CN115203365A - Social event processing method applied to comprehensive treatment field - Google Patents
Social event processing method applied to comprehensive treatment field Download PDFInfo
- Publication number
- CN115203365A CN115203365A CN202210738718.5A CN202210738718A CN115203365A CN 115203365 A CN115203365 A CN 115203365A CN 202210738718 A CN202210738718 A CN 202210738718A CN 115203365 A CN115203365 A CN 115203365A
- Authority
- CN
- China
- Prior art keywords
- event
- social
- component
- class
- management
- 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
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a social event processing method applied to the field of comprehensive treatment. The method solves the problem that the urban social event processing efficiency is low in the prior art. The method comprises the steps of S1, adopting an RE2 model to report event content, carrying out similarity matching with an event content text in a case base, meeting events of a threshold matching condition, and entering S3 to carry out allocation processing by referring to the events matched with the case base; s2, identifying the event which does not meet the threshold matching condition according to a primary component/event open type classification model; s3, transmitting the event from the event in the S1 or the event judged as the first-level component/event class in the S2 to an event acceptance center, and manufacturing a unified interface and a data structure of the access event; and comparing the similarity of the received event and the portrait in the secondary component/event management portrait library by using an RE2 model, and ensuring the accuracy of event division. The invention has the advantages that: the social event processing efficiency is effectively improved.
Description
Technical Field
The invention relates to the technical field of social treatment, in particular to a social event processing method applied to the field of comprehensive treatment.
Background
The event processing flow in the comprehensive treatment field generally comprises the acceptance of events, the reply of processing results, the return visit and the satisfaction survey, the event range processed by the event processing method comprises social aspects such as infrastructure, city appearance, market supervision, street security, community management, rural management and the like, departments for processing the events comprise department units such as city supervision, credit, administrative law enforcement, insurance, communication and the like and companies such as gas, water affairs, telecommunication, mobile and the like, even under certain conditions, the reported social events need to be processed in a cross-department cooperative manner, and a main responsibility department needs to be determined under the condition of multi-department cooperative processing, and the main responsibility department follows and supervises and urges the processing state of the events.
At present, the processing aiming at various social events has the following problems:
1. an event reporting channel is not smooth, and reporting is not known after a problem is found;
2. service acceptance and disposal flows are not standard, all departments fight each other, and a uniform event assignment acceptance method is not provided, so mutual deniability is caused in the event processing process, and the phenomenon of failure ending is frequent;
3. events are not classified and graded, so that the degree and urgency among the events cannot be known when multiple events are processed;
4. the person in charge is not aware of the progress of event handling and the public does not know the processing result of the event without necessary event supervision and feedback.
Most of the solutions for processing the social problems in the prior art focus on a specific link in the process, the process is simple, the events are not classified, classified and distributed, and a plurality of related departments have a unique event acquisition and processing system, so that the problem of incompatibility of the events is caused by the diversity of the system, the real-time performance of problem solution is influenced, and the efficiency of processing the social events is reduced.
Disclosure of Invention
The invention aims to solve the problems and provides a social event processing method which is reasonable in design and high in processing efficiency and is applied to the comprehensive treatment field.
In order to achieve the purpose, the invention adopts the following technical scheme: a social event processing method applied to the comprehensive treatment field is characterized by comprising the following steps:
s1, reporting event content by adopting an RE2 model, performing similarity matching with an event content text in a case library, and entering S3 for allocation processing by referring to an event matched with the case library when the event meets a threshold matching condition; and reporting the event through the RE2 model and comparing and distributing the reported event with the cases in the case base in a pertinence manner, so that the event category is judged, and the data accuracy can be effectively improved.
S2, identifying the event which does not meet the threshold matching condition according to a primary component/event Open type Classification model, namely an Open-set Text Classification model;
s3, transmitting the event from the event in the S1 or the event judged as the first-level component/event class in the S2 to an event acceptance center, and manufacturing a unified interface and a data structure of the access event; the unified interface and the data structure can enable the receiving of the social events to be unified, and management is convenient.
S4, calling out all secondary component/event management images under the current primary component/event type from a secondary component/event management image library according to the primary component/event type of the current event, and detecting the similarity between the content of the current event and a problem description text in the secondary component/event management by adopting an RE2 model; and comparing the similarity of the received event with the image in the secondary component/event management image library by using an RE2 model to ensure the accuracy of event division.
S5, creating a virtual network for the event, adding a responsibility department into the grid as a grid member according to the secondary component/event management image, judging whether the current event is a civil event or not according to a two-classification algorithm model, and if the current event belongs to the civil event, extracting party information from the current event by adopting a named entity extraction mode and adding the party information into the virtual grid;
and S6, event processing result return visit and satisfaction survey. The satisfaction survey is beneficial to optimizing the social event processing mode, and the social event processing mode with high satisfaction is stored and is convenient to refer.
In the above social event processing method applied to the comprehensive treatment field, in step S1, the establishing of the RE2 model specifically includes the following steps:
s11, inputting a current event1 and a case base, and executing the following steps for each event content event2 of the case base:
s12, converting the texts, namely the event1 and the event2, into vectors in an embedding form;
s13, the embedding vector sequences are sent into 3 block blocks to be continuously processed, each block has the same structure and consists of an encoder layer, an alignment layer and a fusion layer, the encoder layer calculates the context characteristics of the sequences, the alignment layer calculates the correlation characteristics of the texts event1 and event2, and the output of the fusion layer is the input of the next block or the input of the posing pooling layer;
s14, converting the result output by the block into a vector with a fixed length by the posing pooling layer;
and S15, after calculating features of the event1 and the event2, constructing a two-classification model at a prediction layer, wherein the category 0 indicates that the event1 is not similar to the event2, and the category 1 indicates that the event1 is similar to the event 2.
In the social event processing method applied to the comprehensive field, in step S2, there are 5 primary component categories in the primary component/event open classification model, which are respectively: public facilities, road transportation facilities, city appearance environment enforcement, landscaping facilities, and expansion components; there are 10 primary event categories, which are: the system comprises a city appearance environment, advertisement publicity, construction management, street order, street security, market supervision, emergency, cell management, rural management and extended event, wherein the total number of secondary components/event categories is 235-245; respectively establishing a secondary component/event management image base for the secondary component/event, wherein the contents of the secondary component/event management image base comprise: class one component/event category, department of responsibility, problem description primary disposition requirements.
In the above social event processing method applied to the comprehensive field, in step S3, a primary component/event Classification model is established by an Open-set Text Classification algorithm, the category number of the primary component/event Classification model is 12+1,12 is a definite and fixed Classification category, which includes the above 10 primary event categories and 5 primary component categories, wherein 1 is an Open category, which includes new and potential component/event categories; the unified interface and data structure comprises a unified interface request mode, a data encryption mode, a department area coding mode and a callback mode.
In the social event processing method applied to the comprehensive treatment field, an Open-set Text Classification algorithm is built based on CNN, and during testing, the last layer of CNN extracts the sentence characteristics of an input Class to obtain an Activation Vector (AV), then the distance value between the Activation Vector of each test sample and the nearest previous k distance values of each known Class is calculated, the Activation Vectors of the previous k samples are recorded as k-Class Activation Vectors (k-CAV), the distances between the AV and the k-CAV of the test samples are calculated, the sum of k probability values of each training Class is recorded as total closed set probability, finally OSP =1-total closed probability is calculated, and the maximum total closed set probability of all the training classes is compared with OSP to determine that the test Class is an unknown Class or a known Class.
In the social event processing method applied to the comprehensive treatment field, in step S4, the responsibility department of the portrait meeting the maximum threshold condition is the recommended processing department of the event, and if the threshold condition cannot be met, the responsibility department is manually assigned, and the staff can determine whether to newly create the secondary part/event management portrait of the event.
In the above social event processing method applied to the comprehensive treatment field, in step S5, the establishing of the two-classification algorithm model specifically includes the following steps:
s51, forming a classified training corpus S by contents except the character information in the event text, manually marking the predictive variable of the corpus S, and recording y i =1 denotes a civil event, y i = -1 denotes non-civil event;
s52, dividing the sentence set S into a string and a Stest according to the ratio of 8:2, and calculating each sentence in the string and the Stest according to the following formula:
s53, combining all sentence vectors in the string to obtain a matrix X, and calculating a first principal component u of the X through TruncatedSVD;
s54, performing the following calculation on each sentence vector Vs in the string and the Stest: v s ＝V s -u*u T *v s ；
S55, for
And
wherein y is i Belongs to { +1, -1}, and i belongs to (1, 2, \8230;, m) < U (1, 2, \8230;, n), and the model is trained and evaluated through a SVM classification algorithm and a Bayesian parameter optimizer.
In the social event processing method applied to the comprehensive treatment field, in step S6, the result of the satisfaction survey is divided into: the method comprises the steps of obtaining a very satisfactory result, obtaining a very satisfactory result and obtaining a satisfactory event, wherein the very satisfactory result and the satisfactory event are brought into an event processing case library, and the events occurring in the future quickly recommend related cooperative departments and processing flows to users according to historical data of the event processing case library.
In the social event processing method applied to the comprehensive treatment field, the event acceptance center comprises a citizen service hotline, a petition and other event sources of relevant industry management information systems, the data structure of the accessible event is standardized, and meanwhile, the additional fields outside the basic fields are allowed to be received and a unified mode is provided for calling back the event processing process. And a diversified social event handling mode is provided, so that the social event can be fed back in time and information can be synchronously processed by each source.
In the social event processing method applied to the comprehensive treatment field, the virtual network sets the first responsible person or responsible unit of the event as the grid length, the grid automatically grows along with the social event circulation and the increase of personnel of the treatment department, and the grid length is responsible for coordinating related resources and tracking the final solution of the event. For events related to civil problems, event-related parties are added into a virtual grid, progress of the whole event is known and supervised in a mode of a PC (personal computer) end and a mobile end, and evaluation is carried out after the event is solved.
Compared with the prior art, the invention has the advantages that: the design is reasonable, the social event processing efficiency is high, the lead coordination of social event problems needing multi-department collaborative solution is strengthened, a secondary classification system of urban parts and events is defined, subclass parts and event management drawings are defined, and an acceptance department recommendation method based on the combination of RE2 and manual assignment is adopted; an event acceptance center is established, and is used for accepting events from different department systems and simultaneously used as a channel for a basic level system to apply for superior coordinated resources; designing a virtual grid, a command room and two concepts, taking an event principal and a party of a civil event as grid members, initiating an online command room aiming at the event needing cross-department cooperative processing, and inviting a relevant department to enter the command room for multi-span cooperative processing; according to the return visit and satisfaction survey of the processing result, the processing process of the good events is stored into the case model base, and when the events appear in the future, the related cooperative departments and the processing flow can be quickly recommended to the user according to the historical data of the case base, so that the processing efficiency of the social events is effectively improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a social event processing method applied to the comprehensive treatment field specifically includes the following steps:
s1, reporting event content by adopting an RE2 model, performing similarity matching with an event content text in a case library, and entering S3 for allocation processing by referring to an event matched with the case library when the event meets a threshold matching condition;
s2, identifying the event which does not meet the threshold matching condition according to a primary component/event Open type Classification model, namely an Open-set Text Classification model;
s3, transmitting the event from the event in the S1 or the event judged as the first-level component/event class in the S2 to an event acceptance center, and manufacturing a unified interface and a data structure of the access event;
s4, calling out all secondary component/event management images under the current primary component/event type from a secondary component/event management image library according to the primary component/event type of the current event, and detecting the similarity between the content of the current event and a problem description text in the secondary component/event management by adopting an RE2 model;
s5, creating a virtual network for the event, adding a responsibility department into the grid as a grid member according to the secondary component/event management image, judging whether the current event is a civil event or not according to a two-classification algorithm model, and if the current event belongs to the civil event, extracting party information from the current event by adopting a named entity extraction mode and adding the party information into the virtual grid;
and S6, event processing result return visit and satisfaction survey.
In step S1, the establishment of the RE2 model specifically includes the following steps:
s11, inputting a current event1 and a case base, and executing the following steps for each event content event2 of the case base:
s12, converting the texts event1 and event2 into vectors in an embedding form;
s13, the embedding vector sequence is sent into 3 block blocks to be continuously processed, each block has the same structure and consists of an encoder layer, an alignment layer and a fusion layer, the encoder layer calculates the context characteristics of the sequence, the alignment layer calculates the correlation characteristics of the texts event1 and event2, and the output of the fusion layer is the input of the next block or the input of the posing pooling layer;
s14, converting the result output by the block into a vector with a fixed length by the posing pooling layer;
s15, after the features are calculated by the event1 and the event2, a two-classification model is built in a prediction layer, wherein the class 0 indicates that the event1 is not similar to the event2, and the class 1 indicates that the event1 is similar to the event 2.
In step S2, there are 5 primary component categories in the primary component/event open classification model, which are respectively: public facilities, road traffic facilities, city appearance environment enforcement, landscaping facilities, and extension components; there are 10 primary event categories, which are: city appearance environment, advertising, construction management, street order, street security, market supervision, emergency, cell management, rural management and extended events, and the total number of second-level components/event categories is 235-245; respectively establishing a secondary component/event management image base for the secondary component/event, wherein the contents of the secondary component/event management image base comprise: class one component/event category, department of responsibility, problem description primary disposition requirements. The first-level component comprises urban infrastructure in an urban management public area, the first-level component comprises two levels, the first level is a major class, the second level is a minor class, and each major class consists of a plurality of minor classes; and the first-level events are related to the behavior activities of people or phenomena and behaviors that the city appearance environment and the order of the city are influenced or destroyed due to natural factors, and the first-level event category comprises two levels of a large category and a small category, wherein the large category consists of a plurality of small categories.
In step S3, a primary component/event Classification model is established by an Open-set Text Classification algorithm, the class number of the primary component/event Classification model is 12+1,12 is a definite and fixed Classification class, which includes the above 10 primary event classes and 5 primary component classes, wherein 1 is an Open class which includes new and potential component/event classes; the unified interface and data structure comprises a unified interface request mode, a data encryption mode, a department area coding mode and a callback mode. With the continuous expansion of the urban development scale and the continuous emergence of new things, part of management contents need to be expanded and perfected, and the expansion principle is as follows: according to the method that the major classes are not changeable and the minor classes are extensible, newly added components and events are added under the categories of the extended components and the extended events.
Further, an Open-set Text Classification algorithm is built based on the CNN, and when testing is carried out, the last layer of the CNN extracts sentence characteristics of input classes to obtain Activation Vectors, namely AV, then the first k distance values from the Activation Vectors of each test sample to each known Class, the Activation Vectors of the first k samples are marked as k-Class Activation Vectors, namely k-CAV, the distances between the AV and the k-CAV of the test samples are calculated, the sum of the k probability values of each training Class is marked as total closed set probability, finally OSP =1-total closed set probability is calculated, and the maximum total closed set probability of all the training classes is compared with the OSP to determine that the test Class is an unknown Class or a known Class.
In step S4, the responsibility department of the image satisfying the maximum threshold condition is the recommended processing department of the event, and if the threshold condition cannot be satisfied, the responsibility department is manually assigned, and the staff can determine whether to create the secondary component/event management image of the event.
In step S5, the building of the binary algorithm model specifically includes the following steps:
s51, forming a classified training corpus S by contents except the character information in the event text, manually marking the predictive variable of the corpus S, and recording y i =1 denotes a civil event, y i =1 represents a non-civil event;
s52, dividing the sentence set S into a string and a Stest according to the ratio of 8:2, and calculating each sentence in the string and the Stest according to the following formula:
s53, combining all sentence vectors in the string to obtain a matrix X, and calculating a first principal component u of the X through TruncatedSVD;
s54, performing the following calculation on each sentence vector Vs in the string and the Stest: v. of s ＝v s -u*u T *v s ；
S55, for
And
wherein y is i Belongs to { +1, -1}, and i belongs to (1, 2, \8230;, m) U (1, 2, \8230;, n), and the model is trained and evaluated through a Support Vector Machine (SVM) classification algorithm and a Bayes parameter optimizer. In addition, the invention provides an extension method, which allows an authorized third-party system to access the event processing method, and facilitates processing departments at different levels and processing flows of different event types in a customized and rich manner. In order to realize the purpose, the invention designs a set of expansion interface and access authentication scheme:
1. the system provides frame specifications according to three unification of a unified interface style, unified interface calling and unified authority control, and a third party can realize seamless access of a self service system by developing and butting according to the specifications;
2. the system adopts a front-end and back-end separation mode, a js script plug-in is provided at the front end, and after the plug-in is introduced into a third-party page, the page style is automatically specified, the plug-in is inserted into a buried point, and the plug-in is connected to a back-end interface; after the developed front-end page is embedded into the system, a dynamic login token can be obtained in the opening process;
3. the system provides the back-end sdk of various commonly used development languages, a safe encryption logic and an open interface are encapsulated, and a third party can conveniently access and call the interface provided by the system only by configuring a host, a key and a secret key; the back end of the third party can acquire the current login user, authority and service information in real time according to the dynamic token taken by the front end, so that the self-owned service process in the third party is continued;
4. providing an encryption logic description for self development access of a development language which is not provided with sdk support;
based on the scheme, the invention not only realizes high expansion flexibility, but also has strict standardization.
In detail, in step S6, the result of the satisfaction survey is divided into: the method comprises the steps of obtaining a very satisfactory result, and bringing the very satisfactory and satisfactory event into an event processing case base, wherein the event occurring in the future quickly recommends a relevant cooperative department and a processing flow to a user according to historical data of the event processing case base. The method helps the user to quickly create an effective command room and solve the problem as soon as possible; the command room invites responsible units of the same administrative region or different administrative regions to establish a multi-department cooperative processing command center aiming at the processing events of cross-department or cross-administrative regions, so that the phenomena of tearing and withering are reduced, the smooth solution of social events is promoted, and the processing efficiency of the social events is improved; and when the events appearing in the future use a recommendation algorithm to quickly recommend related cooperative departments and processing flows to the user according to the historical data of the case base, and the user is assisted to quickly create an effective command room.
Furthermore, the event handling center comprises a citizens service hotline, a petition and other event sources of related industry management information systems, and the event handling center regulates a data structure of an accessible event, allows additional fields outside a basic field to be received and provides a uniform mode for calling back an event processing process.
Preferably, the virtual network sets the first person in charge or responsible unit of the event as the grid length, which is responsible for coordinating the related resources and tracking the final resolution of the event, automatically grows as the number of people in the event circulation and the processing department increases. For the social events related to the civil problems, the parties related to the social events are added into the virtual grid, the progress of the whole event is known and monitored in a mode of a PC (personal computer) end and a mobile end, and evaluation is carried out after the event is solved.
In summary, the principle of the present embodiment is: the social events are accessed by building an event acceptance center with a unified interface for accessing the events and a data structure, intelligent recommendation is performed on a processing department of the social events, quick distribution is facilitated for workers, an actual assignment result can be used as a training material to perform reverse training on a recommendation algorithm, and the recommendation accuracy is improved;
secondly, establishing a virtual network in the social event processing process, initiating an online command room according to needs, applying for multi-department cooperation, enabling related personnel to participate in the cooperative processing process of the whole event through a PC (personal computer) end or a mobile end, and finally feeding a processing result back to all related personnel on an event processing flow line in real time, so as to meet the real-time and high-efficiency of communication in the command room and the smoothness of video and voice cooperative communication, and establishing a hardware server special for the command room;
and finally, after the social event is processed, carrying out satisfaction survey, bringing the event with a very satisfactory satisfaction result and a satisfactory result into an event processing case base, automatically training a recommendation algorithm according to a new case regularly to generate a new model, improving the recommendation accuracy of an event processing mode, and quickly recommending related cooperative departments and processing flows to a user for future social events according to historical data of the event processing case base.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments, or alternatives may be employed, by those skilled in the art, without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (10)
1. A social event processing method applied to the field of comprehensive treatment is characterized by specifically comprising the following steps:
s1, reporting event content by adopting an RE2 model, performing similarity matching with an event content text in a case library, and entering S3 for allocation processing by referring to an event matched with the case library when the event meets a threshold matching condition;
s2, identifying the event which does not meet the threshold matching condition according to a primary component/event Open type Classification model, namely an Open-set Text Classification model;
s3, transmitting the event from the event in the S1 or the event judged as the first-level component/event class in the S2 to an event acceptance center, and manufacturing a unified interface and a data structure of the access event;
s4, calling out all secondary component/event management images under the current primary component/event type from a secondary component/event management image library according to the primary component/event type of the current event, and detecting the similarity between the content of the current event and a problem description text in secondary component/event management by adopting an RE2 model;
s5, creating a virtual network for the event, managing the portrait according to the secondary component/event, adding the responsibility department into the grid as a grid member, judging whether the current event is a civil event or not according to a two-classification algorithm model, and if the current event belongs to the civil event, extracting information of a party from the current event by adopting a named entity extraction mode and adding the information into the virtual grid;
and S6, event processing result return visit and satisfaction survey.
2. The social event processing method applied to the comprehensive treatment field according to claim 1, wherein in the step S1, the establishing of the RE2 model specifically comprises the following steps:
s11, inputting a current event1 and a case base, and executing the following steps for each event content event2 of the case base:
s12, converting the texts event1 and event2 into vectors in an embedding form;
s13, the embedding vector sequences are sent into 3 block blocks to be continuously processed, each block has the same structure and consists of an encoder layer, an alignment layer and a fusion layer, the encoder layer calculates the context characteristics of the sequences, the alignment layer calculates the correlation characteristics of the texts event1 and event2, and the output of the fusion layer is the input of the next block or the input of the posing pooling layer;
s14, converting the result output by the block into a vector with a fixed length by the posing pooling layer;
and S15, after calculating features of the event1 and the event2, constructing a two-classification model at a prediction layer, wherein the category 0 indicates that the event1 is not similar to the event2, and the category 1 indicates that the event1 is similar to the event 2.
3. The method for processing social events applied to the comprehensive treatment field according to claim 1, wherein in step S2, there are 5 primary component categories in the primary component/event open-type classification model, which are respectively: public facilities, road transportation facilities, city appearance environment enforcement, landscaping facilities, and expansion components; there are 10 primary event categories, which are: city appearance environment, advertising, construction management, street order, street security, market supervision, emergency, cell management, rural management and extended events, and the total number of second-level components/event categories is 235-245; establishing a secondary component/event management representation library for the secondary component/event respectively, the contents of the secondary component/event management representation library comprising: class of belonging primary component/event, department of responsibility, problem description primary disposition requirement.
4. The social event processing method applied to the comprehensive field according to claim 1, wherein in step S3, a primary component/event Classification model is established through an Open-set Text Classification algorithm, the category number of the primary component/event Classification model is 12+1,12 is a definite and fixed Classification category, which includes the above 10 primary event categories and 5 primary component categories, wherein 1 is an Open category, which includes new and potential component/event categories; the unified interface and data structure comprises a unified interface request mode, a data encryption mode, a department area coding mode and a callback mode.
5. The social event processing method applied to the field of comprehensive treatment as claimed in claim 4, wherein the Open-set Text Classification algorithm is built based on CNN, and when a test is performed, the last layer of CNN extracts sentence features of an input Class to obtain an Activation Vector, namely AV, then calculates the distance from the Activation Vector of each test sample to the first k nearest distance of each known Class, records the Activation Vectors of the first k samples as k-Class Activation Vectors, namely k-CAV, calculates the distance between the test sample AV and the k-CAV, records the sum of k probability values of each training Class as total closed set probability, finally calculates OSP =1-total closed probability, and compares the maximum total closed set probability of all training classes with OSP to determine that the test Class is an unknown Class or a known Class.
6. The method as claimed in claim 5, wherein in step S4, the responsibility department of the image satisfying the maximum threshold condition is the recommended processing department of the event, and if the threshold condition cannot be satisfied, the responsibility department is manually assigned, so that the staff can determine whether to create the secondary part/event management image of the event.
7. The social event processing method applied to the comprehensive treatment field according to claim 6, wherein in the step S5, the establishing of the two-classification algorithm model specifically comprises the following steps:
s51, forming a classified training corpus S by contents except the text information in the event text, manually marking the predictive variable of the corpus S, and recording y i =1 denotes a civil event, y i = -1 denotes non-civil event;
s52, according to the sentence set S, the sentence set S is set according to the following steps of 8:2 into Strain and Stest, calculated for each sentence in Strain and Stest according to the following formula:
s53, combining all sentence vectors in the string to obtain a matrix X, and calculating a first principal component u of the X through a Trun catedSVD;
s54, performing the following calculation on each sentence vector Vs in the string and the Stest: v. of s ＝v s -u*u T *v s ；
S55, for
And
wherein y is i Belongs to { +1, -1}, and i belongs to (1, 2, \8230;, m) U (1, 2, \8230;, n), and the model is trained and evaluated through a Support Vector Machine (SVM) classification algorithm and a Bayes parameter optimizer.
8. The social event processing method applied to the comprehensive treatment field according to claim 1, wherein in step S6, the result of the satisfaction survey is divided into: very satisfactory, substantially satisfactory, unsatisfactory and very unsatisfactory, with the satisfaction result being very satisfactory and the events being satisfactory being included in a case base, with future occurrences of the events being based on
And quickly recommending related cooperative departments and processing flows to the user by the historical data of the case base.
9. The method as claimed in claim 8, wherein the event processing center includes a citizen service hotline, a petition and other event sources of related industry management information system, and the data structure of the accessible event is standardized, and the method allows receiving additional fields outside the basic field and provides a uniform way to call back the event processing procedure.
10. The social event processing method applied to the comprehensive treatment field as claimed in claim 9, wherein the virtual network sets a first responsible person or responsible unit of the event as a grid length, the grid automatically grows as the number of the event circulation and the personnel of the treatment department increases, and the grid length is responsible for coordinating related resources and tracking the final solution of the event. For the event related to the civil problem, the event related parties are added into the virtual grid, the progress of the whole event is known and monitored in a mode of a PC (personal computer) end and a mobile end, and evaluation is carried out after the event is solved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738718.5A CN115203365A (en) | 2022-06-24 | 2022-06-24 | Social event processing method applied to comprehensive treatment field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738718.5A CN115203365A (en) | 2022-06-24 | 2022-06-24 | Social event processing method applied to comprehensive treatment field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115203365A true CN115203365A (en) | 2022-10-18 |
Family
ID=83577467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210738718.5A Pending CN115203365A (en) | 2022-06-24 | 2022-06-24 | Social event processing method applied to comprehensive treatment field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115203365A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629804A (en) * | 2023-06-06 | 2023-08-22 | 河北华正信息工程有限公司 | Letters, interviews, supervision and tracking management system and management method |
-
2022
- 2022-06-24 CN CN202210738718.5A patent/CN115203365A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629804A (en) * | 2023-06-06 | 2023-08-22 | 河北华正信息工程有限公司 | Letters, interviews, supervision and tracking management system and management method |
| CN116629804B (en) * | 2023-06-06 | 2024-01-09 | 河北华正信息工程有限公司 | Letters, interviews, supervision and tracking management system and management method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021184836A1 (en) | Method and apparatus for training recognition model, device, and readable storage medium | |
| CN111506722A (en) | Knowledge graph question-answering method, device and equipment based on deep learning technology | |
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| CN109740928A (en) | Electric power consultation service treating method and apparatus | |
| CN110472017A (en) | A kind of analysis of words art and topic point identify matched method and system | |
| CN115511501A (en) | Data processing method, computer equipment and readable storage medium | |
| WO2021169364A1 (en) | Semantic emotion analysis method and apparatus, device, and storage medium | |
| CN114398669B (en) | Combined credit scoring method and device based on privacy protection calculation and cross-organization | |
| CN109408574B (en) | Complaint responsibility confirmation system based on text mining technology | |
| CN117745048B (en) | Creative flow management method assisted by artificial intelligence | |
| CN101556582A (en) | System for analyzing and predicting netizen interest in forum | |
| CN114491168B (en) | Method and system for regulating and controlling cloud sample data sharing, computer equipment and storage medium | |
| CN113570222A (en) | User equipment identification method and device and computer equipment | |
| CN115203365A (en) | Social event processing method applied to comprehensive treatment field | |
| CN117688165B (en) | Multi-edge collaborative customer service method, device, equipment and readable storage medium | |
| CN114385609A (en) | Label-based government affair event processing system, method, equipment and storage medium | |
| CN113407726A (en) | Emergency disposal plan method and system | |
| CN117556048A (en) | Artificial intelligence-based intention recognition method, device, equipment and medium | |
| CN115131052A (en) | Data processing method, computer equipment and storage medium | |
| CN115982646B (en) | Management method and system for multisource test data based on cloud platform | |
| CN116739408A (en) | Power grid dispatching safety monitoring method and system based on data tag and electronic equipment | |
| CN116910341A (en) | Label prediction method and device and electronic equipment | |
| CN113032577B (en) | Method and system for constructing knowledge graph of power system and identifying defect target | |
| Li et al. | Enterprise precision marketing effectiveness model based on data mining technology | |
| Yuan et al. | Critical risks identification of Public Private Partnerships in China and the analysis on questionnaire survey |
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 |