CN111782803B - Work order processing method and device, electronic equipment and storage medium - Google Patents
Work order processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111782803B CN111782803B CN202010506232.XA CN202010506232A CN111782803B CN 111782803 B CN111782803 B CN 111782803B CN 202010506232 A CN202010506232 A CN 202010506232A CN 111782803 B CN111782803 B CN 111782803B
- Authority
- CN
- China
- Prior art keywords
- work order
- distributed
- corpus content
- processing object
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title description 4
- 238000012545 processing Methods 0.000 claims abstract description 167
- 238000000034 method Methods 0.000 claims abstract description 51
- 239000013598 vector Substances 0.000 claims description 42
- 238000004458 analytical method Methods 0.000 claims description 27
- 238000004891 communication Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000008451 emotion Effects 0.000 description 24
- 230000008569 process Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- DQXBYHZEEUGOBF-UHFFFAOYSA-N but-3-enoic acid;ethene Chemical compound C=C.OC(=O)CC=C DQXBYHZEEUGOBF-UHFFFAOYSA-N 0.000 description 3
- 239000005038 ethylene vinyl acetate Substances 0.000 description 3
- 229920001200 poly(ethylene-vinyl acetate) Polymers 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 240000005099 Cercis occidentalis Species 0.000 description 1
- 235000006228 Cercis occidentalis Nutrition 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000004035 construction material Substances 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000003472 neutralizing effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
The application relates to a method and a device for processing a work order, electronic equipment and a storage medium, wherein the method comprises the following steps: determining corpus content of work orders to be distributed; inputting the corpus content into a pre-trained text recognition model, and obtaining a recognition result according to the corpus content by the text recognition model; determining a target processing object for processing the work order to be allocated according to the identification result; and sending the work order to be distributed to the target processing object. According to the technical scheme, the text recognition technology in the artificial intelligence technology is utilized to analyze the corpus content of the work orders to be distributed, so that the target processing object for processing the work orders to be distributed is obtained, the complexity of classifying the work orders in a manual mode is effectively solved, manual access is effectively avoided, and the work order processing efficiency is improved.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method and apparatus for processing a work order, an electronic device, and a storage medium.
Background
With the development of the Internet, the contents of the complaint worksheets of users are various in the big data age, and the worksheets are distributed to processing departments through manual understanding of the worksheet contents, so that the processing efficiency of the worksheets is limited to a certain extent. In addition, with the increase of the number of complaints and the continuous development of new demands of new services, the conventional manual processing mode has difficulty in meeting the actual demands of efficient processing of the work orders.
At present, most complaint worksheets are processed mainly by relying on staff to understand the contents of the complaint worksheets, and along with the increase of data and types of the complaint worksheets, the inventor finds that the following problems mainly exist:
Staff needs to review a large number of work orders every day, and meanwhile business accumulation is required to be continuously enriched, so that a large amount of labor cost is occupied;
Because of the deviation of the working manpower in service understanding or working capacity, the condition of wrong handling of the complaint work order is difficult to avoid;
The accumulated large amount of historical complaint worksheet data is a precious resource, and the data is not fully utilized in the traditional worksheet processing flow.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the application provides a processing method, a processing device, electronic equipment and a storage medium of a work order.
In a first aspect, the present application provides a method for processing a work order, including:
determining corpus content of work orders to be distributed;
Inputting the corpus content into a pre-trained text recognition model, and obtaining a recognition result according to the corpus content by the text recognition model;
determining a target processing object for processing the work order to be allocated according to the identification result;
And sending the work order to be distributed to the target processing object.
Optionally, before the corpus content is input into a pre-trained text recognition model, and the recognition model obtains a recognition result according to the corpus content, the method further comprises:
analyzing the corpus content according to a preset rule to obtain an analysis result;
When the target processing object for processing the work order to be distributed is determined to exist according to the analysis result, the work order to be distributed is sent to the target processing object;
or when the processing object of the work order to be distributed is determined to be absent according to the analysis result, inputting the corpus content into a pre-trained text recognition model.
Optionally, the method further comprises:
Acquiring a phrase set obtained by splitting sample corpus content:
determining identification information corresponding to the phrase set;
Training a first preset convolutional neural network model according to the phrase set and the identification information, and learning the relation between the phrase set and the identification information by the first preset convolutional neural network model to obtain the text recognition model.
Optionally, the method further comprises:
Acquiring address information based on the corpus content;
Inputting the address information into a pre-trained address recognition model, and determining a target processing object for processing the work order to be allocated according to the address information by the address recognition model.
Optionally, the address identification model includes: a first sub-model and a second sub-model;
The step of inputting the address information into a pre-trained address recognition model, and determining the target processing object corresponding to the work order to be allocated according to the address information by the address recognition model comprises the following steps:
Inputting the address information into the first sub-model, and converting the address information into word vectors by the first sub-model;
and inputting the word vector into the second sub-model, and determining a target processing object for processing the work order to be distributed by the second sub-model according to the word vector.
Optionally, the method further comprises:
when the corpus content does not carry address information, word segmentation processing is carried out on the corpus content to obtain a first feature vector;
Acquiring a second feature vector corresponding to at least one historical corpus content;
Obtaining semantic similarity based on the first feature vector and the second feature vector;
and executing corresponding processing operation on the work order to be distributed according to the semantic similarity.
Optionally, the executing a corresponding processing operation on the to-be-allocated worksheets according to the semantic similarity includes:
When the semantic similarity is larger than or equal to a preset threshold, taking a processing object corresponding to the history work order with the largest semantic similarity as a target processing object for processing the work order to be allocated;
the work order to be distributed is sent to the target processing object;
Or when the semantic similarity is smaller than a preset threshold, adding the label information to the work order to be distributed, and sending the label information to a designated terminal.
In a second aspect, an apparatus for processing a work order provided by an embodiment of the present application includes:
The first determining module is used for determining the corpus content of the work orders to be distributed;
The processing module is used for inputting the corpus content into a pre-trained text recognition model, and obtaining a recognition result according to the corpus content by virtue of the text recognition model;
the second determining module is used for determining and processing the target processing object of the work order to be distributed according to the identification result;
and the sending module is used for sending the work order to be distributed to the target processing object.
In a third aspect, the present application provides an electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
The memory is used for storing a computer program;
The processor is configured to implement the above-mentioned method steps when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the above-mentioned method steps.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: according to the technical scheme, the text recognition technology in the artificial intelligence technology is utilized to analyze the corpus content of the work orders to be distributed, so that the target processing object for processing the work orders to be distributed is obtained, the complexity of classifying the work orders in a manual mode is effectively solved, manual access is effectively avoided, and the work order processing efficiency is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a flow chart of a method for processing a work order according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a text recognition model according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for processing a work order according to another embodiment of the present application;
FIG. 4 is a flowchart of a method for processing a work order according to another embodiment of the present application;
FIG. 5 is a block diagram of a worksheet processing device according to another embodiment of the present application;
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a method, a device, electronic equipment and a storage medium for processing a work order, and the method provided by the embodiment of the application can be applied to any needed electronic equipment, for example, the electronic equipment can be a server, a terminal and the like, is not particularly limited, and is convenient to describe and is hereinafter referred to as the electronic equipment for short.
The following first describes a method for processing a work order provided by an embodiment of the present invention.
Fig. 1 is a flowchart of a method for processing a work order according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S11, determining corpus content of worksheets to be distributed;
The work sheet referred to in this embodiment is literally understood as a work document. The work order defines a simple maintenance or manufacturing plan consisting of one or more jobs, with the superior department issuing the task and the inferior department receiving the basis of the task. The worksheet may be independent or may be part of a large item.
The to-be-distributed worksheets in the embodiment are complaint worksheets initiated by the client and received by customer service equipment, and the corpus content in the complaint worksheets can be understood as complaint content.
After the corpus content of the work orders to be distributed is determined, the corpus content is analyzed according to a preset rule to obtain an analysis result, when the existence of the target processing object is determined according to the analysis result, the work orders to be distributed are sent to the target processing object, and the target processing object can be a department or terminal equipment for processing the work orders to be distributed.
As an example, when the corpus content of the work order to be allocated and the corpus content of the history work order are repeated, the processing object corresponding to the history work order is directly used as the target processing object, and the work order to be allocated is directly sent to the target processing object, and the subsequent procedure is not executed.
Also for example: and when the corpus content of the worksheet to be allocated is associated with the preset event, directly allocating the worksheet to be allocated to a dedicated department or a host for processing. Preset events such as: work orders that are subject to some external factor that cause temporary closure of the highway.
As another example, when it is determined from the analysis result that the target processing object does not exist, the corpus content is input to a text recognition model trained in advance.
Step S12, inputting corpus content into a pre-trained text recognition model, and obtaining a recognition result according to the corpus content by virtue of the text recognition model;
In this step, the corpus content is input into a text recognition model, the text recognition model splits the corpus content into phrase combinations, and identification information (i.e., recognition results) corresponding to the phrase sets is determined. And then determining the target processing object according to the identification information, wherein the identification information can be a number consisting of numbers, namely the number of the target processing object.
The text recognition model in this embodiment is a short text recognition model, and in the use process, the input dimension of the fixed text recognition model is 200, and if the actual corpus length is greater than 200, the first 100 plus the last 100 are taken as input. If it is less, null character completion is used.
As one example, the set of phrases extracted based on corpus content includes: high new district, tianfu lane, certain medical institution, unestablished, doctor-patient, communication mechanism, etc., the complaint work order belongs to the sanitary log processing terminal, the serial number of the processing terminal: 001. the phrase set extracted based on the corpus content comprises: renting, high and new areas, neutralizing streets, shops, and no handling and handling. The complaint work order belongs to labor and social security processing terminals, and the number of the processing terminals is as follows: 002. the phrase set extracted based on the corpus content comprises: high new area, two street in the house, appearance, traffic jam, the complaint work order belongs to other event processing terminals, the processing terminal number: 003. the phrase set extracted based on the corpus content comprises: wu Houou, fruit-following, resident, disturbing people's action, the work order of should complaining belongs to civil administration processing terminal, and this processing terminal serial number: 004. the phrase set extracted based on the corpus content comprises: high new district, heaven great way, illegal transfer and land use right, the complaint work order belongs to: homeland resource management processing terminal, this processing terminal number: 005. the phrase set extracted based on the corpus content comprises: the large court, construction site, construction material, encroachment and lane, the complaint work order belongs to: urban and rural construction processing terminal, this processing terminal serial number: 006. the phrase set extracted based on the corpus content comprises: consultation, high new district, hot pot shop, and industry. The complaint work order belongs to: an economic management processing terminal, the processing terminal numbering: 007. the phrase set extracted based on the corpus content comprises: registered address, cercis east, travel company, not having qualification proof. The complaint work order belongs to: business travel processing terminal, the processing terminal number: 008. the phrase set extracted based on the corpus content comprises: high and new areas, certain schools, unreasonable and charging phenomena. The complaint work order belongs to an educational literature processing terminal, and the number of the processing terminal is as follows: 009.
The training process of the text recognition model in this embodiment is as follows: the method comprises the steps of obtaining sample corpus content, splitting the sample corpus content to obtain phrase sets, and determining identification information corresponding to the phrase sets, wherein the identification information can be the number of a processing object. And training a first preset convolutional neural network model according to the phrase set and the identification information, and learning the relationship between the phrase set and the identification information by the first preset convolutional neural network model to obtain a text recognition model.
Step S13, determining a target processing object for processing the work order to be allocated according to the identification result;
And step S14, the work order to be distributed is sent to the target processing object.
In the embodiment, the technical scheme analyzes the corpus content of the work orders to be distributed by utilizing a text recognition technology in an artificial intelligence technology, so that a target processing object for processing the work orders to be distributed is obtained, the complexity of classifying the work orders by adopting a manual mode is effectively solved, manual access is effectively avoided, and the work order processing efficiency is improved.
In addition, the emotion index of the corpus content can be obtained by analyzing emotion of the corpus content, and the emergency degree of the work order to be distributed is determined according to the emotion index. Text emotion analysis: also known as opinion mining, tendency analysis, etc. In brief, the process of analyzing, processing, generalizing and reasoning subjective text with emotion colors.
Specifically, a conditional random field model is carried out on each sentence in the language content to mark an analysis object, the word with the largest occurrence number of the whole article is counted as a target analysis object of a work order to be distributed, and then the sentence containing the analysis object is taken as a target sentence. The target sentence is subjected to word segmentation and stop word removal processing, different word segmentation methods can be adopted for different languages, and in the embodiment, a Jieba Chinese word segmentation system is adopted for Chinese to perform word segmentation operation. After the part of speech is obtained, punctuation marks, personification words, exclamation, auxiliary words, conjunctions, prepositions, adverbs, numbers and graduated words in the word segmentation result are removed.
The specific processing flow of taking the sentences containing the analysis objects as target sentences is as follows, and extracting the analysis objects from each sentence in the language content by using a conditional random field;
Firstly, word segmentation is carried out on a worker to be distributed, jieba word segmentation is used for word segmentation operation in the embodiment, and then, marking information of an analysis object is extracted from a word segmentation result by using an IOB (input output) mark as a conditional random field, wherein (1) B EVA (ethylene vinyl acetate) is used for modifying a phrase to start words by the analysis object; (2) EVA, analyzing object modifier phrase internal words; (3) B PRO, analyzing the subject start word; (4) I-PRO, analyzing the subject's internal words; (5) B ATT, analyzing object related attribute start words; (6) I ATT, analyzing the internal words of the related attributes of the object.
And then carrying out semantic analysis on the word segmentation result, and firstly carrying out grammar analysis to obtain a corresponding semantic tree label. And designing a corresponding conditional random field characteristic template according to the word segmentation result, the part of speech and the semantic tree label. B-PRO and I-PRO are the analysis objects of the statement in the marked result.
Counting all words and the occurrence times of the words in the work order to be allocated, wherein the word with the largest occurrence times is a target analysis object of the work order to be allocated, and the sentence containing the word is a target sentence of the work order to be allocated;
Finally, emotion analysis is carried out on the target sentence to obtain an emotion index, specifically, emotion words of the target sentence are traversed, corresponding emotion polarity fractions are recorded according to an emotion dictionary, accumulated and summed to obtain an emotion index, if the emotion index is greater than 0, positive emotion is expressed in the sentence, if the emotion index is less than 0, negative emotion is expressed, and if the emotion index is 0, no obvious emotion is expressed in the sentence.
In this embodiment, when the emotion index is smaller than 0, the score range of the emotion index is determined, and the urgency degree of the work order with allocation is determined according to the score range of the emotion index. According to the method, firstly, a user can be subjected to pacifying operation according to the emergency degree, and meanwhile, when the emergency degree is larger than a preset threshold value, a designated label is added to the work order to be distributed, and the designated label is used for indicating that the work order needs urgent processing.
According to the technical scheme, the emotion strength difference can be effectively distinguished for the work order complaints, and the emergency degree of the work order to be allocated is determined according to the emotion indexes in the work order to be allocated. Through the addition of emotion online calculation and analysis intervention, the method can comprehensively consider the corresponding request party of the work order to be distributed, and can realize emergency treatment on the work order with negative influence. In addition, personalized service can be carried out for the requesting party corresponding to the work order to be allocated through the emotion index of the work order to be allocated, and satisfaction degree of the requesting party corresponding to the work order to be allocated is improved.
Fig. 3 is a flowchart of a method for processing a work order according to an embodiment of the present application. As shown in fig. 3, the method comprises the steps of:
step S31, obtaining address information based on corpus content;
And S32, inputting the address information into a pre-trained address recognition model, and determining a target processing object for processing the work order to be allocated according to the address information by the address recognition model.
The address recognition model in this embodiment includes: a first sub-model and a second sub-model;
Inputting the address information into a pre-trained address recognition model, determining a processing object corresponding to the work order to be allocated by the address recognition model according to the address information, and comprising the following steps: inputting the address information into a first sub-model, and converting the address information into word vectors by the first sub-model; and inputting the word vector into a second sub-model, and determining and processing a target processing object corresponding to the work order to be distributed according to the word vector by the second sub-model.
It should be noted that, the address recognition model adopted in this embodiment is implemented based on bert+bi lstm+crf, where the processing object is obtained by converting address information into word vectors by BERT and then inputting the obtained word vectors into Bi lstm+crf. The address dictionary or entity recognition model is used for extracting address information in corpus content, and the aim is to judge whether an address exists for exclusive processing object processing if the address exists, and if the address exists, the address is directly distributed to the processing object processing.
The address model in this embodiment is trained in the following manner, a sample word vector is obtained, and tag information corresponding to the sample word vector is determined, where the tag information may be a processing object corresponding to the word vector. And inputting the sample word vector into a second preset convolutional neural network model, and learning the relation between the word vector and the label information by the second preset convolutional neural network model to obtain an address recognition model.
Fig. 4 is a flowchart of a method for processing a work order according to an embodiment of the present application. As shown in fig. 4, the method comprises the steps of:
step S41, when the corpus content does not carry address information, word segmentation processing is carried out on the corpus content to obtain a first feature vector;
In this step, a jieba word segmentation tool may be used to analyze the corpus content to obtain a plurality of phrases, and vectorize the plurality of phrases to obtain a first feature vector.
Step S42, obtaining a second feature vector corresponding to at least one historical corpus content;
step S43, obtaining semantic similarity based on the first feature vector and the second feature vector;
Optionally, the second feature vector may be stored in a cloud server, and when the semantic similarity is calculated, the second feature vector may be directly obtained from the cloud server, where the second feature vector is obtained by word segmentation on the historical corpus content of the historical worksheet and vectorization.
And constructing a first feature matrix of the corpus content according to the first feature vector, and constructing a second feature matrix of the historical corpus content according to the second feature vector. And obtaining the semantic similarity of the work orders to be distributed and the historical work orders according to the first feature matrix and the second feature matrix.
And S44, executing corresponding processing operation on the work order to be distributed according to the semantic similarity.
In an embodiment, executing corresponding processing operations on the work order to be allocated according to the semantic similarity includes: when the semantic similarity is larger than or equal to a preset threshold, taking a processing object corresponding to a history work order with the largest semantic similarity as a target processing object, and sending a work order to be distributed to the target processing object; or when the semantic similarity is smaller than a preset threshold, adding the label information to the work order to be distributed, and sending the label information to the appointed terminal.
In the step, when the target processing object of the to-be-allocated work order is not determined in the text recognition model and the address recognition model, similarity calculation can be performed by adopting the historical corpus content and the corpus content of the to-be-allocated work order, the historical work order with the highest similarity with the to-be-allocated work order is determined from the historical record, and then the processing object of the historical work order with the highest similarity is taken as the target processing object of the to-be-allocated work order
The processing method of the work order provided by the other embodiment of the application comprises the following steps:
step S51, determining corpus content of worksheets to be distributed;
Step S52, when the corpus content is matched with a preset rule, determining a target processing object for processing the work order to be distributed, and executing step S60;
Step S53, when the corpus content is not matched with the preset rule, executing step S54;
Step S54, inputting corpus content into a pre-trained text recognition model to obtain a recognition result;
step S56, when it is determined that the target processing object for processing the work order to be allocated exists according to the recognition result, step S60 is executed, and when it is determined that the target processing object for processing the work order to be allocated does not exist according to the recognition result, step S57 is executed;
Step S57, analyzing the corpus content, inputting the address information into a pre-trained address recognition model when the corpus content carries the address information, determining and processing a target processing object corresponding to the work order to be allocated according to the address information by the address recognition model, and executing step S60;
Step S58, when the corpus content does not carry address information, word segmentation processing is carried out on the corpus content to obtain a first feature vector, a second feature vector corresponding to at least one historical corpus content is obtained, and semantic similarity is obtained based on the first feature vector and the second feature vector;
Step S59, when the semantic similarity is greater than or equal to a preset threshold, taking the processing object corresponding to the history work order with the maximum semantic similarity as a target processing object, and executing step S60; and when the semantic similarity is smaller than a preset threshold, adding marking information to the work order to be distributed, and sending the marking information to the appointed terminal.
Step S60, the work order to be distributed is sent to the target processing object.
In this embodiment, the whole process flow of the present step may be regulated according to specific requirements, and the whole process flow may be selectively executed according to project requirements, or a part of the operation steps may be selectively executed.
Fig. 5 is a block diagram of a processing apparatus for a work order according to an embodiment of the present application, where the apparatus may be implemented as part or all of an electronic device by software, hardware, or a combination of both. As shown in fig. 5, the apparatus includes:
A first determining module 61, configured to determine corpus content of work orders to be allocated;
The processing module 62 is configured to input the corpus content into a pre-trained text recognition model, where the text recognition model obtains a recognition result according to the corpus content;
a second determining module 63, configured to determine a target processing object for processing the work order to be allocated according to the identification result;
And a sending module 64, configured to send the work order to be allocated to a target processing object.
The embodiment of the application also provides an electronic device, as shown in fig. 6, the electronic device may include: the device comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 are in communication with each other through the communication bus 1504.
A memory 1503 for storing a computer program;
the processor 1501, when executing the computer program stored in the memory 1503, implements the steps of the above embodiments.
The communication bus mentioned above for the electronic device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, pi) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a Digital signal processor (Digital SignalProcessing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the above embodiments.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
It should be noted that, with respect to the apparatus, electronic device, and computer-readable storage medium embodiments described above, since they are substantially similar to the method embodiments, the description is relatively simple, and reference should be made to the description of the method embodiments for relevant points.
It is further noted that relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for processing a work order, comprising:
determining corpus content of work orders to be distributed;
Inputting the corpus content into a pre-trained text recognition model, and obtaining a recognition result by the text recognition model according to the corpus content;
determining a target processing object for processing the work order to be allocated according to the identification result;
the work order to be distributed is sent to the target processing object;
Before the corpus content is input into a pre-trained text recognition model, and a recognition result is obtained by the recognition model according to the corpus content, the method further comprises:
Analyzing the corpus content according to a preset rule to obtain an analysis result; the preset rule is used for determining whether the corpus content contains address information, if so, the target processing object representing the work order to be distributed exists, and if not, the target processing object representing the work order to be distributed does not exist;
When the target processing object for processing the work order to be distributed is determined to exist according to the analysis result, the work order to be distributed is sent to the target processing object;
or when the processing object of the work order to be distributed is determined to be absent according to the analysis result, inputting the corpus content into a pre-trained text recognition model;
wherein the method further comprises:
when the corpus content does not carry address information, word segmentation processing is carried out on the corpus content to obtain a first feature vector;
Acquiring a second feature vector corresponding to at least one historical corpus content;
Obtaining semantic similarity based on the first feature vector and the second feature vector;
and executing corresponding processing operation on the work order to be distributed according to the semantic similarity.
2. The method according to claim 1, wherein the method further comprises:
Acquiring a phrase set obtained by splitting sample corpus content:
determining identification information corresponding to the phrase set;
Training a first preset convolutional neural network model according to the phrase set and the identification information, and learning the relation between the phrase set and the identification information by the first preset convolutional neural network model to obtain the text recognition model.
3. The method according to claim 1, wherein the method further comprises:
Acquiring address information based on the corpus content;
Inputting the address information into a pre-trained address recognition model, and determining a target processing object for processing the work order to be allocated according to the address information by the address recognition model.
4. A method according to claim 3, wherein the address identification model comprises: a first sub-model and a second sub-model;
The step of inputting the address information into a pre-trained address recognition model, and determining the target processing object corresponding to the work order to be allocated according to the address information by the address recognition model comprises the following steps:
Inputting the address information into the first sub-model, and converting the address information into word vectors by the first sub-model;
and inputting the word vector into the second sub-model, and determining a target processing object for processing the work order to be distributed by the second sub-model according to the word vector.
5. The method according to claim 1, wherein said performing a corresponding processing operation on said work order to be distributed according to said semantic similarity comprises:
When the semantic similarity is larger than or equal to a preset threshold, taking a processing object corresponding to the history work order with the largest semantic similarity as a target processing object for processing the work order to be allocated;
the work order to be distributed is sent to the target processing object;
Or when the semantic similarity is smaller than a preset threshold, adding the label information to the work order to be distributed, and sending the label information to a designated terminal.
6. A worksheet processing device, comprising:
The first determining module is used for determining the corpus content of the work orders to be distributed;
The processing module is used for inputting the corpus content into a pre-trained text recognition model, and obtaining a recognition result according to the corpus content by the text recognition model; before the corpus content is input into a pre-trained text recognition model, and a recognition result is obtained by the recognition model according to the corpus content, the processing module is further used for analyzing the corpus content according to a preset rule to obtain an analysis result; the preset rule is used for determining whether the corpus content contains address information, if so, the target processing object representing the work order to be distributed exists, and if not, the target processing object representing the work order to be distributed does not exist; when the target processing object for processing the work order to be distributed is determined to exist according to the analysis result, the work order to be distributed is sent to the target processing object; or when the processing object of the work order to be distributed is determined to be absent according to the analysis result, inputting the corpus content into a pre-trained text recognition model; the processing module is further used for performing word segmentation processing on the corpus content to obtain a first feature vector when the corpus content does not carry address information; acquiring a second feature vector corresponding to at least one historical corpus content; obtaining semantic similarity based on the first feature vector and the second feature vector; executing corresponding processing operation on the work order to be distributed according to the semantic similarity;
the second determining module is used for determining and processing the target processing object of the work order to be distributed according to the identification result;
and the sending module is used for sending the work order to be distributed to the target processing object.
7. An electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
The memory is used for storing a computer program;
the processor being adapted to carry out the method steps of any one of claims 1-5 when the computer program is executed.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the method steps of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506232.XA CN111782803B (en) | 2020-06-05 | 2020-06-05 | Work order processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506232.XA CN111782803B (en) | 2020-06-05 | 2020-06-05 | Work order processing method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111782803A CN111782803A (en) | 2020-10-16 |
| CN111782803B true CN111782803B (en) | 2024-06-18 |
Family
ID=72754652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506232.XA Active CN111782803B (en) | 2020-06-05 | 2020-06-05 | Work order processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111782803B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988045B (en) * | 2021-12-28 | 2022-04-12 | 浙江口碑网络技术有限公司 | Text similarity determining method, text processing method, corresponding device and equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN110458296A (en) * | 2019-08-02 | 2019-11-15 | 腾讯科技（深圳）有限公司 | The labeling method and device of object event, storage medium and electronic device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3571408B2 (en) * | 1995-03-31 | 2004-09-29 | 株式会社日立製作所 | Document processing method and apparatus |
| CA2883029C (en) * | 2015-02-26 | 2024-04-30 | Kevin Johnston | Method and system for securely updating a website |
| CN108804512B (en) * | 2018-04-20 | 2020-11-24 | 平安科技（深圳）有限公司 | Text classification model generation device and method and computer readable storage medium |
| CN108717406B (en) * | 2018-05-10 | 2021-08-24 | 平安科技（深圳）有限公司 | Text emotion analysis method and device and storage medium |
| CN110750983A (en) * | 2019-10-18 | 2020-02-04 | 深圳前海微众银行股份有限公司 | Corpus identification method, apparatus, device and computer readable storage medium |
-
2020
- 2020-06-05 CN CN202010506232.XA patent/CN111782803B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN110458296A (en) * | 2019-08-02 | 2019-11-15 | 腾讯科技（深圳）有限公司 | The labeling method and device of object event, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111782803A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3144822A1 (en) | Tagging text snippets | |
| CN111428480B (en) | Resume identification method, device, equipment and storage medium | |
| CN112100398B (en) | Patent blank prediction method and system | |
| CN107102993A (en) | A kind of user's demand analysis method and device | |
| CN110851576A (en) | Question and answer processing method, device, equipment and readable medium | |
| CN112036842A (en) | Intelligent matching platform for scientific and technological services | |
| CN114860882A (en) | Fair competition review auxiliary method based on text classification model | |
| CN111859969A (en) | Data analysis method and device, electronic equipment and storage medium | |
| Kim | Analysis of standard vocabulary use of the open government data: the case of the public data portal of Korea | |
| RU2718978C1 (en) | Automated legal advice system control method | |
| CN116542800A (en) | Intelligent financial statement analysis system based on cloud AI technology | |
| CN116775879A (en) | Fine tuning training method of large language model, contract risk review method and system | |
| CN111651994A (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN113590846B (en) | Legal knowledge map construction method and related equipment | |
| CN111782803B (en) | Work order processing method and device, electronic equipment and storage medium | |
| CN113553431B (en) | User tag extraction method, device, equipment and medium | |
| CN114186040A (en) | Operation method of intelligent robot customer service | |
| CN117172508B (en) | Automatic dispatch method and system based on city complaint worksheet recognition | |
| CN114186041A (en) | Answer output method | |
| CN113724057A (en) | Financial budget filling method, system, equipment and medium based on big data | |
| CN117892120A (en) | Method and device for checking vertical model, electronic equipment and readable storage medium | |
| CN116432965B (en) | Post capability analysis method and tree diagram generation method based on knowledge graph | |
| CN112036841A (en) | Policy analysis system and method based on intelligent semantic recognition | |
| CN111145053A (en) | Enterprise law consultant management system and method based on artificial intelligence | |
| EP2605150A1 (en) | Method for identifying the named entity that corresponds to an owner of a web page |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Technology Holding Co.,Ltd. Address before: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: Jingdong Digital Technology Holding Co.,Ltd. Address after: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Digital Technology Holding Co.,Ltd. Address before: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |