CN114219337A - Service quality evaluation method, system, equipment and readable storage medium - Google Patents
Service quality evaluation method, system, equipment and readable storage medium Download PDFInfo
- Publication number
- CN114219337A CN114219337A CN202111574531.8A CN202111574531A CN114219337A CN 114219337 A CN114219337 A CN 114219337A CN 202111574531 A CN202111574531 A CN 202111574531A CN 114219337 A CN114219337 A CN 114219337A
- Authority
- CN
- China
- Prior art keywords
- text
- text data
- emotion
- service quality
- normalized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Finance (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the invention discloses a method, a system, equipment and a readable storage medium for evaluating service quality, wherein the method comprises the following steps: acquiring a target evaluation text of a client; carrying out standardization processing on the target evaluation text to obtain a standardized text; performing word segmentation processing on the normalized text to obtain word segmentation text data; carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data; performing emotion score calculation on the labeled text data based on a preset emotion dictionary to obtain an emotion value of each clause in the labeled text data; and carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score. According to the method and the device, sentence level feelings in the target evaluation text are captured, the evaluation text data of the client is quantized according to the syntax structure, the accuracy of service quality evaluation is improved, and the technical effect of providing effective basis for improving the service quality is achieved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method, a system and equipment for evaluating service quality and a readable storage medium.
Background
The existing bank outlets service quality evaluation is mainly carried out by collecting data adjectives or evaluating the star level and the satisfaction degree of customers. For the evaluation modes of the star rating and the satisfaction degree of the customer, the network provides some service evaluation options for the user to select, such as very satisfied, basically satisfied, unsatisfied and the like, and the network sets different weights for different adjectives or satisfaction degrees during data analysis so as to calculate the overall service quality evaluation.
However, this solution can only provide a rough service quality estimation for the manager and whether there is a space for improving the service quality, and cannot really find the problem of the service quality, and further cannot take a service quality improvement measure in a targeted manner.
Disclosure of Invention
Embodiments of the present invention provide a method, a system, a device and a readable storage medium for evaluating service quality, which solve the technical problems that in the prior art, service quality evaluation can only depend on rough evaluation modes such as "star level", "satisfaction", and the like, which can not really find the problem of service quality and can not improve the service quality in a targeted manner.
In a first aspect, an embodiment of the present invention provides a method for evaluating service quality, where the method for evaluating service quality includes:
acquiring a target evaluation text of a client;
carrying out standardization processing on the target evaluation text to obtain a standardized text;
performing word segmentation processing on the normalized text to obtain word segmentation text data;
carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data;
calculating emotion scores of the marked text data based on a preset emotion dictionary to obtain an emotion value of each clause in the marked text data;
and carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score.
In a second aspect, an embodiment of the present invention further provides a service quality evaluation system, where the service quality evaluation system includes:
the natural language collection module is used for acquiring a target evaluation text of a client;
the natural language processing module is used for carrying out normalized processing on the target evaluation text to obtain a normalized text and carrying out word segmentation processing on the normalized text to obtain word segmentation text data; the system is also used for carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data;
and the natural language analysis module is used for calculating the emotion score of the labeled text data based on a preset emotion dictionary to obtain the emotion value of each clause in the labeled text data, and calculating the weighted average of the emotion values of the clauses to obtain the service quality evaluation score.
In a third aspect, an embodiment of the present invention further provides a device for evaluating service quality, where the device for evaluating service quality includes:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors may implement the method for evaluating quality of service according to any of the first aspect of the embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for evaluating quality of service according to any of the first aspect of the embodiments of the present invention.
The embodiment of the invention discloses a method, a system, equipment and a readable storage medium for evaluating service quality, wherein the method comprises the following steps: acquiring a target evaluation text of a client; carrying out standardization processing on the target evaluation text to obtain a standardized text; performing word segmentation processing on the normalized text to obtain word segmentation text data; carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data; performing emotion score calculation on the labeled text data based on a preset emotion dictionary to obtain an emotion value of each clause in the labeled text data; and carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score. According to the method and the device, sentence level feelings in the target evaluation text are captured, the evaluation text data of the client is quantized according to the syntax structure, the technical problems that the service quality evaluation can only depend on rough evaluation modes such as star level and satisfaction degree in the prior art, the service quality problem cannot be really found, and the service quality cannot be pertinently improved are solved, the evaluation accuracy of the service quality is improved, and the technical effect of providing an effective basis for improving the service quality is achieved.
Drawings
Fig. 1 is a structural diagram of a service quality evaluation system according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for evaluating service quality according to an embodiment of the present invention;
fig. 3 is a flowchart of another method for evaluating quality of service according to an embodiment of the present invention;
fig. 4 is a flowchart of another method for evaluating quality of service according to an embodiment of the present invention;
fig. 5 is a flowchart of another method for evaluating quality of service according to an embodiment of the present invention;
fig. 6 is a flowchart of another method for evaluating quality of service according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a service quality evaluation device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be noted that the terms "first", "second", and the like in the description and claims of the present invention and the accompanying drawings are used for distinguishing different objects, and are not used for limiting a specific order. The following embodiments of the present invention may be implemented individually, or in combination with each other, and the embodiments of the present invention are not limited in this respect.
Fig. 1 is a structural diagram of a service quality evaluation system according to an embodiment of the present invention. As shown in fig. 1, the service quality evaluation system includes a natural language collection module 10, a natural language processing module 20, and a natural language analysis module 30, wherein the natural language collection module 10 is electrically connected to the natural language processing module 20, and the natural language processing module 20 is electrically connected to the natural language analysis module 30; the natural language collection module 10 is used for acquiring a target evaluation text of a client; the natural language processing module 20 is configured to perform normalization processing on the target evaluation text to obtain a normalized text, and perform word segmentation processing on the normalized text to obtain word segmentation text data; the method is also used for carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data; the natural language analysis module 30 is configured to perform emotion score calculation on the tagged text data based on the preset emotion dictionary to obtain an emotion value of each clause in the tagged text data, and perform weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score.
Fig. 2 is a flowchart of a method for evaluating service quality according to an embodiment of the present invention. The service quality evaluation method can be applied to all conditions needing service quality evaluation, such as service quality evaluation of bank outlets. The service quality evaluation method may be performed by a service quality evaluation system, which may be implemented in hardware and/or software, and may be generally integrated in a server.
As shown in fig. 2, the method for evaluating the service quality specifically includes the following steps:
s101, obtaining a target evaluation text of the client.
Specifically, the natural language collection module 10 is provided with a storage node, which is a processing unit and is mainly used for storing the obtained target evaluation text in the big data platform. The natural language collecting module 10 collects a required target evaluation text according to a service type or a sentence text collecting channel, wherein, taking a bank branch service quality evaluation system as an example, the target evaluation text can be an evaluation given by a customer after selling a line product in a bank, can also be a customer evaluation collected when each bank branch serves the customer, and can also be an evaluation left by the customer at a client, a website and the like supported by the bank. After the natural language collection module 10 collects the target evaluation text, the storage node stores the target evaluation text in the big data platform for standby.
It should be noted that, in the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all conform to the relevant regulations of the national laws and regulations.
S102, carrying out standardization processing on the target evaluation text to obtain a standardized text.
Specifically, the natural language processing module 20 is provided with an extraction node, which is a processing unit and is configured to extract a corresponding target evaluation text from the big data platform, perform normalization processing on the target evaluation text, and store the normalized text obtained after the normalization processing in the extraction node.
Optionally, in S102, performing normalization processing on the target evaluation text, and obtaining a normalized text includes: and filtering repeated punctuations and non-text contents in the target evaluation text to obtain the normalized text.
Specifically, since the target evaluation text is usually a natural language and the natural language does not have a fixed text pattern, the target evaluation text without the fixed pattern needs to be normalized, and the non-text content refers to expressions, symbols and the like that cannot be recognized by a machine, so that expressions, symbols and the like that cannot be recognized by the machine in the target evaluation text need to be removed, repeated punctuation marks are filtered out, and the normalized text is finally obtained and stored in the extraction node for use.
S103, performing word segmentation processing on the normalized text to obtain word segmentation text data.
Specifically, the natural language processing module 20 is further provided with a processing node, and the processing node is configured to extract the normalized text from the extraction node and format the normalized text, specifically, perform word segmentation on the normalized text to obtain word segmentation text data, and store the word segmentation text data in the processing node.
And S104, carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data.
Specifically, the processing node in the natural language processing module 20 is further configured to perform syntax structure labeling on the normalized text, and in the embodiment of the present invention, the syntax structure is mainly divided into three types: parallel, progressive and turning, wherein the division of the parallel structure includes but is not limited to: moreover, simultaneously, also, both, and so on, the partitioning of the progressive structure may be according to any of the following, including but not limited to: not only, even, more, especially, etc., the division of the turning structure is according to the following, including but not limited to: but, may, but, not, etc. And the processing node inquires whether similar meaning words similar to the division basis semanteme exist in the normalized text or not according to the word segmentation text data, then carries out syntactic structure identification on the normalized text by utilizing the inquired similar meaning words to obtain labeled text data, and stores the labeled text data in the processing node for later use.
And S105, calculating emotion scores of the labeled text data based on the preset emotion dictionary to obtain the emotion value of each clause in the labeled text data.
Specifically, the natural language analysis module 30 is provided with a computing node, which is a processing unit and is used for completing the computation of the emotion value of the target evaluation text.
Optionally, the preset emotion dictionary is an emotion dictionary determined by merging the open source emotion dictionary with the word segmentation text data.
Specifically, the emotion dictionary depicts a plurality of vocabulary ontologies, and each vocabulary comprises a vocabulary classification, a vocabulary part of speech, a vocabulary belonging emotion classification, a vocabulary belonging emotion polarity, a vocabulary emotion score and the like. The Chinese open source emotion dictionary disclosed currently comprises a Hopkinson emotion dictionary, a simplified Chinese emotion polarity dictionary of Taiwan university, an emotion vocabulary ontology of university of major studios and the like. However, most of the open source emotion dictionaries disclosed currently are common words for expressing emotion, and some popular networks are used for 666 and the like, and are not in the range of the open source emotion dictionary, but the current popular network words are inevitably used when a customer evaluates service quality, so that the open source emotion dictionary needs to be expanded for better assisting emotion calculation, namely, word segmentation text data is merged with a word body in the open source emotion dictionary, the expanded words are labeled, and finally, a preset emotion dictionary is formed.
The emotion calculation is a key means of emotion analysis in the field of natural language processing, and text emotion is summarized by calculating emotion scores of corpora, so that a basis is provided for relevant personnel to take emotion improving measures in a targeted manner. After the preset emotion dictionary is obtained, the computation node in the natural language analysis module 30 performs emotion score computation on the tagged text data based on the preset emotion dictionary, so as to obtain an emotion value of each clause in the tagged text data.
And S106, carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score.
Specifically, the computing node in the natural language analysis module 30 is further configured to perform weighted average computation using the emotion value after obtaining the emotion value of each clause through computation, to finally obtain the service quality evaluation score, and store the calculated emotion value of each clause and the service quality evaluation score in the computing node for later use.
Illustratively, assuming that there are ten clause sentiment values, wherein the keyword of six clauses is "queue", the keyword of three clauses is "attitude", and the keyword of one clause is "disagreeable", the weight of the three clauses is 6:3:1, and when the sentiment values are used for weighted average calculation, calculation needs to be performed according to the weight to obtain the final service quality evaluation score.
In the embodiment of the invention, the accurate evaluation of the service quality is realized by obtaining the target evaluation text of a certain service type or a sentence text acquisition channel, carrying out the processing of normalization processing, word segmentation processing, syntax structure labeling and the like on the target evaluation text and quantizing the sentence emotion in the target evaluation text. The service quality evaluation method provided by the invention can assist in constructing a service-client-data closed loop, effectively promotes the improvement of service quality,
According to the method and the device, sentence level feelings in the target evaluation text are captured, the evaluation text data of the client is quantized according to the syntax structure, the technical problems that the service quality evaluation can only depend on rough evaluation modes such as star level and satisfaction degree in the prior art, the service quality problem cannot be really found, and the service quality cannot be pertinently improved are solved, the evaluation accuracy of the service quality is improved, and the technical effect of providing an effective basis for improving the service quality is achieved.
Based on the foregoing technical solutions, fig. 3 is a flowchart of another service quality evaluation method provided in an embodiment of the present invention, and as shown in fig. 3, in the step S103, performing a word segmentation process on the normalized text to obtain word segmentation text data specifically includes:
s301, performing word segmentation processing on the normalized text according to grammar and part of speech to obtain word segmentation text data.
Specifically, the grammar basis is grammar classification such as a principal and a predicate, the part of speech is part of speech classification such as adjectives, names and adverbs, the normalized text is subjected to word segmentation processing according to the grammar and the part of speech to obtain word segmentation text data, and basis is provided for subsequent syntactic structure labeling and construction of a preset emotion dictionary.
Based on the foregoing technical solutions, fig. 4 is a flowchart of another service quality evaluation method provided in an embodiment of the present invention, and as shown in fig. 4, in the step S104, performing syntax structure labeling on a normalized text based on the participle text data, and obtaining labeled text data specifically includes:
s401, importing the normalized text into a preset word vector model, and determining a near meaning word which is similar to a preset sentence division basis in the normalized text according to a vector similarity method.
Specifically, the preset word vector model may be a preset word vector model obtained based on a preset sentence division basis and word vector training model word2Vec training, and a near-meaning word similar to the preset sentence division basis in the normalized text may be determined and obtained according to a vector similarity method by directly using the word vector trained in an open source. It should be noted that the preset sentence division basis is the above-mentioned division basis of the parallel structure, and includes but is not limited to: moreover, simultaneously, also, both, and so on, the partitioning of the progressive structure may be according to any of the following, including but not limited to: not only, even, more, especially, etc., the division of the turning structure is according to the following, including but not limited to: but, may, but, not, etc.
S402, carrying out syntactic structure labeling on the normalized text based on the determined near-meaning words and the participle text data to obtain labeled text data.
Specifically, after determining the similar near-meaning words in the normalized text to the preset sentence division basis, performing syntax structure labeling on the normalized text according to the participle text data, namely labeling the near-meaning words in the normalized text according to the participle text data, so that the syntax structure of the clause where the normalized text is located can be determined according to the labeled near-meaning words in the subsequent process.
Based on the foregoing technical solutions, fig. 5 is a flowchart of another service quality evaluation method provided in an embodiment of the present invention, and as shown in fig. 5, the step S105 of calculating an emotion score for the annotated text data based on the preset emotion dictionary to obtain an emotion value of each clause in the annotated text data specifically includes:
s501, judging whether the labeled text data has clauses.
Specifically, whether a clause exists in the annotation text data is determined according to whether a comma exists in the text or whether an annotation word exists in the text, if not, the emotion value calculation is directly performed on the annotation text data, that is, step S503 is performed, and if a clause exists, step S502 is performed.
S502, if yes, further determining a syntax structure of the annotation text data.
Specifically, if a clause exists as a result of the determination, it is further determined whether the syntax structure of each clause of the annotation text data is parallel, progressive, or turning.
And S503, calling a preset weight coefficient based on the determined syntax structure, and calculating the emotion value of each clause in the annotation text data based on the preset weight coefficient and an emotion score calculation formula, wherein the preset weight coefficient is the weight value of different clauses determined based on the syntax structure in the emotion score calculation formula obtained by pre-training.
Specifically, after the syntax structure is determined, Score (t) α Score (t) is calculated by the emotion Score calculation formula1)+βScore(t2) Calculating to obtain the emotion value of each clause in the marked text data, wherein Score represents the emotion value, alpha and beta are preset weight coefficients of clause emotion scores respectively, and t1、t2Representing two clauses.
For the determination of the preset weight coefficient, firstly, randomly selecting part of labeled text data as a training set, and respectively giving alpha and beta an initial value, but meeting the following conditions: α + β ═ 1; secondly, inputting a training text, dynamically adjusting alpha and beta values according to the emotion calculation result, and finally obtaining the optimal alpha and beta values, namely determining a preset weight coefficient. For example, the preset weight coefficient may be: both alpha and beta can be set to 0.5 in the parallel structure, respectively to 0.4 and 0.6 in the progressive structure, and respectively to 0.1 and 0.9 in the turning structure.
After the pre-training of the obtained preset weight coefficients, the corresponding preset weight coefficients are called according to the determined syntax structure.
On the basis of the above technical solutions, fig. 6 is a flowchart of another method for evaluating quality of service according to an embodiment of the present invention, and as shown in fig. 6, after S105, the method for evaluating quality of service further includes:
s601, generating a word cloud distribution graph by using the word segmentation text data and the service quality evaluation score.
Specifically, the natural language analysis module 30 is further provided with an analysis node, and after the service quality evaluation score is obtained, the analysis node can also generate a word cloud distribution map from the service quality evaluation score by using word segmentation text data, so that the problem most concerned by a customer can be displayed more intuitively, and the service quality is assisted to be improved. For example, when the score of the service quality evaluation score is low, and the auxiliary word cloud distribution map finds that the words with high occurrence frequency are 'queue', 'duration', and the like, it indicates that the overlong queue time at the service point is a main factor influencing the service quality, so that the service quality of the service point can be improved in a targeted manner.
Fig. 7 is a schematic structural diagram of a service quality evaluation apparatus according to an embodiment of the present invention, as shown in fig. 7, the service quality evaluation apparatus includes a processor 71, a memory 72, an input device 73, and an output device 74; the number of the processors 71 in the service quality evaluation device may be one or more, and one processor 71 is taken as an example in fig. 7; the processor 71, the memory 72, the input device 73 and the output device 74 in the service quality evaluation apparatus may be connected by a bus or other means, and fig. 7 illustrates the connection by a bus as an example.
The memory 72 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the service quality evaluation method in the embodiment of the present invention (for example, the natural language collection module 10, the natural language processing module 20, and the natural language analysis module 30 in the service quality evaluation system). The processor 71 executes various functional applications and data processing of the service quality evaluation device by executing software programs, instructions, and modules stored in the memory 72, that is, implements the service quality evaluation method described above.
The memory 72 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 72 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 72 may further include memory located remotely from the processor 71, which may be connected to the quality of service assessment device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 73 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the quality of service evaluation apparatus. The output device 74 may include a display device such as a display screen.
Embodiments of the present invention also provide a storage medium containing computer-executable instructions for performing a method of quality of service evaluation when executed by a computer processor.
Specifically, the service quality evaluation method includes:
acquiring a target evaluation text of a client;
carrying out standardization processing on the target evaluation text to obtain a standardized text;
performing word segmentation processing on the normalized text to obtain word segmentation text data;
carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data;
performing emotion score calculation on the labeled text data based on a preset emotion dictionary to obtain an emotion value of each clause in the labeled text data;
and carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the service quality evaluation method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Finally, it should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention and the technical principles applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A service quality evaluation method is characterized by comprising the following steps:
acquiring a target evaluation text of a client;
carrying out standardization processing on the target evaluation text to obtain a standardized text;
performing word segmentation processing on the normalized text to obtain word segmentation text data;
carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data;
calculating emotion scores of the marked text data based on a preset emotion dictionary to obtain an emotion value of each clause in the marked text data;
and carrying out weighted average calculation on the emotion values of the clauses to obtain a service quality evaluation score.
2. The method of claim 1, wherein the normalizing the target evaluation text to obtain a normalized text comprises:
and filtering repeated punctuations and non-text contents in the target evaluation text to obtain the normalized text.
3. The method of claim 1, wherein the performing word segmentation on the normalized text to obtain word segmentation text data comprises:
and performing word segmentation processing on the normalized text according to grammar and part of speech to obtain word segmentation text data.
4. The method of claim 1, wherein the performing syntactic structure labeling on the normalized text based on the participle text data to obtain labeled text data comprises:
importing the normalized text into a preset word vector model, and determining a near meaning word which is similar to a preset sentence division basis in the normalized text according to a vector similarity method;
and carrying out syntactic structure labeling on the normalized text based on the determined near-meaning words and the word segmentation text data to obtain labeled text data.
5. The method of claim 1, wherein the calculating the emotion score of the labeled text data based on a preset emotion dictionary to obtain the emotion value of each clause in the labeled text data comprises:
judging whether the labeled text data has clauses or not;
if so, further determining the syntactic structure of the labeled text data;
and calling a preset weight coefficient based on the determined syntax structure, and calculating the emotion value of each clause in the labeled text data based on the preset weight coefficient and an emotion score calculation formula, wherein the preset weight coefficient is the weight value of different clauses determined based on the syntax structure in the emotion score calculation formula obtained by pre-training.
6. The service quality evaluation method according to claim 1, wherein the preset emotion dictionary is an emotion dictionary determined by merging an open source emotion dictionary with the segmented text data.
7. The method of claim 1, wherein after obtaining the quality of service assessment score, the method further comprises:
and generating a word cloud distribution diagram by using the word segmentation text data and the service quality evaluation score.
8. A service quality evaluation system, characterized by comprising:
the natural language collection module is used for acquiring a target evaluation text of a client;
the natural language processing module is used for carrying out normalized processing on the target evaluation text to obtain a normalized text and carrying out word segmentation processing on the normalized text to obtain word segmentation text data; the system is also used for carrying out syntactic structure labeling on the normalized text based on the word segmentation text data to obtain labeled text data;
and the natural language analysis module is used for calculating the emotion score of the labeled text data based on a preset emotion dictionary to obtain the emotion value of each clause in the labeled text data, and calculating the weighted average of the emotion values of the clauses to obtain the service quality evaluation score.
9. A service quality evaluation apparatus characterized by comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a quality of service evaluation method as claimed in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for quality of service evaluation according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111574531.8A CN114219337A (en) | 2021-12-21 | 2021-12-21 | Service quality evaluation method, system, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111574531.8A CN114219337A (en) | 2021-12-21 | 2021-12-21 | Service quality evaluation method, system, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219337A true CN114219337A (en) | 2022-03-22 |
Family
ID=80704817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111574531.8A Pending CN114219337A (en) | 2021-12-21 | 2021-12-21 | Service quality evaluation method, system, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219337A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805147A (en) * | 2023-02-27 | 2023-09-26 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
-
2021
- 2021-12-21 CN CN202111574531.8A patent/CN114219337A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805147A (en) * | 2023-02-27 | 2023-09-26 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
| CN116805147B (en) * | 2023-02-27 | 2024-03-22 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11403680B2 (en) | Method, apparatus for evaluating review, device and storage medium | |
| US11093854B2 (en) | Emoji recommendation method and device thereof | |
| CN110993081B (en) | Doctor online recommendation method and system | |
| CN106777013B (en) | Conversation management method and device | |
| CN111241237B (en) | Intelligent question-answer data processing method and device based on operation and maintenance service | |
| CN112069298A (en) | Human-computer interaction method, device and medium based on semantic web and intention recognition | |
| CN109086265B (en) | Semantic training method and multi-semantic word disambiguation method in short text | |
| CN112765974B (en) | Service assistance method, electronic equipment and readable storage medium | |
| CN108614814B (en) | Evaluation information extraction method, device and equipment | |
| US20150212976A1 (en) | System and method for rule based classification of a text fragment | |
| Chathuranga et al. | Sinhala sentiment analysis using corpus based sentiment lexicon | |
| WO2014002774A1 (en) | Synonym extraction system, method, and recording medium | |
| CN112860896A (en) | Corpus generalization method and man-machine conversation emotion analysis method for industrial field | |
| CN112380866A (en) | Text topic label generation method, terminal device and storage medium | |
| CN110610003A (en) | Method and system for assisting text annotation | |
| CN114219337A (en) | Service quality evaluation method, system, equipment and readable storage medium | |
| CN111815426B (en) | Data processing method and terminal related to financial investment and research | |
| CN108763258B (en) | Document theme parameter extraction method, product recommendation method, device and storage medium | |
| CN115906797A (en) | Text entity alignment method, device, equipment and medium | |
| CN115292492A (en) | Method, device and equipment for training intention classification model and storage medium | |
| CN112735465B (en) | Invalid information determination method and device, computer equipment and storage medium | |
| CN115221280A (en) | Knowledge retrieval method, system and equipment based on aerospace quality knowledge base | |
| CN113947069A (en) | End-to-end multi-task learning dialogue reference resolution method and system | |
| Tao et al. | Mining Pain Points from Hotel Online Comments Based on Sentiment Analysis | |
| Huangfu et al. | An improved sentiment analysis algorithm for Chinese news |
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 |