Dry cleaning store operation management system

Abstract

The invention discloses a dry cleaning store operation management system, which comprises a data acquisition module, a data storage module, a customer portrait construction module, a service generation module and a customer feedback management module, the customer portrait construction module pre-distributes group portraits for customers and perfects the group portraits based on mining of customer data so as to obtain customer portraits, and the two portraits are combined to provide data support for improving service efficiency and optimizing service quality; the service generation module provides basic services based on group portraits, provides additional services based on customer portraits to meet individual demands of customers, adapts to customer changes and improves overall service quality; the customer feedback management module combines automatic processing and manual processing to ensure the processing efficiency of customer feedback, the automatic processing adopts a processing scheme for pacifying customers based on customer portraits, and the manual processing preferentially processes feedback problems affecting consumption willingness and public praise of stores to reduce loss.

Description

Technical Field

[0001] The present invention relates to the technical field of operation management, and in particular to a dry cleaning store operation management system. Background Art

[0002] The dry cleaning store operation management system is a software system designed specifically for dry cleaning stores, which aims to help stores improve operational efficiency, manage customer relationships, optimize business processes and improve service quality. The existing dry cleaning store operation management system has the following shortcomings when in use: First, in the existing system, customer data is not fully mined and analyzed, so it is difficult to quickly and comprehensively understand the customer's situation, affecting the improvement of service quality and efficiency; second, there is a lack of personalized service support, which cannot meet the personalized needs of customers, resulting in a decrease in customer satisfaction; third, there is a lack of a dedicated and efficient customer feedback processing mechanism, which affects customers' willingness to consume again and the store's reputation. Summary of the invention

[0003] The purpose of the present invention is to provide a dry cleaning store operation management system to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: a dry cleaning store operation management system, comprising a data acquisition module, a data storage module, a customer portrait construction module, a service generation module and a customer feedback management module, wherein the data storage module establishes data connections with the data acquisition module, the customer portrait construction module, the service generation module and the customer feedback management module respectively.

[0005] Preferably, the customer portrait construction module includes a group portrait generation submodule, a basic portrait definition submodule and a basic portrait improvement submodule.

[0006] Preferably, the group portrait generation submodule includes an age standardization unit, a gender coding unit, an occupational one-hot coding unit, and an income level classification coding unit. The group portrait generation submodule adopts the K-Means clustering algorithm, and the age standardization unit adopts the following formula:

[0007] in, is the standardized age value, is the original age, is the average age, is the standard deviation of age.

[0008] Preferably, the basic portrait improvement submodule includes a personality feature extraction unit, a clothing feature extraction unit and a consumption habit feature extraction unit.

[0009] Preferably, the service generation module includes a basic service generation submodule and a personalized service generation submodule.

[0010] Preferably, the basic service generation submodule includes a group portrait feature weight definition unit, a group portrait feature quantification unit, a basic service score calculation unit and a basic service type association unit.

[0011] Preferably, the weights defined by the group portrait feature weight definition unit are specifically: age feature weight , gender characteristic weight , occupational characteristics weight , income level characteristic weight , and there are:

[0012] The basic service score calculation unit adopts the following formula:

[0013] in, The quantified value of age feature is Quantify the value of gender characteristics, Quantify the values ​​of occupational characteristics, is the quantitative value of income level characteristics, Score for basic services.

[0014] Preferably, the personalized service generation submodule includes a customer portrait feature weight definition unit, a customer portrait feature quantification unit, a personalized service score calculation unit and an additional service type association unit.

[0015] Preferably, the weights defined by the customer portrait feature weight definition unit are specifically: personality feature weights are , clothing feature weight is , the weight of consumption habit characteristics is , and there are:

[0016] The formula used in the personalized service score calculation unit is as follows:

[0017] in, Quantify the personality traits, Quantify the clothing characteristics. Quantify the consumption habit characteristics. Score points for personalized service.

[0018] Preferably, the customer feedback management module includes a feedback collection submodule, a problem classification submodule, a processing solution improvement submodule, an automatic processing submodule, a priority determination submodule, a manual processing submodule and a processing result evaluation submodule.

[0019] Compared with the prior art, the beneficial effects of the present invention are: the customer portrait construction module of the present invention pre-assigns group portraits to customers, and improves group portraits based on the mining of customer data, thereby obtaining customer portraits. The combination of the two portraits can provide data support for improving service efficiency and optimizing service quality; the service generation module provides basic services based on group portraits, and provides additional services based on customer portraits to meet customer personalized needs, adapt to customer changes, and improve overall service quality; the customer feedback management module combines automatic processing with manual processing to ensure the processing efficiency of customer feedback. Automatic processing adopts a processing solution to appease customers based on customer portraits, and manual processing reduces losses by giving priority to feedback issues that affect consumer willingness and store reputation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a system structure block diagram of the present invention; Figure 2 A structural block diagram of a submodule for generating a group portrait of the present invention; Figure 3 Complete the submodule structure diagram for the basic image of the present invention; Figure 4 Generate a submodule structure diagram for the basic service of the present invention; Figure 5 Generate a submodule structure diagram for the personalized service of the present invention; Figure 6 It is a structural block diagram of the customer feedback management module of the present invention.

[0021] In the figure: 1. Data acquisition module; 2. Data storage module; 3. Customer portrait construction module; 31. Group portrait generation submodule; 311. Age standardization unit; 312. Gender coding unit; 313. Occupational unique coding unit; 314. Income level classification coding unit; 32. Basic portrait definition submodule; 33. Basic portrait improvement submodule; 331. Personality feature extraction unit; 332. Clothing feature extraction unit; 333. Consumption habit feature extraction unit; 4. Service generation module; 41. Basic service generation submodule; 411. Group portrait feature weight definition unit; 412. Group Portrait feature quantification unit; 413, basic service score calculation unit; 414, basic service type association unit; 42, personalized service generation submodule; 421, customer portrait feature weight definition unit; 422, customer portrait feature quantification unit; 423, personalized service score calculation unit; 424, additional service type association unit; 5, customer feedback management module; 51, feedback collection submodule; 52, problem classification submodule; 53, processing solution improvement submodule; 54, automatic processing submodule; 55, priority determination submodule; 56, manual processing submodule; 57, processing result evaluation submodule. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Please refer to the attached Figure 1 -Attached Figure 6, an embodiment provided by the present invention: a dry cleaning store operation management system, including a data acquisition module 1, a data storage module 2, a customer portrait construction module 3, a service generation module 4 and a customer feedback management module 5, the data storage module 2 respectively establishes data connections with the data acquisition module 1, the customer portrait construction module 3, the service generation module 4 and the customer feedback management module 5, obtains historical data, customer data and feedback data of the dry cleaning store through the data acquisition module 1, and stores them in the data storage module 2, the data storage module 2 also stores pre-defined basic services, additional services and automatic processing solutions, the customer portrait construction module 3 constructs a group portrait based on historical data and customer data, and improves the customer portrait based on the group portrait, the service generation module 4 associates basic services based on the group portrait, and associates additional services based on the customer portrait, the customer feedback management module 5 collects and processes the feedback data, and processes it automatically or manually Problems reported by customers; the customer portrait construction module 3 includes a group portrait generation submodule 31, a basic portrait definition submodule 32 and a basic portrait improvement submodule 33. The group portrait generation submodule 31 is used to generate groups, the basic portrait definition submodule 32 is used to define a basic portrait of a group portrait seat for a customer, and the basic portrait improvement submodule 33 is used to improve the basic portrait and obtain a customer portrait; the group portrait generation submodule 31 includes an age standardization unit 311, a gender coding unit 312, an occupational unique hot coding unit 313 and an income level classification coding unit 314. The age standardization unit 311, the gender coding unit 312, the occupational unique hot coding unit 313 and the income level classification coding unit 314 are used to process age, gender, occupation and income level data respectively. The group portrait generation submodule 31 adopts the K-Means clustering algorithm, and the age standardization unit 311 adopts the following formula:

[0024] in, is the standardized age value, is the original age, is the average age, is the age standard deviation; the basic portrait improvement submodule 33 includes a personality feature extraction unit 331, a clothing feature extraction unit 332 and a consumption habit feature extraction unit 333, and the personality feature extraction unit 331, the clothing feature extraction unit 332 and the consumption habit feature extraction unit 333 are used to obtain personality, clothing and consumption habit features respectively; the service generation module 4 includes a basic service generation submodule 41 and a personalized service generation submodule 42, the basic service generation submodule 41 is used to associate basic services with group portraits, and the personalized service generation submodule 42 is used to associate additional services with customer portraits; the basic service generation submodule 41 includes group portraits The basic service generation submodule 41 defines the weight of the group portrait feature through the group portrait feature weight definition unit 411, and then quantifies the group portrait feature through the group portrait feature quantification unit 412, and then calculates the basic service score using the basic service score calculation unit 413. The basic service type association unit 414 divides the basic service score into several intervals and associates the basic service type with it. The weights defined by the group portrait feature weight definition unit 411 are specifically: age feature weight , gender characteristic weight , occupational characteristics weight , income level characteristic weight , and there are:

[0025] The basic service score calculation unit 413 uses the following formula:

[0026] in, The quantified value of age feature is Quantify the value of gender characteristics, Quantify the values ​​of occupational characteristics, is the quantitative value of income level characteristics, The personalized service generation submodule 42 includes a customer portrait feature weight definition unit 421, a customer portrait feature quantification unit 422, a personalized service score calculation unit 423 and an additional service type association unit 424. The personalized service generation submodule 42 defines the customer portrait feature weight through the customer portrait feature weight definition unit 421, and then quantifies the customer portrait feature through the customer portrait feature quantification unit 422, and then calculates the personalized service score using the personalized service score calculation unit 423. The additional service type association unit 424 divides the personalized service score into several intervals and associates additional service types with them. The weights defined by the customer portrait feature weight definition unit 421 are specifically: the personality feature weight is , clothing feature weight is , the weight of consumption habit characteristics is , and there are:

[0027] The personalized service score calculation unit 423 uses the following formula:

[0028] in, Quantify the personality traits, Quantify the clothing characteristics. Quantify the consumption habit characteristics. The customer feedback management module 5 includes a feedback collection submodule 51, a problem classification submodule 52, a processing solution improvement submodule 53, an automatic processing submodule 54, a priority determination submodule 55, a manual processing submodule 56 and a processing result evaluation submodule 57. The feedback collection submodule 51 is used to obtain feedback data. The problem classification submodule 52 adopts a text classification algorithm to divide the problems into those that can be automatically processed and those that require manual processing. The automatic processing submodule 54 obtains a processing solution based on the customer portrait. The priority determination submodule 55 is used to sort multiple problems so that the manual processing submodule 56 gives priority to feedback problems that affect consumer willingness and the reputation of the store. The processing result evaluation submodule 57 is used to receive customer feedback on the processing results. For unsatisfactory feedback, the manual processing submodule 56 is used for secondary processing, and the processing solution improvement submodule 53 is used to further improve the processing solution based on the secondary processing results.

[0029] Working principle: When using the present invention, firstly, the historical data, customer data and feedback data of the dry cleaning shop are obtained through the data acquisition module 1, and stored in the data storage module 2. The data storage module 2 also stores the pre-established basic services, additional services and automatic processing solutions. The customer portrait construction module 3 constructs a group portrait based on the historical data and customer data, and improves the customer portrait based on the group portrait. The service generation module 4 associates the basic services based on the group portrait and associates the additional services based on the customer portrait. The customer feedback management module 5 collects and processes the feedback data, and automatically or manually handles the customer feedback issues; specifically: the group portrait generation submodule 31 uses the K-Means clustering algorithm to construct the group portrait, uses the age standardization unit 311 to standardize the age data, and uses the gender encoding unit 312 to encode the gender, for example, encoding male as 0 and female as 1, and the occupation unique hot encoding unit 313 encodes the occupation, for example, there are shared occupation categories, for each customer's occupation, create a Vector, if the customer's occupation is occupation, then the vectorThe first position is 1, and the rest of the positions are 0. The income level classification coding unit 314 encodes the income level. For example, the income level is divided into three levels: low income, middle income, and high income, which can be coded as 1, 2, and 3 respectively. The basic portrait definition submodule 32 matches a group portrait seat basic portrait for the customer based on the basic information of the customer, and then the basic portrait improvement submodule 33 improves the basic portrait through subsequent data to obtain the customer portrait. The personality feature extraction unit 331 judges the personality features by analyzing the communication and interaction with the new customer. The clothing feature extraction unit 332 analyzes the customer's order and extracts clothing features such as clothing brand, material, and new and old. The consumption habit feature extraction unit 333 analyzes the customer's consumption behavior and extracts the consumption amount. , service selection and consumption frequency characteristics, add more detailed descriptions and labels to the basic portrait; in the service generation module 4, the basic service generation submodule 41 defines the group portrait feature weight through the group portrait feature weight definition unit 411, and then quantifies the group portrait feature through the group portrait feature quantification unit 412, and then uses the basic service score calculation unit 413 to calculate the basic service score, and the basic service type association unit 414 divides the basic service score into several intervals and associates basic service types with them. For example, for the low-scoring interval, economical packages and basic cleaning services are associated, and relatively less experienced employees are assigned to operate them. For the medium-scoring interval, basic care is added to the basic cleaning service, and for the high-scoring interval, fine cleaning and professional care are provided. The personalized service generation submodule 42 defines the customer portrait feature weight through the customer portrait feature weight definition unit 421, and then quantifies the customer portrait feature through the customer portrait feature quantification unit 422, and then uses the personalized service score calculation unit 423 to calculate the personalized service score. The additional service type association unit 424 divides the personalized service score into several intervals and associates additional service types with it. By combining basic services and additional services, higher service quality is provided to customers; in the customer feedback management module 5, the feedback collection submodule 51 is used to obtain feedback data, the problem classification submodule 52 adopts a text classification algorithm to divide the problems into those that can be automatically processed and those that need to be manually processed. The automatic processing submodule 54 is based on the customer portrait. For example, obtaining a processing solution that can appease the customer and will not cause customer disgust, for example, using concise and refined sentences to answer impatient customers, and satisfying the needs of low-income customers through preferential means, etc. The priority determination submodule 55 is used to sort multiple issues, so that the manual processing submodule 56 gives priority to processing feedback issues that affect consumer willingness and the reputation of the store. The processing result evaluation submodule 57 is used to receive customer feedback on the processing results. For unsatisfactory feedback, the manual processing submodule 56 is used for secondary processing, and the processing solution improvement submodule 53 is used to further improve the processing solution based on the secondary processing results; the group portrait generation submodule 31 uses the K-Means clustering algorithm, and the specific method is: S1. Initialization: Random selection data points as the initial cluster centers, denoted as ; S2. Assign data points to the nearest cluster center: For each data point , first calculate it to each cluster center Euclidean distance , the formula is:

[0030] in, is the number of features, including the standardized value of age, gender encoding, one-hot encoding vector of occupation, and encoding of income level; It is a data point No. eigenvalues, is the cluster center No. eigenvalues; Then the data points Assign to the cluster with the nearest cluster center; S3. Update cluster centers: For each cluster, recalculate the mean of all data points in the cluster on each feature as the new cluster center. There are data points, for the Features, new cluster centers No. The formula for calculating the eigenvalue is:

[0031] S4. Repeat S2 and S3 until the stopping condition is met. The stopping condition is that the cluster center no longer changes or the maximum number of iterations is reached. A group portrait.

[0032] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A dry cleaning store operation management system, comprising a data acquisition module (1), a data storage module (2), a customer profile building module (3), a service generation module (4) and a customer feedback management module (5), characterized in that: The data storage module (2) establishes data connections with the data acquisition module (1), the customer profile construction module (3), the service generation module (4) and the customer feedback management module (5) respectively.

2. A dry cleaning store operation management system according to claim 1, characterized in that: The customer portrait construction module (3) comprises a group portrait generation submodule (31), a basic portrait definition submodule (32) and a basic portrait improvement submodule (33).

3. A dry cleaning store operation management system according to claim 2, characterized in that: The group portrait generation submodule (31) includes an age standardization unit (311), a gender coding unit (312), an occupational unique-hot coding unit (313) and an income level classification coding unit (314). The group portrait generation submodule (31) adopts a K-Means clustering algorithm, and the age standardization unit (311) adopts the following formula: in, is the standardized age value, is the original age, is the average age, is the standard deviation of age.

4. A dry cleaning store operation management system according to claim 2, characterized in that: The basic portrait improvement submodule (33) comprises a personality feature extraction unit (331), a clothing feature extraction unit (332) and a consumption habit feature extraction unit (333).

5. The dry cleaning store operation management system according to claim 1, characterized in that: The service generation module (4) comprises a basic service generation submodule (41) and a personalized service generation submodule (42).

6. A dry cleaning store operation management system according to claim 5, characterized in that: The basic service generation submodule (41) comprises a group portrait feature weight definition unit (411), a group portrait feature quantification unit (412), a basic service score calculation unit (413) and a basic service type association unit (414).

7. A dry cleaning store operation management system according to claim 6, characterized in that: The weights defined by the group portrait feature weight definition unit (411) are specifically: age feature weight , gender characteristic weight , occupational characteristics weight , income level characteristic weight , and there are: The basic service score calculation unit (413) uses the following formula: in, The quantified value of age feature is Quantify the value of gender characteristics, Quantify the values ​​of occupational characteristics, is the quantitative value of income level characteristics, Score for basic services.

8. The dry cleaning store operation management system according to claim 5, characterized in that: The personalized service generation submodule (42) comprises a customer portrait feature weight definition unit (421), a customer portrait feature quantification unit (422), a personalized service score calculation unit (423) and an additional service type association unit (424).

9. A dry cleaning store operation management system according to claim 8, characterized in that: The weights defined by the customer profile feature weight definition unit (421) are specifically: the personality feature weight is , clothing feature weight is , the weight of consumption habit characteristics is , and there are: The personalized service score calculation unit (423) uses the following formula: in, Quantify the personality traits, Quantify the clothing characteristics. Quantify the consumption habit characteristics. Score points for personalized service.

10. A dry cleaning store operation management system according to claim 1, characterized in that: The customer feedback management module (5) comprises a feedback collection submodule (51), a problem classification submodule (52), a processing solution improvement submodule (53), an automatic processing submodule (54), a priority determination submodule (55), a manual processing submodule (56) and a processing result evaluation submodule (57).

Images