feature values of the target user including feature values of the plurality of attributes of the target user; vectorizing each characteristic value in the attribute characteristic value set to obtain an attribute vector set; the attribute vector set comprises feature vectors of a plurality of attributes of the target user; user characteristic data of the target user is determined based on the set of attribute vectors.

Wherein, if the user is a legal person, the plurality of attributes of the user may include, but are not limited to, at least two of the following: established time, affiliated section, industry classification, legal type, market subject type, employee social security number, credit rating, administrative penalty, and so forth. If the user is a natural person, the plurality of attributes of the user may include, but are not limited to, at least two of: nationality, highest academic, age, gender, household location, residence, social security payment type, payment of public accumulation type, whether there is a car, driving license type, whether there is a house, marital status, number of children, age of children, whether there is old man, qualification honor, disability type, social aid type, employment status, income situation, and the like.

Considering that the attribute content of the user is not necessarily numerical data, for example, the attribute content of the home location is an administrative division, all attribute contents of the attribute need to be converted into numerical characteristic values, and if the original attribute content is numerical data, the attribute content is subjected to standardized processing.

For example, the characteristic value of the age is the actual age of the user; the characteristic value of the sex is unknown is 0, the characteristic value of the sex is 1, and the characteristic value of the sex is 2; the social security payment type is characterized in that the characteristic value of the town employee type is 1, and the unknown characteristic value of the social security payment type is 0; whether the vehicle is the non-vehicle or not has a characteristic value of 0, and whether the vehicle is the vehicle or not has a characteristic value of 1; whether the driving license is zero or not has a characteristic value of 0, and whether the driving license is zero or not has a characteristic value of 1; whether the room is the non-characteristic value is 0, and whether the room is the non-characteristic value is 1; whether wedding is none is 0, and whether wedding is none is 1; whether the characteristic value of the child is 0 or not and whether the child is 1 or not; the characteristic value of the child age is 0, the characteristic value of the child age is 1 for preschool education, the characteristic value of the child age is 2 for obligation education, and the characteristic value of the child age is 3 for high school; whether the old people are the non-characteristic value is 0, and whether the old people are the characteristic value is 1; the characteristic value of the household registering land is administrative division code; the characteristic value of the qualification honored as none is 0, and the characteristic value of the qualification honored as none is 1; the special crowd type is the characteristic value of the disabled person is 1, the special crowd type is the characteristic value of the rural low-protection is 2, the special crowd type is the characteristic value of the urban and rural low-protection is 3, the special crowd type is the characteristic value of the out-of-service person is 4, and the characteristic crowd type is the characteristic value of no out-of-service person is 5; the characteristic value of the residential area is an administrative division code.

Further, after the user data of the user is acquired, that is, after the attribute contents of the plurality of attributes of the user are acquired, the attribute contents of the plurality of attributes are subjected to data preprocessing. The data preprocessing may include, but is not limited to: data cleansing, data interpolation processing, outlier processing, normalization and feature extraction to provide high quality user representation data. The data cleaning is specifically to remove repeated data, so that the uniqueness of the data is ensured. The data interpolation process is specifically to fill by interpolation (such as mean interpolation, median interpolation) or prediction model based on machine learning. The outlier processing specifically adopts a method such as binning and the like to identify and correct or remove outliers. The normalization is specifically to convert the data into uniform scale by using a normalization method or a normalization method for continuous variables (such as age), and convert the data into numerical data by performing single-heat coding or tag coding for classified variables (such as gender and social security payment type).

It should be appreciated that the eigenvalue of an attribute is vectorized to obtain the eigenvector of the attribute.

Considering that most of the characteristic values are binary values (such as 0 or 1) or a few of the classification values, the data may be highly sparse, especially in the case that the attribute of the user is more or the number of multiple users is larger, the sparse data may reduce the effect of subsequent similarity calculation, based on the result, vectorization processing is performed on the characteristic values, so as to improve accuracy of similarity calculation, further improve accuracy of determination of similar users, and finally improve accuracy of recommendation of government service.

Step 520, determining identification data of a plurality of government services handled in a centralized manner, centralized handling time of the plurality of government services handled in the centralized manner, and handling user feature data of the plurality of government services handled in the centralized manner based on the second user history handling government service data set.

Because the second user history government service data set comprises second user history government service data of a plurality of users, and the second user history government service data of any user comprises identification data of a plurality of government service transacted by the user, the government service transacting time of each government service transacted by the user and user characteristic data of the user; based on this, the centrally transacted government service may be determined based on the second user history transacted government service data set, and the transacted government service may be determined for the time of the centrally transacted government service, after which the centrally transacted government service may be matched with the user characteristic data.

In one embodiment, any centrally transacted government service is determined based on the following: and carrying out time sequence analysis on the second user history transacted government service data set, determining that the centrally transacted government service is periodically transacted government service, and further determining the centrally transacted time of the centrally transacted government service. More specifically, the second user historical office service data is aggregated by time window (e.g., day, week, month, quarter) and a time series chart is drawn to see if there are periodic peaks or abnormal peaks representing the concentrated office time.

And 530, determining the association rule data set based on the identification data of the plurality of centrally handled government service, the centrally handled time of the plurality of centrally handled government service, and the handled user characteristic data of the plurality of government service.

In a particular embodiment, association rules mining is used to discover association rules between user profile data, centralized handling time, and government services. For example, users analyzing which features are more inclined to transact which government services during which time periods. For example, the algorithm of association rule mining is the Apriori algorithm to discover frequent item sets and association rules between item sets from a large number of data sets, e.g., association rules like "users between 30-40 years of age are more prone to transacting social security services in the afternoon of the workday" may be discovered. Further, integrating the time sequence analysis and the association rule mining results, and analyzing the user to intensively transact certain government service in a certain time period; firstly, using time sequence analysis to identify peak time periods of government service transaction; and then, utilizing association rule mining to further analyze which characteristic users in the peak periods are more prone to transacting which government service, so that the user characteristic data are matched for carrying out targeted recommendation of centralized transacting service on the matched users at the recommendation moment.

According to the government service recommendation method provided by the embodiment of the invention, the association relation analysis between government services is automatically carried out in the mode, so that the determination efficiency of the association rule data set is improved, the cost is reduced, namely, the association relation between government services is efficiently mined, and the deep relation between government services can be accurately captured in the mode, so that the determination accuracy of the association rule data set is improved, namely, the association relation between government services is accurately mined, and the recommendation accuracy of government services is further improved.

Based on the embodiments, the invention can realize the intellectualization, individuation and high efficiency of government service recommendation by mining the relationship among the government service, including 'continuing office' (the user handles B in a short time after handling A), 'periodical office' (the user uses a government service regularly), 'centralized office' (a great number of users handle a service in a certain time period) and combining the three association relationships of 'continuing office', 'periodical office' and 'centralized office', thereby predicting the government service recommendation of 'will be handled' for the user in the future and improving the user experience and satisfaction.

The government service recommendation device provided by the invention is described below, and the government service recommendation device described below and the government service recommendation method described above can be correspondingly referred to each other.

Fig. 3 is a schematic structural diagram of the government service recommendation device provided by the invention, and as shown in fig. 3, the government service recommendation device comprises a service determining module 301, a data determining module 302, a confidence determining module 303 and a sequence determining module 304.

The service determining module 301 is configured to determine a target government service that is last transacted by the target user.

The data determining module 302 is configured to determine, from a government service association relationship data set, target government service association relationship data corresponding to the target government service; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability that the same user handles the associated government service after handling the government service.

The confidence determining module 303 is configured to determine, based on the target government service association relationship data, at least one target associated government service associated with the target government service, and a confidence corresponding to each target associated government service.

The order determining module 304 is configured to determine at least one government service to be recommended from the at least one target associated government service based on the confidence level corresponding to each target associated government service, and determine a recommendation order of the at least one government service to be recommended.

The government service recommending device provided by the embodiment of the invention determines the last transacted target government service of a target user, so as to determine target government service association relation data corresponding to the target government service from a government service association relation data set, wherein the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, the government service association relation data corresponding to any government service comprises association relation data corresponding to at least one government service associated with the government service, the association relation data corresponding to any government service comprises identification data of the government service and confidence level corresponding to the government service, the confidence level corresponding to the government service is used for representing the probability of transacting the government service after the government service is transacted by the same user, so that the government service corresponding to the target government service is determined based on the government service association relation data, and the confidence level corresponding to each target government service is determined, the government service is recommended from at least one government service associated with the government service, and the government service is recommended to the government service associated with the target user based on the confidence level corresponding to the government service, and the government service associated with the government service is further improved, and the government service is recommended to the user by the actual user is further recommended to the government service associated with the target government service; determining the recommendation sequence of at least one government service to be recommended based on the confidence coefficient corresponding to each target associated government service, so as to recommend the at least one government service to be recommended to a target user based on the recommendation sequence, thereby further improving the recommendation effect of the government service; in addition, the embodiment of the invention can finish recommendation without manually screening any information by the target user, thereby improving the recommendation efficiency of the government service and further improving the recommendation effect of the government service.

Fig. 4 illustrates a physical schematic diagram of an electronic device, as shown in fig. 4, which may include: processor 410, communication interface (Communications Interface) 420, memory 430, and communication bus 440, wherein processor 410, communication interface 420, and memory 430 communicate with each other via communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a government service recommendation method comprising: determining a target government service which is finally transacted by a target user; determining target government service association relationship data corresponding to the target government service from a government service association relationship data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service; determining at least one target associated government service associated with the target government service and a confidence degree corresponding to each target associated government service based on the target government service association relationship data; and determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended.

Further, the logic instructions in the memory 430 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the government service recommendation method provided by the above methods, the method comprising: determining a target government service which is finally transacted by a target user; determining target government service association relationship data corresponding to the target government service from a government service association relationship data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service; determining at least one target associated government service associated with the target government service and a confidence degree corresponding to each target associated government service based on the target government service association relationship data; and determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A government service recommendation method, comprising:

determining a target government service which is finally transacted by a target user;

Determining target government service association relationship data corresponding to the target government service from a government service association relationship data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service;

Determining at least one target associated government service associated with the target government service and a confidence degree corresponding to each target associated government service based on the target government service association relationship data;

And determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation sequence of the at least one government service to be recommended.

2. The government service recommendation method according to claim 1, wherein the government service association relationship data set is determined based on the following manner:

Acquiring a first user history handling government affair service data set; the first user history government affair service data set comprises first user history government affair service data of a plurality of users, and the first user history government affair service data of any user comprises identification data of a plurality of government affair services which are already handled by the user and the government affair service handling time of each government affair service;

Determining a user transacting government service transaction data set based on the first user history transacting government service data set and a preset time interval threshold; the user transacting government service transaction data set comprises user transacting government service transaction data subsets of the plurality of users, the user transacting government service transaction data subset of any user comprises at least one user transacting government service transaction data of the user, the user transacting government service transaction data of any user comprises identification data of a first government service transacted by the user and identification data of a second government service transacted by the user, the transacting time of the first government service is before the transacting time of the second government service, and the transacting time interval between the first government service and the second government service is smaller than the preset time interval threshold;

Based on the user transacting government affair service transaction data set and a preset minimum confidence threshold, carrying out association relation analysis between government affair services to obtain the government affair service association relation data set; and the confidence coefficient corresponding to the associated government service is larger than the preset minimum confidence coefficient threshold value.

3. The government service recommendation method according to claim 2, wherein the performing association analysis between government services based on the user transacted government service transaction data set and a preset minimum confidence threshold to obtain the government service association data set includes:

Removing the user business transaction data with the occurrence frequency smaller than a preset occurrence frequency threshold value in the user business transaction data set, and obtaining a removed user business transaction data set; the occurrence frequency of any user transaction data included in the removed user transaction data set is greater than or equal to the preset occurrence frequency threshold;

And carrying out association relation analysis between government service based on the removed government service transaction data set and a preset minimum confidence threshold value to obtain the government service association relation data set.

4. The government service recommendation method according to claim 3, wherein the performing association analysis between government services based on the removed user transacted government service transaction data set and a preset minimum confidence threshold to obtain the government service association data set includes:

performing association relation analysis between government service based on the removed government service transaction data set, a preset minimum confidence threshold and a preset minimum support threshold to obtain the government service association relation data set;

The support degree corresponding to the associated government service is larger than the preset minimum support degree threshold; the support degree corresponding to the associated government service is used for representing the probability that the same user transacts the government service and transacts the associated government service.

5. The government service recommendation method according to claim 2, wherein said determining a user transacting government service transaction data set based on said first user history transacting government service data set and a preset time interval threshold comprises:

determining a transacting moment of a plurality of transacted government services transacted by the plurality of users based on the first user history transacting government service data set;

Based on the transacted times of the transacted government service of the plurality of users, respectively sequencing the transacted government service of the plurality of users according to the front-back sequence of the transacted times to obtain sequencing results corresponding to the plurality of users; the sorting result corresponding to any user comprises a plurality of transacted government services which are sequentially sorted according to the sequence before and after the transacting time;

determining an initial user transaction government service transaction data subset of the plurality of users based on the ordering results corresponding to the plurality of users and the first user history transaction government service data of the plurality of users; any user transacting government service transaction data included in the initial user transacting government service transaction data subset of any user comprises identification data of third government service transacted by the user and identification data of fourth government service transacted by the user, wherein the transacting moment of the third government service is before the transacting moment of the fourth government service, and the third government service and the fourth government service are two adjacent transacted government services in a sequencing result corresponding to the user;

Determining minimum handling time intervals corresponding to the users respectively based on the initial user handling government service transaction data subsets of the users and handling moments of the handled government service handled by the users; the minimum processing time interval corresponding to any user is the minimum processing time interval in the processing time intervals corresponding to the business data of each user in the initial user processing business data subset of the user processing business services, and the processing time interval corresponding to the business data of any user processing business is determined based on the processing time of two business services represented by the business data of the user processing business services;

Screening an initial user transaction data subset of the plurality of users to obtain a user transaction data subset of the plurality of users to transact government service based on a preset time interval threshold and minimum transaction time intervals respectively corresponding to the plurality of users; the standard handling time interval between the first government service and the second government service is smaller than the preset time interval threshold, and the standard handling time interval between the first government service and the second government service is the difference value between the handling time interval between the first government service and the second government service and the minimum handling time interval corresponding to the user.

6. The government service recommendation method according to any one of claims 1-5, further comprising:

Acquiring historical user business service handling data of the target user; the historical user transacting government affair service data comprises identification data of a plurality of historical government affair services transacted by the target user and transacting time of each historical government affair service;

Based on the handling time of each historical government service, constructing the identification data of the historical government service into time sequence data;

periodically analyzing the time sequence data to obtain the handling period of the government service;

iteratively training a seasonal differential autoregressive moving average model based on the transaction period and the time series data;

Predicting future government affair service based on the seasonal differential autoregressive moving average model after iterative training;

recommending the future government service to the target user.

7. The government service recommendation method according to any one of claims 1-5, further comprising:

Determining a target association rule data subset corresponding to the target user characteristic data from an association rule data set based on the target user characteristic data of the target user; the association rule data set comprises association rule data subsets corresponding to a plurality of user characteristic data, and any one of the association rule data subsets comprises at least one association rule data; the association rule data corresponding to any user characteristic data comprises identification data of the centrally transacted government service and the centrally transacted time of the centrally transacted government service;

Determining at least one government service which is centrally transacted by the target user and a target centralized transacting time of each government service which is centrally transacted by the target user based on the target association rule data subset;

And determining the recommended time of each government service which is intensively transacted by the target user based on each target centralized transacting time.

8. A government service recommendation device, comprising:

the service determining module is used for determining the last transacted target government service of the target user;

The data determining module is used for determining target government service association relation data corresponding to the target government service from the government service association relation data set; the government service association relation data set comprises government service association relation data corresponding to a plurality of government services, and any government service association relation data corresponding to the government service comprises association relation data corresponding to at least one associated government service associated with the government service; the association relation data corresponding to any associated government service comprises identification data of the associated government service and confidence corresponding to the associated government service; the confidence coefficient corresponding to the associated government service is used for representing the probability of handling the associated government service after the same user handles the government service;

The confidence degree determining module is used for determining at least one target associated government service associated with the target government service and the confidence degree corresponding to each target associated government service based on the target government service association relation data;

The order determining module is used for determining at least one government service to be recommended from the at least one target associated government service based on the confidence degree corresponding to each target associated government service, and determining the recommendation order of the at least one government service to be recommended.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the program when executed by the processor implements the government service recommendation method of any one of claims 1 to 7.

10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the government service recommendation method of any of claims 1 to 7.