CN114936727A - Work order distribution system, method and computer equipment - Google Patents
Work order distribution system, method and computer equipment Download PDFInfo
- Publication number
- CN114936727A CN114936727A CN202210055832.8A CN202210055832A CN114936727A CN 114936727 A CN114936727 A CN 114936727A CN 202210055832 A CN202210055832 A CN 202210055832A CN 114936727 A CN114936727 A CN 114936727A
- Authority
- CN
- China
- Prior art keywords
- work order
- item
- unit
- word segmentation
- output result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06F16/367—Ontology
-
- 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
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Animal Behavior & Ethology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a work order dispatching system, a work order dispatching method and computer equipment, which are used for acquiring text information of a work order; performing word segmentation processing on the text information of the work order to obtain a work order word segmentation set; analyzing and processing the work order word segmentation set based on a pre-constructed item analysis model to obtain the items of the work order; acquiring a processing unit matched with the item of the work order according to the pre-established item and unit corresponding relation; and sending the work order to a processing unit matched with the items of the work order. The work order is automatically sent to a processing unit, so that the automatic processing and dispatching of the work order are realized, the cost is reduced, and the efficiency and the accuracy of dispatching the work order are improved.
Description
Technical Field
The invention relates to the technical field of language processing, in particular to a work order distribution system, a work order distribution method and computer equipment.
Background
12345 the citizen hot line accepts the citizen calls, which are the most important contact carriers with the citizen, complete the acceptance, transfer and return visit of citizen appeal, and communicate and interact with the citizen, the acceptance volume of the current daily telephone appeal reaches 25000 pieces, and the per-day acceptance volume of telephone operators reaches 60 pieces. With the continuous promotion of 12345 to citizen service positioning and the expansion of accepted service range, the requirements for the accuracy assessment of processing efficiency, service answering and appeal undertaking units are continuously improved, and the service acceptance pressure of telephone operators is higher and higher. At present, when a telephone operator accepts a citizen demand each time, time is spent on understanding, analyzing and sorting the demand content proposed in the telephone dictation process of the citizen, and most of work orders need to be distributed to all departments for handling. According to different requirements of citizens, the citizens are dispatched to more than 150 departments such as all levels of public service units, social groups, central direct enterprises and the like, and the accuracy of dispatching the orders depends on the personal capability of operators, so that the service efficiency and the accuracy are not high.
Disclosure of Invention
Based on the above problems, the invention provides a work order dispatching system, a work order dispatching method and computer equipment, and aims to solve the technical problems of low work order dispatching service efficiency, low accuracy and the like in the prior art.
A work order distribution system, comprising:
the text acquisition module is used for acquiring text information of the work order;
the word segmentation processing module is connected with the text acquisition module and is used for carrying out word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
the event analysis module is connected with the word segmentation processing module and used for analyzing and processing the work order word segmentation set based on a pre-constructed event analysis model to obtain the events of the work order;
the matching module is connected with the item analysis module and is used for acquiring a processing unit matched with the item of the work order according to the pre-established item and unit corresponding relation;
and the order sending module is connected with the matching module and used for sending the work order to the processing unit matched with the items of the work order.
Further, the item analysis model comprises an item knowledge graph model and an item classification model, and the item analysis module comprises:
the first analysis unit is used for reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model to obtain a first output result;
the judging unit is connected with the first analyzing unit and used for judging whether the first output result comprises the belonged item of the work order or not and outputting a judging result;
the second analysis unit is connected with the judgment unit and used for learning the work order word segmentation set based on the item classification model to obtain the belonged item of the work order and obtain a second output result when the judgment result is that the belonged item of the work order is not contained;
the sending unit is respectively connected with the judging unit and the second analyzing unit and used for sending the first output result to the matching module when the judging result is that the item to which the work order belongs is contained; and when the judgment result is that the item of the work order is not included, sending a second output result to the matching module.
Further, the item analysis model comprises an item knowledge graph model and an item classification model, and the item analysis module comprises:
the first analysis unit is used for reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model to obtain the item of the work order, and the item is used as a first output result;
a first judgment unit for judging whether the item of the work order is inferred from the first output result and outputting the first judgment result;
the second analysis unit is connected with the first judgment unit and used for learning the work order word segmentation set based on the matter classification model to obtain the belonged matters of the work order as a second output result when the first judgment result is that the belonged matters of the work order are inferred from the first output result;
the second judging unit is connected with the second analyzing unit and used for judging whether the second output result infers the items of the work order or not and outputting a second judging result;
the third judging unit is respectively connected with the first judging unit and the second judging unit and used for outputting a third judging result if the items in the first output result are the same as the items in the second output result when the second judging result is that the second output result infers the items of the work order;
the sending unit is respectively connected with the first judging unit, the second judging unit and the third judging unit and is used for sending the work order to the preprocessing system when the first judging result indicates that the first output result does not infer the belonged item of the work order, or when the second judging result indicates that the second output result does not infer the belonged item of the work order, or when the third judging result indicates that the items in the first output result and the items in the second output result are different; and
and when the third judgment result is that the items in the first output result are the same as the items in the second output result, the items are sent to the matching module.
Further, the word segmentation processing module comprises:
the word segmentation unit is used for carrying out word segmentation processing on the text information of the work order to obtain a word segmentation result;
and the removing unit is connected with the word segmentation unit and used for removing stop words in the word segmentation result according to a preset stop word bank to obtain a work order word segmentation set.
Further, the word segmentation processing module further comprises:
the replacing unit is connected with the removing unit and used for replacing the reserved words into the keywords according to a preset synonym table to form a work order word segmentation set after the stop words in the word segmentation result are removed;
the triplets of the item knowledge graph model are predefined item-relationship-keyword triplets.
Further, the item classification model is obtained based on the training of the processed work order.
A work order dispatching method further comprises the following steps:
step A1, acquiring text information of a work order;
step A2, performing word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
step A3, analyzing and processing the work order word segmentation set based on a pre-constructed item analysis model to obtain the items of the work order;
step A4, acquiring processing units matched with items of the work order according to the pre-established item and unit corresponding relation;
step A5, the work order is sent to the processing unit matching the items to which the work order belongs.
Further, in step a3, the item analysis model includes an item knowledge graph model and an item classification model, and includes the following steps:
step A301, reasoning a work order word segmentation set based on a triplet group of a matter knowledge graph model to obtain a first output result;
step a302, determining whether the first output result includes the item to which the work order belongs:
if yes, continue step A4;
if not, continuing the step A303;
step A303, learning the work order word segmentation set based on the item classification model to obtain the items of the work order, obtaining a second output result, and continuing to step A4.
Further, in step a3, the item analysis model includes an item knowledge graph model and an item classification model, and includes the following steps:
step A311, reasoning the work order participle set based on the triplet group of the item knowledge graph model, and determining whether the affiliated items of the work order can be inferred:
if yes, taking the item of the work order as a first output result, and continuing to the step A302;
if not, continuing to the step A6;
step A312, learning the work order word segmentation set based on the item classification model, and determining whether the items to which the work order belongs are obtained:
if yes, taking the belonged item of the work order as a second output result, and continuing to the step A313;
if not, continue with step A6;
step a313, determining whether the item in the first output result is the same as the item in the second output result:
if yes, continue step A4;
if not, continuing to the step A6;
step A6, send the work order to the preprocessing system.
A computer device comprising a memory for storing a computer program and a processor for running the computer program to implement a method of work order dispatch as hereinbefore described.
The invention has the beneficial technical effects that: according to the invention, the text information is obtained by processing the work order, the keywords are further extracted, the items corresponding to the work order are obtained by utilizing the pre-trained model analysis, the processing unit is obtained according to the items, the work order is automatically dispatched to the processing unit, the automatic processing and dispatching of the work order are realized, the cost is reduced, and the efficiency and the accuracy of dispatching the work order are improved.
Drawings
FIG. 1 is a block diagram of a work order dispatch system of the present invention;
FIG. 2 is a schematic diagram of an embodiment of a transaction analysis module of the work order delivery system of the present invention;
FIG. 3 is a schematic diagram of another embodiment of a transaction analysis module of the work order delivery system of the present invention;
FIG. 4 is a schematic diagram of a word segmentation processing module of the work order delivery system according to the present invention;
FIG. 5 is a flowchart illustrating steps of a work order dispatch method according to the present invention;
FIG. 6 is a flowchart of the steps of one embodiment of a method for work order dispatch for obtaining work order items of the present invention;
FIG. 7 is a flowchart illustrating steps of another embodiment of a method for dispatching a work order to obtain items to which the work order pertains;
FIG. 8 is a schematic diagram of a computer apparatus for dispatching work orders according to the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
Referring to fig. 1, a work order distribution system includes:
the text acquisition module (1) is used for acquiring text information of the work order;
the word segmentation processing module (2) is connected with the text acquisition module (1) and is used for carrying out word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
the item analysis module (3) is connected with the participle processing module (2) and is used for analyzing and processing the work order participle set based on a pre-constructed item analysis model to obtain the belonged items of the work order;
the matching module (4) is connected with the item analysis module (3) and is used for acquiring a processing unit matched with the item of the work order according to the pre-established item and unit corresponding relation;
and the order sending module (5) is connected with the matching module (4) and is used for sending the work order to the processing unit matched with the items of the work order.
Specifically, the item analysis model includes an item knowledge graph model and an item classification model. And the item knowledge graph model is to apply an inference machine and infer the work order word segmentation list based on a pre-constructed item knowledge graph triplet, and the item classification model is to learn the work order word segmentation list in a machine learning mode to obtain the items to which the work order belongs.
Referring to fig. 2, further, the item analysis model includes an item knowledge graph model and an item classification model, and the item analysis module (3) includes:
the first analysis unit (301) is used for reasoning the work order word segmentation set based on the triplets of the item knowledge graph model to obtain a first output result;
the judging unit (302) is connected with the first analyzing unit (301) and is used for judging whether the first output result comprises the belonged item of the work order or not and outputting the judging result;
a second analysis unit (303) connected with the judgment unit (302) and used for learning the work order word segmentation set based on the item classification model to obtain the item of the work order and obtain a second output result when the judgment result is that the item of the work order is not included;
a sending unit (304) which is respectively connected with the judging unit (302) and the second analyzing unit (303) and is used for sending the first output result to the matching module (4) when the judging result is that the item to which the work order belongs is included; and when the judgment result is that the item of the work order is not included, sending a second output result to the matching module (4).
Referring to fig. 3, further, the item analysis model includes an item knowledge graph model and an item classification model, and the item analysis module (3) includes:
the first analysis unit (311) is used for reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model to obtain the belonged items of the work order as a first output result;
a first judgment unit (312) for judging whether the item of the work order is inferred from the first output result and outputting the first judgment result;
the second analysis unit (313) is connected with the first judgment unit (312) and is used for learning the work order word segmentation set based on the matter classification model to obtain the belonged matters of the work order as a second output result when the first judgment result is that the belonged matters of the work order are inferred from the first output result;
a second judgment unit (314) which is connected with the second analysis unit (313) and used for judging whether the second output result infers the item of the work order or not and outputting a second judgment result;
a third judgment unit (315) which is connected with the first judgment unit (312) and the second judgment unit (314) respectively and is used for outputting a third judgment result if the item in the first output result is the same as the item in the second output result when the second judgment result is that the item of the work order is inferred from the second output result;
a sending unit (316) which is respectively connected with the first judging unit (312), the second judging unit (314) and the third judging unit (315) and is used for sending the work order to the preprocessing system when the first judging result is that the first output result does not deduce the belonged item of the work order, or when the second judging result is that the second output result does not deduce the belonged item of the work order, or when the third judging result is that the items in the first output result and the items in the second output result are different; and
and when the third judgment result is that the events in the first output result are the same as the events in the second output result, the events are sent to the matching module (4).
The work order received in the preprocessing system may be scheduled for manual processing. Specifically, the voice data of the work order or the text information of the work order may be directly sent to the preprocessing system. And manually receiving the work order through preset equipment for processing.
And automatically dispatching when the items to which the work orders belong, which are inferred by the triples of the item knowledge graph model, are the same as the items to which the work orders belong, which are obtained by learning the item classification model, so that the accuracy of analyzing and extracting is improved, and the accuracy of dispatching is improved.
Referring to fig. 4, further, the word segmentation processing module (2) includes:
the word segmentation unit (21) is used for carrying out word segmentation processing on the text information of the work order to obtain word segmentation results;
and the removing unit (22) is connected with the word segmentation unit (21) and is used for removing stop words in the word segmentation result according to a preset stop word bank to obtain a work order word segmentation set.
Further, the word segmentation processing module (2) further comprises:
the replacing unit (23) is connected with the removing unit (22) and is used for replacing the reserved words into the keywords according to the preset synonym table to form a work order segmentation set after the stop words in the segmentation result are removed;
the triplets of the item knowledge graph model are predefined item-relationship-keyword triplets.
Further, the item classification model is obtained based on the training of the processed work order.
In the invention, the predefining needs to be performed at the computer database and file system level. Specifically, a knowledge graph model, a correspondence table of items and units, and a synonym table of items need to be built in a database of a computer; item classification model files, stop word stock files, custom word stock files and the like are built in the file system. The triplets of the matter knowledge graph model include: item-relationship-keyword, and specify the definition of the relationship. The triplets of the item knowledge graph model can be constructed according to the transacted historical work orders and the business rules to form items, keywords and relation definitions thereof. The item and unit correspondence table includes: item-attribute-dispatch unit, attribute can be expressed as item occurrence area, item property, etc. The item classification model can be various neural network models, the item classification model file in the file system can adopt a finished worksheet, and the item classification model is obtained by training the neural network model to the finished worksheet through learning and is used for judging items which have not yet been built or have unclear business rules.
The word segmentation result can be obtained by introducing a user-defined word bank to perform word segmentation. The synonym table of the item keywords is used for enhancing item knowledge expression and improving inference capability of an inference engine.
Further, the work order is voice data, and text information of the work order is obtained by processing the voice data.
The text information of the work order may be obtained by processing voice data of the work order (for example, a call with a voice between an operator and a user), and specifically, the voice data of the work order may be converted into text information by a method known to those skilled in the art, which is not described herein again.
The work order may be a 12345 civic hotline work order, but not limited thereto, and various other work orders requiring transfer of processing units may be processed by using the embodiment.
Specifically, the work order participle set is in the form of a work order participle list.
Specifically, the item and unit correspondence is in the form of a list of item and unit correspondence.
Specifically, the method and the device collect the triples of the item knowledge map model and/or the items which cannot be identified by the item classification model, introduce the machine learning classification model, realize the efficient and intelligent identification of the items, serve as the effective supplement and cross validation of knowledge map reasoning, further adjust the business rules, update the knowledge map model, train the item classification model, and further continuously improve the work order distribution accuracy. And a machine learning classification model is introduced as a supplement, so that the method has stronger adaptability and flexible expansion mode.
For the work orders with clear business rules, obvious theme scenes and higher priority, the rules are constructed through the knowledge graph, and the precise identification of items is realized; the machine learning classification model built through the historical work order can efficiently judge the general business work order, and both the efficiency and the precision are considered.
Based on the simple keyword matching rules or similarity calculation in the prior art, the problems of low work order dispatching accuracy, weak expandability, incapability of cross validation and the like under complex service scenes cannot be effectively solved, the invention obtains a work order word segmentation list by segmenting the text information of the work order, then analyzing the work order word segmentation list based on the item knowledge map triple and the item classification model to obtain the items to which the work order belongs, obtaining the information of the processing unit corresponding to the items to which the work order belongs according to the items and the unit corresponding relation table, the invention can realize automatic dispatch of the work order, has more accurate result, reduces the training cost of manual customer service to a certain extent, solves the problem of low dispatch accuracy of the independent machine learning model caused by complex historical data service, and is beneficial to improving the dispatch accuracy and efficiency of the work order.
Referring to fig. 5, a work order distribution system is characterized by comprising the following steps:
step A1, acquiring text information of a work order;
step A2, performing word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
step A3, analyzing and processing the work order word segmentation set based on a pre-constructed item analysis model to obtain the items of the work order;
step A4, acquiring processing units matched with items of the work order according to the pre-established item and unit corresponding relation;
step A5, the work order is sent to the processing unit matching the items to which the work order belongs.
Referring to fig. 6, further, in step a3, the item analysis model includes an item knowledge graph model and an item classification model, and includes the following steps:
step A301, reasoning a work order word segmentation set based on a triplet group of a matter knowledge graph model to obtain a first output result;
step a302, determining whether the first output result includes the items to which the work order belongs:
if yes, continue step A4;
if not, continuing the step A303;
step A303, learning the work order word segmentation set based on the item classification model to obtain the items of the work order, obtaining a second output result, and continuing to step A4.
Referring to fig. 7, further, in step a3, the item analysis model includes an item knowledge graph model and an item classification model, and includes the following steps:
step A311, reasoning the work order participle set based on the triplet group of the item knowledge graph model, and determining whether the affiliated items of the work order can be inferred:
if yes, taking the item of the work order as a first output result, and continuing to the step A302;
if not, continuing to the step A6;
step A312, learning the work order word segmentation set based on the item classification model, and determining whether the items to which the work order belongs are obtained:
if yes, taking the belonged item of the work order as a second output result, and continuing to the step A313;
if not, continue with step A6;
step a313, determining whether the item in the first output result is the same as the item in the second output result:
if yes, continue step A4;
if not, continuing to the step A6;
step A6, send the work order to the preprocessing system.
Referring to fig. 8, a computer apparatus comprises a memory for storing a computer program and a processor for running the computer program to implement a method of work order dispatch as previously described.
The computer device comprises one or more processors 6 and a memory 7, one processor 6 being exemplified in fig. 4. The processor 6 and the memory 7 may be connected by a bus or in another way, and fig. 4 illustrates the connection by a bus as an example. The memory 7, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 6 executes various functional applications of the device and data processing by executing non-volatile software programs, instructions and modules stored in the memory 7, i.e. implements the above-described method.
The memory 7 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function. Further, the memory 7 may include a high speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
One or more modules are stored in memory 7 and, when executed by the one or more processors 6, perform the work order dispatch method of any of the method embodiments described above.
Compared with the prior art, the computer equipment provided by the embodiment of the invention can realize automatic dispatch of the work order, so that the training cost of manual customer service can be reduced to a certain extent, and meanwhile, the problem of low dispatch accuracy of the single machine learning model caused by complex historical data service can be solved, and the dispatch accuracy and efficiency of the work order can be improved.
An embodiment of the present application further provides a non-volatile storage medium for storing a computer-readable program, where the computer-readable program is used for a computer to execute some or all of the above method embodiments.
That is, those skilled in the art can understand that all or part of the steps in the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, etc.) or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The invention can be applied to the scene of task intelligent identification and distribution in the general field, and can be applied to the scene of automatic work order distribution in intelligent customer service in the electric field. The invention can be applied to an intelligent dispatch scene after operation and maintenance information acquisition in the field of telecommunication.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A work order distribution system, comprising:
the text acquisition module is used for acquiring text information of the work order;
the word segmentation processing module is connected with the text acquisition module and is used for carrying out word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
the item analysis module is connected with the word segmentation processing module and used for analyzing and processing the work order word segmentation set based on a pre-constructed item analysis model to obtain the items of the work order;
the matching module is connected with the item analysis module and is used for acquiring a processing unit matched with the item of the work order according to the pre-established item and unit corresponding relation;
and the order sending module is connected with the matching module and used for sending the work order to the processing unit matched with the items of the work order.
2. The work order dispatch system of claim 1, wherein the item analysis model comprises an item knowledge graph model and an item classification model, the item analysis module comprising:
the first analysis unit is used for reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model to obtain a first output result;
the judging unit is connected with the first analyzing unit and used for judging whether a first output result comprises the items of the work order or not and outputting a judgment result;
the second analysis unit is connected with the judgment unit and used for learning the work order word segmentation set based on the item classification model to obtain the item of the work order and obtain a second output result when the judgment result is that the item of the work order is not included;
the sending unit is respectively connected with the judging unit and the second analyzing unit and used for sending a first output result to the matching module when the judging result is that the item to which the work order belongs is included; and when the judgment result is that the item of the work order is not included, sending the second output result to the matching module.
3. The work order dispatch system of claim 1, wherein the item analysis model comprises an item knowledge graph model and an item classification model, the item analysis module comprising:
the first analysis unit is used for reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model so as to obtain the item of the work order as a first output result;
a first judgment unit for judging whether the item of the work order is inferred from the first output result and outputting a first judgment result;
the second analysis unit is connected with the first judgment unit and used for learning the work order word segmentation set based on the item classification model to obtain the item of the work order as a second output result when the first judgment result is that the item of the work order is inferred from the first output result;
the second judging unit is connected with the second analyzing unit and used for judging whether the second output result infers the belonged item of the work order or not and outputting a second judging result;
a third determining unit, respectively connected to the first determining unit and the second determining unit, configured to output a third determining result if the item in the first output result is the same as the item in the second output result when the second determining result indicates that the item of the work order belongs to the second output result;
a sending unit, respectively connected to the first determining unit, the second determining unit, and the third determining unit, for sending the work order to a preprocessing system when the first determination result indicates that the item to which the work order belongs is not inferred from the first output result, or when the second determination result indicates that the item to which the work order belongs is not inferred from the second output result, or when the third determination result indicates that the item in the first output result is different from the item in the second output result; and
and when the third judgment result is that the item in the first output result is the same as the item in the second output result, the item is sent to the matching module.
4. The work order dispatch system of claim 2, wherein the participle processing module comprises:
the word segmentation unit is used for carrying out word segmentation processing on the text information of the work order to obtain a word segmentation result;
and the removing unit is connected with the word segmentation unit and is used for removing stop words in the word segmentation result according to a preset stop word bank to obtain the work order word segmentation set.
5. The work order delivery system of claim 4, wherein the participle processing module further comprises:
the replacing unit is connected with the removing unit and used for replacing the reserved words into the keywords according to a preset synonym table to form the work order participle set after removing stop words in the participle result;
the triples of the item knowledge graph model are predefined item-relationship-keyword triples.
6. The work order distribution system of claim 2, wherein the item classification model is obtained based on learning and training a finished work order.
7. A work order dispatching method is characterized by comprising the following steps:
step A1, acquiring text information of a work order;
step A2, performing word segmentation processing on the text information of the work order to obtain a work order word segmentation set;
step A3, analyzing and processing the work order participle set based on a pre-constructed item analysis model to obtain the items of the work order;
step A4, acquiring a processing unit matched with the item of the work order according to the pre-established item and unit corresponding relation;
step A5, sending the work order to the processing unit matched with the item of the work order.
8. The work order dispatching method as claimed in claim 7, wherein in said step A3, said item analysis model comprises an item knowledge graph model and an item classification model, comprising the steps of:
step A301, reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model to obtain a first output result;
step a302, determining whether the first output result includes the item to which the work order belongs:
if yes, continuing the step A4;
if not, continuing the step A303;
step A303, learning the work order word segmentation set based on the item classification model to obtain the item of the work order, obtaining a second output result, and continuing to the step A4.
9. The work order dispatching method as claimed in claim 7, wherein in said step A3, said item analysis model comprises an item knowledge graph model and an item classification model, comprising the steps of:
step A311, reasoning the work order word segmentation set based on the triplet group of the item knowledge graph model, and determining whether the item of the work order can be inferred:
if yes, taking the item of the work order as a first output result, and continuing to the step A302;
if not, continuing the step A6;
step A312, learning the work order word segmentation set based on the item classification model, and determining whether the item of the work order is obtained:
if yes, taking the item of the work order as a second output result, and continuing to the step A313;
if not, continuing with the step A6;
step a313 of determining whether the item in the first output result and the item in the second output result are the same:
if yes, continuing the step A4;
if not, continuing the step A6;
the step A6 is to send the work order to a preprocessing system.
10. A computer arrangement comprising a memory for storing a computer program and a processor for running the computer program to implement a method of work order dispatch as claimed in any one of claims 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210055832.8A CN114936727A (en) | 2022-01-18 | 2022-01-18 | Work order distribution system, method and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210055832.8A CN114936727A (en) | 2022-01-18 | 2022-01-18 | Work order distribution system, method and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114936727A true CN114936727A (en) | 2022-08-23 |
Family
ID=82862052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210055832.8A Pending CN114936727A (en) | 2022-01-18 | 2022-01-18 | Work order distribution system, method and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114936727A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115495793A (en) * | 2022-11-17 | 2022-12-20 | 中关村科学城城市大脑股份有限公司 | Multi-set problem secure transmission method, device, equipment and medium |
| CN115641090A (en) * | 2022-11-07 | 2023-01-24 | 北京北明数科信息技术有限公司 | Item distribution method, item distribution system, computer device, and medium |
| CN116108169A (en) * | 2022-12-12 | 2023-05-12 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
| CN116402314A (en) * | 2023-05-31 | 2023-07-07 | 北京拓普丰联信息科技股份有限公司 | Information prompting method, device, equipment and medium |
-
2022
- 2022-01-18 CN CN202210055832.8A patent/CN114936727A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115641090A (en) * | 2022-11-07 | 2023-01-24 | 北京北明数科信息技术有限公司 | Item distribution method, item distribution system, computer device, and medium |
| CN115641090B (en) * | 2022-11-07 | 2023-11-07 | 北京北明数科信息技术有限公司 | Item distribution method, system, computer device and medium |
| CN115495793A (en) * | 2022-11-17 | 2022-12-20 | 中关村科学城城市大脑股份有限公司 | Multi-set problem secure transmission method, device, equipment and medium |
| CN116108169A (en) * | 2022-12-12 | 2023-05-12 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
| CN116108169B (en) * | 2022-12-12 | 2024-02-20 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
| CN116402314A (en) * | 2023-05-31 | 2023-07-07 | 北京拓普丰联信息科技股份有限公司 | Information prompting method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114936727A (en) | Work order distribution system, method and computer equipment | |
| CN104598445B (en) | Automatically request-answering system and method | |
| CN108509477B (en) | Method for recognizing semantics, electronic device and computer readable storage medium | |
| CN110110321A (en) | Products Show method, apparatus, equipment and storage medium based on voice data | |
| CN107688667A (en) | Intelligent robot client service method, electronic installation and computer-readable recording medium | |
| CN111125354A (en) | Text classification method and device | |
| CN107807960B (en) | Intelligent customer service method, electronic device and computer readable storage medium | |
| CN107248082A (en) | Support card identification method and device | |
| CN111858854B (en) | Question-answer matching method and relevant device based on historical dialogue information | |
| CN111970400B (en) | Crank call identification method and device | |
| CN112003989A (en) | Agent matching method and device, electronic equipment and computer storage medium | |
| CN110225210A (en) | Based on call abstract Auto-writing work order method and system | |
| CN111274390B (en) | Emotion cause determining method and device based on dialogue data | |
| CN110765776A (en) | Method and device for generating return visit labeling sample data | |
| CN116070019A (en) | Intelligent recruitment recommendation method and system based on big data and readable storage medium | |
| CN113297365B (en) | User intention judging method, device, equipment and storage medium | |
| CN110750626B (en) | Scene-based task-driven multi-turn dialogue method and system | |
| CN113902569A (en) | Method for identifying the proportion of green assets in digital assets and related products | |
| CN117278675A (en) | Outbound method, device, equipment and medium based on intention classification | |
| CN115687754B (en) | Active network information mining method based on intelligent dialogue | |
| CN116501844A (en) | Voice keyword retrieval method and system | |
| CN115953080A (en) | Engineer service level determination method, apparatus and storage medium | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method | |
| CN110162614B (en) | Question information extraction method and device, electronic equipment and storage medium | |
| CN113469237A (en) | User intention identification method and device, electronic equipment and storage medium |
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 |