CN116739256A - Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium - Google Patents
Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium Download PDFInfo
- Publication number
- CN116739256A CN116739256A CN202310672430.7A CN202310672430A CN116739256A CN 116739256 A CN116739256 A CN 116739256A CN 202310672430 A CN202310672430 A CN 202310672430A CN 116739256 A CN116739256 A CN 116739256A
- Authority
- CN
- China
- Prior art keywords
- text
- intelligent
- model
- dispatch
- work order
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000010276 construction Methods 0.000 title claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000012423 maintenance Methods 0.000 claims description 53
- 238000000605 extraction Methods 0.000 claims description 38
- 230000015654 memory Effects 0.000 claims description 28
- 238000004140 cleaning Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 230000002452 interceptive effect Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 239000000047 product Substances 0.000 description 30
- 230000006870 function Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of text processing and discloses an intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium.
Description
Technical Field
The invention relates to the technical field of text processing, in particular to an intelligent form-dispatching model construction method, an intelligent form-dispatching device, intelligent form-dispatching equipment and an intelligent form-dispatching medium.
Background
The "customer-to-customer" is the business spirit of each enterprise and is a constant pursuit of us. In recent years, with the advent of the "internet+" age, various new technologies are continuously combined with the traditional industry, so that the management mode and the operation idea of the traditional enterprise are changed over the sky. From production, sales to after-market services, there is a constant need to accommodate market changes. In order to meet the needs of more customers, better meeting the expectations of consumers, and enabling consumers to enjoy more professional, careless, personalized and high-quality service experience, an after-sales work order system is generated, and an after-sales service management solution is provided for each large manufacturer. After-market dispatch is an increasingly conscious embodiment of enterprise services.
After the relevant intelligent dispatch technique clients reserve on the system, the dispatch personnel can be dispatched directly and randomly by a single person, but the dispatch personnel do not consider whether the dispatch personnel have the capability of completing tasks on time or not, the risks of affecting the client experience are certain, and the possibility of processing and distributing deviation can also occur, for example, the client address and the maintenance service station address are far apart, a maintenance engineer needs to spend a great deal of time to go to the client place, and the overall efficiency of the work order processing is low and the service cost is high.
Disclosure of Invention
In view of the above, the invention provides an intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium, which are used for solving the problem of low overall efficiency of work order processing caused by random dispatching staff.
In a first aspect, the present invention provides a method for constructing an intelligent dispatch model, where the method includes: inputting a historical work order in a historical work order sample set into a preset dispatch model, extracting text content of the work order, and performing word segmentation and feature extraction processing on the text content; classifying the text features obtained after the processing to obtain text feature libraries of different categories and corresponding categories, wherein the different categories comprise customer information, product maintenance information and position information; training preset configuration rules corresponding to the preset dispatch model based on different types and text feature libraries corresponding to the different types to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the product maintenance capability of the service station and the nearest priority order of the service station to the customer position, and the different types are in one-to-one correspondence with the matching flow of the configuration rules.
According to the intelligent dispatch model construction method provided by the invention, the historical work order sample set is input into the preset dispatch model, the text content of the work order is extracted, the text is subjected to word segmentation and feature extraction processing, the text features are subjected to classification processing, the text feature libraries corresponding to different categories and each category are obtained, the preset configuration rules corresponding to the preset dispatch model are trained based on the obtained text feature libraries corresponding to the different categories and each category, the matching flow of the preset configuration rules is to match the service personnel according to the priority order of the service personnel specified by the customer, the service station maintenance product capability and the nearest service station distance from the customer position, and then the service stations are matched according to the priority order of whether the customer specifies the service personnel content and the service station maintenance product capability and the nearest distance based on the work order content, so that the maintenance personnel under the corresponding service station are output, the customer experience is optimized, the human resources are reasonably distributed, the dispatch service with high efficiency, the intelligent and safe is realized, and the completion quality and the efficiency of the task work order are improved.
In an optional implementation manner, the classifying processing is performed on the processed text features to obtain text feature libraries corresponding to different categories and each category, including: classifying the text features by adopting TF-IDF and a clustering algorithm to generate different text feature dictionaries; and carrying out category naming processing on the different text feature dictionaries to obtain text feature libraries corresponding to different categories and each category.
According to the invention, the TF-IDF and the clustering algorithm are adopted to classify the text features, so that the accuracy of feature extraction is improved, the calculation speed is high, and then the obtained text feature libraries of different types and corresponding types are more accurate and comprehensive, and the matching accuracy of the intelligent matching model is improved.
In an optional implementation manner, before the history worksheets in the history worksheet sample set are input into the preset dispatch model, the intelligent dispatch model construction method further includes: and carrying out data cleaning and deduplication processing on the historical work order sample set.
Before the historical work order sample set is input into the preset dispatch model, the data cleaning and duplicate removal processing is carried out on the historical work order sample set, and the time for training the preset dispatch model is reduced by reducing the redundant data and screening useful data in the client contacts and the historical work order, so that the model training efficiency is improved.
In an optional embodiment, after the classifying processing is performed on the text features obtained after the processing to obtain text feature libraries corresponding to different categories and each category, the method for constructing the intelligent dispatch model further includes: and updating and supplementing the text feature library corresponding to each category based on the newly input worksheet.
According to the invention, the text feature library corresponding to each category is updated and supplemented based on the newly input worksheet, so that the existing matching data feature library in the intelligent form-distributing model is more accurate and complete, and the matching accuracy of the intelligent matching model is improved.
In a second aspect, the present invention provides an intelligent dispatch method, including: inputting a work order to be matched into an intelligent matching model, and matching and determining maintenance personnel, wherein the intelligent matching model is constructed by the intelligent order-dispatching model construction method of any one of the first aspect and the corresponding implementation mode; and feeding back the determined maintenance personnel information to the client.
According to the invention, the work orders to be matched are input into the trained intelligent matching model, so that the maintenance personnel can be matched and determined, the efficient, intelligent and safe dispatch service is realized, and the completion quality and efficiency of the task work orders are improved.
In an optional implementation manner, before the worksheet to be matched is input into the intelligent matching model, the intelligent dispatching method further includes: acquiring dialogue interactive text data; and extracting key information in the dialogue interactive text data, and generating the work order to be matched.
According to the invention, the key information in the dialogue interactive text data is extracted based on the dialogue text interactive text data, so that the work order is automatically generated, the false dispatch caused by insufficient manual experience or errors in filling the work order in the related technology is avoided, and the accuracy of intelligent dispatch is improved.
In an alternative embodiment, a text extraction model is used to extract key information in the dialogue interactive text data, and the text extraction model is obtained through the following steps: performing data cleaning treatment on the historical work order sample set; word segmentation and key information extraction processing are carried out on the worksheet data in the historical worksheet sample set after the data cleaning processing; and carrying out classification training on the extracted key information based on a preset corpus to obtain a text extraction model, wherein the preset corpus comprises key words needed by generating work orders, and the key words are in one-to-one correspondence with the key information.
According to the method, a comprehensive and accurate work order sample set is established by means of grabbing, cleaning and the like of the data, the data source and the data analysis capability of the text extraction model are enhanced by focusing on the quality and the integrity of the data, meanwhile, the text extraction model is trained, the data are processed more carefully and intelligently, and then the accuracy and the efficiency of work order matching are improved.
In a third aspect, the present invention provides an intelligent form-delivery model construction device, including: the text processing module is used for inputting the historical worksheets in the historical worksheet sample set into a preset dispatch model, extracting text contents of the worksheets, and performing word segmentation and feature extraction processing on the text contents; the feature classification processing module is used for classifying the processed text features to obtain different categories and text feature libraries corresponding to the categories, wherein the different categories comprise customer information, product maintenance information and position information; the model training module is used for training preset configuration rules corresponding to the preset dispatch model based on different types and text feature libraries corresponding to the different types to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the service station maintenance product capability and the nearest service station to the customer position, and the different types are in one-to-one correspondence with the matching flow of the configuration rules.
In a fourth aspect, the present invention provides an intelligent dispatch device, including: the work order input module is used for inputting the work order to be matched into the intelligent matching model, and matching and determining maintenance personnel, wherein the intelligent matching model is constructed by the intelligent order form model construction method of the first aspect or any corresponding implementation mode; and the result feedback module is used for feeding the determined maintenance personnel information back to the client.
In a fifth aspect, the present invention provides a computer device comprising: the intelligent dispatch model building method comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions to execute the intelligent dispatch model building method according to the first aspect or any corresponding implementation mode thereof or execute the intelligent dispatch method according to the second aspect or any corresponding implementation mode thereof.
In a sixth aspect, the present invention provides a computer readable storage medium, where computer instructions are stored on the computer readable storage medium, where the computer instructions are configured to cause a computer to execute the method for constructing an intelligent dispatch model according to the first aspect or any embodiment corresponding to the first aspect, or execute the method for intelligently dispatching according to the second aspect or any embodiment corresponding to the second aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent dispatch model building method according to an embodiment of the invention;
FIG. 2 is a flow chart of another intelligent dispatch model building method according to an embodiment of the present invention;
FIG. 3 is a flow chart of an intelligent dispatch method according to an embodiment of the present invention;
FIG. 4 is a flow chart of another intelligent dispatch method according to an embodiment of the present invention;
FIG. 5 is a block diagram of an intelligent dispatch model building device according to an embodiment of the present invention;
FIG. 6 is a block diagram of an intelligent dispatch device according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The "customer-to-customer" is the business spirit of each enterprise and is a constant pursuit of us. In recent years, with the advent of the "internet+" age, various new technologies are continuously combined with the traditional industry, so that the management mode and the operation idea of the traditional enterprise are changed over the sky. From production, sales to after-market services, there is a constant need to accommodate market changes. In order to meet the needs of more customers, better meeting the expectations of consumers, and enabling consumers to enjoy more professional, careless, personalized and high-quality service experience, an after-sales work order system is generated, and an after-sales service management solution is provided for each large manufacturer. After-market dispatch is an increasingly conscious embodiment of enterprise services.
After the relevant intelligent dispatch technique clients reserve on the system, the dispatch personnel can be dispatched directly and randomly by a single person, but the dispatch personnel do not consider whether the dispatch personnel have the capability of completing tasks on time or not, the risks of affecting the client experience are certain, and the possibility of processing and distributing deviation can also occur, for example, the client address and the maintenance service station address are far apart, the maintenance personnel need to spend a great deal of time to go to the client places, and the overall efficiency of the work order processing is low and the service cost is high. The embodiment of the invention provides an intelligent form dispatching model construction and intelligent form dispatching method, device, equipment and medium, which are characterized in that a historical form sample set is input into a preset form dispatching model, text content of a form is extracted, text is subjected to word segmentation and feature extraction processing, text features are subjected to classification processing to obtain text feature libraries corresponding to different categories and each category, preset configuration rules corresponding to the preset form dispatching model are trained based on the obtained text feature libraries corresponding to the different categories and each category, and a matching flow of the preset configuration rules is used for matching service personnel according to the priority sequence of a customer designating service personnel, service station maintenance product capability and service station closest to the customer position.
According to an embodiment of the present application, there is provided an intelligent dispatch model building method embodiment, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different from that illustrated herein.
In this embodiment, an intelligent dispatch model construction method is provided, which may be used in the above computer device, and fig. 1 is a flowchart of an intelligent dispatch model construction method according to an embodiment of the present application, as shown in fig. 1, where the flowchart includes the following steps:
step S101, inputting a history work order in a history work order sample set into a preset order-dispatching model, extracting text content of the work order, and performing word segmentation and feature extraction processing on the text content.
According to the embodiment of the application, the historical work order sample set is input into the preset form dispatching model, the method for extracting the text contents in the work order is not limited, for example, the text contents can be extracted from left to right by using a left function, word segmentation and feature extraction processing are needed to be carried out on the text contents after the text contents are extracted, for example, word segmentation processing can be carried out on the text contents according to various special symbols, and the feature is extracted by adopting a TF-IDF algorithm, which is only used as an example and is not limited.
Step S102, classifying the processed text features to obtain text feature libraries corresponding to different categories and each category, wherein the different categories comprise customer information, product maintenance information and position information.
After extracting text features from the work order content in the historical work order sample set, the embodiment of the application can classify the text features, such as carrying out similarity feature analysis on the processed text features, vectorizing an analysis object, carrying out data classification processing by adopting a count or a Hashing method to realize synonym recommendation and generate a thematic dictionary, or classifying the text features by adopting a combination application of a decision tree algorithm, a K-means algorithm or a distance calculation algorithm and the like, classifying all the text features into a plurality of major classes, such as that part of features of a certain class can represent customer information, part of features can represent product maintenance information and the like, and all the text features corresponding to each major class form a text feature library. The names of the categories can be changed into technical nouns which are well known in the prior art by manual operation according to the information represented by the text feature library, for example, if a certain text feature library represents the client information, the corresponding category names are the client information, and the corresponding category names are only taken as examples.
Step S103, training preset configuration rules corresponding to the preset dispatch model based on different categories and text feature libraries corresponding to the categories to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the product maintenance capability of the service station and the nearest priority order of the service station to the customer position, and the different categories are in one-to-one correspondence with the matching flow of the configuration rules.
The matching process of the preset configuration rule in the embodiment of the application can be to judge whether the customer in the work order is a large customer, such as a VIP customer, and whether the customer designates a serviceman, if the serviceman is designated, the serviceman is directly matched, if the serviceman is not designated, the faulty product in the product maintenance information in the work order is judged, or the product warranty information of the customer can be obtained, the product type can be obtained by judging the information of the customer, and the like, whether the maintenance service station has stronger maintenance capability for the product can be automatically matched, if so, the corresponding service station is matched, the serviceman under the corresponding station is output based on the service station, if the service station has stronger maintenance capability for the product, the service station with the closest distance from the customer maintenance place can be selected based on the service station, and the serviceman under the corresponding station is matched and output based on the service station, or the region can be matched, for example, the service station under the corresponding station can be matched, and the configuration rule can be set by self according to the actual requirement based on the service station. The matching flow of the configuration rules corresponds to different categories one by one, namely the capability of a service station corresponding to customer designated service personnel and customer information for maintaining products corresponds to product maintenance information, the service station corresponds to position information closest to the customer position, the preset configuration rules are trained based on text feature libraries corresponding to different categories and each category, whether proper matching objects exist in the corresponding configuration rules can be judged according to a certain feature in the text feature library corresponding to a certain category, and finally the intelligent dispatch model is obtained.
According to the intelligent dispatch model construction method provided by the embodiment of the invention, the historical work order sample set is input into the preset dispatch model, the text content of the work order is extracted, the text is subjected to word segmentation and feature extraction processing, the text features are subjected to classification processing, the text feature libraries corresponding to different categories and each category are obtained, the preset configuration rules corresponding to the preset dispatch model are trained based on the obtained text feature libraries corresponding to the different categories and each category, the matching flow of the preset configuration rules is to match the service personnel according to the priority sequence of the service personnel appointed by the customer, the service station maintenance product capability and the service station closest to the customer position, and then the service station is matched according to the priority sequence of whether the service station maintenance product capability and the service station distance are appointed by the customer based on the work order content, and then the service personnel corresponding to the service station are output, so that the customer experience is optimized, the manpower resources are reasonably distributed, the efficient, intelligent and safe dispatch service is realized, and the completion quality and efficiency of the task work order are improved.
In this embodiment, an intelligent dispatch model construction method is provided, which may be used in the above computer device, and fig. 2 is a flowchart of the intelligent dispatch model construction method according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
Step S201, data cleaning and deduplication processing are carried out on the historical work order sample set.
The embodiment of the application can carry out data cleaning and deduplication processing on the historical work order sample set, wherein the cleaning processing can comprise garbage data cleaning, normalization and standardization processing can be carried out on the data, the deduplication processing can comprise deduplication on redundant data, for example, client contacts in two work orders are identical, and only one client contact data can be reserved for classification processing and storage in a corresponding feature library so as to reduce occupation of storage space and improve data transmission efficiency.
Before the historical work order sample set is input into the preset dispatch model, the data cleaning and duplicate removal processing is carried out on the historical work order sample set, and the time for training the preset dispatch model is reduced by reducing the redundant data and screening useful data in the client contacts and the historical work order, so that the model training efficiency is improved.
Step S202, inputting a history work order in a history work order sample set into a preset order-dispatching model, extracting text content of the work order, and performing word segmentation and feature extraction processing on the text content. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
And step S203, classifying the processed text features to obtain text feature libraries corresponding to different categories and each category.
Wherein the different categories include customer information, product repair information, location information.
Specifically, the step S203 includes:
step S2031, classifying the text features by using TF-IDF and a clustering algorithm to generate different text feature dictionaries.
According to the embodiment of the application, the importance weights of all the features in the text content can be calculated by adopting the TF-IDF, the features are ordered in a descending order of importance, the first few features can be taken as the useful features corresponding to the text content, the features corresponding to the low importance weights, such as stop words, can be deleted, the calculated amount is reduced, after the useful features of the text are obtained, a clustering algorithm, such as a K-means clustering algorithm, can be adopted to classify the useful features of the text, a plurality of center points are randomly selected, useful feature samples are distributed to the center point closest to the useful feature samples, the useful feature samples are recalculated in an average value mode according to the useful features in a certain range of the center points, the useful feature samples are distributed to the center point closest to the useful feature samples again, and the steps are repeated until all the feature samples are not changed, namely all the features in the range of each center point form a text feature dictionary, and the useful feature dictionary is only used as an example.
Step S2032, performing category naming processing on the different text feature dictionaries to obtain different categories and text feature libraries corresponding to the categories.
In the embodiment of the application, after the text features are classified, different text feature dictionaries are generated, the classification can be analyzed according to a manual auditing algorithm based on business problems corresponding to the classified different text feature dictionaries, renaming can be carried out according to client information, product maintenance information and position information, and finally, different classification and text feature libraries corresponding to each classification can be obtained.
According to the application, the TF-IDF and the clustering algorithm are adopted to classify the text features, so that the accuracy of feature extraction is improved, the calculation speed is high, and then the obtained text feature libraries of different types and corresponding types are more accurate and comprehensive, and the matching accuracy of the intelligent matching model is improved.
Step S204, based on the newly input worksheet, updating and supplementing the text feature library corresponding to each category.
After the steps are carried out to obtain text feature libraries corresponding to different categories and each category, after a new work order is input into a preset order assignment model, feature extraction and classification processing are carried out on the new work order, after the features corresponding to each category of the new work order are obtained, if feature data corresponding to the category obtained after the processing of the new work order is not in the original text feature library corresponding to a certain category, the features are added into the text feature library.
According to the invention, the text feature library corresponding to each category is updated and supplemented based on the newly input worksheet, so that the existing matching data feature library in the intelligent form-distributing model is more accurate and complete, and the matching accuracy of the intelligent matching model is improved.
Step S205, training preset configuration rules corresponding to the preset dispatch model based on different categories and text feature libraries corresponding to the categories to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the product maintenance capability of the service station and the nearest priority order of the service station to the customer position, and the different categories are in one-to-one correspondence with the matching flow of the configuration rules. Please refer to step S103 in the embodiment of fig. 1 in detail, which is not described herein.
In this embodiment, an intelligent dispatch method is provided, which may be used in the above-mentioned computer device, and fig. 3 is a flowchart of the intelligent dispatch method according to an embodiment of the present invention, as shown in fig. 3, where the flowchart includes the following steps:
step S301, inputting the worksheets to be matched into the intelligent matching model, and matching and determining maintenance personnel.
The intelligent matching model is constructed by the intelligent form sending model construction method in the embodiment.
The worksheet to be matched in the embodiment of the application can be a worksheet to be matched which is obtained by butting an enterprise ERP (Enterprise Resource Planning ), CRM (Customer Relationship Management, customer relationship management), IPS (Internet Protocol Suite, internet protocol group) system to grab customer data, product data, spare part data information and the like and butting an after-sales service system, text content extraction is carried out on the worksheet to be matched, word segmentation and feature extraction processing are carried out on the text content, the obtained text features are classified, text features corresponding to three categories of customer information, product maintenance information and position information are obtained, matching is carried out on the basis of the three categories and the matching flow of the corresponding text features and configuration rules in an intelligent dispatch model, matching is carried out according to the priority order, and finally matched maintenance personnel are output.
Step S302, the determined maintenance personnel information is fed back to the client.
After the matched maintenance personnel are output, the maintenance personnel can be fed back to the clients through the after-sale service system.
According to the application, the work orders to be matched are input into the trained intelligent matching model, so that the maintenance personnel can be matched and determined, the efficient, intelligent and safe dispatch service is realized, and the completion quality and efficiency of the task work orders are improved.
In this embodiment, an intelligent dispatch method is provided, which may be used in the above-mentioned computer device, and fig. 4 is a flowchart of the intelligent dispatch method according to an embodiment of the present application, as shown in fig. 4, where the flowchart includes the following steps:
in step S401, a text extraction model is used to extract key information in dialogue interactive text data.
The text extraction model is obtained through the following steps:
step S4011, performing data cleaning processing on the historical work order sample set.
The historical work order sample set in the embodiment of the application can be obtained from the existing ERP, CRM and other systems of enterprises, and can be subjected to data processing by adopting a natural language processing technology, for example, redundancy data such as client contacts and position information are reduced by removing duplication, and useful data such as client names and service addresses are screened.
Step S4012, word segmentation and key information extraction processing are carried out on the worksheet data in the historical worksheet sample set after the data cleaning processing;
the method for extracting and processing the word segmentation and the key information according to the embodiment of the present application is not described herein.
Step S4013, classifying and training the extracted key information based on a preset corpus to obtain a text extraction model, wherein the preset corpus comprises key words needed by generating work orders, and the key words are in one-to-one correspondence with the key information.
The corpus in the embodiment of the application can comprise keywords such as positions, contacts, fault descriptions and the like required by generating the work orders, the extracted key information is classified and trained based on the corpus by way of example only, one key information corresponds to one keyword, such as keyword fault description corresponds to key information washing machine fault, the extracted key information is classified and trained based on the set corpus by way of machine learning by way of example only, and finally a text extraction model is obtained.
According to the method, a comprehensive and accurate work order sample set is established by means of grabbing, cleaning and the like of the data, the data source and the data analysis capability of the text extraction model are enhanced by focusing on the quality and the integrity of the data, meanwhile, the text extraction model is trained, the data are processed more carefully and intelligently, and then the accuracy and the efficiency of work order matching are improved.
Step S402, obtaining dialogue interactive text data; and extracting key information in the dialogue interactive text data, and generating a work order to be matched.
According to the embodiment of the application, a customer who is to build the work order carries out dialogue with the customer service agent, dialogue interactive text data can be obtained after the dialogue is finished, a text extraction model can be adopted to extract key information in the dialogue text data, such as customer names, addresses, product maintenance conditions, fault problem descriptions and the like, the work order to be matched can be automatically generated based on the key information, the customer service agent can also check whether the data filled in the work order is correct after the work order is generated, the data comprise contacts, telephones, affiliated customers, customer levels, service addresses, product information, fault problems and the like, the product maintenance information is confirmed, and if the work order has errors, the accuracy of work order matching can be improved through manual supplement and modification.
According to the application, the key information in the dialogue interactive text data is extracted based on the dialogue text interactive text data, so that the work order is automatically generated, the false dispatch caused by insufficient manual experience or errors in filling the work order in the related technology is avoided, and the accuracy of intelligent dispatch is improved.
Step S403, inputting the worksheets to be matched into the intelligent matching model, and matching and determining maintenance personnel. The intelligent matching model is constructed by the intelligent form sending model construction method in the embodiment. Please refer to step S301 in the embodiment of fig. 3 in detail, which is not described herein.
Step S404, feeding back the determined maintenance personnel information to the client. Please refer to step S302 in the embodiment shown in fig. 3 in detail, which is not described herein.
The intelligent form-distributing model construction method and the intelligent form-distributing method are implemented based on the cloud computing platform-Arian cloud, a high-performance and safe intelligent form-distributing technical scheme can be realized, main front and rear end frames are adopted, each service is independent and flexible, and reusability of the service can be improved. And the self data center is built according to the requirements of enterprise clients, so that localization and controllability of the dispatch technique can be improved.
And developing an intelligent dispatch front end and a intelligent dispatch back end, and supporting the issuing, processing, dispatch and tracking of tasks. The back end automatically identifies the work order type and assigns corresponding suppliers/service personnel by calling a machine learning model, and the front end provides unified data display and editing functions, including data visualization, work order state modification, acceleration of communication between the suppliers/service personnel and clients, and the like;
In this embodiment, an intelligent form-distributing model construction and intelligent form-distributing device is further provided, and the device is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The embodiment provides an intelligent dispatch model construction device, as shown in fig. 5, including:
the text processing module 501 is configured to input a historical work order in the historical work order sample set into a preset dispatch model, extract text content of the work order, and perform word segmentation and feature extraction processing on the text content;
the feature classification processing module 502 is configured to perform classification processing on the text features obtained after the processing to obtain different categories and text feature libraries corresponding to each category, where the different categories include customer information, product maintenance information, and location information;
the model training module 503 is configured to train a preset configuration rule corresponding to a preset dispatch model based on different types and text feature libraries corresponding to the different types, so as to obtain an intelligent dispatch model, wherein a matching process of the preset configuration rule is to match service personnel according to a priority order of a customer designated service personnel, a service station maintenance product capability and a service station closest to a customer position, and the different types are in one-to-one correspondence with the matching process of the configuration rule.
In some alternative embodiments, the feature classification processing module includes: the classification processing unit is used for classifying the text features by adopting TF-IDF and a clustering algorithm to generate different text feature dictionaries; and the category naming unit is used for performing category naming processing on different text feature dictionaries to obtain different categories and text feature libraries corresponding to the categories.
In some optional embodiments, the intelligent dispatch model building device further includes: and the data processing module is used for carrying out data cleaning and deduplication processing on the historical work order sample set.
In some optional embodiments, the intelligent dispatch model building device further includes: and the feature library updating module is used for updating and supplementing the text feature library corresponding to each category based on the newly input work order.
The embodiment provides an intelligent dispatch device, as shown in fig. 6, the intelligent dispatch device includes:
the work order input module 601 is configured to input a work order to be matched into an intelligent matching model, and match and determine maintenance personnel, where the intelligent matching model is constructed by the intelligent dispatch model construction method in the above embodiment.
And the result feedback module 602 is used for feeding back the determined maintenance personnel information to the client.
In some optional embodiments, the intelligent dispatch device further includes: the data acquisition module is used for acquiring dialogue interaction text data; and the key information extraction module is used for extracting key information in the dialogue interactive text data and generating a work order to be matched.
In some alternative embodiments, the key information extraction module includes: the data cleaning unit is used for performing data cleaning processing on the historical work order sample set; the data processing unit is used for carrying out word segmentation and key information extraction processing on the worksheet data in the historical worksheet sample set after the data cleaning processing; the model training unit is used for carrying out classified training on the extracted key information based on a preset corpus to obtain a text extraction model, wherein the preset corpus comprises key words needed by generating work orders, and the key words correspond to the key information one by one.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The intelligent dispatch model building device and intelligent dispatch device of the present embodiment are presented in the form of functional units, where the units are ASIC (Application Specific Integrated Circuit ) circuits, processors and memories executing one or more software or firmware programs, and/or other devices that can provide the above functions.
The embodiment of the invention also provides computer equipment, which is provided with the intelligent dispatch model construction device shown in the figure 5 and the intelligent dispatch device shown in the figure 6.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 7, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 7.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device further comprises input means 30 and output means 40. The processor 10, memory 20, input device 30, and output device 40 may be connected by a bus or other means, for example in fig. 7.
The input device 30 may receive input numeric or character information and generate key signal inputs related to customer settings and function control of the computer apparatus, such as a touch screen, keypad, mouse, trackpad, touchpad, pointer stick, one or more mouse buttons, trackball, joystick, and the like. The output means 40 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays, light emitting diodes, displays and plasma displays. In some alternative implementations, the display device may be a touch screen.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (11)
1. The intelligent form distribution model construction method is characterized by comprising the following steps of:
inputting a historical work order in a historical work order sample set into a preset dispatch model, extracting text content of the work order, and performing word segmentation and feature extraction processing on the text content;
classifying the text features obtained after the processing to obtain text feature libraries of different categories and corresponding categories, wherein the different categories comprise customer information, product maintenance information and position information;
training preset configuration rules corresponding to the preset dispatch model based on different types and text feature libraries corresponding to the different types to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the product maintenance capability of the service station and the nearest priority order of the service station to the customer position, and the different types are in one-to-one correspondence with the matching flow of the configuration rules.
2. The method according to claim 1, wherein the classifying the processed text features to obtain text feature libraries corresponding to different categories and each category includes:
classifying the text features by adopting TF-IDF and a clustering algorithm to generate different text feature dictionaries;
And carrying out category naming processing on the different text feature dictionaries to obtain text feature libraries corresponding to different categories and each category.
3. The method of claim 1, wherein before inputting the historical worksheets in the historical worksheet sample set into the preset dispatch model, the method further comprises:
and carrying out data cleaning and deduplication processing on the historical work order sample set.
4. The method for constructing an intelligent form-dispatching model according to claim 1, wherein after classifying the text features obtained after the processing to obtain text feature libraries corresponding to different categories and each category, the method further comprises:
and updating and supplementing the text feature library corresponding to each category based on the newly input worksheet.
5. An intelligent dispatch method, the method comprising:
inputting a work order to be matched into an intelligent matching model, and matching and determining maintenance personnel, wherein the intelligent matching model is constructed by the intelligent order-dispatching model construction method according to any one of claims 1-4;
and feeding back the determined maintenance personnel information to the client.
6. The intelligent dispatch method of claim 5, wherein prior to entering the worksheet to be matched into the intelligent matching model, the method further comprises:
Acquiring dialogue interactive text data;
and extracting key information in the dialogue interactive text data, and generating the work order to be matched.
7. The intelligent dispatch method of claim 6, wherein a text extraction model is used to extract key information in the dialogue interactive text data, the text extraction model is obtained by:
performing data cleaning treatment on the historical work order sample set;
word segmentation and key information extraction processing are carried out on the worksheet data in the historical worksheet sample set after the data cleaning processing;
and carrying out classification training on the extracted key information based on a preset corpus to obtain a text extraction model, wherein the preset corpus comprises key words needed by generating work orders, and the key words are in one-to-one correspondence with the key information.
8. An intelligent dispatch model building device, which is characterized in that the device comprises:
the text processing module is used for inputting the historical worksheets in the historical worksheet sample set into a preset dispatch model, extracting text contents of the worksheets, and performing word segmentation and feature extraction processing on the text contents;
the feature classification processing module is used for classifying the processed text features to obtain different categories and text feature libraries corresponding to the categories, wherein the different categories comprise customer information, product maintenance information and position information;
The model training module is used for training preset configuration rules corresponding to the preset dispatch model based on different types and text feature libraries corresponding to the different types to obtain an intelligent dispatch model, wherein the matching flow of the preset configuration rules is to match service personnel according to the priority order of the service personnel designated by the customer, the service station maintenance product capability and the nearest service station to the customer position, and the different types are in one-to-one correspondence with the matching flow of the configuration rules.
9. An intelligent dispatch device, characterized in that the device comprises:
the work order input module is used for inputting the work order to be matched into the intelligent matching model, and matching and determining maintenance personnel, wherein the intelligent matching model is constructed by the intelligent order form model construction method according to any one of claims 1-4;
and the result feedback module is used for feeding the determined maintenance personnel information back to the client.
10. A computer device, comprising:
a memory and a processor, the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, thereby executing the intelligent dispatch model construction method of any one of claims 1 to 4, or executing the intelligent dispatch method of any one of claims 5 to 7.
11. A computer-readable storage medium, wherein computer instructions are stored on the computer-readable storage medium, and the computer instructions are configured to cause a computer to perform the intelligent dispatch model building method of any one of claims 1 to 4, or perform the intelligent dispatch method of any one of claims 5 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310672430.7A CN116739256A (en) | 2023-06-07 | 2023-06-07 | Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310672430.7A CN116739256A (en) | 2023-06-07 | 2023-06-07 | Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116739256A true CN116739256A (en) | 2023-09-12 |
Family
ID=87916185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310672430.7A Pending CN116739256A (en) | 2023-06-07 | 2023-06-07 | Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739256A (en) |
-
2023
- 2023-06-07 CN CN202310672430.7A patent/CN116739256A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10769187B2 (en) | Crowdsourced training of textual natural language understanding systems | |
| JP6714024B2 (en) | Automatic generation of N-grams and conceptual relationships from language input data | |
| US20200226212A1 (en) | Adversarial Training Data Augmentation Data for Text Classifiers | |
| US11551123B2 (en) | Automatic visualization and explanation of feature learning output from a relational database for predictive modelling | |
| CN111177231A (en) | Report generation method and report generation device | |
| CN110070862B (en) | Method and system for automatic guidance based on ontology in dialogue system | |
| US11567460B2 (en) | Failure mode analytics | |
| CN112711581B (en) | Medical data checking method and device, electronic equipment and storage medium | |
| US20210191938A1 (en) | Summarized logical forms based on abstract meaning representation and discourse trees | |
| CN111435362B (en) | Antagonistic training data enhancement for generating a correlation response | |
| US11144607B2 (en) | Network search mapping and execution | |
| CN110837356A (en) | Data processing method and device | |
| CN112307177A (en) | Generating a process flow model using an unstructured conversational robot | |
| US10262061B2 (en) | Hierarchical data classification using frequency analysis | |
| US11809375B2 (en) | Multi-dimensional data labeling | |
| CN116739256A (en) | Intelligent form-dispatching model construction and intelligent form-dispatching method, device, equipment and medium | |
| US20230029218A1 (en) | Feature engineering using interactive learning between structured and unstructured data | |
| US11481212B2 (en) | Automatic identification of reference data | |
| CN112381167A (en) | Method for training task classification model, and task classification method and device | |
| US20200090185A1 (en) | Product declaration validation | |
| US10572281B1 (en) | Bi-directional notification service | |
| US10387553B2 (en) | Determining and assisting with document or design code completeness | |
| CN114556326B (en) | Method and system for generating natural language expression variants | |
| CN113553431B (en) | User tag extraction method, device, equipment and medium | |
| US20230027897A1 (en) | Rapid development of user intent and analytic specification in complex data spaces |
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 |