CN115049366A - Intelligent circulation method based on dealing with social event management - Google Patents
Intelligent circulation method based on dealing with social event management Download PDFInfo
- Publication number
- CN115049366A CN115049366A CN202210706432.9A CN202210706432A CN115049366A CN 115049366 A CN115049366 A CN 115049366A CN 202210706432 A CN202210706432 A CN 202210706432A CN 115049366 A CN115049366 A CN 115049366A
- Authority
- CN
- China
- Prior art keywords
- department
- event
- circulation
- model
- social
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention belongs to the technical field of social event management application, and particularly relates to an intelligent circulation method based on management of social events, which comprises the steps of introducing deep learning, natural language processing and other technologies in artificial intelligence based on social management inventory events, training a data model suitable for business rules, building a set of intelligent circulation analysis engine, configuring a result threshold value W analyzed by the intelligent circulation analysis engine, appointing a compensation mode when the result of the engine analysis is not enough for automatic circulation, determining a business department for subsequent circulation based on event characteristics and promoting the circulation of the events, and performing the circulation of the events by using the configured compensation mode when the result of the engine analysis is not enough for automatic circulation. The invention solves the problem of low-efficiency circulation treatment of events mainly based on manual operation in the fundamental social treatment, improves the efficiency of treating the events in the fundamental social treatment, improves the efficiency of handling the events, further enhances the happiness and the satisfaction of people, and has practical and practical value.
Description
Technical Field
The invention belongs to the technical field of social event management application, and particularly relates to an intelligent circulation method based on management of social events.
Background
The social management comprises the aspects of coordinating social relations, standardizing social behaviors, solving social problems, resolving social contradictions, promoting social justice, coping with social risks, maintaining social harmony and the like. The method has the advantages of promoting social autonomy, resolving the contradiction between rational economic people and irrational social people, standardizing social behaviors and monitoring and controlling social benefits of the social behaviors.
Social management is mainly a process of organizing, coordinating, guiding, standardizing, supervising and correcting social failures of constituent parts of a social system, different fields of social life and all links of social development by governments and social organizations for promoting the coordinated operation of the social system.
The traditional implementation mode of event circulation handling in the primary social treatment is that a grid member reports an event, and community/village or town street social treatment command center personnel identify the event, determine an event handling unit and dispatch an order; events accessed to the social management platform through other ways, such as WeChat public numbers, 12345 and the like, are also identified, determined and dispatched by personnel of the social management command center at a corresponding level. In this way, the circulation of the events is mainly manual, and due to the limited hands of each social administration command center, the problems of untimely identification and disposal of the events, inaccurate assignment of disposal departments and the like exist, so that the working efficiency is low.
Disclosure of Invention
Aiming at the technical problems in the circulation and disposal process of the social treatment events, the invention provides an intelligent circulation method which is reasonable in design, simple in structure, convenient to process and capable of effectively dealing with the social treatment events.
In order to achieve the purpose, the technical scheme adopted by the invention is an intelligent circulation method based on treatment of social events, which comprises the following steps:
step 1: acquiring a basic level social management stock event, and building an intelligent circulation analysis engine for maintaining the mapping relationship among a standard department, type data and an actual business department in basic level social management;
step 2: based on deep learning, natural language processing and other technologies in artificial intelligence, through characteristic learning of storage event key elements, final disposal units and the like, an incidence relation between event key information and event characteristics is established and continuously learned by utilizing mature technologies and algorithm models in the field of artificial intelligence, and the analysis capability of an intelligent circulation analysis engine is improved;
and step 3: configuring a result threshold value W analyzed by an intelligent circulation analysis engine, and designating a compensation mode when the result of the engine analysis is not enough for automatic circulation;
and 4, step 4: determining a business department of subsequent circulation based on the event characteristics and advancing the event circulation;
and 5: and when the event characteristics analyzed by the intelligent circulation analysis engine are not sufficient for automatic circulation, performing the circulation of the event by using a configured compensation mode.
Preferably, the step 1 specifically comprises the following steps:
1.1: standard project embodiments are: based on implementation accumulation of inventory events in the past local basic level social management project, a basic standard department set is formed by extraction, screening and integration; with the increasing of the implemented projects, the standard department set A is gradually expanded and perfected 1 ,a 2 ,a 3 ,…,a n ,…}；
1.2: the practical project implementation scheme is as follows: the actual business departments involved in the corresponding primary government control work are researched, collected and integrated by the authorization of related local government related departments to form an actual business department set B (B) 1 ,b 2 ,b 3 ,…,b n ,…}；
1.3: configuring in an intelligent circulation analysis engine to form a many-to-many dynamic mapping relation between a standard department set A and an actual business department set B, and mapping relations
1.4: if in the step 1.3, a certain element contained in the set A does not form a mapping relation to the elements of the set B, the special mark X is recorded.
Preferably, the step 2 includes classifying the storage event data text and determining the effective value of each actual business department, and the determination of the effective value of each actual business department adopts a physics power formula: p is W/t is F S/t, wherein: p is an efficiency parameter which reflects the efficiency difference of each actual business department in the actual treatment process, W reflects the comprehensive capacity of each actual business department in the social treatment process, t is the implementation time of each actual business department integrated in the stock event when dealing with the social treatment event, F is the completion degree of each actual business department integrated in the stock event aiming at the social treatment event, and S is the distance between each actual business department and the occurrence position of a new event to be treated.
Preferably, the classifying of the inventory event data text includes model completion training, and the model completion training includes: the method comprises the following steps of data analysis, model design, data preprocessing, model training and model evaluation, and specifically comprises the following steps:
2.1: training data in the data analysis are all events from the fact that internal sources and external sources in the local government project basic level social treatment are transferred to a regional platform for classification; classifying the batch data into a straight district department and a town street department according to a final circulation department;
2.2: according to business requirements, the model is designed into a primary model and a secondary model, wherein the primary model is as follows: directly classifying all data by using a model, wherein the secondary model is as follows: firstly, carrying out secondary classification on data by using one model, and then respectively distributing stock events to detailed departments by using one model;
2.3: the data preprocessing is to perform word segmentation processing on a training data text by utilizing jieba word segmentation based on Python technology, train the word segmentation into word vectors, and input the training data text into a model in the form of the word vectors;
2.4: the model training is to classify the training data texts by using a TextCNN model in the field of text processing;
2.5: and after the model is subjected to model perfection training test, analyzing the overall distribution of data in the primary model and the secondary model, and performing enhanced training and optimization after an ideal model is obtained.
Preferably, the step 3 specifically includes the following steps:
3.1: when the department probability in the output result of the intelligent circulation analysis engine configured according to the actual demand is more than or equal to W, executing the intelligent circulation according to the output result;
3.2: and configuring an event when the output result of the intelligent circulation analysis engine is not enough for automatic circulation, and executing the next manual circulation link.
Preferably, the step 4 specifically includes the following steps:
4.1: inputting event full-factor information reported by hotlines of grid members, crowds and governments into an energy flow analysis engine, wherein the event full-factor information comprises event content, types, levels and the like so as to provide convenience for distributing the event full-factor information to each corresponding actual business department;
4.2: and analyzing the input event full-factor information by an analysis model in the intelligent circulation analysis engine, and outputting a set of judged standard departments with uniqueness and corresponding probabilities.
Preferably, the step 5 specifically includes the following steps:
5.1: if the set output in the step 4.2 has the standard department corresponding probability which is more than or equal to W (W is set in the step 3.1) and at least one standard department which does not carry the special mark X (X is set in the step 1.4), cleaning the standard department, removing the standard department with the special mark X, and forming a standard department result set C;
5.2: if the step 5.1 is established, finding out the actual departments corresponding to the standard departments in the set C (C is the standard department result set formed in the step 5.1) through the mapping relation in the step 1.3, performing repeat-removing cleaning on the found actual department set, removing the parts with lower probability and the highest remaining probability, and sequencing according to the sequence of the probabilities from high to low to form an actual department result set D;
5.3: if the step 5.2 is established, according to the set D (D is an actual department result set formed in the step 5.2), setting the department with the highest probability as a host disposal unit, setting the other departments as co-host disposal units, advancing event circulation, and recording and leaving traces in the whole process;
5.4: if the step 5.2 is not established and no corresponding actual department is found, circulation is carried out according to the configuration of 3.2;
5.5: if the 5.1 step does not hold, then the flow is performed according to the 3.2 configuration.
Compared with the prior art, the invention has the advantages and positive effects that,
1. the intelligent circulation method based on treatment of social events can effectively solve the problem of low-efficiency circulation treatment of events mainly based on manual operation in primary social treatment, trains a data model suitable for business rules by introducing technologies such as deep learning in artificial intelligence and the like, and builds an intelligent circulation analysis engine so as to realize automatic analysis of the events and automatic dispatching of the events to responsibility treatment units for treatment and treatment of the events, improve the circulation efficiency of the primary social treatment events, improve the treatment efficiency of the events, and further enhance the happiness and satisfaction of people; meanwhile, in the circulation process, a more appropriate and more reasonable responsibility disposal unit can be selected according to the corresponding social treatment event, the work circulation process is guaranteed, and the actual use requirement of the society is met.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a schematic flow chart of steps of an intelligent circulation method based on handling social events;
FIG. 2 is a schematic flow chart of a first-level model in model design;
FIG. 3 is a schematic flow chart of a secondary model in model design;
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, the present invention will be further described with reference to the accompanying drawings and examples. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and thus the present invention is not limited to the specific embodiments of the present disclosure.
An embodiment, as shown in fig. 1, fig. 2, and fig. 3, is an intelligent circulation method based on handling social event management, including the following steps:
step 1: acquiring a basic level social management stock event, and building an intelligent circulation analysis engine for maintaining the mapping relationship among a standard department, type data and an actual business department in basic level social management;
step 2: based on deep learning, natural language processing and other technologies in artificial intelligence, through characteristic learning of storage event key elements, final disposal units and the like, an incidence relation between event key information and event characteristics is established and continuously learned by utilizing mature technologies and algorithm models in the field of artificial intelligence, and the analysis capability of an intelligent circulation analysis engine is improved;
and step 3: configuring a result threshold value W analyzed by an intelligent circulation analysis engine, and designating a compensation mode when the result of the engine analysis is not enough for automatic circulation;
and 4, step 4: determining a business department of subsequent circulation based on the event characteristics and advancing the event circulation;
and 5: and when the event characteristics analyzed by the intelligent circulation analysis engine are not enough for automatic circulation, performing the circulation of the event by using a configured compensation mode.
The step 1 is used as a basic condition set up by an intelligent circulation analysis engine, the storage events are classified, and standard departments in an ideal state are planned through corresponding analysis, so that the priority of each actual business department on social management events is ensured, and the working efficiency is improved; step 2, mainly analyzing and learning the social management inventory events to make a comparison template with comprehensive content analysis and high accuracy, thereby providing a prerequisite for the distribution and circulation of subsequent social management events; step 3, a result boundary output by the intelligent circulation analysis engine is used for judging an actual business department which can be more fit with a standard department, and the maneuverability is increased; step 4, ensuring normal circulation of newly-appeared social treatment events under the built intelligent circulation analysis engine, fully reducing the manual burden and workload, and greatly improving the work development process and work efficiency; and step 5, a compensation mode is made based on the inventory events which are not stored, and the inventory data in the intelligent circulation analysis engine can be expanded, so that the inventory data is continuously improved and perfected, and the effective circulation of the events is ensured.
Further, in order to fully ensure the comprehensiveness of building the basic data of the intelligent flow analysis engine, the step 1 specifically includes the following steps:
1.1: standard project embodiments are: based on implementation accumulation of stock events in the past local basic level social governance projects, a basic standard department set is formed by extraction, screening and integration; with the increasing of the implemented projects, the standard department set A is gradually expanded and perfected 1 ,a 2 ,a 3 ,…,a n ,…}；
1.2: the practical project implementation scheme is as follows: authorized by related local government related departments, and through investigation, collection and integration of actual business departments involved in corresponding government basic governing work, a set B of the actual business departments is formed 1 ,b 2 ,b 3 ,…,b n ,…}；
1.3: configuring in an intelligent circulation analysis engine to form a many-to-many dynamic mapping relation between a standard department set A and an actual business department set B, and mapping relations
1.4: if in the step 1.3, a certain element contained in the set A does not form a mapping relation to the elements of the set B, the special mark X is recorded.
Further, in order to fully guarantee the social event management process and allocate appropriate actual business departments to deal with and handle the social event management, so as to improve the satisfaction degree of people, step 2 includes classification of storage event data texts and judgment of effective values of the actual business departments, and the judgment of the effective values of the actual business departments adopts a physical power formula: p is W/t is F S/t, wherein: p is an efficiency parameter, namely an effective value, which reflects the efficiency difference of each actual business department in the actual treatment process, W reflects the comprehensive capacity of each actual business department in the social treatment process, t is the implementation time of each actual business department integrated in the stock event when dealing with the social treatment event, F is the completion degree of each actual business department integrated in the stock event aiming at the social treatment event, and S is represented as the distance between each actual business department and the occurrence position of a new event to be treated.
Wherein, the completion degree represented by F can embody the executive force of each actual business department on the social event management; the implementation time represented by t can embody the mobility of each actual business department for the social event management, the distance represented by S can embody the responsiveness of each actual business department in dealing with different position areas, specifically, when a new social event to be processed is determined and completed based on the event type, and when the department probability in the output result of an intelligent circulation analysis engine configured according to actual requirements is more than or equal to W, an effective value is adopted to select the actual business department which is more optimal for processing the event type, so that the processing department is more accurate, the event processing efficiency is greatly improved, the coordinated operation of the social system is further practically promoted, the social stability is ensured, and meanwhile, the satisfaction degree and the happiness feeling of people are increased.
Further, for the accuracy of the output result of the intelligent flow analysis engine, the step 2 includes classification of the stock event data text and judgment of the effective value of each actual business department, the classification of the stock event data text includes model perfection training, and the model perfection training includes: the method comprises the following steps of data analysis, model design, data preprocessing, model training and model evaluation, and specifically comprises the following steps:
2.1: training data in data analysis are all from events that internal sources and external sources in local government project basic level social treatment are transferred to a regional platform for classification; classifying the batch data into a straight district department and a town street department according to a final circulation department;
2.2: according to business requirements, the model is designed into a primary model and a secondary model, wherein the primary model is as follows: all data are directly classified by using one model, and the secondary model is as follows: firstly, carrying out secondary classification on data by using one model, and then respectively distributing stock events to detailed departments by using one model;
2.3: the data preprocessing is to perform word segmentation processing on a training data text by utilizing jieba word segmentation based on Python technology, train the word segmentation into word vectors, and input the training data text into a model in the form of the word vectors;
2.4: the model training is to classify the training data texts by using a TextCNN model in the field of text processing;
2.5: after model perfection training test, analyzing the overall distribution of data in the primary model and the secondary model, and performing enhanced training and optimization after obtaining an ideal model;
wherein, the effect of the directly classified grade in the training is unsatisfactory after the first-level model classifies the event, and after the analysis according to the data overall distribution, it is comparatively serious to find the whole data slope, especially can highlight the tiltability of data using the first-level model classification, therefore, prefers the second-level model in this embodiment.
It needs to be further explained that: the second-level model consists of three modules, wherein the first module is a two-classification model and is used for distinguishing a straight section door of a district from a town street department; the second module is a town street department classification model, further carries out detailed department classification on the town street content text, and outputs the similar probability with the classification department; and the third module is a straight department classification model, further carries out detailed department classification on the straight department content text, and outputs the similarity probability with the classified department.
Meanwhile, in order to eliminate data skew, training is carried out on the event data of the direct storage of the extracted area and the data of the full town street department, various hyperparameters such as the size of a word vector, the batch of training data, the training times, the learning rate and the number of convolution kernels in the TextCNN model are adjusted to achieve a relatively good training effect, and finally, an analysis model of the intelligent circulation analysis engine is formed through training.
The specific process in step 2.4 is further illustrated as follows:
2.4-1: extracting key information in a text sentence of training data by using a plurality of convolution kernels with different sizes, better capturing local correlation, and meanwhile, calculating the accuracy rate of a verification set and recording loss in training;
2.4-2: testing by using the test set, calculating the accuracy of the test set, and recording the identification accuracy of each classification as a reference;
2.4-3: data proportion: the training set, the verification set and the test set are as follows: 1: 1, distributing;
wherein, the description of the TextCNN model is as follows:
2.4-3.1: embedding is 7 x 5;
2.4-3.2: through 6 groups of convolution kernels, 2 groups of 3 (2 × 5, 3 × 5, 4 × 5) convolution kernels, the dimension of the second dimension of the convolution kernels is consistent with that of the word embedding layer, and the extraction of n-gram features is equivalent to the extraction of n-gram features in the moving process;
2.4-3.3: obtaining convolution vector dimension (d _ embedding-d _ filter + 1)/stride;
2.4-3.4: extracting the maximum value of feature maps by adopting maximum pooling;
2.4-3.5: classifying by adopting softmax;
further, in order to provide a standard for the event flow and ensure that the event flow can be smoothly developed, step 3 specifically includes the following steps:
3.1: when the department probability in the output result of the intelligent circulation analysis engine configured according to the actual demand is more than or equal to W, executing the intelligent circulation according to the output result;
3.2: and configuring an event when the output result of the intelligent circulation analysis engine is not enough for automatic circulation, and executing the next manual circulation link.
Further, in order to ensure that a newly-appeared event to be treated socially can be put in place and solved properly, step 4 specifically includes the following steps:
4.1: inputting event full-factor information reported by hotlines of grid members, crowds and governments into an energy flow analysis engine, wherein the event full-factor information comprises event content, types, levels and the like so as to provide convenience for distributing the event full-factor information to each corresponding actual business department;
4.2: and analyzing the input event full-factor information by an analysis model in the intelligent circulation analysis engine, and outputting a set of judged standard departments with uniqueness and corresponding probabilities.
Further, in order to effectively cope with the compensation manner made by the corresponding event flow when the inventory event data range is limited in the intelligent flow analysis engine, in step 5, the method specifically includes the following steps:
5.1: if the set output in the step 4.2 has the standard department corresponding probability which is more than or equal to W (W is set in the step 3.1) and at least one standard department which does not carry the special mark X (X is set in the step 1.4), cleaning the standard department, removing the standard department with the special mark X, and forming a standard department result set C;
5.2: if the step 5.1 is established, finding out the actual departments corresponding to the standard departments in the set C (C is the standard department result set formed in the step 5.1) through the mapping relation in the step 1.3, performing repeat-removing cleaning on the found actual department set, removing the parts with lower probability and the highest remaining probability, and sequencing according to the sequence of the probabilities from high to low to form an actual department result set D;
5.3: if the step 5.2 is established, setting the department with the highest probability as a host disposal unit and setting the other departments as assistant disposal units according to the set D (D is an actual department result set formed in the step 5.2), advancing event circulation and recording and leaving traces in the whole process;
5.4: if the step 5.2 is not established and no corresponding actual department is found, circulation is carried out according to the configuration of 3.2;
5.5: if the 5.1 step does not hold, then the flow is performed according to the 3.2 configuration.
The method comprises the steps of 3-5, a concrete flow of social management event circulation is included based on the fact that an intelligent circulation analysis engine is built, meanwhile, a compensation mode is made aiming at the situation that the analyzed event characteristics are not enough to automatically circulate, in addition, the method can be used for carrying out matched artificial circulation aiming at special situations, convenience is brought to data expansion of the intelligent circulation analysis engine, compared with the traditional mode that circulation is carried out only by means of manual mode, the method has remarkable progress, timeliness in the event identification and disposal process is guaranteed, reasonable disposal departments are assigned, the circulation efficiency of primary social management events is improved, the event handling efficiency is improved, and further happiness and satisfaction of people are enhanced.
The above description is only a preferred embodiment of the present invention, and not intended to limit the present invention in other forms, and any person skilled in the art may apply the above modifications or changes to the equivalent embodiments with equivalent changes, without departing from the technical spirit of the present invention, and any simple modification, equivalent change and change made to the above embodiments according to the technical spirit of the present invention still belong to the protection scope of the technical spirit of the present invention.
Claims (7)
1. An intelligent circulation method based on treatment of social events is characterized by comprising the following steps:
step 1: acquiring a basic level social management stock event, and building an intelligent circulation analysis engine for maintaining the mapping relationship among a standard department, type data and an actual business department in basic level social management;
step 2: based on deep learning, natural language processing and other technologies in artificial intelligence, through characteristic learning of storage event key elements, final disposal units and the like, an incidence relation between event key information and event characteristics is established and continuously learned by utilizing mature technologies and algorithm models in the field of artificial intelligence, and the analysis capability of an intelligent circulation analysis engine is improved;
and step 3: configuring a result threshold value W analyzed by an intelligent circulation analysis engine, and designating a compensation mode when the result of the engine analysis is not enough for automatic circulation;
and 4, step 4: determining a business department of subsequent circulation based on the event characteristics and advancing the event circulation;
and 5: and when the event characteristics analyzed by the intelligent circulation analysis engine are not enough for automatic circulation, performing the circulation of the event by using a configured compensation mode.
2. The intelligent circulation method for dealing with social event management according to claim 1, wherein the step 1 specifically comprises the following steps:
1.1: standard project embodiments are: based on implementation accumulation of inventory events in the past local basic level social management project, a basic standard department set is formed by extraction, screening and integration; with the increasing of the implemented projects, the standard department set A is gradually expanded and perfected 1 ,a 2 ,a 3 ,…,a n ,…}；
1.2: the practical project implementation scheme is as follows: the actual business departments involved in the corresponding primary government control work are researched, collected and integrated by the authorization of related local government related departments to form an actual business department set B (B) 1 ,b 2 ,b 3 ,…,b n ,…}；
1.3: configuring in an intelligent circulation analysis engine to form a many-to-many dynamic mapping relation between a standard department set A and an actual business department set B, and mapping relations
1.4: if in the step 1.3, a certain element contained in the set A does not form a mapping relation to the elements of the set B, the special mark X is recorded.
3. The intelligent circulation method for dealing with the management of the social events according to claim 2, wherein the step 2 comprises classification of the text of the stock event data and judgment of effective values of each actual business department, and the judgment of the effective values of each actual business department adopts a physics power formula: p ═ W/t ═ F × S/t, where: p is an efficiency parameter which reflects the efficiency difference of each actual business department in the actual treatment process, W reflects the comprehensive capacity of each actual business department in the social treatment process, t is the implementation time of each actual business department integrated in the stock event when dealing with the social treatment event, F is the completion degree of each actual business department integrated in the stock event aiming at the social treatment event, and S is the distance between each actual business department and the occurrence position of a new event to be treated.
4. The intelligent circulation method for dealing with social event management as claimed in claim 3, wherein the classification of the inventory event data text comprises model completion training, and the model completion training comprises: the method comprises the following steps of data analysis, model design, data preprocessing, model training and model evaluation, and specifically comprises the following steps:
2.1: training data in the data analysis are all from events that an internal source and an external source flow to a regional platform for classification in the local government project basic social treatment; classifying the batch data into a straight district department and a town street department according to a final circulation department;
2.2: according to business requirements, the model is designed into a primary model and a secondary model, wherein the primary model is as follows: directly classifying all data by using a model, wherein the secondary model is as follows: firstly, carrying out secondary classification on data by using one model, and then respectively distributing stock events to detailed departments by using one model;
2.3: the data preprocessing is to perform word segmentation processing on a training data text by utilizing jieba word segmentation based on Python technology, train the word segmentation into word vectors, and input the training data text into a model in the form of the word vectors;
2.4: the model training is to classify the training data texts by using a TextCNN model in the field of text processing;
2.5: and after the model is subjected to model perfection training test, analyzing the overall distribution of data in the primary model and the secondary model, and performing enhanced training and optimization after an ideal model is obtained.
5. The intelligent circulation method for dealing with social event management according to claim 4, wherein the step 3 specifically comprises the following steps:
3.1: when the department probability in the output result of the intelligent circulation analysis engine configured according to the actual demand is more than or equal to W, executing the intelligent circulation according to the output result;
3.2: and configuring an event when the output result of the intelligent circulation analysis engine is not enough for automatic circulation, and executing the next manual circulation link.
6. The intelligent circulation method for dealing with social event management according to claim 5, wherein the step 4 specifically comprises the following steps:
4.1: inputting event full-factor information reported by hotlines of grid members, crowds and governments into an energy flow analysis engine, wherein the event full-factor information comprises event content, types, levels and the like so as to provide convenience for distributing the event full-factor information to each corresponding actual business department;
4.2: and analyzing the input event full-factor information by an analysis model in the intelligent circulation analysis engine, and outputting a set of judged standard departments with uniqueness and corresponding probabilities.
7. The intelligent circulation method based on treatment of social events according to claim 6, wherein the step 5 specifically comprises the following steps:
5.1: if the set output in the step 4.2 has the standard department corresponding probability which is more than or equal to W (W is set in the step 3.1) and at least one standard department which does not carry the special mark X (X is set in the step 1.4), cleaning the standard department, removing the standard department with the special mark X, and forming a standard department result set C;
5.2: if the step 5.1 is established, finding out the actual departments corresponding to the standard departments in the set C (C is the standard department result set formed in the step 5.1) through the mapping relation in the step 1.3, performing repeated cleaning on the found actual department set, removing the parts with the same department with lower probability and the highest probability, and sequencing the parts according to the sequence of the probabilities from high to low to form an actual department result set D;
5.3: if the step 5.2 is established, according to the set D (D is an actual department result set formed in the step 5.2), setting the department with the highest probability as a host disposal unit, setting the other departments as co-host disposal units, advancing event circulation, and recording and leaving traces in the whole process;
5.4: if the step 5.2 is not established and no corresponding actual department is found, circulation is carried out according to the configuration of 3.2;
5.5: if the 5.1 step does not hold, then the flow is performed according to the 3.2 configuration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706432.9A CN115049366A (en) | 2022-06-21 | 2022-06-21 | Intelligent circulation method based on dealing with social event management |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706432.9A CN115049366A (en) | 2022-06-21 | 2022-06-21 | Intelligent circulation method based on dealing with social event management |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115049366A true CN115049366A (en) | 2022-09-13 |
Family
ID=83163782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210706432.9A Pending CN115049366A (en) | 2022-06-21 | 2022-06-21 | Intelligent circulation method based on dealing with social event management |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049366A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309948A (en) * | 2013-05-20 | 2013-09-18 | 携程计算机技术（上海）有限公司 | System and method for public opinion monitoring analysis and intelligent distribution processing of coordination center |
| CN110730215A (en) * | 2019-09-20 | 2020-01-24 | 上海东方富联科技有限公司 | Transfer engine, data transfer method, medium and terminal for alarm event |
| CN110851728A (en) * | 2019-11-20 | 2020-02-28 | 软通动力信息技术有限公司 | Event processing method, device, equipment and medium |
| CN113947288A (en) * | 2021-09-18 | 2022-01-18 | 南京莱斯信息技术股份有限公司 | Intelligent traffic alert condition order dispatching method and terminal |
-
2022
- 2022-06-21 CN CN202210706432.9A patent/CN115049366A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309948A (en) * | 2013-05-20 | 2013-09-18 | 携程计算机技术（上海）有限公司 | System and method for public opinion monitoring analysis and intelligent distribution processing of coordination center |
| CN110730215A (en) * | 2019-09-20 | 2020-01-24 | 上海东方富联科技有限公司 | Transfer engine, data transfer method, medium and terminal for alarm event |
| CN110851728A (en) * | 2019-11-20 | 2020-02-28 | 软通动力信息技术有限公司 | Event processing method, device, equipment and medium |
| CN113947288A (en) * | 2021-09-18 | 2022-01-18 | 南京莱斯信息技术股份有限公司 | Intelligent traffic alert condition order dispatching method and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107239446B (en) | A kind of intelligence relationship extracting method based on neural network Yu attention mechanism | |
| CN110807328B (en) | Named entity identification method and system for legal document multi-strategy fusion | |
| CN112214610B (en) | Entity relationship joint extraction method based on span and knowledge enhancement | |
| CN109635108B (en) | Man-machine interaction based remote supervision entity relationship extraction method | |
| CN110188192B (en) | Multi-task network construction and multi-scale criminal name law enforcement combined prediction method | |
| CN103150303B (en) | Chinese semantic meaning lattice layered recognition method | |
| CN111597420A (en) | Deep learning-based rail transit standard relation extraction method | |
| CN110415071B (en) | Automobile competitive product comparison method based on viewpoint mining analysis | |
| CN110717843A (en) | Reusable law strip recommendation framework | |
| CN108052504A (en) | Mathematics subjective item answers the structure analysis method and system of result | |
| CN113191148A (en) | Rail transit entity identification method based on semi-supervised learning and clustering | |
| CN103886030A (en) | Cost-sensitive decision-making tree based physical information fusion system data classification method | |
| CN115238197A (en) | Expert thinking model-based field business auxiliary analysis method | |
| CN115292490A (en) | Analysis algorithm for policy interpretation semantics | |
| CN113742396B (en) | Mining method and device for object learning behavior mode | |
| CN113722494A (en) | Equipment fault positioning method based on natural language understanding | |
| CN113886562A (en) | AI resume screening method, system, equipment and storage medium | |
| CN107403391A (en) | A kind of optimal screening method for oil field development pre-arranged project | |
| Scherger et al. | A systematic overview of the prediction of business failure | |
| CN109543038B (en) | Emotion analysis method applied to text data | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| CN110765781A (en) | Man-machine collaborative construction method for domain term semantic knowledge base | |
| CN106934024A (en) | A kind of data processing method and device | |
| CN115049366A (en) | Intelligent circulation method based on dealing with social event management | |
| CN112256869B (en) | Same-knowledge-point test question grouping system and method based on question meaning text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |