CN112907306B - Customer satisfaction judging method and device - Google Patents
Customer satisfaction judging method and device Download PDFInfo
- Publication number
- CN112907306B CN112907306B CN202110488309.XA CN202110488309A CN112907306B CN 112907306 B CN112907306 B CN 112907306B CN 202110488309 A CN202110488309 A CN 202110488309A CN 112907306 B CN112907306 B CN 112907306B
- Authority
- CN
- China
- Prior art keywords
- image
- training samples
- customer satisfaction
- images
- scale
- 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
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Abstract
The invention provides a method and a device for judging customer satisfaction, and relates to the field of customer satisfaction. A customer satisfaction judging method comprises the following steps: (1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples; (2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample; (3) multi-scale characterization: and carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing. The invention can judge whether the customer is satisfied and meet the requirements of financial institutions.
Description
Technical Field
The invention relates to the field of customer satisfaction identification, in particular to a customer satisfaction judging method and device.
Background
In the current society, financial institutions play an important role, the process of the financial institutions is greatly simplified through networking, and the long-term development of the financial institutions is directly influenced by the satisfaction of customers. Due to regulatory, security, etc., financial institutions often can more easily capture images of customers. Therefore, the method has good practical application value on judging the customer satisfaction by using the image.
Therefore, it is a significant and urgent task to establish a method for determining whether a customer is satisfied.
Disclosure of Invention
The invention aims to provide a customer satisfaction judging method which can judge whether a customer is satisfied and meet the requirements of a financial institution.
Another object of the present invention is to provide a customer satisfaction judging device which can judge whether a customer is satisfied and meet the needs of a financial institution.
The embodiment of the invention is realized by the following steps:
in a first aspect: the embodiment of the application provides a method for judging customer satisfaction, which comprises the following steps:
(1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples;
(2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample;
(3) multi-scale characterization: carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing;
(4) judging a clustering algorithm: when the reinforced and characterized image to be detected is input, the positive training samples and the negative training samples selected for multiple times are subjected to K-means clustering calculation, more than half times of times are judged to be customer satisfaction pictures, the image to be detected is finally judged to be the customer satisfaction pictures, and otherwise, the image to be detected is judged to be the customer dissatisfaction pictures.
In some embodiments of the present invention, in the step (4), the specific operation steps of distinguishing the K-means clustering algorithm are as follows:
(a) respectively selecting any one initial clustering center from the positive training sample and the negative training sample;
(b) calculating the distance from each sample to each cluster center, and clustering each sample to the cluster center closest to the sample;
(c) for each cluster, taking the mean value of all samples of the cluster as a new clustering center;
(d) repeating step (c) until the cluster center does not change or does not change significantly;
(e) if the images to be detected are clustered into positive sample categories, judging the images to be detected as customer satisfaction images; if the images to be detected are clustered into negative sample categories, the images are judged to be unsatisfactory images of clients.
In some embodiments of the present invention, in the step (4), 3 times of selecting the positive training sample and the negative training sample to perform K-means clustering calculation, and if 2 or more times of the image to be detected are determined as the customer satisfaction picture, the image is finally determined as the customer satisfaction picture, otherwise, the image is determined as the customer dissatisfaction picture.
In some embodiments of the present invention, in the step (4), a different number of sets of positive training samples and negative training samples are selected each time, and the number of the positive training samples and the negative training samples in each set is the same.
In some embodiments of the present invention, in the step (4) above: 100 positive training samples and 100 negative training samples are selected for the first time, 300 positive training samples and 300 negative training samples are selected for the second time, and 500 positive training samples and 500 negative training samples are selected for the 3 rd time.
In some embodiments of the present invention, in the step (2), the following steps are further included: respectively recording the client identities of the positive training samples and the negative training samples, identifying the same clients of the positive training samples and the negative training samples according to an image identification technology, classifying the identified positive training samples and the negative training samples according to the client identities, and performing multi-scale reinforcement processing on different types of distinguishing features.
In some embodiments of the present invention, the multi-scale enhancement processing of step (2) above includes the following specific operation steps: the Gaussian blur of a plurality of scales is used and subtracted from the original image to obtain detail information of different degrees, and then the detail information is weighted into the original image in a certain combination mode.
In some embodiments of the present invention, the detail information is optimized by using an SSE image algorithm to realize detail promotion of the multi-scale image.
In some embodiments of the present invention, in the step (3), the specific operation steps of the multi-scale characterization are as follows: SIFT features are extracted from the multi-scale image by using an SIFT algorithm, feature points are searched on different scale spaces, and the directions of the feature points are calculated.
In a second aspect: a customer satisfaction judging device comprising: a memory for storing one or more programs; a processor; the one or more programs, when executed by the processor, implement the method as described in the first aspect.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
the embodiment of the application provides a method for judging customer satisfaction, which comprises the following steps: (1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples; (2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample; (3) multi-scale characterization: carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing; (4) judging a clustering algorithm: when the reinforced and characterized image to be detected is input, the positive training samples and the negative training samples selected for multiple times are subjected to K-means clustering calculation, more than half times of times are judged to be customer satisfaction pictures, the image to be detected is finally judged to be the customer satisfaction pictures, and otherwise, the image to be detected is judged to be the customer dissatisfaction pictures.
With respect to the first aspect: according to the embodiment of the application, the facial image of the satisfied customer is manually selected as the positive training sample, and the facial image of the unsatisfied customer is selected as the negative training sample, so that the sample is conveniently collected from the facial image acquired by a financial institution to carry out big data analysis; carrying out multi-scale image enhancement processing on positive training samples and negative training samples, extracting SIFT (scale invariant feature transform) features after multi-scale pyramid decomposition to realize feature characterization, and thus obtaining identification factors of satisfied clients and unsatisfied clients; the method comprises the steps of selecting a positive training sample and a negative training sample to perform K-means clustering calculation, judging the type of an image to be detected to obtain a result whether a customer is satisfied, and selecting the samples for multiple times to compare to obtain a more accurate judgment result. The invention can realize the judgment of satisfaction of customers and meet the development requirements of financial institutions.
In a second aspect: a customer satisfaction judging device comprising: a memory for storing one or more programs; a processor; the one or more programs, when executed by the processor, implement the method as described in the first aspect.
With respect to the second aspect: which is identical to the working principle and advantageous effects of the first aspect and need not be described here repeatedly.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a customer satisfaction judging method according to embodiment 1 of the present invention;
FIG. 2 is a schematic flow chart of step (4) in example 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally found in use of products of the application, and are used only for convenience in describing the present application and for simplification of description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application.
In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; 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 meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the individual features of the embodiments can be combined with one another without conflict.
Examples
Referring to fig. 1 to 2, fig. 1 to 2 are schematic flow charts illustrating a method for determining customer satisfaction according to an embodiment of the present disclosure. A customer satisfaction judging method comprises the following steps:
(1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples;
(2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample;
(3) multi-scale characterization: carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing;
(4) judging a clustering algorithm: when the reinforced and characterized image to be detected is input, the positive training samples and the negative training samples selected for multiple times are subjected to K-means clustering calculation, more than half times of times are judged to be customer satisfaction pictures, the image to be detected is finally judged to be the customer satisfaction pictures, and otherwise, the image to be detected is judged to be the customer dissatisfaction pictures.
In detail, the facial images of partial satisfied customers are manually selected as positive training samples, the facial images of the unsatisfied customers are manually selected as negative training samples, and whether the customers are satisfied or not can be analyzed by utilizing the characteristics of the customers, such as appearance, expression and the like. In detail, the positive training sample and the negative training sample respectively comprise facial images of a plurality of clients, and the positive training sample and the negative training sample respectively comprise a plurality of facial images of the same client, so that the accuracy of the satisfaction degree identification of the clients is improved. In detail, the multi-scale image enhancement processing, the multi-scale degree calculation and the K-means clustering algorithm are all the prior art, and are not limited specifically herein. In detail, the image to be detected can be subjected to K-means clustering calculation with the positive training sample and the negative training sample, so that the customer satisfaction degree of the image to be detected is identified. In detail, the image to be detected can be compared with the positive training sample and the negative training sample for multiple times respectively. Alternatively, the positive training samples and the negative training samples selected each time for comparing the images to be detected may be the same or different, and the number selected each time may also be different. Optionally, when the positive training sample and the negative training sample are selected for multiple times to distinguish the image to be detected, more than half of the times are judged as the customer satisfaction picture, the image to be detected is finally judged as the customer satisfaction picture, and otherwise, the image to be detected is judged as the customer dissatisfaction picture.
In some embodiments of the present invention, in the step (4), the specific operation steps of distinguishing the K-means clustering algorithm are as follows:
(a) respectively selecting any one initial clustering center from the positive training sample and the negative training sample;
(b) calculating the distance from each sample to each cluster center, and clustering each sample to the cluster center closest to the sample;
(c) for each cluster, taking the mean value of all samples of the cluster as a new clustering center;
(d) repeating step (c) until the cluster center does not change or does not change significantly;
(e) if the images to be detected are clustered into positive sample categories, judging the images to be detected as customer satisfaction images; if the images to be detected are clustered into negative sample categories, the images are judged to be unsatisfactory images of clients.
In detail, one of the positive training sample and the negative training sample is selected as an initial clustering center respectively, so that all samples are classified by the initial clustering centers, the mean value of all samples is used as a clustering center of a cluster, each cluster is classified for multiple times by a clustering algorithm respectively, images to be detected are clustered into one or more clusters according to the distance between the images to be detected and the clustering center of each cluster, and therefore whether the images to be detected are customer satisfactory images or customer unsatisfactory images is judged according to whether the clustering is a positive training sample or a negative training sample. And the obtained positive training samples are more than the negative training samples, which indicates that the image to be detected is a satisfactory image for the client, otherwise, the image to be detected is a unsatisfactory image. Optionally, the multiple judgments may be performed by using different classification times of the clustering algorithm. By the scheme, whether the customer is satisfied can be judged according to the image to be detected, and the accuracy of the judgment result is improved.
In some embodiments of the present invention, in the step (4), 3 times of selecting the positive training sample and the negative training sample to perform K-means clustering calculation, and if 2 or more times of the image to be detected are determined as the customer satisfaction picture, the image is finally determined as the customer satisfaction picture, otherwise, the image is determined as the customer dissatisfaction picture. The selection times are three times, so that the calculation result can be reduced, the calculation resource is further saved, and the identification efficiency is improved.
In some embodiments of the present invention, in the step (4), a different number of sets of positive training samples and negative training samples are selected each time, and the number of the positive training samples and the negative training samples in each set is the same.
In detail, in the step (4) (a), the number of each group of cluster centers selected each time is different, and the number of the positive training samples and the negative training samples of each group of cluster centers is the same, so that the similarity between the image to be detected and the positive training samples and the similarity between the image to be detected and the negative training samples can be reasonably judged from the collected samples. Optionally, the number or types of the positive training samples and the negative training samples collected in step (1) may be the same, where the types may be the same customer group or the service items provided to the customers.
In some embodiments of the present invention, in the step (4) above: 100 positive training samples and 100 negative training samples are selected for the first time, 300 positive training samples and 300 negative training samples are selected for the second time, and 500 positive training samples and 500 negative training samples are selected for the 3 rd time.
In some embodiments of the present invention, in the step (2), the following steps are further included: respectively recording the client identities of the positive training samples and the negative training samples, identifying the same clients of the positive training samples and the negative training samples according to an image identification technology, classifying the identified positive training samples and the negative training samples according to the client identities, and performing multi-scale reinforcement processing on different types of distinguishing features.
In detail, when the sample is collected, the client identity of the sample is recorded at the same time, the client identities of the positive training sample and the negative training sample are identified by using an image identification technology, so that the recorded client identity is compared with an image identification result to obtain the positive training sample and the negative training sample with wrong identity identification, the distinguishing characteristics of the positive training sample and the negative training sample with higher similarity are enhanced, and the accuracy of judging the satisfaction degree of the image to be detected is improved.
In some embodiments of the present invention, the multi-scale enhancement processing of step (2) above includes the following specific operation steps: the Gaussian blur of a plurality of scales is used and subtracted from the original image to obtain detail information of different degrees, and then the detail information is weighted into the original image in a certain combination mode.
In detail, the original image is subtracted from the Gaussian blur of multiple scales, so that detail information with actual value is enhanced, the enhanced information is fused to the original image in a certain combination mode, and the accuracy of original image identification is improved.
In some embodiments of the present invention, the detail information is optimized by using an SSE image algorithm to realize detail promotion of the multi-scale image.
In some embodiments of the present invention, in the step (3), the specific operation steps of the multi-scale characterization are as follows: SIFT features are extracted from the multi-scale image by using an SIFT algorithm, feature points are searched on different scale spaces, the directions of the feature points are calculated, image representation is realized, and therefore whether a client is satisfied with key reasons is analyzed by using the representation features.
Example 2
Referring to fig. 2, an embodiment of the present application provides a device for determining customer satisfaction, including: a memory for storing one or more programs; a processor; the one or more programs, when executed by the processor, implement the method as described in the first aspect.
Wherein the memory, processor and communication interface are electrically connected to each other, directly or indirectly, to enable transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory can be used for storing software programs and modules, such as the customer satisfaction judging method provided in embodiment 1 of the present application. The processor executes various functional applications and data processing by executing software programs and modules stored in the memory. The communication interface may be used for communicating signaling or data with other node devices.
The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowcharts in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart illustrations, and combinations of blocks in the flowchart illustrations, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or by combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
To sum up, the method for judging customer satisfaction provided by the embodiment of the application includes the following steps:
(1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples; (2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample; (3) multi-scale characterization: carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing; (4) judging a clustering algorithm: when the reinforced and characterized image to be detected is input, the positive training samples and the negative training samples selected for multiple times are subjected to K-means clustering calculation, more than half times of times are judged to be customer satisfaction pictures, the image to be detected is finally judged to be the customer satisfaction pictures, and otherwise, the image to be detected is judged to be the customer dissatisfaction pictures.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (8)
1. A customer satisfaction judging method is characterized by comprising the following steps:
(1) collecting samples: manually selecting face images of partial satisfied clients as positive training samples, and manually selecting face images of partial unsatisfied clients as negative training samples;
(2) multi-scale reinforcement: carrying out multi-scale image enhancement processing on the positive training sample and the negative training sample, specifically, simultaneously recording the client identities of the samples when the samples are collected, and identifying the client identities of the positive training sample and the negative training sample by using an image identification technology, so that the recorded client identities are compared with an image identification result to obtain the positive training sample and the negative training sample with wrong identity identification, and further carrying out multi-scale enhancement processing on the distinguishing characteristics of the positive training sample and the negative training sample with higher similarity;
(3) multi-scale characterization: carrying out multi-scale pyramid decomposition on the image subjected to the strengthening treatment, extracting SIFT features under different scales and then fusing;
(4) judging a clustering algorithm: when an image to be detected which is strengthened and characterized is input, performing K-means clustering calculation on a positive training sample and a negative training sample which are selected for multiple times, judging that the image to be detected is a customer satisfaction image for more than half times, and finally judging the image to be detected as the customer satisfaction image, otherwise, judging the image to be detected as the customer dissatisfaction image;
in the step (4), the specific operation steps of distinguishing the K-means clustering algorithm are as follows:
(a) respectively selecting any one initial clustering center from the positive training sample and the negative training sample;
(b) calculating the distance from each sample to each cluster center, and clustering each sample to the cluster center closest to the sample;
(c) for each cluster, taking the mean value of all samples of the cluster as a new clustering center;
(d) repeating step (c) until the cluster center does not change or does not change significantly;
(e) if the images to be detected are clustered into positive sample categories, judging the images to be detected as customer satisfaction images; if the images to be detected are clustered into the negative sample categories, the negative sample categories are judged to be unsatisfactory images of clients, multiple judgments are carried out by utilizing different classification times of a clustering algorithm, the fact that the number of the obtained positive training samples is more than that of the negative training samples shows that the images to be detected are satisfactory images of the clients, otherwise, the negative training samples are unsatisfactory images, and multiple judgments are carried out by utilizing different classification times of the clustering algorithm.
2. The method according to claim 1, wherein in step (4), 3 times of selecting the positive training samples and the negative training samples are performed with K-means clustering calculation, and if 2 or more images to be detected are determined as customer satisfaction pictures, the images are finally determined as customer satisfaction pictures, otherwise, the images are determined as customer satisfaction pictures.
3. The method as claimed in claim 1, wherein in step (4), a different number of positive training samples and negative training samples are selected each time, and the number of positive training samples and negative training samples in each group is the same.
4. A customer satisfaction judging method according to claim 3, characterized in that in the step (4): 100 positive training samples and 100 negative training samples are selected for the first time, 300 positive training samples and 300 negative training samples are selected for the second time, and 500 positive training samples and 500 negative training samples are selected for the 3 rd time.
5. The customer satisfaction judging method according to claim 4, wherein the multi-scale enhancement processing of step (2) is specifically performed by the following steps: and (3) carrying out subtraction with the original image by using Gaussian blur of a plurality of scales to obtain detail information of different degrees, and weighting the detail information into the original image.
6. The method as claimed in claim 5, wherein the detail information is optimized by SSE image algorithm to realize detail enhancement of multi-scale image.
7. The method for determining customer satisfaction according to claim 1, wherein in the step (3), the specific operation steps of the multi-scale characterization are as follows: SIFT features are extracted from the multi-scale image by using an SIFT algorithm, feature points are searched on different scale spaces, and the directions of the feature points are calculated.
8. A customer satisfaction judging device, comprising: a memory for storing one or more programs; a processor; the one or more programs, when executed by the processor, implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110488309.XA CN112907306B (en) | 2021-05-06 | 2021-05-06 | Customer satisfaction judging method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110488309.XA CN112907306B (en) | 2021-05-06 | 2021-05-06 | Customer satisfaction judging method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907306A CN112907306A (en) | 2021-06-04 |
| CN112907306B true CN112907306B (en) | 2022-04-08 |
Family
ID=76108957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110488309.XA Active CN112907306B (en) | 2021-05-06 | 2021-05-06 | Customer satisfaction judging method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907306B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458140A (en) * | 2019-08-20 | 2019-11-15 | 中国工商银行股份有限公司 | Site satisfaction evaluation method and apparatus based on Expression Recognition |
| CN110942108A (en) * | 2019-12-13 | 2020-03-31 | 深圳大学 | Face image clustering method and device and computer readable storage medium |
| CN112329586A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Client return visit method and device based on emotion recognition and computer equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682598B (en) * | 2016-12-14 | 2021-02-19 | 华南理工大学 | Multi-pose face feature point detection method based on cascade regression |
-
2021
- 2021-05-06 CN CN202110488309.XA patent/CN112907306B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458140A (en) * | 2019-08-20 | 2019-11-15 | 中国工商银行股份有限公司 | Site satisfaction evaluation method and apparatus based on Expression Recognition |
| CN110942108A (en) * | 2019-12-13 | 2020-03-31 | 深圳大学 | Face image clustering method and device and computer readable storage medium |
| CN112329586A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Client return visit method and device based on emotion recognition and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 《使用 K-means 算法进行客户分类》;weixin_33717298;《https://blog.csdn.net/weixin_33717298/article/details/89624514》;20180926;第1-10页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907306A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112163008B (en) | Big data analysis-based user behavior data processing method and cloud computing platform | |
| CN113138982B (en) | Big data cleaning method | |
| CN114581207B (en) | Commodity image big data accurate pushing method and system for E-commerce platform | |
| CN113963147B (en) | Key information extraction method and system based on semantic segmentation | |
| CN110795584A (en) | User identifier generation method and device and terminal equipment | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN113158777A (en) | Quality scoring method, quality scoring model training method and related device | |
| CN113032525A (en) | False news detection method and device, electronic equipment and storage medium | |
| CN113313217B (en) | Method and system for accurately identifying dip angle characters based on robust template | |
| CN112906696B (en) | English image region identification method and device | |
| CN112632000A (en) | Log file clustering method and device, electronic equipment and readable storage medium | |
| CN112907306B (en) | Customer satisfaction judging method and device | |
| CN112597997A (en) | Region-of-interest determining method, image content identifying method and device | |
| CN114723536B (en) | E-commerce platform cheap commodity selection method and system based on image big data comparison | |
| CN115641191A (en) | Data pushing method based on data analysis and AI system | |
| CN115392351A (en) | Risk user identification method and device, electronic equipment and storage medium | |
| CN113688206A (en) | Text recognition-based trend analysis method, device, equipment and medium | |
| CN113516165B (en) | Customer satisfaction judging method based on image pyramid matching posterior | |
| CN113239031A (en) | Big data denoising processing method | |
| CN113568952A (en) | Internet of things resource data analysis method | |
| CN113065892A (en) | Information pushing method, device, equipment and storage medium | |
| CN116610806B (en) | AI-based RPA digital service processing method and computer equipment | |
| CN113806338B (en) | Data discrimination method and system based on data sample imaging | |
| CN113361497B (en) | Intelligent tail box application method and device based on training sample fingerprint identification | |
| CN112633399B (en) | Sparse collaborative joint representation pattern recognition method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |