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

CN118710474BActive Publication Date: 2024-12-03数字安徽有限责任公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411188744.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03
Estimated Expiration
2044-08-28

AI Technical Summary

Technical Problem

The current government service recommendation methods are low in accuracy, which makes it difficult for users to find services that meet their own needs, and requires manual filtering, which is inefficient.

Method used

By determining the last government service handled by the target user, the confidence of the associated government service is analyzed from the government service relationship data center, the government service related relationships are recommended, and the government service associated with it is analyzed and predicted future needs using user historical data and time series, and the recommendation order is automatically sorted.

Benefits of technology

It improves the accuracy and efficiency of government service recommendations, reduces the user's need to manually screen information, and improves the recommendation effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118710474B_ABST
    Figure CN118710474B_ABST
Patent Text Reader

Abstract

The present invention provides a government service recommendation method, device, electronic device and storage medium, and relates to the field of service recommendation technology. The method includes: determining the target government service last handled by the target user; determining the target government service association relationship data corresponding to the target government service from the government service association relationship data set; based on the target government service association relationship data, determining at least one target-related government service associated with the target government service, and the confidence corresponding to each target-related government service; based on the confidence corresponding to each target-related government service, determining at least one government service to be recommended from at least one target-related government service, and determining the recommendation order of at least one government service to be recommended. The present invention can improve the recommendation accuracy of government services, and thus improve the recommendation effect of government services.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of service recommendation technology, and in particular to a government service recommendation method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of science and technology, government services are gradually turning to intelligence. In order to meet the needs of intelligent government services, it is necessary to actively recommend government services to users. The number of government services provided by the government to the outside world is increasing, and the relationship between government services is becoming increasingly complex, involving multiple departments, levels, and service objects on the social side. Therefore, government services have the characteristics of numerous categories, complex content, and wide coverage; based on this, it is very difficult for users to find government services that match their own needs.

[0003] At present, most government services related to the search content are recommended to users through user search. However, some government services are highly similar, so too many government services may be recommended, or too much search information may be provided for selection, so that users still need to manually filter the recommended government services or filter the search information repeatedly to find the government services that meet the actual needs of users. Therefore, the current government service recommendation method has low recommendation accuracy, which will lead to poor recommendation effect of government services. Summary of the invention

[0004] The present invention provides a government service recommendation method, device, electronic device and storage medium, which are used to solve the defect of poor government service recommendation effect in the prior art and achieve efficient and accurate government service recommendation.

[0005] The present invention provides a government service recommendation method, comprising:

[0006] Determine the target government service that the target user finally handles;

[0007] Determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set; the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one associated government service associated with the government service; the association relationship data corresponding to any of the associated government services includes identification data of the associated government service and a confidence level corresponding to the associated government service; the confidence level corresponding to the associated government service is used to characterize the probability that the same user will handle the associated government service after handling the government service;

[0008] Based on the target government service association relationship data, determining at least one target-associated government service associated with the target government service, and a confidence level corresponding to each of the target-associated government services;

[0009] Based on the confidence level corresponding to each of the target-related government services, at least one government service to be recommended is determined from the at least one target-related government service, and a recommendation order of the at least one government service to be recommended is determined.

[0010] According to a government service recommendation method provided by the present invention, the government service association relationship data set is determined based on the following method:

[0011] Acquire a data set of historical government service processing by a first user; the data set of historical government service processing by a first user includes historical government service processing data of a plurality of users by the first user, and the historical government service processing data of any of the users includes identification data of a plurality of government services processed by the user, and the processing time of each of the government services processed;

[0012] Based on the first user's historical data set of government service handling and a preset time interval threshold, a data set of government service affairs handled by users is determined; the data set of government service affairs handled by users includes a subset of government service affairs handled by users of the multiple users, the subset of government service affairs handled by users of any of the users includes at least one government service affairs handled by users of the user, any government service affairs handled by users of the user includes identification data of a first government service handled by the user and identification data of a second government service handled by the user, the handling time of the first government service is before the handling time of the second government service, and the handling time interval between the first government service and the second government service is less than the preset time interval threshold;

[0013] Based on the user's government service transaction data set and a preset minimum confidence threshold, an association relationship analysis is performed between government services to obtain the government service association relationship data set; the confidence corresponding to the associated government service is greater than the preset minimum confidence threshold.

[0014] According to a government service recommendation method provided by the present invention, the correlation relationship analysis between government services is performed based on the government service transaction data set handled by the user and a preset minimum confidence threshold to obtain the government service correlation relationship data set, including:

[0015] Removing the user-handled government service transaction data whose occurrence frequency is less than a preset occurrence frequency threshold from the user-handled government service transaction data set, to obtain a user-handled government service transaction data set after removal; the occurrence frequency of any user-handled government service transaction data included in the user-handled government service transaction data set after removal is greater than or equal to the preset occurrence frequency threshold;

[0016] Based on the removed user-handled government service transaction data set and a preset minimum confidence threshold, an association relationship analysis is performed between government services to obtain the government service association relationship data set.

[0017] According to a government service recommendation method provided by the present invention, the association relationship analysis between government services is performed based on the removed user government service transaction data set and a preset minimum confidence threshold to obtain the government service association relationship data set, including:

[0018] Based on the removed data set of government service affairs handled by users, a preset minimum confidence threshold and a preset minimum support threshold, performing correlation analysis between government services to obtain the government service correlation data set;

[0019] Among them, the support degree corresponding to the related government service is greater than the preset minimum support degree threshold; the support degree corresponding to the related government service is used to characterize the probability that the same user handles the government service and the related government service.

[0020] According to a government service recommendation method provided by the present invention, the determining of the government service transaction data set of the user based on the first user's historical government service data set and a preset time interval threshold comprises:

[0021] Determining, based on the first user historical government service processing data set, processing times of multiple government services processed by the multiple users;

[0022] Based on the processing times of the multiple government services that have been processed by the multiple users, the multiple government services that have been processed by the multiple users are sorted in the order of the processing times to obtain sorting results corresponding to the multiple users; the sorting result corresponding to any of the users includes the multiple government services that have been processed by the user sorted in the order of the processing times;

[0023] Based on the sorting results corresponding to the multiple users and the historical government service handling data of the first users of the multiple users, a subset of the government service transaction data handled by the initial users of the multiple users is determined; any user-handled government service transaction data included in the subset of the initial user-handled government service transaction data of any of the users includes identification data of a third government service handled by the user and identification data of a fourth government service handled by the user, the handling time of the third government service is before the handling time of the fourth government service, and the third government service and the fourth government service are two adjacent handled government services in the sorting results corresponding to the user;

[0024] Based on the subset of the initial user government service transaction data of the multiple users and the processing times of the multiple government services that have been processed by the multiple users, determine the minimum processing time intervals corresponding to the multiple users respectively; the minimum processing time interval corresponding to any of the users is the smallest processing time interval among the processing time intervals corresponding to the government service transaction data of each user in the subset of the initial user government service transaction data of the user, and the processing time interval corresponding to the government service transaction data of any of the users is determined based on the processing times of two government services represented by the government service transaction data of the user;

[0025] Based on a preset time interval threshold and the minimum processing time interval corresponding to the multiple users, a subset of the initial user government service transaction data of the multiple users is screened to obtain a subset of the user government service transaction data of the multiple users; the standard processing time interval between the first government service and the second government service is less than the preset time interval threshold, and the standard processing time interval between the first government service and the second government service is the difference between the processing time interval between the first government service and the second government service and the minimum processing time interval corresponding to the user.

[0026] According to a government service recommendation method provided by the present invention, the method further includes:

[0027] Acquire historical government service data of the target user; the historical government service data includes identification data of multiple historical government services that the target user has handled, and the handling time of each of the historical government services;

[0028] Based on the processing time of each of the historical government services, constructing the identification data of the plurality of historical government services into time series data;

[0029] Perform periodic analysis on the time series data to obtain the processing cycle of government services;

[0030] Iteratively training a seasonal difference autoregressive moving average model based on the processing cycle and the time series data;

[0031] Predict future government services based on the iteratively trained seasonal difference autoregressive moving average model;

[0032] The future government service is recommended to the target user.

[0033] According to a government service recommendation method provided by the present invention, the method further includes:

[0034] 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 includes association rule data subsets corresponding to a plurality of user characteristic data, any of the association rule data subsets includes at least one association rule data; the association rule data corresponding to any of the user characteristic data includes identification data of a centrally handled government service, and a centrally handled time of the centrally handled government service;

[0035] Based on the target association rule data subset, determining at least one government service that the target user centrally handles, and a target centralized handling time for each government service that the target user centrally handles;

[0036] Based on the target centralized processing time, the recommended time for each government service that the target users centrally handle is determined.

[0037] The present invention also provides a government service recommendation device, comprising:

[0038] A service determination module is used to determine the target government service that the target user has finally handled;

[0039] A data determination module, used to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set; the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one associated government service associated with the government service; the association relationship data corresponding to any of the associated government services includes identification data of the associated government service and a confidence level corresponding to the associated government service; the confidence level corresponding to the associated government service is used to characterize the probability that the same user will handle the associated government service after handling the government service;

[0040] A confidence determination module, used to determine at least one target-associated government service associated with the target government service and the confidence corresponding to each of the target-associated government services based on the target government service association relationship data;

[0041] The order determination module is used to determine at least one government service to be recommended from the at least one target-related government service based on the confidence corresponding to each target-related government service, and determine the recommendation order of the at least one government service to be recommended.

[0042] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the government service recommendation methods described above is implemented.

[0043] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any of the government service recommendation methods described above.

[0044] The government service recommendation method, device, electronic device and storage medium provided by the present invention determine the target government service last handled by the target user, so as to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set, and the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any government service includes association relationship data corresponding to at least one associated government service associated with the government service, and the association relationship data corresponding to any associated government service includes identification data of the associated government service, and confidence level corresponding to the associated government service, and the confidence level corresponding to the associated government service is used to characterize the probability of the same user handling the associated government service after handling the government service, so as to determine at least one target associated government service associated with the target government service based on the target government service association relationship data, and confidence level corresponding to each target associated government service, so as to determine the target associated government service based on each target associated government service. According to the confidence degree corresponding to the target government service, at least one to-be-recommended government service is determined from at least one target-related government service, and a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user the related government service associated with the target government service based on the target government service last handled by the target user, that is, the target user is recommended the related government service that may be handled after handling the target government service, so that the recommendation of the related government service is more in line with the actual needs of the user, thereby improving the accuracy of the recommendation of the government service, and further improving the effect of the recommendation of the government service; and based on the confidence degree corresponding to each target-related government service, a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user at least one to-be-recommended government service based on the recommendation order, thereby further improving the effect of the recommendation of the government service; and the embodiment of the present invention can complete the recommendation without the target user manually screening any information, thereby improving the efficiency of the recommendation of the government service, and further improving the effect of the recommendation of the government service. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is one of the flow charts of the government service recommendation method provided by the present invention.

[0047] Figure 2 This is the second flow chart of the government service recommendation method provided by the present invention.

[0048] Figure 3 It is a structural schematic diagram of the government service recommendation device provided by the present invention.

[0049] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In view of the above problems, the present invention proposes the following embodiments. Figure 1-Figure 2 The government service recommendation method of the present invention is described.

[0052] Figure 1 This is one of the flow charts of the government service recommendation method provided by the present invention, such as Figure 1 As shown, the government service recommendation method includes the following steps 110, 120, 130 and 140.

[0053] Step 110: Determine the target government service that the target user last processed.

[0054] The executor of the government service recommendation method provided in the embodiment of the present invention can be a server, such as a server corresponding to a government APP or a government mini-program; it can also be a terminal device, such as a government service device and a smart phone, etc., which is not specifically limited by the embodiment of the present invention.

[0055] It should be noted that the embodiments of the present invention may involve the use of user data. In actual applications, the user's specific personal data may be used in the scheme described in the text within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0056] Here, the target user is the user to whom the government service is to be recommended. The target government service is the government service that has been processed last among all the government services processed by the target user.

[0057] In one embodiment, within a preset time period after the target user handles the target government service, the target government service that the target user has handled the last time is determined, and the preset time period is a relatively short time period, so that the target user is recommended to handle related government services within a relatively short period of time after the target user handles the target government service, that is, based on the government service behavior that the target user has handled recently, the government service that the target user "should handle" in the future is predicted and recommended to the target user. For example, a resident who handles the "unemployment registration" government service should apply for unemployment insurance benefits, and the "unemployment insurance benefit application" government service can be recommended to the resident based on the front-end relationship between government services, that is, a continuous handling of the case.

[0058] Step 120: Determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set.

[0059] Among them, the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one related government service associated with the government service; the association relationship data corresponding to any of the related government services includes identification data of the related government service, and the confidence level corresponding to the related government service; the confidence level corresponding to the related government service is used to characterize the probability of the same user handling the related government service after handling the government service.

[0060] Here, the related government service is a government service related to the government service, and the related government service should be a service handled after the government service is handled; for example, the "unemployment insurance benefit application" government service is a related government service of the "unemployment registration" government service.

[0061] Here, the identification data of the associated government service is used to uniquely identify the associated government service.

[0062] Furthermore, the association relationship data corresponding to any associated government service also includes identification data of the government service, that is, the association relationship data includes identification data of the government service handled first, identification data of the government service handled later to be recommended, and the confidence level corresponding to the government service handled later.

[0063] It should be noted that there may be one or more associated government services associated with any government service. Based on this, the government service association relationship data corresponding to any government service includes association relationship data corresponding to one or more associated government services.

[0064] In one embodiment, the government service association relationship data set is determined after manually analyzing the relationships between government services, that is, the government service association relationship data set is manually preset.

[0065] In another embodiment, the government service association relationship data set is determined by analyzing the relationship between government services using a data analysis tool.

[0066] In another embodiment, the government service association relationship data set is determined based on the following method: obtaining a first user historical government service processing data set; the first user historical government service processing data set includes the first user historical government service processing data of multiple users, and the first user historical government service processing data of any user includes the identification data of multiple government services processed by the user, and the processing time of each processed government service; based on the first user historical government service processing data set, determining the user government service transaction data set; the user government service transaction data set includes a subset of user government service transaction data of multiple users, and the user government service transaction data subset of any user includes at least one user government service transaction data of the user, and any user government service transaction data of the user includes the identification data of the first government service processed by the user and the identification data of the second government service processed by the user, and the processing time of the first government service is before the processing time of the second government service; based on the user government service transaction data set and the preset minimum confidence threshold, performing association relationship analysis between government services to obtain a government service association relationship data set; the confidence corresponding to the associated government service is greater than the preset minimum confidence threshold.

[0067] Furthermore, based on the data set of users handling government service transactions, a preset minimum confidence threshold and a preset minimum support threshold, an analysis of the correlation relationship between government services is performed to obtain a government service correlation relationship data set; wherein the support corresponding to the related government services is greater than the preset minimum support threshold; the support corresponding to the related government services is used to characterize the probability that the same user handles both government services and related government services.

[0068] Step 130: Based on the target government service association relationship data, determine at least one target-associated government service associated with the target government service, and the confidence level corresponding to each of the target-associated government services.

[0069] Since the government service association relationship data corresponding to any government service includes association relationship data corresponding to at least one related government service associated with the government service, the association relationship data corresponding to any related government service includes identification data of the related government service and the confidence corresponding to the related government service; based on this, based on the target government service association relationship data, at least one target related government service associated with the target government service and the confidence corresponding to each target related government service can be determined.

[0070] Step 140: Based on the confidence level corresponding to each of the target-related government services, determine at least one government service to be recommended from the at least one target-related government service, and determine a recommendation order for the at least one government service to be recommended.

[0071] Specifically, based on the confidence corresponding to each target-related government service, at least one government service to be recommended is determined from at least one target-related government service; based on the confidence corresponding to at least one government service to be recommended, a recommendation order (recommendation priority) of at least one government service to be recommended is determined, so as to recommend at least one government service to be recommended to the target user based on the recommendation order.

[0072] In one embodiment, at least one target-related government service is determined as a government service to be recommended.

[0073] In another embodiment, based on the confidences corresponding to the target-related government services and sorting results from high to low confidences, a preset number of government services to be recommended with the highest confidences are determined from at least one target-related government service.

[0074] In another embodiment, based on the confidences corresponding to the target-related government services, the government services to be recommended with a preset ratio and the highest confidence are determined from at least one target-related government service. For example, if the number of at least one target-related government service is 10 and the preset ratio is 0.2, there are 2 government services to be recommended.

[0075] In another embodiment, based on the confidence corresponding to each target-related government service, a government service to be recommended having a confidence greater than a preset confidence threshold is determined from at least one target-related government service.

[0076] In a specific embodiment, the recommendation order of at least one government service to be recommended is determined based on the confidence corresponding to at least one government service to be recommended and the confidence is sorted from large to small.

[0077] The government service recommendation method provided by the embodiment of the present invention determines the target government service last handled by the target user, so as to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set, and the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any government service includes association relationship data corresponding to at least one associated government service associated with the government service, and the association relationship data corresponding to any associated government service includes identification data of the associated government service, and a confidence level corresponding to the associated government service, and the confidence level corresponding to the associated government service is used to characterize the probability of the same user handling the associated government service after handling the government service, so as to determine at least one target associated government service associated with the target government service based on the target government service association relationship data, and the confidence level corresponding to each target associated government service, so as to determine the confidence level corresponding to each target associated government service based on the placement data corresponding to each target associated government service. confidence, at least one to-be-recommended government service is determined from at least one target-related government service, and a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user the associated government service associated with the target government service based on the target government service last handled by the target user, that is, to recommend to the target user the associated government service that may be handled after handling the target government service, so that recommending the associated government service is more in line with the actual needs of the user, thereby improving the accuracy of government service recommendations, and further improving the effect of government service recommendations; and based on the confidence corresponding to each target-related government service, a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user at least one to-be-recommended government service based on the recommendation order, thereby further improving the effect of government service recommendations; and the embodiment of the present invention can complete the recommendation without the target user manually screening any information, thereby improving the efficiency of government service recommendations, and further improving the effect of government service recommendations.

[0078] Based on any of the above embodiments, Figure 2 This is the second flow chart of the government service recommendation method provided by the present invention. Figure 2 As shown, the government service association relationship data set is determined based on the following method:

[0079] Step 210: Obtain a data set of the first user's historical government service handling.

[0080] Among them, the first user historical government service data set includes the first user historical government service data of multiple users, and the first user historical government service data of any of the users includes the identification data of multiple government services that have been handled by the user, and the handling time of each of the government services.

[0081] In one embodiment, the first user's historical government service data set can be obtained by collecting government service data handled by multiple users on online platforms and offline windows.

[0082] Here, the identification data of the processed government service is used to uniquely identify the processed government service. Further, the first user historical government service processing data of any user also includes the user information of the user.

[0083] Step 220: Determine a data set of government service transactions handled by the user based on the data set of the first user's history of handling government service transactions and a preset time interval threshold.

[0084] Among them, the user-handled government service transaction data set includes a subset of the user-handled government service transaction data of the multiple users, any user-handled government service transaction data subset of the users includes at least one user-handled government service transaction data of the user, any user-handled government service transaction data of the user includes identification data of the first government service handled by the user and identification data of the second government service handled by the user, the handling time of the first government service is before the handling time of the second government service, and the handling time interval between the first government service and the second government service is less than the preset time interval threshold.

[0085] Here, the preset time interval threshold is a preset continuous processing time interval. Specifically, according to the processing time interval between the user and the two government services, the first user's historical government service processing data set is clustered to obtain a clustered user government service transaction data subset of multiple users.

[0086] Considering that two government services are relatively related, the processing time interval between the two government services should be less than the preset time interval threshold, and the preset time interval threshold is a relatively short time period, so that the target user can be recommended to handle the related government service in a relatively short time period after the target user handles the target government service, that is, based on the government service behavior that the target user has handled recently, the government service that the target user "should handle" in the future is predicted and recommended to the target user. Specifically, the above step 110 includes: within the preset time period after the target user handles the target government service, determining the target government service that the target user last handled, and the preset time period is the preset time interval threshold.

[0087] Specifically, based on a preset time interval threshold, the historical government service data set of the first user is screened, and the government service transaction data set of the user is reconstructed based on the screening result.

[0088] Furthermore, the first user's historical government service data set is preprocessed to determine the user's government service transaction data set based on the preprocessed first user's historical government service data set. The data preprocessing method may include but is not limited to at least one of the following: cleaning of the user's historical government service data, conversion of the user's historical government service data, and processing of the user's historical government service data; data cleaning is mainly to remove noise, errors, duplications, invalid values ​​or incomplete data in the first user's historical government service data set, which includes processing missing values, outliers, etc.; data conversion is mainly to standardize the user's historical government service data, such as converting the processing time into a standard timestamp; data processing is mainly to process and assemble the user's historical government service data according to rules, and process it into data calculated by subsequent algorithm models.

[0089] Step 230: Based on the data set of government service transactions handled by the user and a preset minimum confidence threshold, perform correlation analysis between government services to obtain the government service correlation data set.

[0090] Among them, the confidence corresponding to the associated government service is greater than the preset minimum confidence threshold.

[0091] Here, the algorithm for association analysis can be set according to actual needs. The embodiment of the present invention takes the FP-Growth (Frequent Pattern Growth) algorithm as an example for explanation. The algorithm for association analysis is used to analyze the association, regularity and trend between two government services in any user's government service transaction data in the user's government service transaction data set, and mine frequent item sets, that is, mine frequent government service association relationship data to obtain a government service association relationship data set.

[0092] It should be understood that in the FP-Growth algorithm, any data of a user handling government service transactions in the user handling government service transaction data set is an item set.

[0093] Furthermore, based on the data set of users handling government service transactions, a preset minimum confidence threshold and a preset minimum support threshold, an analysis of the correlation relationship between government services is performed to obtain a government service correlation relationship data set; wherein the support corresponding to the related government services is greater than the preset minimum support threshold; the support corresponding to the related government services is used to characterize the probability that the same user handles both government services and related government services.

[0094] In a specific embodiment, a preset minimum confidence threshold and a preset minimum support threshold are obtained, and an FP-Growth algorithm model is constructed based on a data set of government service transactions handled by users, a preset minimum confidence threshold and a preset minimum support threshold, so as to obtain a government service association relationship data set based on the FP-Growth algorithm model. More specifically, a model is trained based on a data set of government service transactions handled by users, a preset minimum confidence threshold and a preset minimum support threshold to obtain a government service association relationship data set. Furthermore, considering that government services include high-frequency services and low-frequency services, the preset minimum confidence threshold or the preset minimum support threshold is continuously adjusted and the FP-Growth algorithm model is continuously updated in combination with manual judgment, so as to obtain a more accurate government service association relationship data set.

[0095] It is understandable that if the government service association relationship data set is determined by manual analysis, it will consume a lot of manpower and material resources, and it is easily affected by subjective factors, which will lead to inaccurate government service association relationship data set, and then lead to inaccurate government service recommendations; based on this, through the above method, the association relationship analysis between government services is automatically performed, and the confidence level corresponding to the associated government services can be determined, thereby improving the efficiency of determining the government service association relationship data set and reducing costs, that is, efficiently mining the association relationship between government services, and through the above method, the deep-level relationship between government services can be accurately captured, thereby improving the accuracy of determining the government service association relationship data set, that is, accurately mining the association relationship between government services, and then improving the accuracy of government service recommendations.

[0096] It is understandable that, considering that if the government service association relationship data set is determined by a data analysis tool, since the current data analysis tools can only process simple data relationships, the ability to mine the relationships between complex government services is limited, which leads to inaccurate government service association relationship data sets, and further leads to inaccurate government service recommendations; based on this, through the above method, the association relationship analysis between government services is automatically performed, and the confidence level corresponding to the associated government services can be determined, thereby improving the efficiency of determining the government service association relationship data set, that is, efficiently mining the association relationship between government services, and through the above method, the deep-level relationship between government services can be accurately captured, thereby improving the accuracy of determining the government service association relationship data set, that is, accurately mining the association relationship between government services, and thus improving the accuracy of government service recommendations.

[0097] The government service recommendation method provided by the embodiment of the present invention can automatically analyze the association relationship between government services through the above-mentioned method, and can determine the confidence level corresponding to the associated government services, thereby improving the efficiency of determining the government service association relationship data set and reducing costs, that is, efficiently mining the association relationship between government services, and can accurately capture the deep-level relationship between government services through the above-mentioned method, thereby improving the accuracy of determining the government service association relationship data set, that is, accurately mining the association relationship between government services, and then improving the accuracy of government service recommendations.

[0098] Based on any of the above embodiments, in the method, the above step 230 includes:

[0099] Removing the user-handled government service transaction data whose occurrence frequency is less than a preset occurrence frequency threshold from the user-handled government service transaction data set, to obtain a user-handled government service transaction data set after removal; the occurrence frequency of any user-handled government service transaction data included in the user-handled government service transaction data set after removal is greater than or equal to the preset occurrence frequency threshold;

[0100] Based on the removed user-handled government service transaction data set and a preset minimum confidence threshold, an association relationship analysis is performed between government services to obtain the government service association relationship data set.

[0101] Here, the frequency of occurrence of the data of government service transactions handled by users is the number of data of government service transactions handled by the same user. More specifically, the frequency of occurrence of the data of government service transactions handled by users is the number of data of government service transactions handled by users that includes the identification data of the same two government services, that is, if the same user or different users handle the second government service after handling the first government service, then multiple data of government service transactions handled by users can be obtained respectively, and the data of government service transactions handled by multiple users are the same, then the frequency of occurrence can be determined.

[0102] Here, the preset occurrence frequency threshold can be set according to actual needs and is not specifically limited here.

[0103] In a specific embodiment, the data of each user handling government service transaction in the user handling government service transaction data set are sorted in order of occurrence frequency from high to low to obtain a sorting result; the user handling government service transaction data with an occurrence frequency less than a preset occurrence frequency threshold in the sorting result is removed to obtain the user handling government service transaction data set after removal.

[0104] The government service recommendation method provided in the embodiment of the present invention removes the user-handled government service transaction data whose appearance frequency is less than a preset frequency threshold from the user-handled government service transaction data set, and obtains the user-handled government service transaction data set after removal, thereby screening the user-handled government service transaction data set to remove the user-handled government service transaction data whose appearance frequency is less than the preset frequency threshold, thereby ensuring that the association relationship between the two government services included in the user-handled government service transaction data set in the user-handled government service transaction data set after removal is a strong association relationship, thereby improving the determination accuracy of the government service association relationship data set, and further improving the recommendation accuracy of government services.

[0105] Based on any of the above embodiments, in the method, the correlation relationship analysis between government services is performed based on the removed user-handled government service transaction data set and the preset minimum confidence threshold to obtain the government service correlation relationship data set, including: based on the removed user-handled government service transaction data set, the preset minimum confidence threshold and the preset minimum support threshold, the correlation relationship analysis between government services is performed to obtain the government service correlation relationship data set.

[0106] Among them, the support degree corresponding to the related government service is greater than the preset minimum support degree threshold; the support degree corresponding to the related government service is used to characterize the probability that the same user handles the government service and the related government service.

[0107] In a specific embodiment, a preset minimum confidence threshold and a preset minimum support threshold are obtained, and an FP-Growth algorithm model is constructed based on the data set of government service transactions handled by users after removal, 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 data set of government service transactions handled by users after removal, the preset minimum confidence threshold and the preset minimum support threshold, so as to obtain a government service association relationship data set.

[0108] The government service recommendation method provided by the embodiment of the present invention can automatically analyze the association relationship between government services through the above-mentioned method, and can determine the confidence level corresponding to the associated government services, thereby improving the efficiency of determining the government service association relationship data set and reducing costs, that is, efficiently mining the association relationship between government services, and can accurately capture the deep-level relationship between government services through the above-mentioned method, thereby improving the accuracy of determining the government service association relationship data set, that is, accurately mining the association relationship between government services, and then improving the accuracy of government service recommendations.

[0109] Based on any of the above embodiments, taking into account that the processing time intervals of two related government services may vary from person to person, that is, for different users, the processing time intervals of the same two related government services may be different; based on this, the above step 220 includes: steps 221-225.

[0110] Step 221, based on the first user's historical government service processing data set, determine the processing time of multiple government services that have been processed by the multiple users.

[0111] Since the first user's historical government service processing data set includes the first user's historical government service processing data of multiple users, and the first user's historical government service processing data of any user includes the identification data of multiple government services processed by the user, as well as the processing time of each processed government service, therefore, based on the first user's historical government service processing data set, the processing time of multiple government services processed by multiple users can be determined.

[0112] Step 222, based on the processing times of the multiple government services processed by the multiple users, sort the multiple government services processed by the multiple users in the order of the processing times to obtain the sorting results corresponding to the multiple users; the sorting result corresponding to any of the users includes the multiple government services processed by the user sorted in sequence according to the processing times.

[0113] Here, the sorting results corresponding to each user are obtained respectively. The sorting result corresponding to any user is based on the processing time of multiple government services that the user has processed, and the multiple government services that the user has processed are sorted in the order of the processing time.

[0114] Step 223, based on the sorting results corresponding to the multiple users and the historical government service data of the first users of the multiple users, determine a subset of the initial user government service transaction data of the multiple users; any user government service transaction data included in the subset of the initial user government service transaction data of any of the users includes identification data of a third government service handled by the user and identification data of a fourth government service handled by the user, the handling time of the third government service is before the handling time of the fourth government service, and the third government service and the fourth government service are two adjacent handled government services in the sorting results corresponding to the user.

[0115] Specifically, based on the sorting results corresponding to multiple users, the first user's historical government service data set is reconstructed to obtain a user's government service transaction data set. Since the sorting results corresponding to multiple users are obtained, the two government services included in any user's government service transaction data are the two most adjacent government services at the time of processing, which facilitates subsequent screening to obtain a user's government service transaction data subset.

[0116] Step 224, based on the subset of the initial user government service transaction data of the multiple users and the processing times of the multiple government services that have been processed by the multiple users, determine the minimum processing time interval corresponding to the multiple users respectively; the minimum processing time interval corresponding to any of the users is the smallest processing time interval among the processing time intervals corresponding to the government service transaction data of each user in the subset of the initial user government service transaction data of the user, and the processing time interval corresponding to the government service transaction data of any of the users is determined based on the processing times of two government services represented by the government service transaction data of the user.

[0117] It should be noted that the minimum processing time interval is different for each user, so it needs to be determined separately.

[0118] Step 225, based on the preset time interval threshold and the minimum processing time interval corresponding to the multiple users, screen the initial user government service transaction data subset of the multiple users to obtain the user government service transaction data subset of the multiple users; the standard processing time interval between the first government service and the second government service is less than the preset time interval threshold, and the standard processing time interval between the first government service and the second government service is the difference between the processing time interval between the first government service and the second government service and the minimum processing time interval corresponding to the user.

[0119] Specifically, based on a preset time interval threshold, a subset of initial user government service transaction data of multiple users is screened, and a user government service transaction data set is reconstructed based on the screening result.

[0120] In a specific embodiment, for any user, multiple government services handled by the user are sorted in ascending order according to the handling time of the services, and the time interval between each currently handled government service and the last handled government service is calculated. The time interval of the first handling time in the sorting is set to 0 by default, and the initial user government service transaction data subset is obtained for the user; the initial user government service transaction data subset is traversed, each handling time interval is compared with a preset time interval threshold, and the user government service transaction data greater than or equal to 0 and less than the preset time interval threshold is retained; if the user government service transaction data greater than or equal to 0 and less than the preset time interval threshold is not traversed, the data is discarded.

[0121] The government service recommendation method provided by the embodiment of the present invention determines the minimum processing time intervals corresponding to multiple users respectively in the above manner, and thus screens the initial user government service transaction data subsets of multiple users based on the preset time interval threshold and the minimum processing time intervals corresponding to multiple users, so as to obtain a more accurate user government service transaction data subset of multiple users, that is, taking into account that the processing time intervals of the same two related government services may be different for different users, standardization is performed to improve the determination accuracy of the user government service transaction data set, thereby improving the determination accuracy of the government service association relationship data set, and ultimately improving the recommendation accuracy of government services.

[0122] Based on any of the above embodiments, the method further includes: steps 310 to 360.

[0123] Step 310: Obtain historical data of government services handled by the target user; the historical data of government services handled by the target user includes identification data of multiple historical government services handled by the target user, and the handling time of each of the historical government services.

[0124] In one embodiment, historical data on government service handling by users can be obtained by collecting data on government service handled by target users on online platforms and offline windows.

[0125] Here, the identification data of the historical government service is used to uniquely identify the historical government service. Further, the historical user handling government service data also includes the user information of the target user.

[0126] Furthermore, data preprocessing is performed on historical user government service data. The data preprocessing method may include but is not limited to at least one of the following: data cleaning, data conversion and data processing; data cleaning mainly removes noise, errors, duplications, invalid values ​​or incomplete data, including processing missing values, outliers, etc.; data conversion mainly standardizes data, such as converting the processing time into a standard timestamp; data processing mainly processes and assembles data according to rules, and processes it into data for subsequent algorithm model calculation.

[0127] Step 320: Based on the processing time of each of the historical government services, construct the identification data of the multiple historical government services into time series data.

[0128] Since the historical user government service data includes the identification data of multiple historical government services that the target user has handled, as well as the handling time of each historical government service, based on this, the identification data of multiple historical government services can be constructed into time series data based on the handling time of each historical government service.

[0129] Step 330: Perform periodic analysis on the time series data to obtain the processing cycle of government services.

[0130] Here, the algorithm for periodic analysis can be set according to actual needs, for example, the processing period of government services can be determined through the autocorrelation function (ACF) algorithm, or, according to the periodogram algorithm, the time series data can be converted from the time domain to the frequency domain using Fourier transform to identify and analyze the period of the data, that is, to obtain the processing period of government services.

[0131] Step 340: iteratively train a seasonal difference autoregressive moving average model based on the processing cycle and the time series data.

[0132] In a specific embodiment, the processing cycle is used as the season (cycle length) of the seasonal autoregressive moving average model (SARIMA model), and the seasonal autoregressive moving average model is iteratively trained based on time series data. More specifically, according to the data characteristics and analysis results, the seasonal autoregressive moving average model is selected, the model is fitted using time series data, the parameters of the model are estimated, and the seasonal autoregressive moving average model is used for prediction to obtain the prediction results, the prediction results are evaluated, and the difference between the predicted value and the actual value is compared to complete the training.

[0133] Furthermore, the seasonal difference autoregressive moving average model is continuously optimized and adjusted. Since the selection and tuning of model parameters are crucial to the accuracy and stability of prediction, the model is adjusted and optimized based on the evaluation results, and different model parameters and orders are tried to make the model prediction more accurate.

[0134] Step 350: Predict future government services based on the iteratively trained seasonal difference autoregressive moving average model.

[0135] Specifically, based on the optimal seasonal difference autoregressive moving average model, future government services are predicted. The future government services are government services that target users handle regularly, such as government services related to pensions, that is, periodic handling of cases.

[0136] Furthermore, the processing cycle of government services has been determined above. Based on this, the processing time of future government services can also be predicted based on the seasonal difference autoregressive sliding average model after iterative training, so as to determine the recommended time of future government services based on the processing time of future government services.

[0137] Step 360: Recommend the future government service to the target user.

[0138] In a specific embodiment, based on the recommended time of the future government service, the future government service is recommended to the target user. The recommended time may be before the processing time of the future government service, and the specific time may be set according to actual needs.

[0139] The government service recommendation method provided by the embodiment of the present invention obtains the historical user data of government service handling by the target user, and the historical user data of government service handling by the target user includes the identification data of multiple historical government services handled by the target user, and the handling time of each historical government service, so as to construct the identification data of multiple historical government services into time series data based on the handling time of each historical government service, to perform periodic analysis on the time series data, to obtain the handling cycle of the government service, to iteratively train the seasonal difference autoregressive sliding average model based on the handling cycle and the time series data, and to predict future government services based on the seasonal difference autoregressive sliding average model after iterative training, so as to recommend future government services to the target user based on the historical user data of government service handling by the target user, that is, to recommend the government services that the target user periodically handles to the target user, so that the recommendation of the future government service is more in line with the actual needs of the user, thereby improving the recommendation accuracy of the government service, and further improving the recommendation effect of the government service; and the embodiment of the present invention can complete the recommendation without the target user manually screening any information, thereby improving the recommendation efficiency of the government service, and further improving the recommendation effect of the government service.

[0140] Based on any of the above embodiments, the method further includes: step 410 to step 430.

[0141] Step 410: Based on the target user characteristic data of the target user, determine from the association rule data set a target association rule data subset corresponding to the target user characteristic data; the association rule data set includes association rule data subsets corresponding to multiple user characteristic data, and any of the association rule data subsets includes at least one association rule data; any of the association rule data corresponding to the user characteristic data includes identification data of centrally handled government services, and centralized handling time of the centrally handled government services.

[0142] Here, the centralized government services are those that most users handle in one time period; for example, users between the ages of 30 and 40 tend to handle social security services in the afternoons on weekdays, that is, social security services are centralized government services.

[0143] Here, the centralized processing time can be a time period or a moment.

[0144] It should be noted that the number of association rule data associated with any user feature data may be one or more.

[0145] In one embodiment, the association rule data set is determined after manually analyzing the relationship between government services, that is, the association rule data set is manually preset.

[0146] In another embodiment, the association rule data set is determined by analyzing the relationships between government services using a data analysis tool.

[0147] Step 420: Based on the target association rule data subset, determine at least one government service that the target user centrally handles, and the target centralized handling time of each government service that the target user centrally handles.

[0148] Since any association rule data subset includes at least one association rule data, and the association rule data corresponding to any user characteristic data includes the identification data of the centrally handled government services, and the centralized handling time of the centrally handled government services; based on this, based on the target association rule data subset, at least one government service centrally handled by the target user, and the target centralized handling time of each government service centrally handled by the target user can be determined.

[0149] Step 430: Based on the target centralized processing time, determine the recommended time for each government service that the target user centrally processes.

[0150] Here, the recommended time may be before the corresponding target concentrated processing time, or may be during the corresponding target concentrated processing time.

[0151] Furthermore, based on the recommended time of each government service that the target user centrally handles, each government service that the target user centrally handles is recommended to the target user.

[0152] The government service recommendation method provided by the embodiment of the present invention determines 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, and the association rule data set includes multiple association rule data subsets corresponding to user characteristic data, any association rule data subset includes at least one association rule data, and the association rule data corresponding to any user characteristic data includes identification data of centrally handled government services and the central handling time of centrally handled government services, so as to determine at least one government service centrally handled by the target user and the target central handling time of each government service centrally handled by the target user based on the target association rule data subset, so as to determine the recommended time of each government service centrally handled by the target user based on each target central handling time, so as to recommend the government service centrally handled by the target user to the target user based on the association rule data set, so that the recommendation of the centrally handled government service is more in line with the actual needs of the user, thereby improving the recommendation accuracy of the government service, and further improving the recommendation effect of the government service; and the embodiment of the present invention can complete the recommendation without the target user manually screening any information, thereby improving the recommendation efficiency of the government service, and further improving the recommendation effect of the government service.

[0153] Based on any of the above embodiments, the association rule data set is determined based on the following method, which includes steps 510 to 530.

[0154] Step 510, obtain a second user historical government service data set; the second user historical government service data set includes second user historical government service data of multiple users, and the second user historical government service data of any of the users includes identification data of multiple government services that have been handled by the user, as well as the handling time of each of the handled government services, and user characteristic data of the user.

[0155] In one embodiment, the second user historical government service data set can be obtained by collecting government service data handled by multiple users on online platforms and offline windows.

[0156] Here, the identification data of the processed government services is used to uniquely identify the processed government services.

[0157] In one embodiment, the user characteristic data is determined based on the user portrait data. Furthermore, the user portrait data of any user is determined based on the user's electronic certificate data. The user characteristic data of any user is used to characterize the attribute content of at least one attribute of the user. The user portrait data of a user is used to determine the user characteristic data of the user, that is, to label and classify each user to form a characterized user portrait.

[0158] Considering that electronic certificate data can be obtained in the government field, determining the user portrait data of the user based on the electronic certificate data can improve the accuracy and efficiency of determining the user feature data, thereby improving the accuracy and efficiency of recommending government services.

[0159] The electronic certificate data may include but is not limited to at least one of the following: household registration book, social security card, driver's license, birth certificate, real estate certificate, academic certificate, vehicle registration certificate, marriage certificate, disability certificate, rural resident minimum living security certificate, urban and rural resident minimum living security certificate and employment and unemployment registration certificate, etc.

[0160] In a specific embodiment, based on the user portrait data of the target user, the attribute feature value set of the target user is determined, the user portrait data of the target user includes the attribute content of multiple attributes of the target user, and the attribute feature value set of the target user includes the feature values ​​of multiple attributes of the target user; each feature value in the attribute feature value set is vectorized to obtain an attribute vector set; the attribute vector set includes feature vectors of multiple attributes of the target user; based on the attribute vector set, the user feature data of the target user is determined.

[0161] If the user is a legal person, the user's multiple attributes may include but are not limited to at least two of the following: establishment time, region, industry classification, legal person type, market entity type, number of employees paying social security, credit rating, administrative penalties, etc. If the user is a natural person, the user's multiple attributes may include but are not limited to at least two of the following: nationality, ethnicity, highest education level, age, gender, household registration place, place of residence, type of social security payment, type of provident fund payment, whether there is a car, type of driver's license, whether there is a house, marital status, number of children, age of children, whether there are elderly people, qualifications and honors, type of disability, type of social assistance, employment status, income, etc.

[0162] Considering that the attribute content of the user is not necessarily numerical data, for example, the attribute content of the registered residence is the administrative division, it is necessary to convert the attribute content of all attributes into numerical feature values. If the original attribute content is numerical data, the attribute content can be standardized.

[0163] For example, the feature value of age is the actual age of the user; the feature value of unknown gender is 0, the feature value of male gender is 1, and the feature value of female gender is 2; the feature value of social security payment type is 1 for urban employee type, and the feature value of unknown social security payment type is 0; the feature value of whether there is a car is 0 if no, and the feature value of whether there is a car is 1 if yes; the feature value of whether there is a driver's license is 0 if no, and the feature value of whether there is a driver's license is 1 if yes; the feature value of whether there is a house is 0 if no, and the feature value of whether there is a house is 1 if yes; the feature value of whether married is 0 if no, and the feature value of whether married is 1 if yes; the feature value of whether there are children is 0 if no, and the feature value of whether there are children is 1; The characteristic value of age is 0 if it is none, the characteristic value of child age is 1 if it is preschool education, the characteristic value of child age is 2 if it is compulsory education, and the characteristic value of child age is 3 if it is high school; the characteristic value of whether there are elderly people is 0 if it is none, and the characteristic value of whether there are elderly people is 1 if it is yes; the characteristic value of household registration is the administrative division code; the characteristic value of no qualifications and honors is 0, and the characteristic value of qualifications and honors is 1; the characteristic value of special population type is 1 if it is disabled, the characteristic value of special population type is 2 if it is rural minimum living security, the characteristic value of special population type is 3 if it is urban and rural minimum living security, the characteristic value of special population type is 4 if it is unemployed, and the characteristic value of no special population type is 5; the characteristic value of residence is the administrative division code.

[0164] Furthermore, after obtaining the user data of the user, that is, after obtaining the attribute contents of multiple attributes of the user, data preprocessing is performed on the attribute contents of the multiple attributes. The data preprocessing may include, but is not limited to: data cleaning, data interpolation processing, outlier processing, standardization and feature extraction to provide high-quality user portrait data. Among them, data cleaning specifically removes duplicate data to ensure the uniqueness of the data. Data interpolation processing specifically uses interpolation methods (such as mean interpolation, median interpolation) or machine learning-based prediction models for filling. Outlier processing specifically uses binning and other methods to identify and correct or remove outliers. Standardization specifically uses standardization methods or normalization methods to convert continuous variables (such as age) into a unified scale, and performs unique hot encoding or label encoding on categorical variables (such as gender, social security payment type) to convert them into numerical data.

[0165] It should be understood that the feature value of an attribute is vectorized to obtain the feature vector of the attribute.

[0166] Considering that most eigenvalues ​​are binary values ​​(such as 0 or 1) or a few categorical values, this may lead to high sparsity of data, especially when the user has many attributes or the number of multiple users is large. Sparse data may reduce the effect of subsequent similarity calculation. Based on this, the eigenvalues ​​are vectorized to improve the accuracy of similarity calculation, thereby improving the accuracy of determining similar users and ultimately improving the accuracy of government service recommendations.

[0167] Step 520: Based on the second user's historical government service data set, determine the identification data of multiple government services that are centrally handled, the centralized handling time of the multiple government services that are centrally handled, and the characteristic data of the users who handle the multiple government services that are centrally handled.

[0168] Since the second user historical government service processing data set includes the second user historical government service processing data of multiple users, and the second user historical government service processing data of any user includes the identification data of multiple government services that have been processed by the user, as well as the processing time of each processed government service, and the user characteristic data of the user; based on this, based on the second user historical government service processing data set, the government services that are centrally processed can be determined, and the processing time of the centrally processed government services can be determined, and then the centrally processed government services can be matched with the user characteristic data.

[0169] In a specific embodiment, any centralized government service is determined based on the following method: a time series analysis is performed on the data set of historical government services handled by the second user to determine that the centralized government service is a periodically handled government service, and then the centralized handling time of the centralized government service is determined. More specifically, the historical government service data of the second user is aggregated according to a time window (such as day, week, month, quarter), and a time series graph is drawn to observe whether there are periodic peaks or abnormal peaks, which represent the centralized handling time.

[0170] Step 530: Determine the association rule data set based on the identification data of the plurality of government services that are centrally handled, the centralized handling time of the plurality of government services that are centrally handled, and the characteristic data of the users who handle the plurality of government services.

[0171] In a specific embodiment, association rule mining is used to discover association rules between user feature data, centralized processing time and government services. For example, it is analyzed which users with which features are more inclined to handle which government services in which time periods. For example, the algorithm of association rule mining is the Apriori algorithm, which is used to discover frequent item sets and association rules between item sets from a large number of data sets. For example, association rules such as "users aged between 30 and 40 are more inclined to handle social security services in the afternoon on weekdays" can be found. Further, the results of time series analysis and association rule mining are integrated to more comprehensively analyze the centralized processing of certain government services by users in a certain time period; first, time series analysis is used to identify the peak time period for government service processing; then, association rule mining is used to further analyze which users with which features are more inclined to handle which government services during these peak time periods, so as to further match user feature data for subsequent targeted recommendation of centralized processing services to matching users at the recommendation time.

[0172] The government service recommendation method provided by the embodiment of the present invention automatically performs association relationship analysis between government services through the above-mentioned method, thereby improving the efficiency of determining the association rule data set and reducing costs, that is, efficiently mining the association relationship between government services, and through the above-mentioned method, the deep-level relationship between government services can be accurately captured, thereby improving the accuracy of determining the association rule data set, that is, accurately mining the association relationship between government services, and then improving the accuracy of government service recommendations.

[0173] Based on the above embodiments, the present invention mines the relationship between government services, including "continuous processing" (users process B within a short period of time after processing A), "periodic processing" (users regularly use a certain government service), and "centralized processing" (a large number of users centrally process a certain service within a certain period of time). By integrating the three association relationships of "continuous processing", "periodic processing" and "centralized processing", the present invention can realize the intelligent, personalized and efficient recommendation of government services, predict the government services that users "should process" in the future and recommend them to users, thereby improving user experience and satisfaction.

[0174] The government service recommendation device provided by the present invention is described below. The government service recommendation device described below and the government service recommendation method described above can be referenced to each other.

[0175] Figure 3 is a schematic diagram of the structure of the government service recommendation device provided by the present invention, such as Figure 3 As shown, the government service recommendation device includes a service determination module 301, a data determination module 302, a confidence determination module 303 and an order determination module 304.

[0176] The service determination module 301 is used to determine the target government service last handled by the target user.

[0177] The data determination module 302 is used to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set; the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one related government service associated with the government service; the association relationship data corresponding to any of the related government services includes identification data of the related government service, and the confidence level corresponding to the related government service; the confidence level corresponding to the related government service is used to characterize the probability of the same user handling the related government service after handling the government service.

[0178] The confidence determination module 303 is used to determine at least one target-associated government service associated with the target government service and the confidence corresponding to each of the target-associated government services based on the target government service association relationship data.

[0179] The order determination module 304 is used to determine at least one to-be-recommended government service from the at least one target-related government service based on the confidence level corresponding to each target-related government service, and determine the recommendation order of the at least one to-be-recommended government service.

[0180] The government service recommendation device provided by the embodiment of the present invention determines the target government service last handled by the target user, so as to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set, and the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any government service includes association relationship data corresponding to at least one associated government service associated with the government service, and the association relationship data corresponding to any associated government service includes identification data of the associated government service, and confidence level corresponding to the associated government service, and the confidence level corresponding to the associated government service is used to characterize the probability of the same user handling the associated government service after handling the government service, so as to determine at least one target associated government service associated with the target government service based on the target government service association relationship data, and confidence level corresponding to each target associated government service, so as to determine the confidence level corresponding to each target associated government service based on the position data corresponding to each target associated government service. confidence, at least one to-be-recommended government service is determined from at least one target-related government service, and a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user the associated government service associated with the target government service based on the target government service last handled by the target user, that is, to recommend to the target user the associated government service that may be handled after handling the target government service, so that recommending the associated government service is more in line with the actual needs of the user, thereby improving the accuracy of government service recommendations, and further improving the effect of government service recommendations; and based on the confidence corresponding to each target-related government service, a recommendation order of at least one to-be-recommended government service is determined, so as to recommend to the target user at least one to-be-recommended government service based on the recommendation order, thereby further improving the effect of government service recommendations; and the embodiment of the present invention can complete the recommendation without the target user manually screening any information, thereby improving the efficiency of government service recommendations, and further improving the effect of government service recommendations.

[0181] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute the government service recommendation method, which includes: determining the target government service last handled by the target user; determining the target government service association relationship data corresponding to the target government service from the government service association relationship data set; the government service association relationship data set includes government service association relationship data corresponding to multiple government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one associated government service associated with the government service; the association relationship data corresponding to any of the associated government services includes identification data of the associated government service, and a confidence level corresponding to the associated government service; the confidence level corresponding to the associated government service is used to characterize the probability that the same user handles the associated government service after handling the government service; based on the target government service association relationship data, determining at least one target associated government service associated with the target government service, and a confidence level corresponding to each of the target associated government services; based on the confidence level corresponding to each of the target associated government services, determining at least one government service to be recommended from the at least one target associated government service, and determining the recommendation order of the at least one government service to be recommended.

[0182] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0183] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the government service recommendation method provided by the above-mentioned methods, the method comprising: determining the target government service last handled by the target user; determining the target government service association relationship data corresponding to the target government service from a government service association relationship data set; the government service association relationship data set comprises government service association relationship data corresponding to a plurality of government services, the government service association relationship data corresponding to any of the government services comprises association relationship data corresponding to at least one associated government service associated with the government service; the association relationship data corresponding to any of the associated government services comprises identification data of the associated government service, and a confidence level corresponding to the associated government service; the confidence level corresponding to the associated government service is used to characterize the probability that the same user handles the associated government service after handling the government service; based on the target government service association relationship data, determining at least one target associated government service associated with the target government service, and a confidence level corresponding to each of the target associated government services; based on the confidence level corresponding to each of the target associated government services, determining at least one government service to be recommended from the at least one target associated government service, and determining a recommendation order for the at least one government service to be recommended.

[0184] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A government service recommendation method, characterized in that: include: Determine the target government service that the target user finally handles; Determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set; The government service association relationship data set includes government service association relationship data corresponding to a plurality of government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one associated government service associated with the government service; The association relationship data corresponding to any of the related government services include identification data of the related government service and the confidence level corresponding to the related government service; the confidence level corresponding to the related government service is used to characterize the probability that the same user handles the related government service after handling the government service; Based on the target government service association relationship data, determining at least one target-associated government service associated with the target government service, and a confidence level corresponding to each of the target-associated government services; Based on the confidence level corresponding to each of the target-related government services, determining at least one government service to be recommended from the at least one target-related government service, and determining a recommendation order of the at least one government service to be recommended; The government service association relationship dataset is determined based on the following method: Acquire a data set of historical government service processing by a first user; the data set of historical government service processing by a first user includes historical government service processing data of a plurality of users by the first user, and the historical government service processing data of any of the users includes identification data of a plurality of government services processed by the user, and the processing time of each of the government services processed; Determine a data set of government service transactions handled by the user based on the first user's historical data set of government service handled and a preset time interval threshold; The user-handled government service transaction data set includes a subset of the user-handled government service transaction data of the multiple users, the user-handled government service transaction data subset of any of the users includes at least one user-handled government service transaction data of the user, any user-handled government service transaction data of the user includes identification data of a first government service handled by the user and identification data of a second government service handled by the user, the handling time of the first government service is before the handling time of the second government service, and the handling time interval between the first government service and the second government service is less than the preset time interval threshold; Based on the data set of government service affairs handled by the user and a preset minimum confidence threshold, performing correlation analysis between government services to obtain the data set of correlation relationship of government services; The confidence level corresponding to the associated government service is greater than the preset minimum confidence level threshold; The determining, based on the first user's historical government service data set and a preset time interval threshold, a user's government service transaction data set includes: Determining, based on the first user historical government service processing data set, processing times of multiple government services processed by the multiple users; Based on the processing times of the multiple government services that have been processed by the multiple users, the multiple government services that have been processed by the multiple users are sorted in the order of the processing times to obtain sorting results corresponding to the multiple users; the sorting result corresponding to any of the users includes the multiple government services that have been processed by the user sorted in the order of the processing times; Based on the sorting results corresponding to the multiple users and the historical government service handling data of the first users of the multiple users, a subset of the government service transaction data handled by the initial users of the multiple users is determined; any user-handled government service transaction data included in the subset of the initial user-handled government service transaction data of any of the users includes identification data of a third government service handled by the user and identification data of a fourth government service handled by the user, the handling time of the third government service is before the handling time of the fourth government service, and the third government service and the fourth government service are two adjacent handled government services in the sorting results corresponding to the user; Based on the subset of the initial user government service transaction data of the multiple users and the processing times of the multiple government services that have been processed by the multiple users, determine the minimum processing time intervals corresponding to the multiple users respectively; the minimum processing time interval corresponding to any of the users is the smallest processing time interval among the processing time intervals corresponding to the government service transaction data of each user in the subset of the initial user government service transaction data of the user, and the processing time interval corresponding to the government service transaction data of any of the users is determined based on the processing times of two government services represented by the government service transaction data of the user; Based on a preset time interval threshold and the minimum processing time interval corresponding to the multiple users, a subset of the initial user government service transaction data of the multiple users is screened to obtain a subset of the user government service transaction data of the multiple users; the standard processing time interval between the first government service and the second government service is less than the preset time interval threshold, and the standard processing time interval between the first government service and the second government service is the difference between the processing time interval between the first government service and the second government service and the minimum processing time interval corresponding to the user.

2. The government service recommendation method according to claim 1, characterized in that: The process of performing correlation analysis between government services based on the government service transaction data set handled by the user and a preset minimum confidence threshold to obtain the government service correlation data set includes: Removing the user-handled government service transaction data whose occurrence frequency is less than a preset occurrence frequency threshold from the user-handled government service transaction data set, to obtain a user-handled government service transaction data set after removal; the occurrence frequency of any user-handled government service transaction data included in the user-handled government service transaction data set after removal is greater than or equal to the preset occurrence frequency threshold; Based on the removed user-handled government service transaction data set and a preset minimum confidence threshold, an association relationship analysis is performed between government services to obtain the government service association relationship data set.

3. The government service recommendation method according to claim 2, characterized in that: The process of performing correlation analysis between government services based on the removed data set of government service transactions handled by users and a preset minimum confidence threshold to obtain the government service correlation data set includes: Based on the removed data set of government service affairs handled by users, a preset minimum confidence threshold and a preset minimum support threshold, performing correlation analysis between government services to obtain the government service correlation data set; Among them, the support degree corresponding to the related government service is greater than the preset minimum support degree threshold; the support degree corresponding to the related government service is used to characterize the probability that the same user handles the government service and the related government service.

4. The government service recommendation method according to any one of claims 1 to 3, characterized in that: The method further comprises: Acquire historical government service data of the target user; the historical government service data includes identification data of multiple historical government services that the target user has handled, and the handling time of each of the historical government services; Based on the processing time of each of the historical government services, constructing the identification data of the plurality of historical government services into time series data; Perform periodic analysis on the time series data to obtain the processing cycle of government services; Iteratively training a seasonal difference autoregressive moving average model based on the processing cycle and the time series data; Predict future government services based on the iteratively trained seasonal difference autoregressive moving average model; The future government service is recommended to the target user.

5. The government service recommendation method according to any one of claims 1 to 3, characterized in that: The method further comprises: 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 includes association rule data subsets corresponding to a plurality of user characteristic data, any of the association rule data subsets includes at least one association rule data; the association rule data corresponding to any of the user characteristic data includes identification data of a centrally handled government service, and a centrally handled time of the centrally handled government service; Based on the target association rule data subset, determining at least one government service that the target user centrally handles, and a target centralized handling time for each government service that the target user centrally handles; Based on the target centralized processing time, the recommended time for each government service that the target users centrally handle is determined.

6. A government service recommendation device, characterized in that: include: A service determination module is used to determine the target government service that the target user has finally handled; A data determination module, used to determine the target government service association relationship data corresponding to the target government service from the government service association relationship data set; The government service association relationship data set includes government service association relationship data corresponding to a plurality of government services, and the government service association relationship data corresponding to any of the government services includes association relationship data corresponding to at least one associated government service associated with the government service; The association relationship data corresponding to any of the related government services include identification data of the related government service and the confidence level corresponding to the related government service; the confidence level corresponding to the related government service is used to characterize the probability that the same user handles the related government service after handling the government service; A confidence determination module, used to determine at least one target-associated government service associated with the target government service and the confidence corresponding to each of the target-associated government services based on the target government service association relationship data; An order determination module, configured to determine at least one to-be-recommended government service from the at least one target-related government service based on the confidence level corresponding to each of the target-related government services, and determine a recommendation order for the at least one to-be-recommended government service; The government service association relationship dataset is determined based on the following method: Acquire a data set of historical government service processing by a first user; the data set of historical government service processing by a first user includes historical government service processing data of a plurality of users by the first user, and the historical government service processing data of any of the users includes identification data of a plurality of government services processed by the user, and the processing time of each of the government services processed; Determine a data set of government service transactions handled by the user based on the first user's historical data set of government service handled and a preset time interval threshold; The user-handled government service transaction data set includes a subset of the user-handled government service transaction data of the multiple users, the user-handled government service transaction data subset of any of the users includes at least one user-handled government service transaction data of the user, any user-handled government service transaction data of the user includes identification data of a first government service handled by the user and identification data of a second government service handled by the user, the handling time of the first government service is before the handling time of the second government service, and the handling time interval between the first government service and the second government service is less than the preset time interval threshold; Based on the data set of government service affairs handled by the user and a preset minimum confidence threshold, performing correlation analysis between government services to obtain the data set of correlation relationship of government services; The confidence level corresponding to the associated government service is greater than the preset minimum confidence level threshold; The determining, based on the first user's historical government service data set and a preset time interval threshold, a user's government service transaction data set includes: Determining, based on the first user historical government service processing data set, processing times of multiple government services processed by the multiple users; Based on the processing times of the multiple government services that have been processed by the multiple users, the multiple government services that have been processed by the multiple users are sorted in the order of the processing times to obtain sorting results corresponding to the multiple users; the sorting result corresponding to any of the users includes the multiple government services that have been processed by the user sorted in the order of the processing times; Based on the sorting results corresponding to the multiple users and the historical government service handling data of the first users of the multiple users, a subset of the government service transaction data handled by the initial users of the multiple users is determined; any user-handled government service transaction data included in the subset of the initial user-handled government service transaction data of any of the users includes identification data of a third government service handled by the user and identification data of a fourth government service handled by the user, the handling time of the third government service is before the handling time of the fourth government service, and the third government service and the fourth government service are two adjacent handled government services in the sorting results corresponding to the user; Based on the subset of the initial user government service transaction data of the multiple users and the processing times of the multiple government services that have been processed by the multiple users, determine the minimum processing time intervals corresponding to the multiple users respectively; the minimum processing time interval corresponding to any of the users is the smallest processing time interval among the processing time intervals corresponding to the government service transaction data of each user in the subset of the initial user government service transaction data of the user, and the processing time interval corresponding to the government service transaction data of any of the users is determined based on the processing times of two government services represented by the government service transaction data of the user; Based on a preset time interval threshold and the minimum processing time interval corresponding to the multiple users, a subset of the initial user government service transaction data of the multiple users is screened to obtain a subset of the user government service transaction data of the multiple users; the standard processing time interval between the first government service and the second government service is less than the preset time interval threshold, and the standard processing time interval between the first government service and the second government service is the difference between the processing time interval between the first government service and the second government service and the minimum processing time interval corresponding to the user.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the government service recommendation method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the government service recommendation method as described in any one of claims 1 to 5.