CN114492663B - Event intelligent allocation method, device, equipment and storage medium - Google Patents
Event intelligent allocation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114492663B CN114492663B CN202210137918.5A CN202210137918A CN114492663B CN 114492663 B CN114492663 B CN 114492663B CN 202210137918 A CN202210137918 A CN 202210137918A CN 114492663 B CN114492663 B CN 114492663B
- Authority
- CN
- China
- Prior art keywords
- event
- vector set
- preset
- text
- vector
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000013598 vector Substances 0.000 claims abstract description 236
- 230000007613 environmental effect Effects 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 52
- 238000007637 random forest analysis Methods 0.000 claims abstract description 43
- 238000013139 quantization Methods 0.000 claims abstract description 17
- 238000012216 screening Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 23
- 238000003066 decision tree Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000007726 management method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- -1 noise Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 239000002910 solid waste Substances 0.000 description 2
- 238000003911 water pollution Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- 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
- G06Q10/06398—Performance of employee with respect to a job function
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses an event intelligent allocation method, which comprises the following steps: collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set; classifying the text vector set in a grading manner based on a pre-constructed random forest classification model; screening out a repeated problem set and a non-repeated problem set from the problem set by utilizing a pre-constructed automatic weight judging model, processing the repeated problem set, and generating an environmental problem event set by utilizing the non-repeated problem set; and calculating the comprehensive score of the disposal personnel in the preset disposal personnel group, and distributing the problem event to the corresponding disposal personnel for processing based on the classification result and the comprehensive score. In addition, the present invention relates to blockchain technology, and the problem set can be stored in nodes of the blockchain. The invention also provides a problem event intelligent distributing device, electronic equipment and a storage medium. The invention can improve the accuracy and efficiency of problem time allocation.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to an event intelligent allocation method, an event intelligent allocation device, an electronic device, and a computer readable storage medium.
Background
The public service system for processing the environmental problem event in the construction of the smart city has a plurality of sources and routes of the environmental problem event, and the event needs to be allocated and then processed.
The current environmental problem event distribution method mainly has the following two problems: 1. the tasks are allocated manually through judgment of allocation personnel, the allocation personnel often carry out manual judgment to allocate according to the contents such as the source, the type and the problem description of the event by virtue of own experience, and the allocation accuracy is low; 2. the source of each event data is single, the related event data of a plurality of business departments cannot be integrated, the overall supervision cannot be realized, each event is allocated, and the situation of processing repeated events exists.
In summary, the current environmental problem event allocation has the problem of low allocation accuracy and efficiency.
Disclosure of Invention
The invention provides an event intelligent distribution method, an event intelligent distribution device and a computer readable storage medium, and mainly aims to solve the problem of lower accuracy in product recommendation.
In order to achieve the above object, the present invention provides an event intelligent distributing method, including:
Collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
extracting a time text vector set in the text vector set, and grading the time text vector set based on a pre-constructed first random forest classification model to obtain the emergency degree of each environmental problem in the problem set;
Extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set;
Extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
Performing de-duplication treatment on the problem set by using a pre-constructed automatic duplication judgment model, generating a problem event set according to the de-duplication treated problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The emergency degree, the importance degree, the problem category and the region attribute of the problem event are obtained from the library to be allocated, the comprehensive score of the disposal personnel in the preset disposal personnel group is calculated, and the problem event is allocated to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
Optionally, the quantization processing is performed on the problem set to obtain a text vector set, including:
word segmentation is carried out on the problem set to obtain a word set;
Quantizing the word set by using a pre-constructed quantization tool to obtain a word vector set;
sequentially labeling the word vector sets according to preset position codes to obtain sequential word vector sets;
splitting the sequential word vector set according to a preset formatting rule, and arranging splitting results to obtain a text vector set of matrix vectors.
Optionally, before grading the time text vector set based on the first pre-constructed random forest classification model to obtain the emergency degree of each environmental problem in the problem set, the method further includes:
Selecting one of the time text vectors from the time text vector set one by one as a target time text vector;
The target time text vector is used as a parameter to carry out assignment on a preset decision function, and the assigned decision function is used as a decision condition to generate a decision tree;
and summarizing the obtained decision tree to obtain the first random forest classification model.
Optionally, the screening the repeated problem set from the problem set by using the pre-constructed automatic weight judging model includes:
extracting text feature vectors of all the problems in the problem set by using a BERT model in a pre-constructed automatic weight judging model;
calculating similarity scores among text feature vectors of all problems by using a preset similarity calculation model in a preset automatic weight judging model;
when the similarity score is greater than or equal to a preset similarity threshold, defining the corresponding environmental problem as a first type of repeated problem;
Calculating the similarity score of the text feature vector of each problem and the text feature vector of the problem event in the preset allocated library by using the similarity calculation model;
when the similarity score is greater than or equal to a preset similarity threshold, defining the corresponding environmental problem as a second type of repeated problem;
And converging the first type of repeated problems and the second type of repeated problems to obtain a repeated problem set, and performing de-duplication treatment on the repeated problem set according to a preset rule.
Optionally, the calculating the similarity score between the text feature vectors of each problem by using a preset similarity calculation model in the preset automatic weight judging model includes:
randomly selecting a text feature vector of one of the problems as a first text feature vector, and calculating the similarity between the first text feature vector and each other text feature vector in the environmental problem to obtain a similarity matrix;
Carrying out normalization weighting treatment on the similarity matrix according to rows and columns to obtain attention weight;
Weighting the first text feature vector and the other text feature vectors by using the attention weight to obtain a weighted first text feature vector and weighted other text feature vectors respectively;
And splicing the weighted first text feature vector and the weighted other text feature vectors, and calculating to obtain the similarity score of the spliced first text feature vector and the weighted other text feature vectors through a softmax function. Alternatively, the process may be carried out in a single-stage,
Optionally, the performing deduplication processing on the duplicate problem set according to a preset rule includes:
Merging two of the first type of repeat questions;
And establishing association between the second type of repeated problems and corresponding problem events in the preset allocated library.
Optionally, the importance degree, the question category, the region attribute and the composite score distribute the question event to corresponding disposal personnel for processing, including:
Acquiring the number of events currently processed by a disposal person, and grading the load of the disposal person according to the number of events;
acquiring the preset end date of a current processing event of a disposal person, and grading the task clinic period of the disposal person according to the end date;
Comprehensively calculating the comprehensive score of the disposal personnel according to the load score and the task clinical score;
selecting a preset disposal personnel group according to the emergency degree, the importance degree, the problem category and the regional attribute;
selecting a disposal person with high comprehensive score from the preset disposal person group, and distributing the problem event to the disposal person with high comprehensive score.
In order to solve the above problems, the present invention further provides an intelligent distribution device for environmental problem events, the device comprising:
the text vector acquisition module is used for acquiring problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
The classification and grading module is used for extracting a time text vector set in the text vector set, grading the time text vector set based on a pre-constructed first random forest classification model, and obtaining the emergency degree of each environmental problem in the problem set; extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set; extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
The de-duplication module is used for de-duplication processing the problem set by utilizing a pre-built automatic duplication judgment model, generating a problem event set according to the de-duplication processed problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The event distribution module is used for acquiring the emergency degree, the importance degree, the problem category and the region attribute of the problem event from the library to be distributed, calculating the comprehensive score of the disposal personnel in the preset disposal personnel group, and distributing the problem event to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the event intelligent distribution method described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the event intelligent distribution method described above.
According to the embodiment of the invention, the text vector set is obtained by collecting the problem sets of different channel sources and carrying out quantization processing on the problem sets; extracting a time text vector set in the text vector set, classifying the time text vector set in a grading manner based on a pre-constructed random forest classification model to obtain the emergency degree, the importance degree, the problem category and the regional attribute of each environmental problem in the problem set, classifying the problem set in a grading manner, facilitating flattening management and improving allocation accuracy; screening out a repeated problem set and a non-repeated problem set from the problem set by utilizing a pre-constructed automatic weight judging model, processing the repeated problem set, generating an environment problem event set by utilizing the non-repeated problem set, and identifying repeated problems, thereby being beneficial to reducing the repeated processing times of the problem events and further improving the efficiency of distributing the problem events; calculating the comprehensive score of the disposal staff in the preset disposal staff group, distributing the problem event to the corresponding disposal staff for processing based on the emergency degree, the importance degree, the problem category, the regional attribute and the comprehensive score of the disposal staff, calculating the score of the disposal staff in the preset disposal staff group, distributing the new task to the disposal staff with fewer tasks and low emergency degree preferentially, and improving the problem event distribution accuracy and efficiency. Therefore, the intelligent event distribution method, the intelligent event distribution device, the electronic equipment and the computer readable storage medium can solve the problem of low accuracy and efficiency of event distribution.
Drawings
Fig. 1 is a flow chart of an event intelligent allocation method according to an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating a detailed implementation flow of one of the steps in the intelligent event distribution method shown in FIG. 1;
FIG. 3 is a schematic diagram illustrating a detailed implementation flow of another step in the event intelligent distribution method shown in FIG. 1;
FIG. 4 is a functional block diagram of an intelligent distribution device for environmental problem events according to an embodiment of the present invention;
Fig. 5 is a schematic structural diagram of an electronic device for implementing the event intelligent allocation method according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an event intelligent allocation method. The execution subject of the event intelligent allocation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the event intelligent distribution method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of an intelligent event distribution method according to an embodiment of the invention is shown. In this embodiment, the event intelligent allocation method includes:
s1, collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set.
In one embodiment of the present invention, the problem set from different channel sources may include problem logs generated by automatic monitoring devices of all environmental elements such as atmosphere, water, ecological environment, radiation, soil, noise, solid waste, and motor vehicle supervision, or environmental problems generated by systems such as a letter complaint system, a grid inspection system, and an environmental pollution online monitoring system.
In detail, the quantization processing of the question set in S1 to obtain a text vector set includes:
word segmentation is carried out on the problem set to obtain a word set;
Quantizing the word set by using a pre-constructed quantization tool to obtain a word vector set;
sequentially labeling the word vector sets according to preset position codes to obtain sequential word vector sets;
splitting the sequential word vector set according to a preset formatting rule, and arranging splitting results to obtain a text vector set of matrix vectors.
According to the embodiment of the invention, the word set is obtained through word segmentation operation, and then the word set is quantized through quantization tools such as word2Vec models to obtain the word vector set, and as the data of the word vector set are discrete and are unfavorable for subsequent classification, the word vector set is subjected to sentence segmentation and sorting operation through preset position codes such as [ extra-sentence codes (E_ A, E _ B, E _C … …) and intra-sentence codes (E_0, E_1 and E_2 … …) ], so that a sequential word vector set is obtained. Wherein the word2S6Vec model is a group of related models used to generate word vectors, and the word-to-word relationships are represented by mapping each word to a word vector.
In the embodiment of the invention, the text vector set can be divided into a time text vector set, a question type vector set, an environment type vector set and a place information vector set according to different data types. Wherein the time text vector set refers to text vectors with time labels in the text vector set. Such as the occurrence time, end time, etc. of the problem. The question type vector set refers to the source type of the question in the text vector set. In the embodiment of the invention, the problem type vector set comprises request law enforcement, equipment calibration, letter complaints, data anomalies and the like; the environment type vector set refers to an environment type corresponding to the problem in the text vector set, and in the embodiment of the invention, the environment type comprises air, wading, ecological environment, radiation, soil, noise, solid waste and the like. The location information vector set refers to location information contained in the text vector set. The location information is a location where a problem occurs, such as a province, a city, a district, a street, a cell, or a road name, etc. where the problem occurs.
S2, extracting a time text vector set in the text vector set, and grading the time text vector set based on a pre-constructed first random forest classification model to obtain the emergency degree of each environmental problem in the problem set.
In the embodiment of the invention, the Random Forest algorithm (RF for short) is an algorithm for integrating a plurality of trees through the idea of ensemble learning, and the basic unit of the algorithm is a decision tree. Taking the classification problem as an example, each decision tree is a classifier, for one input sample, N classification results are obtained for N trees, all classification voting results are integrated by random forests, and the class with the largest voting frequency is designated as the final output, so that the optimal class is obtained.
In one embodiment of the present invention, before the classifying the time text vector set based on the first random forest classification model constructed in advance in S2 to obtain the emergency degree of each environmental problem in the problem set, the method further includes:
Selecting one of the time text vectors from the time text vector set one by one as a target time text vector;
The target time text vector is used as a parameter to carry out assignment on a preset decision function, and the assigned decision function is used as a decision condition to generate a decision tree;
and summarizing the obtained decision tree to obtain the first random forest classification model.
Illustratively, the decision function may be:
wherein f (x) is the output value of the decision function, x is the parameter of the decision function, and g (y) is the input value of the decision function.
In detail, the embodiment of the invention can select one of the time text vectors from the time text vector set one by one as a target time text vector, assign the parameter x of the decision function by using the target time text vector, and generate the following decision tree by taking the assigned decision function as a decision condition:
when the input value g (y) of the decision tree is the same as the parameter x of the decision tree, the decision tree outputs a value f (x) =α;
When the input to the decision tree g (y) is different from the parameter x of the decision tree, the decision tree outputs a value f (x) =β.
In the embodiment of the invention, the decision trees corresponding to each time text vector in the time text vector set can be collected in a parallel or serial mode to obtain a first random forest classification model.
Further, the classifying the time text vector set based on the first random forest classification model constructed in advance to obtain the emergency degree of each environmental problem in the problem set, including:
Acquiring a plurality of decision trees in the first random forest classification model and decision dimension indexes and decision conditions of at least one layer of nodes in each decision tree;
Performing feature extraction on the time text vector set according to a decision dimension index of a first node in the first random forest classification model to obtain a feature value of the time text vector set on a split dimension of the first node;
Judging the characteristic value according to the decision condition of the first node, and determining a traversed second node from branch nodes of the first node according to a judgment result;
and continuously extracting the characteristic value of the time text vector set at the second node according to the current decision dimension index and decision conditions, and determining the next node to be traversed until the decision tree is traversed, so as to obtain the emergency degree of each environmental problem in the problem set.
In the embodiment of the invention, the decision dimension index is used for uniquely determining a split dimension, and the split dimension and the decision condition are used for determining the next node to be traversed from branch nodes of the corresponding nodes.
In the embodiment of the present invention, the emergency degree of the environmental problem is classified by using the time text vector, for example: the environmental problems are classified as urgent, general, and are easily distributed to the blind disposal staff according to the degree of urgency.
S3, extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain importance degrees of all environmental problems in the problem set.
In the embodiment of the present invention, the step of classifying the problem type vector set based on the second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set is similar to the step of classifying the time text vector set based on the first random forest classification model constructed in advance in S2 to obtain the urgency degree of each environmental problem in the problem set, and will not be described herein.
In the embodiment of the invention, the questions are classified according to the question types in the question type vector set to obtain the importance degree of each question. For example: the problems are divided into primary early warning, secondary early warning, tertiary early warning and the like, and the problems can be distributed to disposal staff of different levels according to the importance degree of the problems.
S4, extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem category set and a region attribute set of each environment problem in the problem set.
In the embodiment of the present invention, the step of classifying the environment type vector set and the location information vector set based on the third random forest classification model constructed in advance to obtain a problem class set and a region attribute set of each environmental problem in the problem set is similar to the step of classifying the time text vector set based on the first random forest classification model constructed in advance in S2 to obtain the urgency degree of each environmental problem in the problem set, and will not be described herein.
In the embodiment of the invention, the problems are classified according to the environment types in the environment type vector set to obtain the problem types and the area attributes of the problems, and the problems are pushed to different treatment departments according to the problem types and the area attributes.
In one embodiment of the present invention, the steps S2, S3, S4 are not in a fixed sequence, and may be executed in parallel, or may be executed sequentially in any sequence.
S5, performing de-duplication processing on the problem set by using a pre-built automatic duplication judgment model, generating a problem event set according to the de-duplication processed problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and region attribute into a preset library to be allocated.
In the embodiment of the invention, the automatic weight judging model can be constructed by a BERT model and a similarity calculation model together; the BERT model is a large-scale pre-training language model based on a bidirectional transducer, has strong language characterization capability and characteristic extraction capability, and can extract and match the characteristics of each word in a text; the similarity calculation model comprises a similarity matching layer and a full-connection layer, wherein the similarity matching layer can carry out outer product on texts to be matched to obtain a similarity matrix; wherein the fully connected layer can normalize the two-dimensional vector by softmax to obtain a similarity score.
In detail, referring to fig. 2, the performing a de-duplication process on the problem set using the pre-constructed automatic duplication judgment model in S5 includes:
s51, extracting text feature vectors of all problems in the problem set by using a BERT model in a pre-constructed automatic weight judging model;
S52, calculating similarity scores among text feature vectors of all the problems by using a similarity calculation model preset in the pre-built automatic weight judging model;
s53, defining the corresponding environmental problems as first-class repeated problems when the similarity score is greater than or equal to a preset similarity threshold;
S54, calculating the similarity score of the text feature vector of each problem and the text feature vector of the problem event in the preset allocated library by using the similarity calculation model;
S55, defining the corresponding problem as a second type repeated problem when the similarity score is greater than or equal to a preset similarity threshold;
s56, converging the first type of repeated problems and the second type of repeated problems to obtain a repeated problem set, and performing de-duplication processing on the repeated problem set according to a preset rule.
In detail, referring to fig. 3, the step S52 further includes:
S521, randomly selecting a text feature vector of one of the problems as a first text feature vector, and calculating the similarity between the first text feature vector and each other text feature vector in the problem to obtain a similarity matrix;
S522, carrying out normalization weighting processing on the similarity matrix according to rows and columns to obtain attention weights;
S523, weighting the first text feature vector and the other text feature vectors by using the attention weight to obtain a weighted first text feature vector and weighted other text feature vectors respectively;
s524, splicing the weighted first text feature vector and the weighted other text feature vectors, and calculating through a softmax function to obtain similarity scores of the spliced first text feature vector and the weighted other text feature vectors.
According to the embodiment of the invention, the accuracy of similarity score calculation between the problems is improved through the attention weight, so that the accuracy of problem event distribution is improved.
Further, in S56, the performing deduplication processing on the duplicate problem set according to a preset rule includes:
Merging two of the first type of repeat questions;
And establishing association between the second type of repeated problems and corresponding problem events in the preset allocated library.
The embodiment of the invention combines two repeated problems in the first type of repeated problems, defines the combined problems as problem events, defines the combined repeated problems as repeated events, and stores the repeated events into a preset library to be confirmed. After the problem event is treated, the handling flow of the problem event is automatically associated to the corresponding repeated event, and meanwhile, the handling flow of the corresponding repeated event is activated. The repeated problems are automatically identified, so that the repeated processing times of the environmental problem events are reduced, and the efficiency of distributing the environmental problem events is improved.
Further, in the embodiment of the present invention, a second type of repeated problems are associated with problem events in the preset allocated library, and after the problem events in the preset allocated library are processed, the to-be-allocated library is automatically associated, and meanwhile, the processing flow of the second type of repeated problems is activated.
S6, acquiring the emergency degree, the importance degree, the problem category and the region attribute of the problem event from the library to be allocated, calculating the comprehensive score of the disposal personnel in the preset disposal personnel group, and distributing the problem event to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
In detail, the calculating a composite score of the treatment staff in the preset treatment staff group in S6 assigns the problem event to the corresponding treatment staff for processing based on the urgency level, the importance level, the problem category, the region attribute, and the composite score includes:
Acquiring the number of events currently processed by a disposal person, and grading the load of the disposal person according to the number of events;
the calculation method of the load score by the treatment personnel is as follows:
Wherein the method comprises the steps of Scoring the load of the jth treatment person; j is the j-th disposal person; a is the mark of the load score; t j is the task number of the disposal personnel; max jTj is the number of maximum events for the jth handler, min jTj is the number of minimum events for the jth handler.
Acquiring the preset end date of a current processing event of a disposal person, and grading the task clinic period of the disposal person according to the end date;
Wherein the method comprises the steps of Task clinical scores for the j-th treatment person; j is the j-th disposal person; c is the mark of the task deadline score;
Comprehensively calculating the comprehensive score of the disposal personnel according to the load score and the task clinical score;
selecting a preset disposal personnel group according to the emergency degree, the importance degree, the problem category and the regional attribute;
selecting a disposal person with high comprehensive score from the preset disposal person group, and distributing the problem event to the disposal person with high comprehensive score.
In the embodiment of the invention, the disposal personnel groups are classified according to different service systems and different areas, for example, emergency degree corresponding to a certain environmental problem event is emergency, importance degree is secondary, problem category is water pollution, area attribute is a certain street, and the emergency degree is distributed to law enforcement personnel groups of environmental protection departments corresponding to the certain street; for example, the emergency degree corresponding to a certain environmental problem event is general, the importance degree is three-level, the problem category is water pollution, and the regional attribute is that a certain street is allocated to a grid personnel group of an environmental protection department corresponding to a certain street.
Further, the embodiment of the invention selects the high-scoring processor to process the problem according to the comprehensive score of the processor in the corresponding processor group.
According to the embodiment of the invention, the comprehensive scoring is carried out on the disposal staff according to the number of the events currently processed by the disposal staff and the preset ending date of the current processing event, and the environmental problem event is distributed to the disposal staff with high comprehensive score in the disposal staff group. The management system can take the balance of the existing task load of each disposal person and the emergency degree of the problem event of the establishment into consideration, and preferentially distributes new tasks to disposal persons with fewer tasks and low emergency degree, and supports the realization responsibility to the person and the flattening management mode.
According to the embodiment of the invention, the text vector set is obtained by collecting the problem sets of different channel sources and carrying out quantization processing on the problem sets; extracting a time text vector set in the text vector set, classifying the time text vector set in a grading manner based on a pre-constructed random forest classification model to obtain the emergency degree, the importance degree, the problem category and the regional attribute of each environmental problem in the problem set, classifying the problem set in a grading manner, facilitating flattening management and improving allocation accuracy; screening out a repeated problem set and a non-repeated problem set from the problem set by utilizing a pre-constructed automatic weight judging model, processing the repeated problem set, generating an environment problem event set by utilizing the non-repeated problem set, and identifying repeated problems, thereby being beneficial to reducing the repeated processing times of the problem events and further improving the efficiency of distributing the problem events; calculating the comprehensive score of the disposal staff in the preset disposal staff group, distributing the problem event to the corresponding disposal staff for processing based on the emergency degree, the importance degree, the problem category, the regional attribute and the comprehensive score of the disposal staff, calculating the score of the disposal staff in the preset disposal staff group, distributing the new task to the disposal staff with fewer tasks and low emergency degree preferentially, and improving the problem event distribution accuracy and efficiency. Therefore, the intelligent event distribution method provided by the invention can solve the problems of low accuracy and efficiency of event distribution.
Fig. 4 is a functional block diagram of an intelligent distribution device for environmental problem events according to an embodiment of the present invention.
The intelligent distribution device 100 for environmental problem events can be installed in electronic equipment. Depending on the implementation, the intelligent distribution device 100 for environmental problem events may include a text vector acquisition module 101, a classification and classification module 102, a deduplication module 103, and an event distribution module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
The text vector acquisition module 101 is configured to acquire problem sets from different channels, and perform quantization processing on the problem sets to obtain a text vector set;
The classification and grading module 102 is configured to extract a time text vector set in the text vector set, and grade the time text vector set based on a pre-constructed first random forest classification model, so as to obtain the urgency degree of each environmental problem in the problem set; extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set; extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
The de-duplication module 103 is configured to perform de-duplication processing on the problem set by using a pre-built automatic duplication judgment model, generate a problem event set according to the de-duplication processed problem set, and store the problem event set and the corresponding urgency, importance, problem category and region attribute into a preset library to be allocated;
The event distribution module 104 is configured to obtain an urgency degree, an importance degree, a problem category, and an area attribute of the problem event from the library to be distributed, calculate a comprehensive score of a disposal person in a preset disposal person group, and distribute the problem event to a corresponding disposal person for processing based on the urgency degree, the importance degree, the problem category, the area attribute, and the comprehensive score.
In detail, each module in the intelligent distribution device 100 for environmental problem event in the embodiment of the present invention adopts the same technical means as the intelligent distribution method for event described in fig. 1 to 3, and can produce the same technical effects, which are not described herein.
Fig. 5 is a schematic structural diagram of an electronic device for implementing an event intelligent allocation method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as an environmental problem event intelligent distribution program, stored in the memory 11 and executable on the processor 10.
The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (e.g., execution of an environmental problem event intelligent distribution program, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device and process data.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various data such as codes of an intelligent distribution program of an environmental problem event, etc., but also for temporarily storing data that has been output or is to be output.
The communication bus 12 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 5 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The intelligent allocation of environmental problem events program stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, can implement:
Collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
extracting a time text vector set in the text vector set, and grading the time text vector set based on a pre-constructed first random forest classification model to obtain the emergency degree of each environmental problem in the problem set;
Extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set;
Extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
Performing de-duplication treatment on the problem set by using a pre-constructed automatic duplication judgment model, generating a problem event set according to the de-duplication treated problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The emergency degree, the importance degree, the problem category and the region attribute of the problem event are obtained from the library to be allocated, the comprehensive score of the disposal personnel in the preset disposal personnel group is calculated, and the problem event is allocated to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
Collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
extracting a time text vector set in the text vector set, and grading the time text vector set based on a pre-constructed first random forest classification model to obtain the emergency degree of each environmental problem in the problem set;
Extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set;
Extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
Performing de-duplication treatment on the problem set by using a pre-constructed automatic duplication judgment model, generating a problem event set according to the de-duplication treated problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The emergency degree, the importance degree, the problem category and the region attribute of the problem event are obtained from the library to be allocated, the comprehensive score of the disposal personnel in the preset disposal personnel group is calculated, and the problem event is allocated to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. An event intelligent allocation method, which is characterized by comprising the following steps:
Collecting problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
extracting a time text vector set in the text vector set, and grading the time text vector set based on a pre-constructed first random forest classification model to obtain the emergency degree of each environmental problem in the problem set;
Extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set;
Extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
Performing de-duplication treatment on the problem set by using a pre-constructed automatic duplication judgment model, generating a problem event set according to the de-duplication treated problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The emergency degree, the importance degree, the problem category and the region attribute of the problem event are obtained from the library to be allocated, the comprehensive score of the disposal personnel in the preset disposal personnel group is calculated, and the problem event is allocated to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
2. The method for intelligently distributing events according to claim 1, wherein said quantizing said problem set to obtain a text vector set comprises:
word segmentation is carried out on the problem set to obtain a word set;
Quantizing the word set by using a pre-constructed quantization tool to obtain a word vector set;
sequentially labeling the word vector sets according to preset position codes to obtain sequential word vector sets;
splitting the sequential word vector set according to a preset formatting rule, and arranging splitting results to obtain a text vector set of matrix vectors.
3. The method for intelligently assigning events according to claim 2, wherein before ranking the set of time text vectors based on the pre-constructed first random forest classification model to obtain the urgency of each environmental problem in the set of problems, the method further comprises:
Selecting one of the time text vectors from the time text vector set one by one as a target time text vector;
The target time text vector is used as a parameter to carry out assignment on a preset decision function, and the assigned decision function is used as a decision condition to generate a decision tree;
and summarizing the obtained decision tree to obtain the first random forest classification model.
4. The method for intelligently distributing events according to claim 1, wherein said screening out duplicate problem sets from said problem sets using a pre-constructed automatic weight determination model comprises:
extracting text feature vectors of all the problems in the problem set by using a BERT model in a pre-constructed automatic weight judging model;
calculating similarity scores among text feature vectors of all problems by using a preset similarity calculation model in a preset automatic weight judging model;
when the similarity score is greater than or equal to a preset similarity threshold, defining the corresponding environmental problem as a first type of repeated problem;
Calculating the similarity score of the text feature vector of each problem and the text feature vector of the problem event in the preset allocated library by using the similarity calculation model;
when the similarity score is greater than or equal to a preset similarity threshold, defining the corresponding environmental problem as a second type of repeated problem;
And converging the first type of repeated problems and the second type of repeated problems to obtain a repeated problem set, and performing de-duplication treatment on the repeated problem set according to a preset rule.
5. The method for intelligently assigning events according to claim 4, wherein calculating the similarity score between text feature vectors of each question using a similarity calculation model preset in the pre-constructed automatic weight determination model comprises:
randomly selecting a text feature vector of one of the problems as a first text feature vector, and calculating the similarity between the first text feature vector and each other text feature vector in the environmental problem to obtain a similarity matrix;
Carrying out normalization weighting treatment on the similarity matrix according to rows and columns to obtain attention weight;
Weighting the first text feature vector and the other text feature vectors by using the attention weight to obtain a weighted first text feature vector and weighted other text feature vectors respectively;
and splicing the weighted first text feature vector and the weighted other text feature vectors, and calculating to obtain the similarity score of the spliced first text feature vector and the weighted other text feature vectors through a softmax function.
6. The method for intelligently distributing events according to claim 4, wherein said performing a deduplication process on said set of recurring problems according to a preset rule comprises:
Merging two of the first type of repeat questions;
And establishing association between the second type of repeated problems and corresponding problem events in the preset allocated library.
7. The event intelligent distribution method according to any one of claims 1 to 6, wherein the calculating a composite score of a treatment person in a preset treatment person group, the distributing the problem event to a corresponding treatment person for processing based on the urgency level, the importance level, the problem category, the region attribute, and the composite score includes:
Acquiring the number of events currently processed by a disposal person, and grading the load of the disposal person according to the number of events;
acquiring the preset end date of a current processing event of a disposal person, and grading the task clinic period of the disposal person according to the end date;
Comprehensively calculating the comprehensive score of the disposal personnel according to the load score and the task clinical score;
selecting a preset disposal personnel group according to the emergency degree, the importance degree, the problem category and the regional attribute;
selecting a disposal person with high comprehensive score from the preset disposal person group, and distributing the problem event to the disposal person with high comprehensive score.
8. An intelligent distribution device for environmental problem events, characterized in that the device comprises:
the text vector acquisition module is used for acquiring problem sets of different channel sources, and carrying out quantization processing on the problem sets to obtain a text vector set;
The classification and grading module is used for extracting a time text vector set in the text vector set, grading the time text vector set based on a pre-constructed first random forest classification model, and obtaining the emergency degree of each environmental problem in the problem set; extracting a problem type vector set in the text vector set, and grading the problem type vector set based on a second random forest classification model constructed in advance to obtain the importance degree of each environmental problem in the problem set; extracting an environment type vector set and a place information vector set in the text vector set, and classifying the environment type vector set and the place information vector set based on a pre-constructed third random forest classification model to obtain a problem class set and a region attribute set of each environment problem in the problem set;
The de-duplication module is used for de-duplication processing the problem set by utilizing a pre-built automatic duplication judgment model, generating a problem event set according to the de-duplication processed problem set, and storing the problem event set, the corresponding emergency degree, importance degree, problem category and regional attribute into a preset library to be allocated;
The event distribution module is used for acquiring the emergency degree, the importance degree, the problem category and the region attribute of the problem event from the library to be distributed, calculating the comprehensive score of the disposal personnel in the preset disposal personnel group, and distributing the problem event to the corresponding disposal personnel for processing based on the emergency degree, the importance degree, the problem category, the region attribute and the comprehensive score.
9. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the event intelligent distribution method of any of claims 1 to 7.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the event intelligent distribution method according to any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210137918.5A CN114492663B (en) | 2022-02-15 | 2022-02-15 | Event intelligent allocation method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210137918.5A CN114492663B (en) | 2022-02-15 | 2022-02-15 | Event intelligent allocation method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114492663A CN114492663A (en) | 2022-05-13 |
CN114492663B true CN114492663B (en) | 2024-06-07 |
Family
ID=81479958
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210137918.5A Active CN114492663B (en) | 2022-02-15 | 2022-02-15 | Event intelligent allocation method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114492663B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115170053A (en) * | 2022-05-24 | 2022-10-11 | 中睿信数字技术有限公司 | Event distribution processing system based on cluster fusion |
CN115203361B (en) * | 2022-06-13 | 2024-04-02 | 华院计算技术(上海)股份有限公司 | Event distribution method and device, storage medium and terminal |
CN116777174A (en) * | 2023-07-05 | 2023-09-19 | 中国环境科学研究院 | River basin supervision method, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112749264A (en) * | 2020-12-30 | 2021-05-04 | 平安科技(深圳)有限公司 | Problem distribution method and device based on intelligent robot, electronic equipment and storage medium |
CN113535959A (en) * | 2021-07-29 | 2021-10-22 | 长三角信息智能创新研究院 | Automatic event distribution method for primary treatment |
CN113706322A (en) * | 2021-08-31 | 2021-11-26 | 康键信息技术(深圳)有限公司 | Service distribution method, device, equipment and storage medium based on data analysis |
CN113806492A (en) * | 2021-09-30 | 2021-12-17 | 中国平安人寿保险股份有限公司 | Record generation method, device and equipment based on semantic recognition and storage medium |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103577915A (en) * | 2012-08-01 | 2014-02-12 | 鸿富锦精密工业(深圳)有限公司 | Task allocation management system and method |
CN111401033B (en) * | 2020-03-19 | 2023-07-25 | 北京百度网讯科技有限公司 | Event extraction method, event extraction device and electronic equipment |
-
2022
- 2022-02-15 CN CN202210137918.5A patent/CN114492663B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112749264A (en) * | 2020-12-30 | 2021-05-04 | 平安科技(深圳)有限公司 | Problem distribution method and device based on intelligent robot, electronic equipment and storage medium |
CN113535959A (en) * | 2021-07-29 | 2021-10-22 | 长三角信息智能创新研究院 | Automatic event distribution method for primary treatment |
CN113706322A (en) * | 2021-08-31 | 2021-11-26 | 康键信息技术(深圳)有限公司 | Service distribution method, device, equipment and storage medium based on data analysis |
CN113806492A (en) * | 2021-09-30 | 2021-12-17 | 中国平安人寿保险股份有限公司 | Record generation method, device and equipment based on semantic recognition and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN114492663A (en) | 2022-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114492663B (en) | Event intelligent allocation method, device, equipment and storage medium | |
CN104820629A (en) | Intelligent system and method for emergently processing public sentiment emergency | |
CN109408574B (en) | Complaint responsibility confirmation system based on text mining technology | |
CN113033198B (en) | Similar text pushing method and device, electronic equipment and computer storage medium | |
CN113806434B (en) | Big data processing method, device, equipment and medium | |
CN112948595A (en) | Method, system and equipment for building urban group operation state knowledge graph | |
CN113628043B (en) | Complaint validity judging method, device, equipment and medium based on data classification | |
CN114626735A (en) | Urging case allocation method, urging case allocation device, urging case allocation equipment and computer readable storage medium | |
CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
CN114399212A (en) | Ecological environment quality evaluation method and device, electronic equipment and storage medium | |
CN114969484A (en) | Service data searching method, device, equipment and storage medium | |
CN111930963B (en) | Knowledge graph generation method and device, electronic equipment and storage medium | |
CN114418360A (en) | Smart city operation sign big data analysis method and device | |
CN117155771B (en) | Equipment cluster fault tracing method and device based on industrial Internet of things | |
CN111950623B (en) | Data stability monitoring method, device, computer equipment and medium | |
CN116843481A (en) | Knowledge graph analysis method, device, equipment and storage medium | |
CN113657546B (en) | Information classification method, device, electronic equipment and readable storage medium | |
CN113515591B (en) | Text defect information identification method and device, electronic equipment and storage medium | |
CN115221274A (en) | Text emotion classification method and device, electronic equipment and storage medium | |
CN113570286A (en) | Resource allocation method and device based on artificial intelligence, electronic equipment and medium | |
Bisso et al. | Efficient determination of heliports in the city of Rio de Janeiro for the olympic games and world cup: a fuzzy logic approach | |
CN113627800B (en) | Water source land inspection point position determining method and device, electronic equipment and medium | |
CN114781833B (en) | Capability assessment method, device and equipment based on business personnel and storage medium | |
CN117910884B (en) | Method, device, equipment and medium for detecting quality of stock futures industry control | |
CN118155819B (en) | External defibrillator deployment method, equipment and medium based on emergency response |
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 | ||
GR01 | Patent grant |