Method and device for processing government affairs

Abstract

The embodiments of the present application provide a method and apparatus for processing government affairs, which relate to machine learning in the field of artificial intelligence technology. The method for processing government affairs in the embodiments of the present application includes: obtaining multiple enterprise attribute information of an enterprise, and the item name information of various government affairs corresponding to the enterprise; generating enterprise features based on the multiple enterprise attribute information of the enterprise, and generating government affairs item features based on the item name information of various government affairs; performing feature fusion processing on the government affairs item features and the enterprise features to generate a fused feature vector; based on the fused feature vector, predicting the handling frequency of various government affairs of the enterprise. The technical solution of the embodiments of the present application improves the accuracy of predicting the handling of government affairs by enterprises, making it convenient for enterprises to quickly find government affairs that are suitable for handling.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a method and apparatus for processing government affairs. Background Art

[0002] With the development of Internet technology, the government affairs that enterprises need to handle can be handled online through applications specifically for handling government affairs. Compared with offline manual handling methods, online handling through applications can effectively improve service efficiency.

[0003] To facilitate the handling of government affairs by businesses, related technologies often employ applications that perform simple data analysis on past government affairs handled by businesses, thereby predicting the likelihood of businesses handling similar affairs based on these past affairs. However, these methods fail to account for the varying needs of businesses of varying nature for the affairs they handle, resulting in low prediction accuracy. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for processing government affairs, which can solve the technical problem of low accuracy in predicting government affairs that enterprises need to handle in related technologies.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of an embodiment of the present application, a method for handling government affairs is provided, including: obtaining multiple enterprise attribute information of an enterprise, and item name information of various government affairs corresponding to the enterprise; generating enterprise characteristics based on the multiple enterprise attribute information of the enterprise, and generating government affairs item characteristics based on the item name information of various government affairs; performing feature fusion processing on the government affairs item characteristics and the enterprise characteristics to generate a fused feature vector; and predicting the handling frequency of various government affairs of the enterprise based on the fused feature vector.

[0007] According to one aspect of an embodiment of the present application, a device for processing government affairs is provided, including: a first acquisition unit, used to acquire multiple enterprise attribute information of an enterprise, and item name information of various government affairs corresponding to the enterprise; a generation unit, used to generate enterprise characteristics based on the multiple enterprise attribute information of the enterprise, and generate government affairs item characteristics based on the item name information of various government affairs; a fusion unit, used to perform feature fusion processing on the government affairs item characteristics and the enterprise characteristics to generate a fused feature vector; and a prediction unit, used to predict the handling frequency of various government affairs of the enterprise based on the fused feature vector.

[0008] In some embodiments of the present application, based on the aforementioned scheme, the generation unit is configured as: a first extraction sub-unit, used to extract the features of multiple enterprise attribute information of the enterprise respectively, and obtain the features corresponding to the multiple enterprise attribute information; a first generation sub-unit, used to perform full connection processing on the features corresponding to the multiple enterprise attribute information to generate enterprise features.

[0009] In some embodiments of the present application, based on the aforementioned scheme, the generation unit is configured as: a second extraction sub-unit, used to perform feature extraction on the item name information of each type of government affairs, and obtain item name features corresponding to each type of government affairs; a second generation sub-unit, used to perform full connection processing on the item name features corresponding to each type of government affairs, and generate government affairs item features.

[0010] In some embodiments of the present application, based on the aforementioned scheme, the government affairs processing device further includes: a recommendation unit, which is used to determine the pending government affairs recommended to the enterprise based on the predicted handling frequency of various types of government affairs.

[0011] In some embodiments of the present application, based on the aforementioned scheme, the execution unit is configured to: sort various types of government affairs in order from high to low according to the predicted handling frequency of each type of government affairs, and generate a ranked list of government affairs; select a predetermined number of government affairs ranked at the top from the ranked list of government affairs as pending government affairs recommended to the enterprise.

[0012] In some embodiments of the present application, based on the aforementioned scheme, the execution unit is configured to: obtain the historical handling records of the enterprise for government affairs; based on the historical handling records, determine the government affairs that the enterprise has not handled as alternative government affairs; based on the predicted handling frequency of various types of government affairs, determine the predicted handling frequency for the alternative government affairs; based on the predicted handling frequency for the alternative government affairs, determine the pending government affairs to be recommended to the enterprise.

[0013] In some embodiments of the present application, based on the aforementioned scheme, the device for processing government affairs further includes: a recommendation unit for recommending a recommendation message containing pending government affairs to the enterprise based on the pending government affairs recommended to the enterprise; and an update unit for updating the pending government affairs recommended to the enterprise based on the predicted handling frequency of various types of government affairs if no handling record of the pending government affairs by the enterprise is detected within a preset time period after recommending the recommendation message.

[0014] In some embodiments of the present application, based on the aforementioned scheme, a pre-trained machine learning model is used to generate the enterprise characteristics, the government affairs characteristics, the fused feature vector, and predict the handling frequency of various government affairs of the enterprise.

[0015] In some embodiments of the present application, based on the aforementioned scheme, the device for processing government affairs further includes: a second acquisition unit, used to acquire training set sample data for training the machine learning model to be trained, the sample data in the training set sample data including multiple enterprise attribute information of the sample enterprise, the item name information of the sample government affairs, and the handling frequency of the sample enterprise for the sample government affairs; a training unit, used to train the machine learning model to be trained using the training set sample data to obtain the pre-trained machine learning model.

[0016] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for processing government affairs as described in the above embodiment is implemented.

[0017] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method for processing government affairs as described in the above embodiments.

[0018] In the technical solutions provided in some embodiments of the present application, enterprise characteristics can reflect the characteristic information of different enterprises, and government affairs characteristics can reflect the characteristic information of different government affairs. A fused feature vector is generated based on the enterprise characteristics and the government affairs characteristics, and the handling frequency of various government affairs of the enterprise is predicted based on the fused feature vector. This can effectively take into account the differences in needs of enterprises of different natures when handling various government affairs, and then recommend government affairs with a high degree of relevance to their business to the enterprises, thereby improving the accuracy of predicting the government affairs that the enterprises need to handle, and facilitating the enterprises to quickly find suitable government affairs.

[0019] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, explaining the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0021] Figure 1 A schematic diagram shows an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

[0022] Figure 2 A flowchart of a method for handling government affairs according to an embodiment of the present application is shown.

[0023] Figure 3 The flowchart for generating enterprise characteristics based on multiple enterprise attribute information of the enterprise is schematically shown.

[0024] Figure 4 The flowchart for generating government affairs features based on the name information of various government affairs is schematically shown.

[0025] Figure 5 The flowchart for training the machine learning model to be trained is schematically shown.

[0026] Figure 6 The flowchart schematically shows the process of determining the pending government affairs recommended to enterprises based on the predicted handling frequency of various government affairs.

[0027] Figure 7 The flowchart schematically shows the process of determining the pending government affairs recommended to enterprises based on the predicted handling frequency of various government affairs.

[0028] Figure 8 A flowchart of a method for handling government affairs according to an embodiment of the present application is shown.

[0029] Figure 9 A block diagram of a device for processing government affairs according to an embodiment of the present application is shown.

[0030] Figure 10 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0032] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0035] Machine learning (ML) is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0036] The solution provided in the embodiment of the present application involves technologies such as machine learning. Enterprise characteristics can reflect the characteristic information of different enterprises, and government affairs characteristics can reflect the characteristic information of different government affairs. A fused feature vector is generated based on the enterprise characteristics and the government affairs characteristics, and the handling frequency of various government affairs of the enterprise is predicted based on the fused feature vector. This can effectively take into account the differences in needs of enterprises of different natures when handling various government affairs, and then recommend government affairs with a high degree of relevance to their business to the enterprises, thereby improving the accuracy of predicting the government affairs that the enterprises need to handle, and facilitating enterprises to quickly find suitable government affairs.

[0037] Figure 1 A schematic diagram shows an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

[0038] like Figure 1 As shown, the system architecture may include a client 101, a network 102, and a server 103. The client 101 and the server 103 are connected via the network 102 and perform data exchange based on the network 102. The network may include various connection types, such as wired communication links, wireless communication links, etc.

[0039] It should be understood that Figure 1 The number of clients 101, networks 102 and servers 103 in FIG. 1 is merely illustrative and any number of clients 101, networks 102 and servers 103 may be provided according to implementation requirements.

[0040] The server 103 obtains multiple enterprise attribute information of the enterprise, and obtains the item name information of various government affairs corresponding to the enterprise, wherein the multiple enterprise attribute information of the enterprise can be obtained from the client 101; the server 103 generates enterprise features based on the multiple enterprise attribute information of the enterprise, and generates government affairs item features based on the item name information of various government affairs; the server 103 performs feature fusion processing on the government affairs item features and the enterprise features to generate a fused feature vector, and predicts the handling frequency of various government affairs of the enterprise based on the fused feature vector.

[0041] From the above, it can be seen that enterprise characteristics can reflect the characteristic information of different enterprises, and government affairs characteristics can reflect the characteristic information of different government affairs. Based on the enterprise characteristics and government affairs characteristics, a fused feature vector is generated, and the handling frequency of various government affairs of the enterprise is predicted based on the fused feature vector. This can effectively take into account the differences in needs of enterprises of different natures when handling various government affairs, and then recommend government affairs with a high degree of relevance to their business to the enterprises, thereby improving the accuracy of predicting the government affairs that enterprises need to handle, and facilitating enterprises to quickly find suitable government affairs.

[0042] It should be noted that the method for processing government affairs provided in the embodiments of this application is generally executed by server 103. Accordingly, the device for processing government affairs is generally located in server 103. However, in other embodiments of this application, client 101 may also have similar functions to server 103, thereby implementing the method for processing government affairs provided in the embodiments of this application. The following details the implementation of the technical solution of the embodiments of this application.

[0043] Figure 2 A flowchart of a method for processing government affairs according to an embodiment of the present application is shown. The method for processing government affairs can be executed by a server, which can be Figure 1 Refer to the server shown in . Figure 2 As shown, the method for handling government affairs includes at least steps S210 to S240, which are described in detail below.

[0044] In step S210, a plurality of enterprise attribute information of the enterprise and item name information of various government affairs corresponding to the enterprise are obtained.

[0045] In one embodiment of the present application, enterprise attribute information is a type of attribute information that reflects the characteristics of the enterprise. It may include the type of enterprise, business scope, industry type, registered capital, etc. The item name information of various government affairs corresponding to the enterprise refers to the specific names of various government service items that the enterprise can handle, such as business license processing, enterprise address change, and commercial housing pre-sale permit processing.

[0046] The enterprise attribute information of an enterprise is the information that the enterprise needs to provide when registering. This information can be obtained from a database that stores various attribute information of the enterprise based on the enterprise ID of the enterprise.

[0047] The item name information of various government affairs corresponding to the enterprise can be uploaded to the server's database in advance by manual operation, and the server can directly obtain the item name information of various government affairs from the database.

[0048] In step S220, enterprise characteristics are generated based on multiple enterprise attribute information of the enterprise, and government affairs characteristics are generated based on the matter name information of various government affairs.

[0049] In one embodiment of the present application, enterprise features are feature information generated based on multiple enterprise attribute information. Enterprise features can reflect the characteristics of the enterprise and can be a feature vector. Government affairs features are feature information generated based on the name information of various government affairs. Government affairs features can reflect the characteristics of various government affairs that an enterprise can handle and can also be a feature vector.

[0050] In one embodiment of the present application, Figure 3 As shown, a flowchart of generating enterprise characteristics based on multiple enterprise attribute information of an enterprise is schematically shown, which specifically includes the following steps S310 to S320, which are described in detail below.

[0051] In step S310 , features of multiple pieces of enterprise attribute information are extracted respectively to obtain features corresponding to the multiple pieces of enterprise attribute information.

[0052] In one embodiment of the present application, when generating enterprise features based on multiple enterprise attribute information, features of each piece of enterprise attribute information can be extracted to obtain features corresponding to each piece of enterprise attribute information. When extracting features from multiple pieces of enterprise attribute information, the enterprise attribute information can be converted into a digital matrix, and the digital matrix generated based on the enterprise attribute information is the feature corresponding to the enterprise attribute information.

[0053] In step S320, full connection processing is performed on the features corresponding to the plurality of enterprise attribute information to generate enterprise features.

[0054] In one embodiment of the present application, after obtaining features corresponding to multiple enterprise attribute information, a full join process can be performed on the features corresponding to the multiple enterprise attribute information to generate an enterprise feature. Specifically, performing a full join process on the features corresponding to the multiple enterprise attribute information can be performed by matrix multiplication of a digital matrix generated based on the enterprise attribute information to obtain a feature vector, which is the enterprise feature.

[0055] In one embodiment of the present application, steps S310 to S320 may be implemented by a pre-trained machine learning model, which may be a convolutional neural network (CNN) model or a deep neural network model, which is not limited here.

[0056] Optionally, the network structure within the pre-trained machine learning model may include a text convolutional network and a fully connected network, wherein the text convolutional network is used to extract the features of multiple enterprise attribute information of an enterprise respectively to obtain features corresponding to the multiple enterprise attribute information, and the fully connected network is used to perform fully connected processing on the features corresponding to the multiple enterprise attribute information to generate enterprise features.

[0057] In one embodiment of the present application, Figure 4 As shown, a flowchart of generating government affairs features based on the name information of various government affairs is schematically shown, which specifically includes the following steps S410 to S420, which are introduced in detail as follows.

[0058] In step S410, feature extraction is performed on the item name information of each type of government affairs item to obtain item name features corresponding to each type of government affairs item.

[0059] In one embodiment of the present application, when generating government item features based on the item name information of various government items, the features of the item name information of each government item can be extracted to obtain the item name features corresponding to the government item. When extracting features from the item name information of the government item, the item name information of the government item can be converted into a digital matrix. The digital matrix generated based on the item name information of the government item is the item name feature corresponding to the government item.

[0060] In step S420, the item name features corresponding to each type of government affairs item are fully connected to generate government affairs item features.

[0061] In one embodiment of the present application, after obtaining the item name features corresponding to each type of government affairs item, a full join process can be performed on the item name features corresponding to each type of government affairs item to generate a government affairs item feature. Specifically, when performing the full join process on the item name features corresponding to each type of government affairs item, a matrix multiplication process can be performed on the digital matrix corresponding to the item name features to obtain a feature vector, which is the government affairs item feature.

[0062] In one embodiment of the present application, steps S410 to S420 may be implemented by a pre-trained machine learning model, which may be a convolutional neural network (CNN) model or a deep neural network model, which is not limited here.

[0063] Optionally, the network structure within the pre-trained machine learning model may also include a text convolutional network and a fully connected network, wherein the text convolutional network is used to perform feature extraction on the item name information of various types of government affairs respectively to obtain the item name features corresponding to various types of government affairs, and the fully connected network is used to perform feature fusion processing on the government affairs item features and enterprise features to generate a fused feature vector.

[0064] In step S230, feature fusion processing is performed on the government affairs features and the enterprise features to generate a fused feature vector.

[0065] In one embodiment of the present application, after obtaining the government affairs features and enterprise features, when generating a fused feature vector based on these two features, the two feature vectors corresponding to the government affairs features and the enterprise features respectively can be multiplied to generate a new feature vector. The generated feature vector is the fused feature vector, and the fused feature vector includes the features corresponding to the government affairs features and the features corresponding to the enterprise attribute information.

[0066] In one embodiment of the present application, step S230 can be implemented by a pre-trained machine learning model, which can be a convolutional neural network (CNN) model or a deep neural network model, which is not limited here.

[0067] In step S240, based on the fused feature vector, the handling frequency of various government affairs of the enterprise is predicted.

[0068] In one embodiment of the present application, since there are differences in the likelihood of enterprises with different enterprise attribute information handling the same government affairs, and there are also differences in the likelihood of enterprises with the same enterprise attribute information handling different government affairs, the fused feature vector contains the features corresponding to the government affairs and the features corresponding to the enterprise attribute information. Therefore, the frequency of enterprises handling various government affairs can be predicted based on the fused feature vector and the correspondence between the fused feature vector and the frequency of enterprises handling various government affairs. It can be understood that the higher the handling frequency, the higher the possibility of the enterprise handling the government affairs, and the lower the handling frequency, the lower the possibility of the enterprise handling the government affairs.

[0069] In one embodiment of the present application, step S240 can be implemented by a pre-trained machine learning model, which can be a convolutional neural network (CNN) model or a deep neural network model, which is not limited here.

[0070] In one embodiment of the present application, a pre-trained machine learning model can be used to generate enterprise features, generate government affairs features, generate fused feature vectors, and predict the handling frequency of various government affairs of the enterprise.

[0071] Optionally, the generated enterprise characteristics, government affairs features, fused feature vectors and predicted handling frequencies of various government affairs of the enterprise can be achieved through a pre-trained machine learning model. The pre-trained machine learning model can achieve one or more steps of generating enterprise characteristics, government affairs features, fused feature vectors and predicting handling frequencies of various government affairs of the enterprise through different internal network structures.

[0072] In one embodiment of the present application, Figure 5 As shown, a flowchart of training a machine learning model to be trained is schematically shown, which specifically includes the following steps S510 to S50, which are described in detail as follows.

[0073] In step S510, training set sample data is obtained for training the machine learning model to be trained. The sample data in the training set sample data includes multiple enterprise attribute information of the sample enterprise, the item name information of the sample government affairs, and the handling frequency of the sample enterprise for the sample government affairs.

[0074] In one embodiment, the sample data in the training set sample data includes multiple enterprise attribute information of sample enterprises, item name information of sample government affairs, and the handling frequency of the sample enterprises for the sample government affairs. The sample enterprises refer to the set of enterprises that have handled the sample government affairs, the sample government affairs are all government affairs that the sample enterprises can handle, and the handling frequency of the sample enterprises for the sample government affairs is the number of times each sample enterprise has historically handled each sample government affairs item.

[0075] In step S520, the machine learning model to be trained is trained using the training set sample data to obtain a pre-trained machine learning model.

[0076] In one embodiment, training set sample data is input into a machine learning model, and the machine learning model to be trained is trained using the training set sample data to obtain a trained machine learning model. The process of training the machine learning model is to adjust various coefficients in the network structure corresponding to the machine learning model so that, for multiple enterprise attribute information of the input sample enterprises, the various coefficients in the network structure corresponding to the machine learning model are calculated, and the output result is the frequency of the sample enterprises handling sample government affairs.

[0077] From the above, it can be seen that enterprise characteristics can reflect the characteristic information of different enterprises, and government affairs characteristics can reflect the characteristic information of different government affairs. Based on the enterprise characteristics and government affairs characteristics, a fused feature vector is generated, and the handling frequency of various government affairs of the enterprise is predicted based on the fused feature vector. This can effectively take into account the differences in needs of enterprises of different natures when handling various government affairs, and then recommend government affairs with a high degree of relevance to their business to the enterprises, thereby improving the accuracy of predicting the government affairs that enterprises need to handle, and facilitating enterprises to quickly find suitable government affairs.

[0078] In one embodiment of the present application, the method for handling government affairs in this embodiment may further include the steps of: determining pending government affairs to be recommended to the enterprise based on the predicted handling frequency of various types of government affairs.

[0079] In this embodiment, the predicted handling frequencies of various government affairs are obtained. Since the handling frequencies reflect the likelihood that an enterprise will need to handle various government affairs, a high handling frequency indicates that the enterprise is more likely to handle such government affairs, while a low handling frequency indicates that the enterprise is less likely to handle such government affairs. Therefore, based on the predicted handling frequencies of various government affairs, government affairs with high handling frequencies can be recommended to enterprises as pending government affairs.

[0080] Optionally, government affairs matters with a handling frequency higher than a predetermined frequency threshold may be selected as pending government affairs matters to be recommended to the enterprise.

[0081] By recommending government affairs matters with high handling frequency as pending government affairs matters to be handled to enterprises, the government affairs matters recommended to enterprises are government affairs matters with a higher possibility of being handled, thereby improving the accuracy of recommending pending government affairs matters to enterprises.

[0082] In one embodiment of the present application, Figure 6 As shown, a flowchart for determining the pending government affairs recommended to enterprises based on the predicted handling frequency of various government affairs is schematically shown, which specifically includes the following steps S610 to S620, which are described in detail below.

[0083] In step S610, various government affairs matters are sorted in descending order according to the predicted handling frequencies of the various government affairs matters, and a sorted list of government affairs matters is generated.

[0084] In one embodiment of the present application, after obtaining the predicted handling frequencies of various types of government affairs, in order to determine the government affairs to be handled that are recommended to the enterprise based on the predicted handling frequencies of various types of government affairs, the various types of government affairs can be sorted in descending order according to the predicted handling frequencies of the various types of government affairs to generate a ranked list of government affairs. It is understood that in the generated ranked list of government affairs, government affairs with higher handling frequencies are arranged first, and government affairs with lower handling frequencies are arranged last. Two or more government affairs with the same handling frequencies can be randomly sorted.

[0085] In step S620, a predetermined number of government affairs items ranked at the top are selected from the government affairs item ranking list as pending government affairs items recommended to the enterprise.

[0086] In one embodiment of the present application, after obtaining a ranked list of government affairs, when determining pending government affairs to be recommended to an enterprise, a predetermined number of government affairs ranked at the top of the ranked list may be selected as pending government affairs to be recommended to the enterprise. For example, the top five government affairs ranked at the top of the ranked list may be selected as pending government affairs to be recommended to the enterprise.

[0087] Optionally, the predetermined number is a preset value preset according to demand, and it can be set to be consistent with the number of government affairs recommendation columns for recommending government affairs to be handled by the client.

[0088] Figure 6 In the scheme of the illustrated embodiment, various types of government affairs are sorted in order from high to low according to the predicted handling frequency of each type of government affairs, a ranked list of government affairs is generated, and a predetermined number of government affairs items ranked at the top are selected from the ranked list of government affairs as pending government affairs items recommended to enterprises. This ensures that the pending government affairs items recommended to enterprises are all government affairs items that are highly likely to be handled by the enterprises, effectively improving the accuracy of recommending pending government affairs items to enterprises.

[0089] In one embodiment of the present application, Figure 7 As shown, a flowchart for determining the pending government affairs recommended to enterprises based on the predicted handling frequency of various government affairs is schematically shown, which specifically includes the following steps S710 to S740, which are described in detail below.

[0090] In step S710, the historical records of the enterprise's handling of government affairs are obtained.

[0091] In one embodiment of the present application, in order to determine the government affairs that the enterprise has not handled, the enterprise's historical handling records for government affairs can be obtained to determine the government affairs that the enterprise has handled, and then determine the government affairs that the enterprise has not handled. The enterprise's historical handling records for government affairs are record information after the enterprise has handled government affairs in the past. When the enterprise handles a certain government affairs once, it will generate a historical handling record. The historical handling record can include the time of successful handling and the name of the government affairs. It is understandable that the historical handling records obtained can refer to historical handling records within a specific time period, for example, historical handling records within one year from the current time, and of course it can also be all historical handling records of the enterprise, which is not specifically limited here.

[0092] In step S720, based on the historical processing records, government affairs that the enterprise has not handled are determined as alternative government affairs.

[0093] In one embodiment of the present application, after obtaining the historical handling records of government affairs of an enterprise, the government affairs that the enterprise has handled can be determined based on the matter name information of the government affairs contained in the historical handling records. After filtering out the government affairs that the enterprise has handled from various types of government affairs, the government affairs that the enterprise has not handled can be obtained. All government affairs that the enterprise has not handled can be regarded as alternative government affairs, and the alternative government affairs can be recommended as government affairs that can be handled.

[0094] In step S730, based on the predicted handling frequencies of various government affairs, the predicted handling frequencies for the candidate government affairs are determined.

[0095] In one embodiment of the present application, after obtaining the candidate government affairs, the predicted handling frequency of the candidate government affairs can be determined based on the predicted handling frequency of various types of government affairs.

[0096] In step S740, based on the predicted handling frequency of the candidate government affairs, the pending government affairs to be recommended to the enterprise are determined.

[0097] In one embodiment of the present application, when determining the predicted handling frequency of alternative government affairs matters, the alternative government affairs matters can be sorted in descending order according to the predicted handling frequency of the alternative government affairs matters, and a ranked list of alternative government affairs matters can be generated. A predetermined number of government affairs matters ranked at the top of the ranked list of alternative government affairs matters can be selected as pending government affairs matters recommended to the enterprise.

[0098] In one embodiment of the present application, alternative government affairs matters with a handling frequency higher than a predetermined frequency threshold may also be selected as pending government affairs matters to be recommended to the enterprise.

[0099] Figure 7 In the scheme of the illustrated embodiment, government affairs that have not been handled by the enterprise are determined as alternative government affairs based on historical handling records, and the pending government affairs recommended to the enterprise are determined based on the predicted handling frequency of the alternative government affairs, so that the pending government affairs recommended to the enterprise are government affairs that are highly likely to be handled by the enterprise and have not been handled by the enterprise. Compared with directly using government affairs that are highly likely to be handled by the enterprise as pending government affairs recommended to the enterprise, this method makes the pending government affairs recommended to the enterprise be government affairs that have not been handled by the enterprise, and achieves the recommendation of government affairs that have not been handled and have a high possibility of being handled to the enterprise, which can further improve the accuracy of recommending pending government affairs to the enterprise, thereby increasing the possibility of the enterprise handling government affairs.

[0100] In one embodiment of the present application, Figure 8 A flowchart showing a method for processing government affairs according to an embodiment of the present application is shown. Figure 8 As shown, the method for handling government affairs further includes steps S810 to S820, which are described in detail as follows.

[0101] In step S810, based on the pending government affairs recommended to the enterprise, a recommendation message containing the pending government affairs is recommended to the enterprise.

[0102] In one embodiment of the present application, after determining the pending government affairs items recommended to the enterprise, a recommendation message containing the pending government affairs items can be recommended to the enterprise based on the pending government affairs items recommended to the enterprise. Specifically, a recommendation message containing each pending government affairs item recommended to the enterprise can be generated, and the generated recommendation message can be recommended to the enterprise. For example, the server can send the recommendation message to the client, so that the client displays the recommendation message.

[0103] In step S820, if no record of the enterprise's handling of pending government affairs is detected within a preset time period after the recommendation message is sent, the pending government affairs recommended to the enterprise are updated based on the predicted handling frequency of various types of government affairs.

[0104] In one embodiment of the present application, after receiving a recommendation message, an enterprise will process the pending government affairs items listed in the recommendation message if there is a need for processing them. When the enterprise completes the processing of the pending government affairs items, a processing record for the pending government affairs items will be generated. If the enterprise does not process the government affairs items listed in the recommendation message within a period of time after receiving the recommendation message, it is likely that the enterprise does not need to process the pending government affairs items listed in the recommendation message, and therefore no processing record for the pending government affairs items will be generated.

[0105] In response to the above situation, in order to improve the accuracy of the recommended messages sent to enterprises, the enterprise's handling records for pending government affairs can be checked within a preset time period after the recommended message is sent. If no handling records for the pending government affairs are detected within the preset time period after the recommended message is sent, it indicates that the enterprise is likely not to need to handle the pending government affairs listed in the recommended message. The preset time period can be manually set as needed, such as 7 days. By not detecting the enterprise's handling records for pending government affairs within the preset time period after the recommended message is sent, the pending government affairs recommended to the enterprise can be updated based on the predicted handling frequency of various types of government affairs, avoiding the continued recommendation of pending government affairs that the enterprise does not need to handle.

[0106] Optionally, when updating the recommended pending government affairs items for enterprises based on the predicted handling frequencies of various government affairs items, some or all of the pending government affairs items previously pushed can be replaced. It is understood that the government affairs items used for replacement are those that are ranked higher in the government affairs ranking list or have a frequency higher than a predetermined threshold.

[0107] Figure 8 In the scheme of the illustrated embodiment, after recommending a recommendation message containing pending government affairs to an enterprise, the enterprise's handling record of the pending government affairs can be detected to determine whether the enterprise has handled the recommended government affairs. By using the above method, if the government affairs recommended to the enterprise last time is not the government affairs that the enterprise needs to handle, it is possible to avoid continuing to recommend government affairs that do not need to be handled to the enterprise, which can effectively improve the accuracy of recommending government affairs to the enterprise and avoid causing a bad recommendation experience for the enterprise.

[0108] The following describes an embodiment of the device of the present application, which can be used to execute the method for processing government affairs in the above-mentioned embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for processing government affairs in the above-mentioned embodiment of the present application.

[0109] Figure 9 A block diagram of a device for processing government affairs according to an embodiment of the present application is shown.

[0110] Reference Figure 9As shown, according to an embodiment of the present application, a device 900 for processing government affairs includes: a first acquisition unit 910, a generation unit 920, a fusion unit 930, and a prediction unit 940. The first acquisition unit 910 is configured to acquire multiple enterprise attribute information of an enterprise and item name information of various government affairs corresponding to the enterprise; the generation unit 920 is configured to generate enterprise features based on the multiple enterprise attribute information of the enterprise, and to generate government affairs item features based on the item name information of various government affairs; the fusion unit 930 is configured to perform feature fusion processing on the government affairs item features and the enterprise features to generate a fused feature vector; and the prediction unit 940 is configured to predict the handling frequency of various government affairs of the enterprise based on the fused feature vector.

[0111] In some embodiments of the present application, based on the aforementioned scheme, the generation unit 920 is configured as: a first extraction sub-unit, used to extract the features of multiple enterprise attribute information of the enterprise respectively, and obtain the features corresponding to the multiple enterprise attribute information; a first generation sub-unit, used to perform full connection processing on the features corresponding to the multiple enterprise attribute information to generate enterprise features.

[0112] In some embodiments of the present application, based on the aforementioned scheme, the generation unit 920 is configured as: a second extraction sub-unit, used to perform feature extraction on the item name information of each type of government affairs, and obtain item name features corresponding to each type of government affairs; a second generation sub-unit, used to perform full connection processing on the item name features corresponding to each type of government affairs, and generate government affairs features.

[0113] In some embodiments of the present application, the apparatus for processing government affairs further includes: an execution unit for determining pending government affairs to be recommended to the enterprise based on the predicted handling frequency of various types of government affairs.

[0114] In some embodiments of the present application, the execution unit is configured to: sort various types of government affairs in order from high to low according to the predicted handling frequency of each type of government affairs, and generate a ranked list of government affairs; select a predetermined number of government affairs ranked at the top from the ranked list of government affairs as pending government affairs recommended to the enterprise.

[0115] In some embodiments of the present application, based on the aforementioned scheme, the execution unit is configured to: obtain the historical handling records of the enterprise for government affairs; based on the historical handling records, determine the government affairs that the enterprise has not handled as alternative government affairs; based on the predicted handling frequency of various types of government affairs, determine the predicted handling frequency for the alternative government affairs; based on the predicted handling frequency for the alternative government affairs, determine the pending government affairs to be recommended to the enterprise.

[0116] In some embodiments of the present application, based on the aforementioned scheme, the device for processing government affairs further includes: a recommendation unit for recommending a recommendation message containing pending government affairs to the enterprise based on the pending government affairs recommended to the enterprise; and an update unit for updating the pending government affairs recommended to the enterprise based on the predicted handling frequency of various types of government affairs if no handling record of the pending government affairs by the enterprise is detected within a preset time period after recommending the recommendation message.

[0117] In some embodiments of the present application, based on the aforementioned scheme, a pre-trained machine learning model is used to generate the enterprise characteristics, the government affairs characteristics, the fused feature vector, and predict the handling frequency of various government affairs of the enterprise.

[0118] In some embodiments of the present application, based on the aforementioned scheme, the device for processing government affairs further includes: a second acquisition unit, used to acquire training set sample data for training the machine learning model to be trained, the sample data in the training set sample data including multiple enterprise attribute information of the sample enterprise, the item name information of the sample government affairs, and the handling frequency of the sample enterprise for the sample government affairs; a training unit, used to train the machine learning model to be trained using the training set sample data to obtain the pre-trained machine learning model.

[0119] Figure 10 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0120] It should be noted that Figure 10 The computer system 1000 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0121] like Figure 10As shown, the computer system 1010 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1008 into the random access memory (RAM) 1003, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 1003. The CPU 1001, ROM 1002 and RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0122] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. Removable media 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1010 as needed, so that computer programs read therefrom can be installed into the storage section 1008 as needed.

[0123] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1009, and / or installed from a removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the various functions defined in the system of the present application are executed.

[0124] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0127] As another aspect, the present application further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device implements the method described in the above embodiments.

[0128] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0129] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0130] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0131] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for handling government affairs, characterized in that: include: Obtaining multiple enterprise attribute information of an enterprise, as well as the name information of various government affairs corresponding to the enterprise; Using different text convolutional networks in the pre-trained machine learning model, features of multiple enterprise attribute information of the enterprise are extracted respectively to obtain features corresponding to the multiple enterprise attribute information. Feature extraction is also performed on the item name information of various government affairs items to obtain item name features corresponding to the various government affairs items. Through different fully connected networks in the pre-trained machine learning model, fully connected processing is performed on the features corresponding to the multiple enterprise attribute information to generate enterprise features, fully connected processing is performed on the item name features corresponding to various government items to generate government item features, and feature fusion processing is performed on the government item features and the enterprise features to generate a fused feature vector; the government item features are used to reflect the characteristic information of the various government items that the enterprise is qualified to handle; Using the pre-trained machine learning model, based on the fused feature vectors, the frequency of handling various government affairs of the enterprise is predicted; Based on the predicted handling frequency of various government affairs, determine the government affairs to be recommended to the enterprise; Based on the pending government affairs recommended to the enterprise, recommend a recommendation message containing the pending government affairs to the enterprise; If no record of the enterprise handling the pending government affairs is detected within a preset time period after the recommendation message is recommended, the pending government affairs recommended to the enterprise are updated based on the predicted handling frequency of various types of government affairs.

2. The method for handling government affairs according to claim 1, characterized in that: The process of determining the pending government affairs to be recommended to the enterprise based on the predicted handling frequency of various government affairs includes: Sort various government affairs matters in descending order according to the predicted handling frequencies of the various government affairs matters, and generate a ranked list of government affairs matters; A predetermined number of government affairs items ranked at the top are selected from the government affairs item ranking list as pending government affairs items recommended to the enterprise.

3. The method for handling government affairs according to claim 1, characterized in that: The process of determining the pending government affairs to be recommended to the enterprise based on the predicted handling frequency of various government affairs includes: Obtain the historical records of the enterprise in handling government affairs; Based on the historical handling records, determining government affairs that the enterprise has not handled as candidate government affairs; Determining a predicted handling frequency for the candidate government affairs items based on the predicted handling frequencies of various government affairs items; Based on the predicted handling frequency of the alternative government affairs, determine the pending government affairs to be recommended to the enterprise.

4. The method for handling government affairs according to claim 1, characterized in that: The method for handling government affairs also includes: Obtaining training set sample data for training a machine learning model to be trained, wherein the sample data in the training set sample data includes multiple enterprise attribute information of a sample enterprise, item name information of a sample government item, and the handling frequency of the sample enterprise for the sample government item; The machine learning model to be trained is trained using the training set sample data to obtain the pre-trained machine learning model.

5. A device for processing government affairs, characterized in that: include: The first acquisition unit is used to acquire multiple enterprise attribute information of an enterprise and item name information of various government affairs corresponding to the enterprise; a generating unit configured to extract features of multiple enterprise attribute information of the enterprise using different text convolutional networks in a pre-trained machine learning model to obtain features corresponding to the multiple enterprise attribute information, and to extract features of item name information of various types of government affairs to obtain item name features corresponding to the various types of government affairs; Through different fully connected networks in the pre-trained machine learning model, the features corresponding to the multiple enterprise attribute information are fully connected to generate enterprise features, and the item name features corresponding to various government items are fully connected to generate government item features; the government item features are used to reflect the characteristic information of the various government items that the enterprise is qualified to handle; a fusion unit, configured to perform feature fusion processing on the government affairs feature and the enterprise feature using a fully connected network in the pre-trained machine learning model that is different from the fully connected network used to generate the enterprise feature and the fully connected network used to generate the government affairs feature, to generate a fused feature vector; A prediction unit, configured to predict the handling frequency of various government affairs of the enterprise based on the fused feature vectors using the pre-trained machine learning model; An execution unit, configured to determine the pending government affairs to be recommended to the enterprise based on the predicted handling frequencies of various government affairs; a recommendation unit, configured to recommend a recommendation message containing pending government affairs matters to the enterprise based on the pending government affairs matters recommended to the enterprise; An updating unit is used to update the pending government affairs matters recommended to the enterprise based on the predicted handling frequency of various types of government affairs matters if no handling record of the enterprise for the pending government affairs matters is detected within a preset time period after the recommendation message is recommended.

6. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 4.

7. A computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program is configured to perform the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The computer program product comprises a computer program carried on a computer-readable medium, wherein the computer program is adapted to be loaded by a processor and to execute the method according to any one of claims 1 to 4.

Images