CN112528031A - Work order intelligent distribution method and system - Google Patents
Work order intelligent distribution method and system Download PDFInfo
- Publication number
- CN112528031A CN112528031A CN202110173997.0A CN202110173997A CN112528031A CN 112528031 A CN112528031 A CN 112528031A CN 202110173997 A CN202110173997 A CN 202110173997A CN 112528031 A CN112528031 A CN 112528031A
- Authority
- CN
- China
- Prior art keywords
- work order
- classification
- data
- training
- target data
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- 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
Abstract
The embodiment of the invention provides a work order intelligent dispatching method and a work order intelligent dispatching system, wherein the method comprises the steps of obtaining sample data of a work order to dispatch, and obtaining target data after processing; inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results; and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result. According to the invention, multiple preprocessed data are selected to learn according to different data types and characteristics, and the learning results of the multiple models are fused to obtain the final result of the order dispatching, so that the efficiency of model learning is improved, and the accuracy and efficiency of the order dispatching are improved.
Description
Technical Field
The invention relates to the technical field of urban brains, in particular to a work order intelligent dispatching method and system and a computer readable storage medium.
Background
In a government affair service hotline, the complaint amount of a complaint hotline system in urban life is more and more, the problem of a work order is more and more complex, particularly, the work order needs to be dispatched to a plurality of department units for processing, and the problem of multiple circulation exists in the same case. In the current stage, the problems of complex links and overlong period often exist when manual customer service dispatches orders, and the satisfaction degree of complainers and the assessment indexes of relevant departments are influenced.
The prior art work order dispatching system analyzes through a historical work order, trains through some networks to obtain a model, and dispatches the work order, so that the accuracy is low, and the problem that multiple departments process the work order is difficult to solve. And the adjustment of the dispatching business type cannot adjust and intervene the model in time.
Disclosure of Invention
In order to enable the order dispatching model to be more accurate, improve the response rate of the order dispatching and reduce the influence of manual intervention, the embodiment of the invention provides a work order intelligent dispatching method and a work order intelligent dispatching system. The specific technical scheme is as follows:
in order to achieve the above object, an embodiment of the present invention provides an intelligent work order dispatching method, including:
acquiring sample data of a dispatching work order, and processing the sample data to obtain target data;
inputting the target data into a plurality of classification models and an Elasticissearch correlation algorithm program which are trained in advance to obtain a plurality of classification results;
and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result.
Further, the training process of the multi-classification supervised model comprises the following steps:
collecting historical order dispatching data, and screening and enhancing the historical order dispatching data to obtain training data;
and respectively inputting the training data into a plurality of category classification models, and respectively training the category classification models to obtain a plurality of classification models.
Furthermore, a pre-training model is adopted in the classification model, and post-training based on current work order data is carried out on the pre-training model before classification training is carried out on the pre-training model, so that a pre-training model more suitable for the current field is obtained.
Further, the filtering and enhancing the historical dispatch data includes:
carrying out statistical classification on the historical dispatch data, and deleting sample data smaller than a minimum sample threshold value and larger than a maximum sample threshold value to obtain retained data;
for the reserved data, aiming at different types of work orders, sorting different levels of keywords of a plurality of different types of work orders;
judging the keywords of different types and a writing threshold, discarding sample data more than the writing threshold, establishing an index by adopting an Elasticisach method, and writing the index into work order data.
Further, the step of inputting the target data into a pre-trained multi-class supervised model to obtain a plurality of classification results includes:
inputting the target data into a pre-trained rapid text classification model, and performing sample word segmentation by using a pre-established expert dictionary to obtain first work order texts of different categories;
inputting the target data into a pre-trained semantic classification model, and classifying according to different semantics to obtain a second work order text;
and inputting the target data into an Elasticissearch correlation algorithm program, and performing expert mapping on the work order type and the keywords by combining word frequency statistical matching and expert dictionary weighting to obtain a third work order text.
Furthermore, the semantic classification model adopts a BERT Chinese pre-training model and adopts historical work order data for post-training, so that the pre-training model adapts to the work order field, and then the semantic classification model is trained.
A second aspect of the embodiments of the present invention provides an intelligent work order distribution system, including:
the acquisition module is used for acquiring sample data of the dispatching work order and obtaining target data after processing;
the classification module is used for inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results;
and the fusion module is used for fusing and classifying the plurality of classification results to obtain a final work order classification result and distributing the work orders according to the classification result.
Furthermore, the pre-training module also comprises a classification model based on BERT, and before the pre-training model is subjected to classification training, the pre-training model is subjected to post-training based on current work order data to obtain a pre-training model more suitable for the current field.
The third aspect of the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the processor is enabled to process the steps of the intelligent work order dispatching method.
A fourth aspect of the present invention provides an electronic apparatus comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of intelligent work order distribution described above.
The embodiment of the invention provides a work order intelligent dispatching method and a work order intelligent dispatching system, wherein the method comprises the steps of obtaining sample data of a work order to dispatch, and obtaining target data after processing; inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results; and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result. According to the invention, multiple preprocessed data are selected to learn according to different data types and characteristics, and the learning results of the multiple models are fused to obtain the final result of the order dispatching, so that the efficiency of model learning is improved, and the accuracy and efficiency of the order dispatching are improved.
Drawings
Fig. 1 is a flowchart of an implementation manner of an intelligent work order dispatching method according to embodiment 1 of the present invention;
FIG. 2 is a block diagram illustrating a structure of an intelligent work order dispatching system according to an embodiment of the present invention;
FIG. 3 shows a schematic structural diagram of an electronic device according to one embodiment of the invention;
FIG. 4 shows a schematic structural diagram of a computer-readable storage medium according to one embodiment of the invention;
in the figure: 31-a processor; 32-a memory; 33-storage space; 34-program code; 41-program code.
Detailed Description
In order to clearly and thoroughly show the technical solution of the present invention, the following description is made with reference to the accompanying drawings, but the scope of the present invention is not limited thereto.
Referring to fig. 1, a flowchart of an implementation manner of the intelligent work order dispatching method provided in embodiment 1 of the present invention includes the steps of:
acquiring sample data of a dispatching work order, and processing the sample data to obtain target data;
inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results;
and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result.
The target data is data obtained by preprocessing the sample data of the dispatching list, and the preprocessing process (which can also be called processing) is the same as the preprocessing process involved in the model training process. The pretreatment process comprises the following steps:
collecting historical order dispatching data, and screening and enhancing the historical order dispatching data to obtain training data;
and respectively inputting the training data into multiple category classification models, and respectively training the multiple category classification models to obtain multiple category supervised models.
Due to the imbalance problem with the work order type, upsampling and text data enhancement techniques are used to process the data.
The screening and enhancing processing of the historical dispatch data comprises:
1. and carrying out statistical classification on the historical dispatch data, and deleting the sample data smaller than the minimum sample threshold and larger than the maximum sample threshold to obtain the retained data. Specifically, the category number of the work orders is counted and divided into three categories, the maximum sample Threshold value MAX _ Threshold is obtained, and samples with the category number larger than the value are discarded; the minimum number of training samples MIN Threshold, less than which samples are removed and not involved in training.
2. And (4) carrying out supervised classification training of different networks on the 1-processed retained data to obtain a classification training model. The network adopts two modes of a rapid classification model and a semantic classification model.
3. For the reserved data, aiming at different types of work orders, sorting different levels of keywords of a plurality of different types of work orders; preferably, keywords of different types of work orders are manually arranged, wherein each type corresponds to three levels of keywords and corresponds to three weights. Representing the feature contribution of that time to the category.
4. Judging the keywords of different types and a writing threshold, discarding sample data more than the writing threshold, establishing an index by adopting an Elasticisach method, and writing the index into work order data. In other words, the Elasticserach (distributed full-text search engine with multi-user capability) establishes indexes to write work order data, and sets a writing threshold value of each type before writing, wherein more than the threshold value is discarded, and less than the threshold value is used for sample expansion. Sample expansion adopts a data enhancement method, and random replacement and abandonment of near-meaning words are carried out by using non-key words.
In an optional embodiment of the present invention, inputting the target data into 2 classification models trained in advance and a similarity algorithm program to obtain a plurality of classification results, comprises the steps of:
inputting the target data into a pre-trained fast text classification model, and performing sample word segmentation by using a pre-established expert dictionary to obtain first work order text classifications of different categories;
inputting the target data into a pre-trained semantic classification model, and classifying according to different semantics to obtain a second work order text classification;
and inputting the target data into an Elasticissearch similarity calculation program, and performing expert mapping on the work order type and the keywords by combining word frequency statistical matching and expert dictionary weighting to obtain a third work order text classification.
And finally, fusing the obtained first work order text classification, the second work order text classification and the third work order text classification to obtain a final classification result, and distributing the work orders according to the classification result.
The fast text classification model adopts a fasttext text classification model, and the fasttext classification model is a fast text classification method and has a structure with three layers: input layer, hidden layer and output layer (Hierarchical software max), wherein the input is a plurality of words represented by vectors, the output is a specific target, and the hidden layer is the superposition average of a plurality of word vectors. Although only three layers can often achieve accuracy comparable to deep networks, they are orders of magnitude faster in training time than deep networks. The training method utilizes a pre-obtained expert dictionary to segment words of a training sample, fully considers worksheet business knowledge, and solves the problem of word segmentation sequence to a certain extent through segmented words Ngrams. The definition dimension is the hidden layer dimension 100.
The semantic classification model adopts a BERT pre-training model, and is characterized in that a text is added to specific characteristic information, and a special mark is added in the middle of the text, so that the characteristic information is conveniently added for training. The training samples were as follows:
the short feature set of one sample is F ∈ { F1, F2 … fk }:
the work order text is T, and the feature marker (feature marker) is marked as { fm1, fm2 …, Fmk }.
According to the method, the feature marker utilizes unusd type words in a BERT pre-training model, fmi is replaced by unusd, and the feature marker is added in advance as priori knowledge, so that the model can better notice that the sample data TF after specific feature combination is TF = T + fm1+ f1+ fm2+ f2 ….
The multi-dimensional characteristic information in the work order is considered, and the Focal local is added to replace the traditional cross entropy, the number of samples in the data processing stage is used for balancing the Loss function, and the data updating weight with few samples is increased.
And (3) post-training the BERT pre-training model, wherein the post-training data adopts a historical work order in a mode of randomly covering a mask 15% character token and simultaneously carrying out relation judgment on the next sentence. And self-supervision is adopted to learn the field information.
The above-mentioned keyword-based index matching, which is divided into two steps,
the first step is text matching, and the tf-idf algorithm is adopted to match the work order text. And obtaining the historical work orders and labels with the maximum correlation, and reserving the top 20 data with the highest scores. The Elasticsearch contains three key points, one with a keyword dictionary, the other with a synonym dictionary, and the third which can support hot update.
And secondly, weighting the first 20 data obtained in the first step by keywords, and fully considering the characteristic contributions of different keywords to different types of work orders.
The embodiment of the invention provides a work order intelligent dispatching method and a work order intelligent dispatching system, wherein the method comprises the steps of obtaining sample data of a work order to dispatch, and obtaining target data after processing; inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results; and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result. According to the invention, multiple preprocessed data are selected to learn according to different data types and characteristics, and the learning results of the multiple models are fused to obtain the final result of the order dispatching, so that the efficiency of model learning is improved, and the accuracy and efficiency of the order dispatching are improved. And a plurality of supervised models, one type considers the training and forecasting rates, and the other type fully considers the semantic characteristics of the models and combines the advantages of the training and forecasting rates. The above-described method is implemented based on the keyword classification model, so that online intervention is guaranteed and the classification model is adjusted. The defect of small number of samples for supervised learning is overcome. Classification can also be done with few samples. The fusion model solves the problem of difficult manual experience in different model selections. Intelligent selection of the model is achieved.
Referring to fig. 2, a schematic block diagram of a work order intelligent dispatch system provided by the embodiment of the present invention includes:
the acquisition module is used for acquiring sample data of the dispatching work order and obtaining target data after processing;
the classification module is used for inputting the target data into a multi-classification supervised model trained in advance to obtain a plurality of classification results;
and the fusion module is used for fusing the classification results to obtain a final work order classification result, and distributing the work orders according to the classification result.
The third aspect of the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the processor is enabled to process the steps of the intelligent work order dispatching method.
A fourth aspect of the present invention provides an electronic apparatus comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of intelligent work order distribution described above.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the apparatus for detecting a wearing state of an electronic device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
For example, fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device conventionally comprises a processor 31 and a memory 32 arranged to store computer-executable instructions (program code). The memory 32 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 32 has a storage space 33 storing program code 34 for performing the method steps shown in fig. 1 and in any of the embodiments. For example, the storage space 33 for storing the program code may comprise respective program codes 34 for implementing the various steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 4. The computer readable storage medium may have memory segments, memory spaces, etc. arranged similarly to the memory 32 in the electronic device of fig. 3. The program code may be compressed, for example, in a suitable form. In general, the memory space stores program code 41 for performing the steps of the method according to the invention, i.e. there may be program code, such as read by the processor 31, which, when run by the electronic device, causes the electronic device to perform the steps of the method described above.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (9)
1. An intelligent work order dispatching method is characterized by comprising the following steps:
acquiring sample data of a dispatching work order, and processing the sample data to obtain target data;
inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results;
and fusing a plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result.
2. The intelligent work order dispatching method of claim 1, wherein the training process of the plurality of supervised classification models comprises the steps of:
collecting historical order dispatching data, and screening and enhancing the historical order dispatching data to obtain training data;
and respectively inputting the training data into various category classification networks, and respectively training the various category classification models to obtain a plurality of supervised classification models.
3. The intelligent work order dispatching method of claim 1, wherein after obtaining and processing work order sample data to obtain target data, the target data is input to a plurality of supervised classification models trained in advance.
4. The intelligent work order dispatching method as claimed in claim 2, wherein said screening and enhancing said historical dispatch data comprises:
carrying out statistical classification on the historical dispatch data, and deleting sample data smaller than a minimum sample threshold value and larger than a maximum sample threshold value to obtain retained data;
for the reserved data, aiming at different types of work orders, sorting different levels of keywords of a plurality of different types of work orders;
judging the keywords of different types and a writing threshold, discarding sample data more than the writing threshold, establishing an index by adopting an Elasticisach method, and writing the index into work order data.
5. The intelligent work order dispatching method as claimed in claim 2, wherein the step of inputting the target data into a plurality of pre-trained supervised models of different categories to obtain a plurality of classification results comprises the steps of:
inputting the target data into a pre-trained fast text classification model, and performing sample word segmentation by using a pre-established expert dictionary to obtain first work order text classifications of different categories;
inputting the target data into a pre-trained semantic classification model, and classifying according to different semantics to obtain a second work order text classification;
and inputting the target data into an Elasticissearch correlation algorithm program, and performing expert mapping on the work order type and the keywords by combining word frequency statistical matching and expert dictionary weighting to obtain a third work order text classification.
6. The intelligent work order dispatching method as claimed in claim 5, wherein the semantic classification model adopts a BERT Chinese pre-training model and adopts historical work order data for post-training, so that the pre-training model adapts to the work order field, and then the semantic classification model is trained.
7. The utility model provides a work order intelligence dispatch system which characterized in that includes:
the acquisition module is used for acquiring sample data of the dispatching work order and obtaining target data after processing;
the classification module is used for inputting the target data into a plurality of pre-trained supervised classification models to obtain a plurality of classification results;
and the fusion module is used for fusing and reclassifying the plurality of classification results to obtain a final work order classification result, and distributing the work orders according to the classification result.
8. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, causes the processor to process the steps of the intelligent work order dispatch method of any one of claims 1-6.
9. An electronic device, comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of intelligent work order distribution of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110173997.0A CN112528031A (en) | 2021-02-09 | 2021-02-09 | Work order intelligent distribution method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110173997.0A CN112528031A (en) | 2021-02-09 | 2021-02-09 | Work order intelligent distribution method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112528031A true CN112528031A (en) | 2021-03-19 |
Family
ID=74975638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110173997.0A Pending CN112528031A (en) | 2021-02-09 | 2021-02-09 | Work order intelligent distribution method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112528031A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238792A (en) * | 2021-05-14 | 2021-08-10 | 北京百度网讯科技有限公司 | Feedback information processing method, device, equipment and storage medium |
| CN113537775A (en) * | 2021-07-16 | 2021-10-22 | 北京政信1890智能科技有限公司 | Government appeal processing method and system |
| CN114372458A (en) * | 2022-01-20 | 2022-04-19 | 北京零点远景网络科技有限公司 | Emergency detection method based on government work order |
| CN115983609A (en) * | 2023-03-17 | 2023-04-18 | 中关村科学城城市大脑股份有限公司 | Work order processing method and device, electronic equipment and computer readable medium |
| CN116611453A (en) * | 2023-07-19 | 2023-08-18 | 天津奇立软件技术有限公司 | Intelligent order-distributing and order-following method and system based on big data and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
| CN108897815A (en) * | 2018-06-20 | 2018-11-27 | 淮阴工学院 | A kind of multi-tag file classification method based on similarity model and FastText |
| CN111291180A (en) * | 2018-12-07 | 2020-06-16 | 中移在线服务有限公司 | Work order data classification method, terminal and storage medium |
| CN111737473A (en) * | 2020-07-17 | 2020-10-02 | 浙江口碑网络技术有限公司 | Text classification method, device and equipment |
| CN111858848A (en) * | 2020-05-22 | 2020-10-30 | 深圳创新奇智科技有限公司 | Semantic classification method and device, electronic equipment and storage medium |
| CN111881296A (en) * | 2020-07-31 | 2020-11-03 | 深圳市万物云科技有限公司 | Work order processing method based on community scene and related components |
-
2021
- 2021-02-09 CN CN202110173997.0A patent/CN112528031A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
| CN108897815A (en) * | 2018-06-20 | 2018-11-27 | 淮阴工学院 | A kind of multi-tag file classification method based on similarity model and FastText |
| CN111291180A (en) * | 2018-12-07 | 2020-06-16 | 中移在线服务有限公司 | Work order data classification method, terminal and storage medium |
| CN111858848A (en) * | 2020-05-22 | 2020-10-30 | 深圳创新奇智科技有限公司 | Semantic classification method and device, electronic equipment and storage medium |
| CN111737473A (en) * | 2020-07-17 | 2020-10-02 | 浙江口碑网络技术有限公司 | Text classification method, device and equipment |
| CN111881296A (en) * | 2020-07-31 | 2020-11-03 | 深圳市万物云科技有限公司 | Work order processing method based on community scene and related components |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238792A (en) * | 2021-05-14 | 2021-08-10 | 北京百度网讯科技有限公司 | Feedback information processing method, device, equipment and storage medium |
| CN113537775A (en) * | 2021-07-16 | 2021-10-22 | 北京政信1890智能科技有限公司 | Government appeal processing method and system |
| CN114372458A (en) * | 2022-01-20 | 2022-04-19 | 北京零点远景网络科技有限公司 | Emergency detection method based on government work order |
| CN115983609A (en) * | 2023-03-17 | 2023-04-18 | 中关村科学城城市大脑股份有限公司 | Work order processing method and device, electronic equipment and computer readable medium |
| CN116611453A (en) * | 2023-07-19 | 2023-08-18 | 天津奇立软件技术有限公司 | Intelligent order-distributing and order-following method and system based on big data and storage medium |
| CN116611453B (en) * | 2023-07-19 | 2023-10-03 | 天津奇立软件技术有限公司 | Intelligent order-distributing and order-following method and system based on big data and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tur et al. | Combining active and semi-supervised learning for spoken language understanding | |
| CN112528031A (en) | Work order intelligent distribution method and system | |
| CN104781837B (en) | System and method for forming predictions using event-based sentiment analysis | |
| CN108573047A (en) | A kind of training method and device of Module of Automatic Chinese Documents Classification | |
| CN106126751A (en) | A kind of sorting technique with time availability and device | |
| Carrasco et al. | A fuzzy linguistic RFM model applied to campaign management | |
| CN109299245B (en) | Method and device for recalling knowledge points | |
| CN109871443A (en) | A kind of short text classification method and device based on book keeping operation scene | |
| CN113420145B (en) | Semi-supervised learning-based bid-bidding text classification method and system | |
| CN112256845A (en) | Intention recognition method, device, electronic equipment and computer readable storage medium | |
| CN110347791B (en) | Topic recommendation method based on multi-label classification convolutional neural network | |
| CN112131876A (en) | Method and system for determining standard problem based on similarity | |
| CN115952292B (en) | Multi-label classification method, apparatus and computer readable medium | |
| CN111737544A (en) | Search intention recognition method and device, electronic equipment and storage medium | |
| CN114911929A (en) | Classification model training method, text mining equipment and storage medium | |
| Schofield et al. | Identifying hate speech in social media | |
| CN112215629B (en) | Multi-target advertisement generating system and method based on construction countermeasure sample | |
| CN111651597A (en) | Multi-source heterogeneous commodity information classification method based on Doc2Vec and convolutional neural network | |
| CN111709225A (en) | Event cause and effect relationship judging method and device and computer readable storage medium | |
| CN111930944B (en) | File label classification method and device | |
| CN113486143A (en) | User portrait generation method based on multi-level text representation and model fusion | |
| Patidar et al. | Automatic conversational helpdesk solution using seq2seq and slot-filling models | |
| US20230004581A1 (en) | Computer-Implemented Method for Improving Classification of Labels and Categories of a Database | |
| CN113570380A (en) | Service complaint processing method, device and equipment based on semantic analysis and computer readable storage medium | |
| Kim et al. | High-quality train data generation for deep learning-based web page classification models |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210319 |
|
| RJ01 | Rejection of invention patent application after publication |