CN115062119A

CN115062119A - Government affair event handling recommendation method and device

Info

Publication number: CN115062119A
Application number: CN202210989776.5A
Authority: CN
Inventors: 葛标; 王辉; 郭宝松; 柳进军; 张聪聪; 赵志宾; 赵祥; 孙冬雪; 张昆鹏; 王远航
Original assignee: Zhongguancun Smart City Co Ltd
Current assignee: Zhongguancun Smart City Co Ltd
Priority date: 2022-08-18
Filing date: 2022-08-18
Publication date: 2022-09-16
Anticipated expiration: 2042-08-18
Also published as: CN115062119B

Abstract

The embodiment of the disclosure discloses a government affair event handling recommendation method and device. One embodiment of the method comprises: acquiring historical government affair event data; performing part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data; performing entity identification on the marked data to determine entities in the marked data; fusing the marked data with the structured data to obtain fused data; constructing a knowledge graph based on the incidence relation among the entities in the fusion data; generating an event handling sequence corresponding to each figure entity according to the knowledge graph; training to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity, and acquiring a to-be-handled event set and current position information of a user input by the user through a terminal; and inputting the to-be-handled event set into a government event handling recommendation model to obtain a to-be-handled event sequence. The accuracy of the transaction sequence prediction is realized, and the transaction efficiency is improved.

Description

Government affair event handling recommendation method and device

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for recommending government affair event handling.

Background

Since most users are not familiar with government events, such as ID card subsidy, social security migration, etc. Currently, the consultation sequence is generally carried out by means of telephone consultation or window consultation. However, the inventors have found that when the handling order is determined in the above manner, there are often technical problems as follows:

firstly, the manually determined work handling sequence depends on experience, so the accuracy is low;

secondly, because different data sources in historical government affair event data are different, the problems of irregular event naming and the like exist, for example, the same event has a plurality of names, which is not beneficial to the training of the model;

thirdly, in the process of determining the transaction sequence of the events, only the relationship of the positions is usually considered, and other factors cannot be considered, so that some events cannot be successfully transacted due to lack of materials, and the transaction efficiency of the events is influenced.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art in this country.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose government event handling recommendation methods, apparatuses, devices, computer readable media and program products to address one or more of the technical problems noted in the background section above.

In a first aspect, some embodiments of the present disclosure provide a government event transaction recommendation method, including: acquiring historical government affair event data, wherein the historical government affair event data comprises structured data, unstructured data and semi-structured data; performing part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data; performing entity identification on the marked data to determine entities in the marked data, wherein the entities are character entities, event entities and event attribute entities; fusing the marked data with the structured data to obtain fused data; constructing a knowledge graph based on the incidence relation among the entities in the fusion data, wherein nodes in the knowledge graph represent the entities, and edges in the knowledge graph represent the incidence relation among different entities; generating an event handling sequence corresponding to each character entity according to the knowledge graph, wherein the event handling sequence is used for representing handling sequences of a plurality of events corresponding to the character entities; training to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity; acquiring a to-do event set and user current position information input by a user through a terminal; and inputting the to-be-handled event set into a government event handling recommendation model to obtain a to-be-handled event sequence.

In a second aspect, some embodiments of the present disclosure provide a government event transaction recommendation device, including: an acquisition unit configured to acquire historical government event data including structured data, unstructured data and semi-structured data; the part-of-speech tagging unit is configured to perform part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data; the entity identification unit is configured to perform entity identification on the marked data so as to determine entities in the marked data, wherein the entities are a character entity, an event entity and an event attribute entity; the fusion unit is configured to fuse the marked data and the structured data to obtain fused data; a construction unit configured to construct a knowledge graph based on an incidence relation between entities in the fusion data, nodes in the knowledge graph representing the entities, and edges in the knowledge graph representing the incidence relation between different entities; the generating unit is configured to generate an event handling sequence corresponding to each human entity according to the knowledge graph, wherein the event handling sequence is used for representing handling sequences of a plurality of events corresponding to the human entities; the training unit is configured to train to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity; the information acquisition unit is configured to acquire a to-do event set and user current position information input by a user through a terminal; and the prediction model is configured to input the to-do event set into the government event handling recommendation model to obtain the to-do event sequence.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantages: historical government affair event data are processed to generate a knowledge map, an event handling sequence is generated according to the knowledge map, a government affair event handling recommendation model is obtained through training, and a to-be-handled event sequence is generated through the government affair event handling recommendation model. Therefore, the handling sequence among the events can be obtained through the government affair event handling recommendation model, the accuracy of handling sequence prediction is improved, and the handling efficiency is improved. In addition, the knowledge graph can be used for better expressing the incidence relation between entities and between the entities and the event attribute information, so that the relation between different events can be found more easily, the generated event handling sequence is more accurate, and the trained government affair event handling recommendation model is more accurate.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

FIG. 1 is a flow diagram of some embodiments of a government event transaction recommendation method according to the present disclosure;

FIG. 2 is a schematic diagram of some embodiments of a government event transaction recommendation device according to the present disclosure;

FIG. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure;

FIG. 4 is an exemplary diagram of a knowledge-graph.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Referring to fig. 1, a flow 100 of some embodiments of a government event transaction recommendation method according to the present disclosure is shown. The government affair event handling recommendation method comprises the following steps:

step 101, obtaining historical government affair event data, wherein the historical government affair event data comprises structured data, unstructured data and semi-structured data.

In some embodiments, the executive body of the government event transaction recommendation method (e.g., the government service management platform) may first obtain historical government event data. In practice, the historical government event data may be government event data for a preset historical period of time. The government event data may be various data related to the government event including time, place, event name, required materials, and the like. The government affair event can be determined by a designated mode and can also be obtained by certain condition screening. For example, an event containing keywords such as identity documents, social security, etc. may be determined as a government event. Specifically, the identity document transaction and the social insurance transaction are both government affair times. In practice, the format of the data is different due to different sources of the data corresponding to different events, and therefore, the historical government affair event data comprises structured data, unstructured data and semi-structured data.

And 102, performing part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data.

In some embodiments, the execution subject may perform part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data. For example, the annotation can be performed by using an annotation method such as BIO and BIOSE. The data may be first participled and then labeled for each word. Using the BIO labeling method as an example, each word is labeled as "B-X", "I-X", or "O". Where "B-X" indicates that the fragment in which the word resides is of type X and that the word is at the beginning of the fragment, "I-X" indicates that the fragment in which the word resides is of type X and that the word is in the middle of the fragment, and "O" indicates that it does not belong to any type. And marking to obtain marked data. In the process, the labeling can be assisted by customizing the dictionary, so that the labeling result is more consistent with the scene requirement.

Optionally, on the basis of obtaining the labeled data, the relationship identification may be performed through the following function or an artificial neural network, that is, the labeled data is classified:

wherein the vector

Sum vector

Respectively corresponding vectors of two data in the marked data,

the standard deviation is indicated. The data can be divided by utilizing the high-dimensional linear divisible characteristic of the function, so that the classified data is obtained after the data are marked.

And 103, performing entity identification on the marked data to determine entities in the marked data, wherein the entities are character entities, event entities and event attribute entities.

In some embodiments, the entity recognition model applied to the government event scenario may be trained in advance, thereby improving the recognition rate in that scenario. For example, the solid recognition model may include algorithms such as Bi-LSTM, CRF (Conditional Random Field), and the like. Therefore, the execution subject can continuously perform entity identification on the marked data so as to determine various entities in the marked data. In the application scenario of government event handling, entities may include a human entity, an event entity, and an event attribute entity. The event attribute entity includes an event address, an event time, and the like. The event entity may be an event needing to be transacted in a government affairs service scenario, including but not limited to: certificate handling, insurance handling, and the like. The human entity may be, for example, Zhang three, Li four, etc. In addition, if necessary, entity identification may be performed on the basis of the classification data, and each entity may be determined.

And step 104, fusing the marked data with the structured data to obtain fused data, wherein the fused data comprises entity and event attribute information.

In some embodiments, the execution subject may fuse the labeled data with the structured data to obtain fused data. It can be understood that the annotated data has been identified as entities, and various entities therein have been identified. Thus, fusion with structured data is possible. The merging method may be to unify names of synonymous events, for example, the refund event and the refund event are substantially the same event, and may be collectively called a refund event.

In some embodiments, in order to solve the technical problem two described in the background section, "there are problems of irregular naming of events due to different data sources in the historical government event data, for example, the same event has multiple names, which is not beneficial to the training of models", as an inventive point of the present disclosure, the similarity between two texts can be determined by the following formula

：

Where S, T denotes two pieces of text,

indicating the number of elements in the intersection of two texts, i.e. the number of words that overlap,

and

respectively representing the number of words of the text S and T,

the number of elements in the union of two texts is represented, i.e. the number of non-repeating words contained by the two texts.

For example, S represents a "refund event", T represents a "refund event",

and

is a preset coefficient, for example, each 0.5, and the similarity between S, T is 0.675.

On the basis, if the similarity of the two texts is greater than or equal to a preset threshold (for example, 0.6), the two texts can be considered to represent a synonymy event, and name unification can be performed. If the similarity is smaller than the preset threshold, the events can be regarded as different events, and fusion is not needed.

It can be seen that the problem that the same event has multiple names can be solved by performing the synonymous event fusion through the formula. For two texts, the similarity is related to the overlapped contents on one hand, and is generally expressed by the number of overlapped words, and is related to the different contents on the other hand. For different contents, the above formula adopts two expression modes, namely

And

. Two representations, using two and one counts of the overlap, represent two boundary values. On the basis, the weight of each representation mode is controlled through a preset coefficient, so that the similarity of the two texts can be calculated more flexibly and accurately.

And 105, constructing a knowledge graph based on the incidence relation among the entities in the fusion data, wherein the nodes in the knowledge graph represent the entities, and the edges in the knowledge graph represent the incidence relation among different entities.

In some embodiments, the execution subject may construct the knowledge graph with entities as nodes and associations between entities as edges, as shown in fig. 4.

And 106, generating an event handling sequence corresponding to each human entity according to the knowledge graph, wherein the event handling sequence is used for representing the handling sequence of a plurality of events corresponding to the human entities.

First, a plurality of events corresponding to each human entity are determined according to a knowledge graph, and as shown in fig. 4, a transactor 1 corresponds to an event a, an event B, and an event C. The transactor 2 corresponds to event C, event D, and event E.

Secondly, determining address information corresponding to each event in the plurality of events to obtain an address information set.

Thirdly, determining a target path according to the positions represented by the address information in the address information set, wherein the target path is connected with the positions represented by the address information in series.

In the process, a map interface can be called, and the path planning is carried out by taking the address information as input, so that a target path is obtained. Or a path ranking algorithm is utilized to obtain the target path.

Fourthly, determining an event handling sequence corresponding to each human entity according to the sequence of the target path passing through each position.

For example, the event transaction sequence for transactor 1 may be event C-event B-event A.

In addition, the relation between the positions represented by the address information and the dependency relation of the materials required by the events can be comprehensively considered, and path planning is carried out to determine the shortest path meeting the dependency relation as the target path.

And step 107, training to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity.

For example, for an event sequence, event C-event B-event a, event a may be used as an input, event B and event C may be used as a desired output, and an artificial neural network (CBOW or Skip-Gram may be used) is trained, so as to obtain a government event handling recommendation model. According to actual needs, the event B, that is, the next event, may be output as expected, or the event B-event C, that is, the subsequent event sequence, may be output as expected.

The objective function used in the above training process may be:

wherein,

is shown in the event

In case of occurrence, event

The probability of occurrence;

is an event

Is represented by a vector of (a) or (b),

is an event

N denotes the total number of events, k is any integer between 1 and N.

The loss function used for the above training may be:

the method provided by some embodiments of the present disclosure performs part-of-speech tagging and entity recognition operations on unstructured data and semi-structured data in sequence, and on this basis, fuses with structured data, thereby achieving the effect of expanding training samples. In addition, the names of the synonymous events can be unified through fusion, so that the training of the model is facilitated.

Optionally, the method further includes: acquiring a to-do event set and user current position information input by a user through a terminal; inputting the to-be-handled event set into a government event handling recommendation model to obtain a to-be-handled event sequence; and generating a transaction path based on the current position information of the user and the sequence of the events to be handled. For example, the current position information of the user is used as a starting point and is sequentially connected with the positions corresponding to the events to be handled in each sequence of the events to be handled, so that the transaction path is obtained. Sending the office path to the terminal so that the terminal displays the office path in the electronic map, wherein the office path comprises position marks corresponding to each event to be handled in the event set to be handled, and the marks are connected through directed line segments; in response to receiving the movement information of a user for a target endpoint in the directed line segment, adjusting the transaction path according to an original position mark and a target position mark corresponding to the target endpoint to generate a target transaction path; and sending the target transaction path to the terminal.

And step 108, acquiring a to-do event set and current position information of the user, which are input by the user through the terminal.

In some embodiments, after training is completed, the trained government event handling recommendation model can be deployed. On this basis, the execution main body may receive the to-do event set and the current location information of the user, which are sent by the terminal. The to-do event set may include a plurality of to-do event identifiers.

Step 109, inputting the to-be-done event set into the government affair event handling recommendation model to obtain the to-be-done event sequence.

In order to solve the technical problem three described in the background section, in some embodiments of the present disclosure, before determining a target path according to positions represented by respective address information in an address information set, and before the target path concatenates the positions represented by the respective address information, the method further includes: and determining the dependency relationship of a plurality of events corresponding to each human entity. For example, identity cards are needed for handling insurance services, which depend on handling identity card services, and "handling insurance services" needs to be arranged after "handling identity card services". Therefore, the problem that the events cannot be handled smoothly due to the fact that only the position relation is considered is avoided. On the basis, sequencing a plurality of events according to the dependency relationship to obtain an event dependency sequence; and determining a target path according to the positions represented by the address information in the address information set, wherein the target path is connected with the positions represented by the address information in series, and the method comprises the following steps: and determining the shortest path of each event in the series event dependency sequence as a target path. Therefore, the shortest path can be determined on the premise of meeting the dependency relationship, so that the handling events are saved.

Wherein, the dependent sequences can be one or more. For example, if there is a dependency relationship between each of a plurality of events, a dependency sequence is generally obtained, for example, if event C depends on event B, and event B depends on event a, then the dependency sequence is: event C-event B-event a. If, for example, event C depends on event B, and both event C and event B have no dependency relationship with event a, then multiple dependency sequences, event C-event B-event a, event a-event C-event B, may be obtained. In the case where there are a plurality of dependent sequences, the shortest path may be set as the target path. Therefore, the dependency relationship among the events is considered, so that the problem that the transaction sequence is wrong and materials are lacked is avoided, and the event transaction efficiency is improved.

With further reference to fig. 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a government event handling recommendation device, which correspond to those shown in fig. 1, and which can be applied in various electronic devices.

As shown in fig. 2, the government event handling recommending apparatus 200 of some embodiments includes: the acquisition unit 201 is configured to acquire historical government event data including structured data, unstructured data and semi-structured data. The part-of-speech tagging unit 202 is configured to perform part-of-speech tagging on the unstructured data and the semi-structured data, resulting in tagged data. The entity identification unit 203 is configured to perform entity identification on the annotated data to determine entities in the annotated data, wherein the entities are a person entity, an event entity and an event attribute entity. The fusion unit 204 is configured to fuse the annotated data with the structured data, resulting in fused data. The construction unit 205 is configured to construct a knowledge graph based on the association between the entities in the fused data, the nodes in the knowledge graph representing the entities, and the edges in the knowledge graph representing the association between different entities. The generating unit 206 is configured to generate an event transaction sequence corresponding to each human entity according to the knowledge graph, wherein the event transaction sequence is used for representing transaction sequences of a plurality of events corresponding to the human entities. The training unit 207 is configured to train to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each human entity. The information obtaining unit 208 is configured to obtain a set of to-do events input by a user through a terminal and user current location information. The prediction model 209 is configured to input the set of to-do events into the government event handling recommendation model, resulting in a sequence of to-do events.

It will be understood that the units described in the apparatus 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 200 and the units included therein, and are not described herein again.

Referring now to FIG. 3, a block diagram of an electronic device 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 3 may represent one device or may represent multiple devices, as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. The computer program, when executed by the processing apparatus 301, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring historical government affair event data, wherein the historical government affair event data comprises structured data, unstructured data and semi-structured data; performing part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data; performing entity identification on the marked data to determine entities in the marked data, wherein the entities are character entities, event entities and event attribute entities; fusing the marked data with the structured data to obtain fused data; constructing a knowledge graph based on the incidence relation among the entities in the fusion data, wherein nodes in the knowledge graph represent the entities, and edges in the knowledge graph represent the incidence relation among different entities; generating an event handling sequence corresponding to each character entity according to the knowledge graph, wherein the event handling sequence is used for representing handling sequences of a plurality of events corresponding to the character entities; training to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity, and acquiring a to-be-handled event set and current position information of a user input by the user through a terminal; and inputting the to-be-handled event set into a government event handling recommendation model to obtain a to-be-handled event sequence.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A government affair event handling recommendation method comprises the following steps:

acquiring historical government affair event data, wherein the historical government affair event data comprises structured data, unstructured data and semi-structured data;

performing part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data;

performing entity identification on the marked data to determine entities in the marked data, wherein the entities are an object entity, an event entity and an event attribute entity;

fusing the marked data with the structured data to obtain fused data;

constructing a knowledge graph based on the incidence relation among the entities in the fusion data, wherein nodes in the knowledge graph represent the entities, and edges in the knowledge graph represent the incidence relation among different entities;

generating an event handling sequence corresponding to each human entity according to the knowledge graph, wherein the event handling sequence is used for representing handling sequences of a plurality of events corresponding to the human entities;

training to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity;

acquiring a to-do event set and user current position information input by a user through a terminal;

and inputting the to-be-handled event set into the government affair event handling recommendation model to obtain the to-be-handled event sequence.

2. The method of claim 1, wherein training a government event handling recommendation model based on the event handling sequence corresponding to each human entity comprises:

and for the event handling sequence corresponding to each character entity, taking at least one event in the event handling sequence as input, taking subsequent matters of the at least one event as expected output, and training to obtain a government event handling recommendation model.

3. The method of claim 2, wherein the generating an event handling sequence for each human entity from the knowledge graph comprises:

determining a plurality of events corresponding to each person entity according to the knowledge graph;

determining address information corresponding to each event in the plurality of events to obtain an address information set;

determining a target path according to the positions represented by the address information in the address information set, wherein the target path is connected with the positions represented by the address information in series;

and determining an event handling sequence corresponding to each human entity according to the sequence of the target path passing through each position.

4. The method of claim 3, wherein the method further comprises:

generating a transaction path based on the current position information of the user and the event sequence to be handled;

sending the office path to the terminal so that the terminal displays the office path in an electronic map, wherein the office path comprises position marks corresponding to each event to be handled in the event set, and the marks are connected through directed line segments;

in response to receiving the movement information of the user for a target endpoint in the directed line segment, adjusting the transaction path according to an original position mark and a target position mark corresponding to the target endpoint to generate a target transaction path;

and sending the target transaction path to the terminal.

5. The method of claim 4, wherein the method further comprises:

acquiring terminal position information input by the user through a terminal; and

generating an event handling path based on the current position information of the user and the event sequence to be handled, including:

and generating a transaction path based on the current position information of the user, the sequence of the events to be handled and the end point position information.

6. A government event handling recommendation device comprising:

a data acquisition unit configured to acquire historical government event data including structured data, unstructured data and semi-structured data;

the part-of-speech tagging unit is configured to perform part-of-speech tagging on the unstructured data and the semi-structured data to obtain tagged data;

an entity identification unit configured to perform entity identification on the annotated data to determine entities in the annotated data, wherein the entities are an object entity, an event entity and an event attribute entity;

the fusion unit is configured to fuse the labeled data with the structured data to obtain fused data;

a construction unit configured to construct a knowledge graph based on an association relationship between entities in the fusion data, nodes in the knowledge graph representing the entities, edges in the knowledge graph representing association relationships between different entities;

the generating unit is configured to generate an event handling sequence corresponding to each human entity according to the knowledge graph, wherein the event handling sequence is used for representing handling sequences of a plurality of events corresponding to the human entities;

the training unit is configured to train to obtain a government affair event handling recommendation model based on the event handling sequence corresponding to each character entity;

the information acquisition unit is configured to acquire a to-do event set and user current position information input by a user through a terminal;

and the prediction model is configured to input the to-do event set into the government affair event handling recommendation model to obtain a to-do event sequence.

7. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.

8. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-5.