Commodity classification management and recommendation method and system for cosmetic sample vending machine

Abstract

The invention discloses a commodity classification management and recommended purchase method and system for a cosmetic sample vending machine. The method comprises a commodity information storage step: storing a unique identifier and a related label of each commodity in the vending machine; a voice data acquisition step: acquiring voice input data of a user; a voice recognition step: converting the collected voice input data into text data; a natural language processing step: performing language processing on the text data and performing semantic understanding; a keyword mapping and label matching step: matching the semantic words processed in the natural language processing step with labels in a commodity database of the vending machine; and a sorting and displaying step: sorting and displaying the commodities after label matching by adopting a sorting algorithm, and in the method, through commodity classification management and recommendation function setting, the time for deleting and selecting the functions of the required products by consumers is shortened, so that the consumers can quickly purchase favorite cosmetic samples.

Description

Technical Field

[0001] The present invention relates to the field of self-service vending equipment, and in particular to a commodity classification management and purchase recommendation method and system for a cosmetic sample vending machine. Background Art

[0002] Many consumers like to try beauty and personal care products before buying them to ensure that they are suitable for their skin type and needs. Cosmetic samples provide a low-cost trial opportunity, allowing consumers to try multiple cosmetics and explore new brands or products without purchasing a full bottle of product. Self-service vending machines provide 24-hour service, allowing consumers to purchase cosmetic samples of multiple brands at any time and place. This convenience and immediacy significantly improves the consumer experience, but current self-service vending machines cannot give consumers purchase recommendations, which requires buyers to spend a lot of time when choosing beauty samples. Summary of the invention

[0003] The technical problem solved by the present invention is to provide a commodity classification management and purchase recommendation method for a cosmetic sample vending machine, which can enable customers to quickly find the sample products they want to buy.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a commodity classification management and purchase recommendation method for a cosmetic sample vending machine, comprising:

[0005] Product information storage step: storing the unique identification and related labels of each product in the vending machine;

[0006] Voice data collection step: collect user's voice input data;

[0007] Speech recognition step: converting the collected speech input data into text data;

[0008] Natural language processing step: perform language processing on text data and make semantic understanding;

[0009] Keyword mapping and label matching step: matching the semantic words processed by the natural language processing step with the labels in the product database of the vending machine;

[0010] Sorting and display steps: Use a sorting algorithm to sort and display the products after tag matching.

[0011] Furthermore, in the commodity information storage step, the unique identification and related labels of each commodity in the vending machine are stored;

[0012] The labels include primary classification and secondary classification, the primary classification is a commodity category label, and the secondary classification is a commodity characteristic label.

[0013] Furthermore, in the natural language processing step, the text data is language processed and semantically understood, specifically:

[0014] Text preprocessing steps: perform word segmentation, stop word filtering and word form normalization on text data;

[0015] Keyword extraction step: extract high-frequency keywords through word frequency statistics and named entity recognition;

[0016] Semantic understanding step: parse the grammatical structure and semantic relationship of the sentence.

[0017] Furthermore, in the keyword mapping and label matching step, the semantic words processed by the natural language processing step are matched with the labels in the commodity database of the vending machine, specifically:

[0018] Synonym step: map synonyms of different expressions to unified labels;

[0019] Tag matching step: Use inverted index or hash mapping to quickly match the tags mapped with synonyms to the tags in the product database;

[0020] Similarity evaluation step: Calculate the similarity between user requirements and product labels.

[0021] Furthermore, in the ranking and displaying step, a weighted scoring method is used to rank and display the candidate commodities.

[0022] The present invention also discloses a commodity classification management and purchase recommendation system for a cosmetic sample vending machine, including a commodity information storage module, a voice data collection module, a voice recognition module, a natural language processing module, a keyword mapping and label matching module, and a sorting display module;

[0023] The commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine;

[0024] The voice data collection module is used to collect the user's voice input data;

[0025] The speech recognition module is used to convert the collected speech input data into text data;

[0026] The natural language processing module is used to perform language processing on text data and perform semantic understanding;

[0027] The keyword mapping and label matching module is used to match the semantic words processed by the natural language processing step with the labels in the commodity database of the vending machine;

[0028] The sorting and display module is used to sort and display the commodities after tag matching by using a sorting algorithm.

[0029] Furthermore, the speech recognition module includes a microphone and an audio processing chip.

[0030] Furthermore, the commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine;

[0031] The labels include primary classification and secondary classification, the primary classification is a commodity category label, and the secondary classification is a commodity characteristic label.

[0032] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned commodity classification management and purchase recommendation method for the cosmetics sample vending machine are implemented.

[0033] The present invention also discloses a computer device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; wherein:

[0034] The memory is used to store computer programs;

[0035] The processor is used to execute the steps of the above-mentioned method for commodity classification management and purchase recommendation of the cosmetics sample vending machine by running the program stored in the memory.

[0036] The beneficial effect of the present invention is that the method reduces the time for consumers to select the desired product functions through commodity classification management and the setting of purchase recommendation functions, so that consumers can quickly purchase their favorite cosmetic samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the flow of the product classification management and purchase recommendation method of the cosmetic sample vending machine according to the embodiment of the present application.

[0038] Figure 2 This is a schematic diagram of the module framework of the commodity classification management and purchase recommendation system of the cosmetic sample vending machine according to the embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0040] like Figure 1 As shown, the present application discloses a first embodiment, which is a commodity classification management and purchase recommendation method for a cosmetic sample vending machine, comprising:

[0041] Product information storage step: storing the unique identification and related labels of each product in the vending machine;

[0042] Voice data collection step: collect user's voice input data;

[0043] Speech recognition step: converting the collected speech input data into text data;

[0044] Natural language processing step: perform language processing on text data and make semantic understanding;

[0045] Keyword mapping and label matching step: matching the semantic words processed by the natural language processing step with the labels in the product database of the vending machine;

[0046] Sorting and display steps: Use a sorting algorithm to sort and display the products after tag matching.

[0047] In this method, by managing commodity categories and setting up a purchase recommendation function, the time for consumers to select desired product functions is reduced, so that consumers can quickly purchase their favorite cosmetic samples.

[0048] In this embodiment, in the commodity information storage step, the unique identification and related labels of each commodity in the vending machine are stored; the labels include primary classification and secondary classification, the primary classification is the commodity type label, and the secondary classification is the commodity characteristic label.

[0049] Specific examples can be shown in the following table:

[0050] Field Name Field English name Remark Product ID PRODUCT_ID Primary Key Product Name PRODUCT_NAME Product sales PRODUCT_SALE brand PRODUCT_BRAND Net Content PRODUCT_CONTENT price PRODUCT_PRICE First level classification label PRODUCT_TYPE Secondary classification label one Secondary classification label 2 ……

[0051] Among them, the first-level classification is the product type, such as lotions and creams in the skin care category, foundation and concealer in the base makeup category, etc. The second-level classification is the personalized classification of the same type of products according to their characteristics, such as color, texture, efficacy, etc.

[0052] The above classification can ensure the uniqueness of each product, thus facilitating subsequent accurate recommendations.

[0053] Specifically, the device needs to be equipped with a voice data collection module and a natural language processing module (NLP, Natural Language Processing) to collect the user's voice, extract and recognize keywords in the input voice, and locate the user's purchasing needs.

[0054] The voice data acquisition module installed in the device is used to record the user's voice input. The hardware of the acquisition module includes a microphone and an audio processing chip. The collected voice data will be converted into text data through automatic speech recognition (ASR) technology and prepared for the next step of processing.

[0055] In this embodiment, in the natural language processing step, language processing and semantic understanding are performed on the text data. Specifically:

[0056] Text preprocessing step: perform word segmentation, stop word filtering, and word normalization operations on the text data;

[0057] Keyword extraction step: extract high-frequency keywords through word frequency statistics and named entity recognition;

[0058] Semantic understanding step: analyze the grammatical structure and semantic relationship of the sentence.

[0059] Specifically, in the text preprocessing step:

[0060] Word segmentation is to perform word segmentation on the text after speech recognition. For example, when the user inputs: "I want an oil-control cream suitable for oily skin.", it will be divided into "I / want / to / a / suitable / oily skin / of / oil-control / cream".

[0061] Stop word filtering is to remove common but meaningless stop words, such as "I", "of", etc.

[0062] Word normalization is to normalize synonyms and near-synonyms. For example, "oily skin" and "oily complexion" are normalized to "oily skin".

[0063] In the keyword extraction step described above, word frequency statistics is to extract high-frequency keywords by counting word frequencies. For example, in the above text, "oily skin", "oil control", and "cream" are high-frequency words. Extract keywords with high distinctiveness from a large amount of corpus;

[0064] Named entity recognition is to identify specific entities in the user input, such as brand names, product categories, etc.

[0065] In the semantic understanding step described above, analyze the grammatical structure and semantic relationship of the sentence. For example, analyze that "cream" is the commodity the user wants, "oily skin" and "oil control" are demand conditions, and the user input "I want" is recognized as a purchase intention.

[0066] The above settings of the method can accurately extract the customer's needs, thus facilitating subsequent label matching.

[0067] In this embodiment, in the keyword mapping and label matching step, the semantic words processed by the natural language processing step are matched with the labels in the commodity database of the vending machine, specifically:

[0068] Synonym step: map synonyms of different expressions to unified labels;

[0069] Tag matching step: Use inverted index or hash mapping to quickly match the tags mapped with synonyms to the tags in the product database;

[0070] Similarity evaluation step: Calculate the similarity between user requirements and product labels.

[0071] In the ranking and displaying step, a weighted scoring method is used to rank and display the candidate commodities.

[0072] Specifically, in the above steps, synonyms with different expressions are mapped to a unified label. For example, "oil control" and "anti-oil" are mapped to the same label. When performing label matching, the keywords are quickly matched to the labels in the product database using an inverted index or hash mapping. For example, "oil control face cream" is mapped to the "oil control" label in the "face cream" category. Then, the similarity between user needs and product labels is calculated, and products with high matching degrees are screened out. Then, a comprehensive sorting algorithm such as a weighted scoring method is used to sort the candidate products. For example, factors such as product ratings, sales volume, and matching degrees are considered and displayed to users in order.

[0073] Through the above steps, accurate recommendations of cosmetic samples can be made according to customer needs, thereby reducing buyers' screening time.

[0074] The present invention also discloses a second embodiment, which is a commodity classification management and purchase recommendation system for a cosmetic sample vending machine, including a commodity information storage module, a voice data collection module, a voice recognition module, a natural language processing module, a keyword mapping and label matching module, and a sorting display module;

[0075] The commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine;

[0076] The voice data collection module is used to collect the user's voice input data;

[0077] The speech recognition module is used to convert the collected speech input data into text data;

[0078] The natural language processing module is used to perform language processing on text data and perform semantic understanding;

[0079] The keyword mapping and label matching module is used to match the semantic words processed by the natural language processing step with the labels in the commodity database of the vending machine;

[0080] The sorting and display module is used to sort and display the commodities after tag matching by using a sorting algorithm.

[0081] Specifically, the speech recognition module includes a microphone and an audio processing chip. The collected speech data will be converted into text data through speech recognition technology (ASR, Automatic Speech Recognition) and prepared for the next step of processing.

[0082] Specifically, the commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine;

[0083] The labels include primary classification and secondary classification, the primary classification is a commodity category label, and the secondary classification is a commodity characteristic label.

[0084] Among them, the first-level classification is the product type, such as lotions and creams in the skin care category, foundation and concealer in the base makeup category, etc. The second-level classification is the personalized classification of the same type of products according to their characteristics, such as color, texture, efficacy, etc.

[0085] The present invention also discloses a third embodiment, which is a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for commodity classification management and purchase recommendation of the cosmetics sample vending machine are implemented.

[0086] In addition, the computer-readable storage medium of this embodiment may adopt any combination of one or more computer-readable storage media, wherein the computer-readable storage medium includes electrical, optical, electromagnetic, infrared or semiconductor systems, devices or components, or any combination thereof.

[0087] The present invention also discloses a fourth embodiment, which is a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; wherein:

[0088] The memory is used to store computer programs;

[0089] The processor is used to execute the steps of the above-mentioned commodity classification management and purchase recommendation method for the cosmetics sample vending machine by running the program stored in the memory.

[0090] As an embodiment of the present invention, the communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0091] As an implementation mode of the present invention, the communication interface is used for communication between the above-mentioned terminal and other devices.

[0092] As an embodiment of the present invention, the memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0093] As an embodiment of the present invention, the above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0094] Different from the prior art, this method reduces the time consumers spend on selecting the desired product functions through commodity classification management and the setting of purchase recommendation functions, thereby enabling consumers to quickly purchase their favorite cosmetic samples.

[0095] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for commodity classification management and purchase recommendation of a cosmetic sample vending machine, characterized in that: include: Product information storage step: storing the unique identification and related labels of each product in the vending machine; Voice data collection step: collect user's voice input data; Speech recognition step: converting the collected speech input data into text data; Natural language processing step: perform language processing on text data and make semantic understanding; Keyword mapping and label matching step: matching the semantic words processed by the natural language processing step with the labels in the product database of the vending machine; Sorting and display steps: Use a sorting algorithm to sort and display the products after tag matching.

2. The method for commodity classification management and purchase recommendation of a cosmetic sample vending machine according to claim 1, characterized in that: In the commodity information storage step, the unique identification and related labels of each commodity in the vending machine are stored; The labels include primary classification and secondary classification, the primary classification is a commodity category label, and the secondary classification is a commodity characteristic label.

3. The method for commodity classification management and purchase recommendation of a cosmetic sample vending machine according to claim 1, characterized in that: In the natural language processing step, language processing and semantic understanding are performed on the text data, specifically: Text preprocessing steps: perform word segmentation, stop word filtering and word form normalization on text data; Keyword extraction step: extract high-frequency keywords through word frequency statistics and named entity recognition; Semantic understanding step: parse the grammatical structure and semantic relationship of the sentence.

4. The method for commodity classification management and purchase recommendation of a cosmetic sample vending machine according to claim 1, characterized in that: In the keyword mapping and label matching step, the semantic words processed by the natural language processing step are matched with the labels in the commodity database of the vending machine, specifically: Synonym step: map synonyms of different expressions to unified labels; Tag matching step: Use inverted index or hash mapping to quickly match the tags mapped with synonyms to the tags in the product database; Similarity evaluation step: Calculate the similarity between user requirements and product labels.

5. The method for commodity classification management and purchase recommendation of a cosmetic sample vending machine according to claim 1, characterized in that: In the ranking and displaying step, a weighted scoring method is used to rank and display the candidate commodities.

6. A commodity classification management and purchase recommendation system for a cosmetic sample vending machine, characterized in that: It includes product information storage module, voice data collection module, voice recognition module, natural language processing module, keyword mapping and label matching module and sorting display module; The commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine; The voice data collection module is used to collect the user's voice input data; The speech recognition module is used to convert the collected speech input data into text data; The natural language processing module is used to perform language processing on text data and perform semantic understanding; The keyword mapping and label matching module is used to match the semantic words processed by the natural language processing step with the labels in the commodity database of the vending machine; The sorting and display module is used to sort and display the commodities after tag matching by using a sorting algorithm.

7. The commodity classification management and purchase recommendation system for cosmetic sample vending machines according to claim 6, characterized in that: The speech recognition module includes a microphone and an audio processing chip.

8. The commodity classification management and purchase recommendation system for cosmetic sample vending machines according to claim 6, characterized in that: The commodity information storage module is used to store the unique identification and related labels of each commodity in the vending machine; The labels include primary classification and secondary classification, the primary classification is a commodity category label, and the secondary classification is a commodity characteristic label.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the commodity classification management and purchase recommendation method for a cosmetic sample vending machine according to any one of claims 1 to 5.

10. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; wherein: The memory is used to store computer programs; The processor is used to execute the steps of the commodity classification management and purchase recommendation method for a cosmetic sample vending machine according to any one of claims 1 to 5 by running the program stored in the memory.

Images