CN112488551A - XGboost algorithm-based hot line intelligent order dispatching method - Google Patents
XGboost algorithm-based hot line intelligent order dispatching method Download PDFInfo
- Publication number
- CN112488551A CN112488551A CN202011436852.7A CN202011436852A CN112488551A CN 112488551 A CN112488551 A CN 112488551A CN 202011436852 A CN202011436852 A CN 202011436852A CN 112488551 A CN112488551 A CN 112488551A
- Authority
- CN
- China
- Prior art keywords
- case
- classification
- department
- xgboost algorithm
- intelligent
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000013145 classification model Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000003058 natural language processing Methods 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention particularly relates to an intelligent hot line dispatching method based on an XGboost algorithm. The XGboost algorithm-based hotline intelligent order dispatching method firstly finds out case occurrence addresses and case descriptions; carrying out standardized processing on case attributes by using a natural language processing technology, applying the case attributes to an XGboost algorithm, and finally obtaining a classification model with higher accuracy through multiple training and optimization; when a new hot-line case exists, the occurrence location and the case description of the case are used as parameters and transmitted into a trained classification model, the case is dispatched to a corresponding department for disposal according to the output result of the classification model, and a main responsibility department and a cooperative department are determined. According to the intelligent hot line dispatching method based on the hot line of the XGboost algorithm, data cleaning is carried out on historical data to form a historical sample set; then, the manual experience dependence of the hot-line order dispatching process is reduced by an intelligent order dispatching method in the historical samples, the accuracy and the efficiency of the order dispatching are improved, so that the human resources are saved, the labor cost is reduced, and the method is suitable for popularization and application.
Description
Technical Field
The invention relates to the technical field of big data analysis and mining, in particular to an XGboost algorithm-based hot line intelligent order dispatching method.
Background
The 12345 hotline is a very important field in government services, being the bridge and the tie that connects the civilians and the government. With the rise of government service capabilities, people are becoming more accustomed to consulting questions and seeking help by typing 12345 hotlines. Therefore, 12345 hot line business personnel in each city receive a large number of work orders each day and dispatch them to the right department for disposal according to the content of the work orders. The work order is dispatched to the correct department, the requirement on business personnel is very high, the personnel dispatching the work order need to have a large amount of business experience accumulation, and the responsibility of which department the work order belongs to can be quickly judged according to the content of the work order. According to statistics, the time of 3-5 years is probably needed to cultivate a business person with a menu accuracy rate of more than 60%, and the labor cost is very high due to the fact that the mobility of hot-line workers is high.
In addition, the customer service personnel of each enterprise and public institution also face the same dilemma. Therefore, a method capable of guiding customer service personnel/service personnel to correctly dispatch orders is urgently needed, and if correct treatment departments can be intelligently recommended, the labor cost is inevitably greatly saved by combining with manual experience.
Machine learning is a relatively popular technique in recent years and is increasingly used in the analysis and mining of data. The classification in machine learning is one of the most widely applied methods, and can solve many problems in actual business. XGboost is one of boosting algorithms.
In order to reduce the dependence on manual experience in the hot-line order dispatching process and improve the efficiency and accuracy of the order dispatching, the invention provides an intelligent hot-line order dispatching method based on an XGboost algorithm.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a simple and efficient hot line intelligent dispatching method based on the XGboost algorithm.
The invention is realized by the following technical scheme:
the utility model provides a hotline intelligence sends an order method based on XGboost algorithm which characterized in that: the method comprises the following steps:
firstly, performing data cleaning on historical data to form a historical sample set with enough quantity and correct dispatching and classifying;
secondly, screening the attributes in the historical samples to find two most useful attributes for classification, namely case occurrence address and case description;
thirdly, carrying out standardized processing on case attributes by using a natural language processing technology, applying the case attributes to an XGboost algorithm, and finally obtaining a classification model with higher accuracy through multiple training and optimization;
and fourthly, when a new hot-line case exists, transmitting the occurrence place of the case and the case description as parameters into the trained classification model, dispatching the case to a corresponding department for disposal according to the output result of the classification model, and determining a principal and responsibility department and a cooperative department.
In the first step, mass historical data in the hot-line service system is cleaned, dirty data are removed, and data with correct treatment departments, complete case description and address description are selected to form an effective training sample set.
In the third step, firstly, performing department and street secondary classification on hot line data by an XGboost method; after the data of the hot line is subjected to secondary classification processing, the data is further trained for multiple classifications of departments and streets according to the result of the secondary classification, and finally a final classification model is formed through a two-step classification method.
And in the third step, natural language processing is carried out on the training sample set, the case occurrence address and case description of the sample, word segmentation is carried out according to the existing word stock, words are removed, and words effective for classification are reserved.
In the third step, the word frequency is calculated by using a TF-IDF (term frequency-inverse document frequency index) method for the sample after the word processing, and the word vector of the occurrence address and the description of each case is formed.
In the third step, the XGboost algorithm is used for carrying out secondary classification on the sample data, and samples belonging to departments and streets are identified; and then performing department multi-classification or street multi-classification on the sample data by using an XGboost method.
In the third step, performing two-classification training on the sample which forms the word vector and is formatted by using an XGboost algorithm to form a two-classification classifier; and the two-classification classifier preliminarily judges whether the case belongs to a street or a department according to the description and the address of the case.
In the third step, the second-stage classifiers are combined, the first-stage classifier firstly judges whether the case belongs to a street or a department, and the second-stage classifier judges which street or which department the case specifically belongs to;
training cases to be dispatched to the street according to the address to obtain a classifier capable of correctly classifying the street; when a new case arrives, inputting the address of the case, and obtaining the street to which the case should be dispatched;
training cases to be dispatched to departments according to the description of the cases to obtain classifiers capable of correctly classifying the departments; when a new case comes, the description information of the case is input, and the department to which the case should be dispatched can be obtained.
The invention has the beneficial effects that: the XGboost algorithm-based hot line intelligent order dispatching method reduces the dependence of manual experience on the hot line order dispatching process, improves the accuracy and efficiency of the order dispatching, saves human resources, reduces labor cost and is suitable for popularization and application.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an intelligent hot-line dispatching method based on an XGBoost algorithm according to the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the embodiment of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The idea of Boosting is to integrate many weak classifiers together to form one strong classifier. Because the XGboost is a lifting tree model, a plurality of tree models are integrated together to form a strong classifier. The idea of the XGBoos algorithm is to continuously add trees, continuously perform feature splitting to grow a tree, and each time a tree is added, actually learn a new function to fit the residual error predicted last time. When training is completed to obtain k trees, a score of a sample is predicted, namely, according to the characteristics of the sample, a corresponding leaf node is fallen in each tree, each leaf node corresponds to a score, and finally, the predicted value of the sample is obtained by only adding the scores corresponding to each tree.
Through experiments on various different classification algorithms, the XGboost algorithm is found to have the best effect in a hot-line dispatch scene, and the classification accuracy rate reaches about 80%.
The XGboost algorithm-based hotline intelligent dispatching method comprises the following steps:
firstly, performing data cleaning on historical data to form a historical sample set with enough quantity and correct dispatching and classifying;
secondly, screening the attributes in the historical samples to find two most useful attributes for classification, namely case occurrence address and case description;
thirdly, carrying out standardized processing on case attributes by using a natural language processing technology, applying the case attributes to an XGboost algorithm, and finally obtaining a classification model with higher accuracy through multiple training and optimization;
and fourthly, when a new hot-line case exists, transmitting the occurrence place of the case and the case description as parameters into the trained classification model, dispatching the case to a corresponding department for disposal according to the output result of the classification model, and determining a principal and responsibility department and a cooperative department.
In the first step, mass historical data in the hot-line service system is cleaned, dirty data are removed, and data with correct treatment departments, complete case description and address description are selected to form an effective training sample set.
In the third step, firstly, performing department and street secondary classification on hot line data by an XGboost method; after the data of the hot line is subjected to secondary classification processing, the data is further trained for multiple classifications of departments and streets according to the result of the secondary classification, and finally a final classification model is formed through a two-step classification method.
And in the third step, natural language processing is carried out on the training sample set, the case occurrence address and case description of the sample, word segmentation is carried out according to the existing word stock, words are removed, and words effective for classification are reserved.
In the third step, the word frequency is calculated by using a TF-IDF (term frequency-inverse document frequency index) method for the sample after the word processing, and the word vector of the occurrence address and the description of each case is formed.
TF-IDF is a statistical method to evaluate the importance of a word to one of a set of documents or a corpus. The importance of a word increases in proportion to the number of times it appears in a document, but at the same time decreases in inverse proportion to the frequency with which it appears in the corpus.
In the third step, the XGboost algorithm is used for carrying out secondary classification on the sample data, and samples belonging to departments and streets are identified; and then performing department multi-classification or street multi-classification on the sample data by using an XGboost method.
In the third step, performing two-classification training on the sample which forms the word vector and is formatted by using an XGboost algorithm to form a two-classification classifier; and the two-classification classifier preliminarily judges whether the case belongs to a street or a department according to the description and the address of the case.
In the third step, the second-stage classifiers are combined, the first-stage classifier firstly judges whether the case belongs to a street or a department, and the second-stage classifier judges which street or which department the case specifically belongs to;
training cases to be dispatched to the street according to the address to obtain a classifier capable of correctly classifying the street; when a new case arrives, inputting the address of the case, and obtaining the street to which the case should be dispatched;
training cases to be dispatched to departments according to the description of the cases to obtain classifiers capable of correctly classifying the departments; when a new case comes, the description information of the case is input, and the department to which the case should be dispatched can be obtained.
In conclusion, the XGboost algorithm-based hot-line intelligent order dispatching method adopts the XGboost algorithm and trains a large number of hot-line order dispatching historical cases to obtain an intelligent order dispatching classifier; when a new case arrives, corresponding parameters are introduced, and the classifier can calculate which department the case should be sent to for disposal. The intelligent mode is used for assisting in order dispatching, so that the dependence of manual experience in the hot-line order dispatching process can be reduced, and the accuracy and efficiency of the order dispatching are improved. Even a new person who is not near to business is trained simply, and the order dispatching accuracy can reach 80% under the guidance of an intelligent order dispatching algorithm.
The above-described embodiment is only one specific embodiment of the present invention, and general changes and substitutions by those skilled in the art within the technical scope of the present invention are included in the protection scope of the present invention.
Claims (8)
1. The utility model provides a hotline intelligence sends an order method based on XGboost algorithm which characterized in that: the method comprises the following steps:
firstly, performing data cleaning on historical data to form a historical sample set with enough quantity and correct dispatching and classifying;
secondly, screening the attributes in the historical samples to find two most useful attributes for classification, namely case occurrence address and case description;
thirdly, carrying out standardized processing on case attributes by using a natural language processing technology, applying the case attributes to an XGboost algorithm, and finally obtaining a classification model with higher accuracy through multiple training and optimization;
and fourthly, when a new hot-line case exists, transmitting the occurrence place of the case and the case description as parameters into the trained classification model, dispatching the case to a corresponding department for disposal according to the output result of the classification model, and determining a principal and responsibility department and a cooperative department.
2. The XGboost algorithm-based hotline intelligent lemma of claim 1, wherein: in the first step, mass historical data in the hot-line service system is cleaned, dirty data are removed, and data with correct treatment departments, complete case description and address description are selected to form an effective training sample set.
3. The XGboost algorithm-based hotline intelligent lemma according to claim 1 or 2, wherein: in the third step, firstly, performing department and street secondary classification on hot line data by an XGboost method; after the data of the hot line is subjected to secondary classification processing, the data is further trained for multiple classifications of departments and streets according to the result of the secondary classification, and finally a final classification model is formed through a two-step classification method.
4. The XGboost algorithm-based hotline intelligent lemma of claim 3, wherein: and in the third step, natural language processing is carried out on the training sample set, the case occurrence address and case description of the sample, word segmentation is carried out according to the existing word stock, words are removed, and words effective for classification are reserved.
5. The XGboost algorithm-based hotline intelligent lemma of claim 4, wherein: and in the third step, calculating the word frequency of the samples after the word segmentation processing by using a TF-IDF method and forming a word vector of each case occurrence address and case description.
6. The XGboost algorithm-based hotline intelligent lemma of claim 5, wherein: in the third step, the XGboost algorithm is used for carrying out secondary classification on the sample data, and samples belonging to departments and streets are identified; and then performing department multi-classification or street multi-classification on the sample data by using an XGboost method.
7. The XGboost algorithm-based hotline intelligent lemma of claim 6, wherein: in the third step, performing two-classification training on the sample which forms the word vector and is formatted by using an XGboost algorithm to form a two-classification classifier; and the two-classification classifier preliminarily judges whether the case belongs to a street or a department according to the description and the address of the case.
8. The XGboost algorithm-based hotline intelligent lemma of claim 7, wherein: in the third step, the second-stage classifiers are combined, the first-stage classifier firstly judges whether the case belongs to a street or a department, and the second-stage classifier judges which street or which department the case specifically belongs to;
training cases to be dispatched to the street according to the address to obtain a classifier capable of correctly classifying the street; when a new case arrives, inputting the address of the case, and obtaining the street to which the case should be dispatched;
training cases to be dispatched to departments according to the description of the cases to obtain classifiers capable of correctly classifying the departments; when a new case comes, the description information of the case is input, and the department to which the case should be dispatched can be obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436852.7A CN112488551B (en) | 2020-12-11 | 2020-12-11 | Hot line intelligent order dispatching method based on XGboost algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436852.7A CN112488551B (en) | 2020-12-11 | 2020-12-11 | Hot line intelligent order dispatching method based on XGboost algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488551A true CN112488551A (en) | 2021-03-12 |
| CN112488551B CN112488551B (en) | 2023-04-07 |
Family
ID=74940987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011436852.7A Active CN112488551B (en) | 2020-12-11 | 2020-12-11 | Hot line intelligent order dispatching method based on XGboost algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488551B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919811A (en) * | 2021-10-15 | 2022-01-11 | 长三角信息智能创新研究院 | Hot line event distribution method based on strengthened correlation |
| CN115935245A (en) * | 2023-03-10 | 2023-04-07 | 吉奥时空信息技术股份有限公司 | Automatic classification and distribution method for government affair hotline cases |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103123636A (en) * | 2011-11-21 | 2013-05-29 | 北京百度网讯科技有限公司 | Method to build vocabulary entry classification models, method of vocabulary entry automatic classification and device |
| CN108197194A (en) * | 2017-12-27 | 2018-06-22 | 贵州小爱机器人科技有限公司 | A kind of processing method and system of information of reporting a case to the security authorities |
| CN110110087A (en) * | 2019-05-15 | 2019-08-09 | 济南浪潮高新科技投资发展有限公司 | A kind of Feature Engineering method for Law Text classification based on two classifiers |
| WO2019214133A1 (en) * | 2018-05-08 | 2019-11-14 | 华南理工大学 | Method for automatically categorizing large-scale customer complaint data |
| CN110543562A (en) * | 2019-08-19 | 2019-12-06 | 武大吉奥信息技术有限公司 | Event map-based automatic urban management event distribution method and system |
| CN110782155A (en) * | 2019-10-23 | 2020-02-11 | 上海浦东临港智慧城市发展中心 | Order dispatching system and method for urban transportation center case |
| CN111861201A (en) * | 2020-07-17 | 2020-10-30 | 南京汇宁桀信息科技有限公司 | Intelligent government affair order dispatching method based on big data classification algorithm |
-
2020
- 2020-12-11 CN CN202011436852.7A patent/CN112488551B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103123636A (en) * | 2011-11-21 | 2013-05-29 | 北京百度网讯科技有限公司 | Method to build vocabulary entry classification models, method of vocabulary entry automatic classification and device |
| CN108197194A (en) * | 2017-12-27 | 2018-06-22 | 贵州小爱机器人科技有限公司 | A kind of processing method and system of information of reporting a case to the security authorities |
| WO2019214133A1 (en) * | 2018-05-08 | 2019-11-14 | 华南理工大学 | Method for automatically categorizing large-scale customer complaint data |
| CN110110087A (en) * | 2019-05-15 | 2019-08-09 | 济南浪潮高新科技投资发展有限公司 | A kind of Feature Engineering method for Law Text classification based on two classifiers |
| CN110543562A (en) * | 2019-08-19 | 2019-12-06 | 武大吉奥信息技术有限公司 | Event map-based automatic urban management event distribution method and system |
| CN110782155A (en) * | 2019-10-23 | 2020-02-11 | 上海浦东临港智慧城市发展中心 | Order dispatching system and method for urban transportation center case |
| CN111861201A (en) * | 2020-07-17 | 2020-10-30 | 南京汇宁桀信息科技有限公司 | Intelligent government affair order dispatching method based on big data classification algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919811A (en) * | 2021-10-15 | 2022-01-11 | 长三角信息智能创新研究院 | Hot line event distribution method based on strengthened correlation |
| CN113919811B (en) * | 2021-10-15 | 2023-01-06 | 长三角信息智能创新研究院 | Hot line event distribution method based on strengthened correlation |
| CN115935245A (en) * | 2023-03-10 | 2023-04-07 | 吉奥时空信息技术股份有限公司 | Automatic classification and distribution method for government affair hotline cases |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488551B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109189901B (en) | Method for automatically discovering new classification and corresponding corpus in intelligent customer service system | |
| WO2018032937A1 (en) | Method and apparatus for classifying text information | |
| CN109492101A (en) | File classification method, system and medium based on label information and text feature | |
| CN106776538A (en) | The information extracting method of enterprise's noncanonical format document | |
| CN112488551B (en) | Hot line intelligent order dispatching method based on XGboost algorithm | |
| CN109034861A (en) | Customer churn prediction technique and device based on mobile terminal log behavioral data | |
| CN106572001B (en) | A kind of dialogue method and system of intelligent customer service | |
| CN109919368B (en) | Law recommendation prediction system and method based on association graph | |
| CN107729468A (en) | Answer extracting method and system based on deep learning | |
| CN107273295B (en) | Software problem report classification method based on text chaos | |
| WO2019001359A1 (en) | Data processing method and data processing apparatus | |
| CN113590764B (en) | Training sample construction method and device, electronic equipment and storage medium | |
| CN110516057B (en) | Petition question answering method and device | |
| CN113468296A (en) | Model self-iteration type intelligent customer service quality inspection system and method capable of configuring business logic | |
| WO2020253506A1 (en) | Contract content extraction method and apparatus, and computer device and storage medium | |
| CN113672732B (en) | Method and device for classifying service data | |
| CN109063983B (en) | Natural disaster damage real-time evaluation method based on social media data | |
| CN111462752A (en) | Client intention identification method based on attention mechanism, feature embedding and BI-L STM | |
| CN107368895A (en) | A kind of combination machine learning and the action knowledge extraction method planned automatically | |
| CN115099310A (en) | Method and device for training model and classifying enterprises | |
| CN111008329A (en) | Page content recommendation method and device based on content classification | |
| CN110362828B (en) | Network information risk identification method and system | |
| CN109033378A (en) | A kind of application method of Zero-shot Learning in intelligent customer service system | |
| CN113095723A (en) | Coupon recommendation method and device | |
| CN110782221A (en) | Intelligent interview evaluation system and method |
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 | ||
| GR01 | Patent grant |