CN112463959A - Service processing method based on uplink short message and related equipment - Google Patents
Service processing method based on uplink short message and related equipment Download PDFInfo
- Publication number
- CN112463959A CN112463959A CN202011182917.XA CN202011182917A CN112463959A CN 112463959 A CN112463959 A CN 112463959A CN 202011182917 A CN202011182917 A CN 202011182917A CN 112463959 A CN112463959 A CN 112463959A
- Authority
- CN
- China
- Prior art keywords
- short message
- client
- short messages
- historical
- word
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 41
- 239000013598 vector Substances 0.000 claims abstract description 37
- 238000013145 classification model Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 238000002372 labelling Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000010801 machine learning Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 claims description 2
- 230000008451 emotion Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000007637 random forest analysis Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
One or more embodiments of the present specification provide a service processing method and related device based on an uplink short message; the method comprises the following steps: extracting historical short messages from a business database, and marking the historical short messages as at least one marking category; extracting the characteristics of the contents of the historical short messages by a word segmentation method, constructing word vectors of words, further constructing sentence vectors, and obtaining the digital characteristics of the contents of the historical short messages; combining the digital features and the labeling categories to obtain a training set; training the training set data by using a machine learning algorithm to construct a client short message classification model; extracting the client short messages which are not classified currently, and inputting the client short message classification model for classification to obtain a classification result; and processing the short message of the customer according to the classification result. The method can realize the recognition of the emotion of the client, improve the recognition accuracy and save the operation cost.
Description
Technical Field
The present invention relates to the technical field of customer service, and in particular, to a service processing method based on an uplink short message and a related device.
Background
Classification is a subject of research in the field of information retrieval for many years, and on one hand, the effectiveness and efficiency under certain conditions are improved by taking the application of search as an objective; on the other hand, classification is also a classical machine learning technique. In the field of machine learning, classification is performed under a labeled predefined class system, and therefore belongs to a supervised learning problem; clustering, in contrast, is an unsupervised learning problem.
The existing method utilizes a rule matching method to classify the customer uplink short messages through a Structured Query Language (SQL), for example, if the short messages contain 'wrong' keywords, the short messages are classified into 'suspected error pieces'. The existing method has the advantages that the keyword is accurately identified, but the emotion of a client cannot be identified, so that the customer service staff cannot conveniently perform differentiated services on the client, when the number of clients of a company is large, the short message amount is large, the content of the short message is identified manually, the work is heavy, and the cost is high.
Based on this, a service processing method capable of recognizing the emotion of the client, improving the recognition accuracy and saving the operation cost is needed.
The invention contents,
In view of the above, one or more embodiments of the present disclosure are directed to a method for processing a service based on an uplink short message and a related device.
Based on the above purpose, one or more embodiments of the present specification provide a service processing method based on an uplink short message, including:
extracting historical short messages from a business database, and marking the historical short messages as at least one marking category;
extracting the characteristics of the contents of the historical short messages by a word segmentation method, constructing word vectors of words, further constructing sentence vectors, and obtaining the digital characteristics of the contents of the historical short messages;
combining the digital features and the labeling categories to obtain a training set;
training the training set data by using a machine learning algorithm to construct a client short message classification model;
extracting the client short messages which are not classified currently, and inputting the client short message classification model for classification to obtain a classification result;
and processing the short message of the customer according to the classification result.
Based on the same inventive concept, one or more embodiments of the present specification further provide a service processing apparatus based on an uplink short message, including:
a labeling category module: configured to extract historical short messages from a service database and label the historical short messages as at least one labeling category;
a digital feature module: the system is configured to perform feature extraction on the content of the historical short message by a word segmentation method, construct word vectors of words and phrases, further construct sentence vectors and obtain digital features of the content of the historical short message;
combining the modules: configured to combine the digital features with the annotation classes, resulting in a training set;
a model construction module: the short message classification method comprises the steps of training the training set data by using a machine learning algorithm to construct a client short message classification model;
a short message classification module: the short message classification module is configured to extract the client short messages which are not classified currently, and input the client short message classification module for classification to obtain a classification result;
the short message processing module: and the short message processing device is configured to process the customer short message according to the classification result.
Based on the same inventive concept, one or more embodiments of the present specification further provide an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the method as described in any one of the above items when executing the program.
Based on the same inventive concept, one or more embodiments of the present specification also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method as described in any one of the above.
As can be seen from the above, in the service processing method based on the uplink short message provided in one or more embodiments of the present specification, the historical short message is divided into at least one labeled category, the client short message classification model is established to classify the client short message that is not classified currently, and corresponding processing is performed according to different classification results, so that the client emotion can be effectively identified, the accuracy of short message content identification is greatly improved, and meanwhile, the labor cost of operation is saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a service processing method based on an uplink short message according to one or more embodiments of the present disclosure;
fig. 2 is a schematic structural diagram of a service processing apparatus based on an uplink short message according to one or more embodiments of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to one or more embodiments of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
As described above, the existing method classifies the uplink short messages of the client through the structured query language SQL, and although the keywords are accurately identified, the emotion of the client cannot be identified, for example, although the short message of the client contains the "wrong" word, the meaning expressed in the content of the short message of the client is not the wrong short message, so the accuracy of the method is low; when the number of the short messages is large, the in-doubt short messages are identified manually, and the operation cost is high.
In view of this, one or more embodiments of the present disclosure provide a service processing method and related device based on an uplink short message.
Referring to fig. 1, a flowchart of a service processing method based on an uplink short message according to one or more embodiments of the present invention is shown.
The uplink short message is a short message sent to a communication service provider and is used for customizing a certain service, completing a certain query or handling a certain service.
The service processing method based on the uplink short message comprises the following steps:
step S101: extracting historical short messages from a business database, and manually marking at least one marking category of the historical short messages.
In an embodiment of the present specification, the labeling categories may include five categories, specifically including: suspected error pieces, suspected complaints pieces, no actual content information, formatted replies, and consultancy pieces.
Step S102: and performing feature extraction on the content of the historical short message by a word segmentation method, constructing word vectors of words, further constructing sentence vectors, and obtaining the digital features of the content of the historical short message.
In this step, the characteristics include words of the sentences in the historical short messages after word segmentation, and if the contents of the historical short messages are sentences, the sentences need to be segmented. Specifically, in some embodiments of the present specification, a jieba word segmentation tool may be selected to perform word segmentation, the jieba word segmentation tool implements efficient word graph scanning based on a prefix dictionary, generates a Directed Acyclic Graph (DAG) formed by all possible word-forming conditions of the chinese characters in a sentence, finds a large probability path by using dynamic programming, finds a large segmentation combination based on word frequency, and for unknown words, uses a Hidden Markov Model (HMM) based on word-forming capability of the chinese characters, and uses a Viterbi (Viterbi) algorithm to perform solution.
During feature extraction, stop words without practical meaning, such as stop words like's', etc., can be removed by using a jieba tool according to the part-of-speech labels, or a stop word list is constructed and maintained, and stop words in the list are removed.
And digitalizing the word characteristics after the word processing by constructing a word frequency-inverse text frequency index (TF-IDF) matrix to obtain the digitalized characteristics of the contents of the historical short messages.
Further, word vectors can be constructed by using a word2vec method, sentence vectors are constructed through the word vectors, and the word vectors and the sentence vectors are used as digital features of model training. The word2vec model is a simplified neural network. The input is a heat Vector (One-Hot Vector), and the Hidden Layer (Hidden Layer) has no activation function, i.e. linear unit. The dimension of the Output Layer (Output Layer) is the same as that of the Input Layer (Input Layer), and a Softmax logistic regression model is applied. After the model is trained, the weight matrix of the hidden layer is obtained to be used as a word vector of a word. Training this model is divided into two models, the continuous bag of words model (CBOW) and the Skip-Gram model (Skip-Gram). The training of the CBOW model inputs the context of a word and the output is the word. The Skip-Gram model is that the input is a word and the output is a context word vector corresponding to the word. After the model is trained by the two methods, the weight matrix of the hidden layer is obtained as a word vector of the word. The word vectors of a sentence are extracted and then summed up to be averaged or spliced in sequence to construct a sentence vector, which can be used as the digital characteristic of the sentence.
Step S103: and combining the digital features and the labeling categories to obtain a training set.
In this step, the digital features of the converted contents of the historical short messages are used to form a feature matrix, the manually labeled categories are used as training target columns, and the feature matrix and the target columns are used to form a training data matrix, so as to determine the training set.
In other embodiments of the present disclosure, the training data matrix may be further divided into a training set and a test set according to a preset ratio. For example, the preset ratio is 4: 1, i.e. 80% of the data is used for training and 20% of the data is used for comparing and verifying the correctness of model prediction.
Step S104: and training the training set data by using a machine learning algorithm to construct a client short message classification model.
In the embodiment of the present specification, the machine learning algorithm may be a random forest algorithm, where the random forest is a classifier including a plurality of decision trees, and the output class of the random forest is determined by the mode of the class output by the individual trees. Each decision tree is a classifier (assuming the classification problem is now addressed), then for an input sample, N trees will have N classification results. And the random forest integrates all classification voting results, and the classification with the largest voting times is designated as final output.
This step is followed by: and evaluating the effect of the customer short message classification model according to the data of the test set, adjusting parameters of the customer short message classification model and adjusting a word vector extraction method, and optimizing the model.
And adjusting the parameters of the client short message classification model, automatically searching parameters by using a Bayesian parameter adjusting method, setting parameters to be searched and assignment ranges thereof, parameter searching targets and the number of rounds to be iterated, and automatically searching a group of parameter values meeting the parameter searching targets in the appointed number of rounds of iteration by using a machine.
The method for extracting the word vectors is changed into the method for extracting the word vectors by utilizing a dynamic word vector ELMo model.
The ELMo model is used for training to obtain word vectors, and the ELMo model can train the same word to obtain different word vectors through different sentences, so that different meanings of the same word under different contexts can be effectively distinguished (for example, an apple can represent an apple, and an iphone can also represent an iphone). The method is essentially characterized in that Word Embedding (Word Embedding) of a Word is learned by a language model, when the method is used, the Word has a specific context, and the Word Embedding of the Word is adjusted according to the semantics of the context, so that the adjusted Word Embedding can express the specific meaning in the context, the Word ambiguity problem is solved, and the ELMO essence is the process of dynamically adjusting the Word Embedding according to the current context.
Step S105: and extracting the client short messages which are not classified currently, and inputting the client short message classification model for classification to obtain a classification result.
Step S106: and processing the short message of the customer according to the classification result.
In this step, for suspected error pieces, suspected complaints and formatted reply short messages, system work orders can be generated according to different labeling types and delivered to customer service personnel for processing such as security, comfort and the like; and for the consultation member, manually sending a short message to the client to guide the client to carry out self-service treatment by using company APP and other modes.
Therefore, in this embodiment, a client short message classification model is constructed according to the historical short messages, the client short messages which are not classified at present can be input into the client short message classification model for classification, and the client short messages are processed according to the classification result. According to the method, the intention of the customer can be accurately identified by using the data value of the historical short message, the customer is differentially served, the manual workload is reduced, the user experience is improved, and the operation cost is saved.
In other embodiments of the present disclosure, the method may further include: and manually rechecking the classified short messages, and training the client short message classification model by using the classification result of the client short messages determined after rechecking. That is, the rechecked data is used for the iteration of the client short message classification model, so that the accuracy of the client short message classification model is further optimized.
It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, one or more embodiments of the present specification further provide a service processing apparatus based on the uplink short message.
Referring to fig. 2, the service processing apparatus based on the uplink short message includes:
a labeling category module: the system comprises a service database, a database server and a database server, wherein the service database is configured to extract historical short messages from the service database, and manually mark the historical short messages into five marking categories of a suspected error element, a suspected complaint element, no actual content information, formatted reply and a consultation element;
a digital feature determination module: the system is configured to perform feature extraction on the content of the historical short message by a word segmentation method, construct word vectors of words and phrases, further construct sentence vectors and obtain digital features of the content of the historical short message;
a test set and training set dividing module: configured to combine the digital features with label categories and partition a test set and a training set;
constructing a model module: the short message classification method comprises the steps of training the training set data by using a machine learning algorithm to construct a client short message classification model;
a short message classification module: the short message classification module is configured to extract the client short messages which are not classified currently, and input the client short message classification module for classification to obtain a classification result;
a customer service module: the method is configured to manually recheck the short messages of the five labeling categories, use the rechecked data in model iteration and perform customer service on customers according to the content of the short messages.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, one or more embodiments of the present specification further provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the service processing method based on the uplink short message according to any one of the embodiments.
Fig. 3 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A business processing method based on uplink short messages is applied to insurance industry and is characterized by comprising the following steps:
extracting historical short messages from a business database, and marking the historical short messages as at least one marking category;
extracting the characteristics of the contents of the historical short messages by a word segmentation method, constructing word vectors of words, further constructing sentence vectors, and obtaining the digital characteristics of the contents of the historical short messages;
combining the digital features and the labeling categories to obtain a training set;
training the training set data by using a machine learning algorithm to construct a client short message classification model;
extracting the client short messages which are not classified currently, and inputting the client short message classification model for classification to obtain a classification result;
and processing the short message of the customer according to the classification result.
2. The method of claim 1, wherein the extracting the features of the content of the history short message by a word segmentation method comprises:
the characteristics comprise words of the sentences in the short messages after word segmentation processing, and words without practical meanings are removed according to part-of-speech labels or stop words in the table are removed by constructing a stop word table.
3. The method of claim 1, wherein combining the digital features with label categories to obtain a training set comprises:
and forming a feature matrix by using the digital features of the converted contents of the historical short messages, taking the at least one labeled category as a training target column, and forming a training data matrix by using the feature matrix and the target column to obtain the training set.
4. The method of claim 3, wherein the training set data to construct a client short message classification model by using a machine learning algorithm further comprises:
dividing the training data matrix into the training set and the test set according to a set proportion;
and evaluating the effect of the customer short message classification model according to the data of the test set, adjusting parameters of the customer short message classification model and adjusting a word vector extraction method, and optimizing the model.
5. The method of claim 4, wherein the adjusting the customer short message classification model parameters and adjusting the word vector extraction method comprises:
adjusting the parameters of the client short message classification model, automatically searching parameters by using a Bayesian parameter adjusting method, setting parameters to be searched and assignment ranges thereof, parameter searching targets and the number of rounds to be iterated, and automatically searching a group of parameter values meeting the parameter searching targets in the appointed number of rounds of iteration by a machine;
the method for extracting the word vector is changed into a dynamic word vector ELMo model to extract the word vector.
6. The method of claim 1, further comprising:
manually rechecking the classified customer short messages;
and training the client short message classification model by using the classification result of the client short message determined after rechecking.
7. A service processing device based on uplink short message is characterized by comprising:
a labeling category module: configured to extract historical short messages from a service database and label the historical short messages as at least one labeling category;
a digital feature module: the system is configured to perform feature extraction on the content of the historical short message by a word segmentation method, construct word vectors of words and phrases, further construct sentence vectors and obtain digital features of the content of the historical short message;
combining the modules: configured to combine the digital features with the annotation classes, resulting in a training set;
a model construction module: the short message classification method comprises the steps of training the training set data by using a machine learning algorithm to construct a client short message classification model;
a short message classification module: the short message classification module is configured to extract the client short messages which are not classified currently, and input the client short message classification module for classification to obtain a classification result;
the short message processing module: and the short message processing device is configured to process the customer short message according to the classification result.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 6 when executing the program.
9. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011182917.XA CN112463959A (en) | 2020-10-29 | 2020-10-29 | Service processing method based on uplink short message and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011182917.XA CN112463959A (en) | 2020-10-29 | 2020-10-29 | Service processing method based on uplink short message and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112463959A true CN112463959A (en) | 2021-03-09 |
Family
ID=74835146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011182917.XA Pending CN112463959A (en) | 2020-10-29 | 2020-10-29 | Service processing method based on uplink short message and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112463959A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357837A (en) * | 2017-06-22 | 2017-11-17 | 华南师范大学 | The electric business excavated based on order-preserving submatrix and Frequent episodes comments on sensibility classification method |
| US20190188277A1 (en) * | 2017-12-18 | 2019-06-20 | Fortia Financial Solutions | Method and device for processing an electronic document |
| CN110442823A (en) * | 2019-08-06 | 2019-11-12 | 北京智游网安科技有限公司 | Website classification method, Type of website judgment method, storage medium and intelligent terminal |
| WO2020019686A1 (en) * | 2018-07-27 | 2020-01-30 | 众安信息技术服务有限公司 | Session interaction method and apparatus |
| CN110781276A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Text extraction method, device, equipment and storage medium |
| CN110825845A (en) * | 2019-10-23 | 2020-02-21 | 中南大学 | Hierarchical text classification method based on character and self-attention mechanism and Chinese text classification method |
| AU2020100710A4 (en) * | 2020-05-05 | 2020-06-11 | Chen, Dadu Mr | A method for sentiment analysis of film reviews based on deep learning and natural language processing |
| CN111447574A (en) * | 2018-12-27 | 2020-07-24 | 中国移动通信集团辽宁有限公司 | Short message classification method, device, system and storage medium |
| CN111581386A (en) * | 2020-05-08 | 2020-08-25 | 深圳市第五空间网络科技有限公司 | Construction method, device, equipment and medium of multi-output text classification model |
| CN111767741A (en) * | 2020-06-30 | 2020-10-13 | 福建农林大学 | Text emotion analysis method based on deep learning and TFIDF algorithm |
-
2020
- 2020-10-29 CN CN202011182917.XA patent/CN112463959A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357837A (en) * | 2017-06-22 | 2017-11-17 | 华南师范大学 | The electric business excavated based on order-preserving submatrix and Frequent episodes comments on sensibility classification method |
| US20190188277A1 (en) * | 2017-12-18 | 2019-06-20 | Fortia Financial Solutions | Method and device for processing an electronic document |
| WO2020019686A1 (en) * | 2018-07-27 | 2020-01-30 | 众安信息技术服务有限公司 | Session interaction method and apparatus |
| CN111447574A (en) * | 2018-12-27 | 2020-07-24 | 中国移动通信集团辽宁有限公司 | Short message classification method, device, system and storage medium |
| CN110442823A (en) * | 2019-08-06 | 2019-11-12 | 北京智游网安科技有限公司 | Website classification method, Type of website judgment method, storage medium and intelligent terminal |
| CN110781276A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Text extraction method, device, equipment and storage medium |
| CN110825845A (en) * | 2019-10-23 | 2020-02-21 | 中南大学 | Hierarchical text classification method based on character and self-attention mechanism and Chinese text classification method |
| AU2020100710A4 (en) * | 2020-05-05 | 2020-06-11 | Chen, Dadu Mr | A method for sentiment analysis of film reviews based on deep learning and natural language processing |
| CN111581386A (en) * | 2020-05-08 | 2020-08-25 | 深圳市第五空间网络科技有限公司 | Construction method, device, equipment and medium of multi-output text classification model |
| CN111767741A (en) * | 2020-06-30 | 2020-10-13 | 福建农林大学 | Text emotion analysis method based on deep learning and TFIDF algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 杜思佳等: "基于深度学习的文本分类研究进展", 网络与信息安全学报, pages 1 - 13 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363790B (en) | Method, device, equipment and storage medium for evaluating comments | |
| KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
| CN107436875B (en) | Text classification method and device | |
| CN110781276A (en) | Text extraction method, device, equipment and storage medium | |
| CN110705286A (en) | Comment information-based data processing method and device | |
| CN112632226B (en) | Semantic search method and device based on legal knowledge graph and electronic equipment | |
| CN104834651B (en) | Method and device for providing high-frequency question answers | |
| US11741094B2 (en) | Method and system for identifying core product terms | |
| CN107291840B (en) | User attribute prediction model construction method and device | |
| CN110827797B (en) | Voice response event classification processing method and device | |
| CN113515629A (en) | Document classification method and device, computer equipment and storage medium | |
| CN111753082A (en) | Text classification method and device based on comment data, equipment and medium | |
| CN111274371B (en) | Intelligent man-machine conversation method and equipment based on knowledge graph | |
| CN114357117A (en) | Transaction information query method and device, computer equipment and storage medium | |
| CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
| CN117608650B (en) | Business flow chart generation method, processing device and storage medium | |
| CN104778283A (en) | User occupation classification method and system based on microblog | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN110795942B (en) | Keyword determination method and device based on semantic recognition and storage medium | |
| CN113392920B (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN114722198A (en) | Method, system and related device for determining product classification code | |
| US20210117448A1 (en) | Iterative sampling based dataset clustering | |
| CN111198949A (en) | Text label determination method and system | |
| CN116048463A (en) | Intelligent recommendation method and device for content of demand item based on label management | |
| CN115309995A (en) | Scientific and technological resource pushing method and device based on demand text |
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 |