CN112818215A - Product data processing method, device, equipment and storage medium - Google Patents
Product data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112818215A CN112818215A CN202110036535.4A CN202110036535A CN112818215A CN 112818215 A CN112818215 A CN 112818215A CN 202110036535 A CN202110036535 A CN 202110036535A CN 112818215 A CN112818215 A CN 112818215A
- Authority
- CN
- China
- Prior art keywords
- data
- product
- preset
- numerical
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003860 storage Methods 0.000 title claims abstract description 38
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 95
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 238000002372 labelling Methods 0.000 claims description 31
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000013467 fragmentation Methods 0.000 claims description 7
- 238000006062 fragmentation reaction Methods 0.000 claims description 7
- 239000012634 fragment Substances 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000007619 statistical method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000009897 systematic effect Effects 0.000 description 6
- 238000007621 cluster analysis Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241001494479 Pecora Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of big data, and provides a method, a device, equipment and a storage medium for processing product data, which are used for improving the accuracy of the product data processed based on intelligent recommendation. The product data processing method comprises the following steps: classifying product data to be processed according to data types to obtain initial text type data and initial numerical type data; performing semantic meaning and semantic classification on the initial text type data through a language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through an artificial neural network model to obtain candidate numerical data; carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and customer group positioning information; and storing the data after the marks are gathered into a preset product database according to the preset attribute category. In addition, the invention also relates to a block chain technology, and the product data to be processed can be stored in the block chain.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a method, an apparatus, a device, and a storage medium for processing product data.
Background
With the development of internet technology and business, intelligent recommendation of business products is concerned, and the application and management of product data are an important link in the intelligent recommendation technology of business products. At present, for the application and management of product data, the product data is generally classified and attribute replaced by user tags.
However, in the above method, the classification method of the product data is single, and the product data is not systematically analyzed and planned, so that the accuracy of the product data after being processed based on intelligent recommendation is low.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for processing product data, which are used for improving the accuracy of the product data processed based on intelligent recommendation.
The invention provides a product data processing method in a first aspect, which comprises the following steps:
the method comprises the steps of obtaining product data to be processed, classifying the product data to be processed according to data types, and obtaining initial text type data and initial numerical type data;
performing semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and passenger group positioning information;
and storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain target product data.
Optionally, in a first implementation manner of the first aspect of the present invention, the performing classification type labeling and summarization processing on the candidate text data and the candidate numerical data includes:
carrying out product type labeling on the candidate text data through a preset labeling algorithm, and carrying out labeling numerical calculation and numerical labeling on the candidate numerical data to obtain data to be summarized;
acquiring customer information of the product data to be processed, and classifying the data to be summarized according to the customer information to obtain summarized data;
converting the summarized data into a high-density subgraph.
Optionally, in a second implementation manner of the first aspect of the present invention, the storing the data after the mark aggregation to a preset product database according to a preset attribute category to obtain target product data includes:
classifying the data after the marks are gathered according to preset attribute categories to obtain classified data;
writing the classified data into a preset hash table to obtain data to be stored, and carrying out fragmentation processing on the data to be stored to obtain fragmented data;
and creating an index of the fragment data to obtain index data, and writing the index data into a preset storage file of a preset product database to obtain target product data.
Optionally, in a third implementation manner of the first aspect of the present invention, the obtaining product data to be processed and classifying the product data to be processed according to data types to obtain initial text-type data and initial numerical-type data includes:
acquiring product data to be processed, and performing semantic recognition on the product data to be processed through a preset semantic recognition model to obtain recognition data;
and calling a preset character type decision tree and a preset digital type decision tree according to the data type, and respectively matching and extracting the identification data to obtain initial text type data and initial numerical type data.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the performing numerical processing on the initial numerical data through a preset artificial neural network model to obtain candidate numerical data includes:
converting the data type of the initial numerical data into a preset data type through a preset artificial neural network model to obtain converted numerical data;
acquiring a target field of the converted numerical data, and identifying and acquiring a field name corresponding to the target field in a preset field table;
and determining the conversion numerical data and the field name as candidate numerical data.
Optionally, in a fifth implementation manner of the first aspect of the present invention, after the storing the data after the mark aggregation to a preset product database according to a preset attribute category to obtain target product data, the method further includes:
acquiring user retrieval information, and matching corresponding client group data from the target product data according to the user retrieval information, wherein the user retrieval information comprises user information and/or product scene information;
performing product attribute clustering analysis on the customer group data through a preset clustering algorithm to obtain target product attributes;
and according to the target product attribute, carrying out full search and screening on the preset product data in the preset product database to obtain recommended product data.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after the performing full search and screening on the preset product data in the preset product database according to the target product attribute to obtain recommended product data, the method further includes:
and obtaining interested product data based on the recommended product data, updating the preset product database according to the interested product data, and optimizing the execution process of the target product data.
A second aspect of the present invention provides a product data processing apparatus, including:
the classification module is used for acquiring product data to be processed and classifying the product data to be processed according to data types to obtain initial text type data and initial numerical type data;
the first processing module is used for performing semantic meaning transfer and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
the second processing module is used for carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and passenger group positioning information;
and the storage module is used for storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain the target product data.
Optionally, in a first implementation manner of the second aspect of the present invention, the second processing module is specifically configured to:
carrying out product type labeling on the candidate text data through a preset labeling algorithm, and carrying out labeling numerical calculation and numerical labeling on the candidate numerical data to obtain data to be summarized;
acquiring customer information of the product data to be processed, and classifying the data to be summarized according to the customer information to obtain summarized data;
converting the summarized data into a high-density subgraph.
Optionally, in a second implementation manner of the second aspect of the present invention, the storage module is specifically configured to:
classifying the data after the marks are gathered according to preset attribute categories to obtain classified data;
writing the classified data into a preset hash table to obtain data to be stored, and carrying out fragmentation processing on the data to be stored to obtain fragmented data;
and creating an index of the fragment data to obtain index data, and writing the index data into a preset storage file of a preset product database to obtain target product data.
Optionally, in a third implementation manner of the second aspect of the present invention, the classification module is specifically configured to:
acquiring product data to be processed, and performing semantic recognition on the product data to be processed through a preset semantic recognition model to obtain recognition data;
and calling a preset character type decision tree and a preset digital type decision tree according to the data type, and respectively matching and extracting the identification data to obtain initial text type data and initial numerical type data.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the first processing module is specifically configured to:
converting the data type of the initial numerical data into a preset data type through a preset artificial neural network model to obtain converted numerical data;
acquiring a target field of the converted numerical data, and identifying and acquiring a field name corresponding to the target field in a preset field table;
and determining the conversion numerical data and the field name as candidate numerical data.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the device for processing product data further includes:
the matching module is used for acquiring user retrieval information, and matching corresponding client group data from the target product data according to the user retrieval information, wherein the user retrieval information comprises user information and/or product scene information;
the cluster analysis module is used for carrying out product attribute cluster analysis on the customer group data through a preset cluster algorithm to obtain target product attributes;
and the searching and screening module is used for carrying out full searching and screening on the preset product data in the preset product database according to the target product attribute to obtain recommended product data.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the device for processing product data further includes:
and the updating optimization module is used for acquiring the interested product data based on the recommended product data, updating the preset product database according to the interested product data and optimizing the execution process of the target product data.
A third aspect of the present invention provides a product data processing apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to enable the processing device of the product data to execute the processing method of the product data.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-described method of processing product data.
According to the technical scheme provided by the invention, product data to be processed are obtained, and data type classification is carried out on the product data to be processed to obtain initial text type data and initial numerical type data; performing semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data; carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data to obtain data to be processed, wherein the data to be processed comprises product attributes and customer group positioning information; and storing the data to be processed into a preset product database according to the preset attribute category to obtain target product data. In the embodiment of the invention, the initial text type data is subjected to semantic escaping and semantic classification by performing semantic identification and numerical identification on the product data to be processed, the initial numerical type data is subjected to numerical processing, the candidate text data and the candidate numerical data are subjected to classification type marking and summarizing, the data to be processed is stored in the preset product database according to the preset attribute type, the product type classification and the numerical data classification based on the text type data of the product data to be processed in multiple classification modes are realized, the product data to be processed is subjected to systematic analysis and planning, the accuracy of classification and marking of the product data to be processed is improved, and the accuracy of the product data processed based on intelligent recommendation is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for processing product data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a method for processing product data according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a device for processing product data according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a product data processing device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a device for processing product data in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for processing product data, which improve the accuracy of the product data processed based on intelligent recommendation.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for processing product data according to an embodiment of the present invention includes:
101. and acquiring product data to be processed, and classifying the product data to be processed according to the data type to obtain initial text type data and initial numerical type data.
It is to be understood that the execution subject of the present invention may be a processing device of product data, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
The product data to be processed comprises client income data, client family information and client personal condition information which are interested in a certain type of products in the past, current sales data of the type of products, activity information and client conversion rate data of promoted products and the like, and the sales data are as follows: the system comprises the following components of repurchase condition data, customer conversion condition data, profit proportion data, combined sales data and the like, wherein the customer personal condition information comprises the following components: generic terms, constellation, gender, credit level, customer registration, etc. The product data to be processed may correspond to one type of product, and may also correspond to multiple types of products, for example: the product data to be processed can be client income data, client family information and client personal condition information of A-type products, current sales data of the products, activity information and client conversion rate data of promoted products and the like, and the product data to be processed can also be client income data, client family information and client personal condition information respectively corresponding to the A-type products and the B-type products, current sales data of the products, activity information and client conversion rate data of the promoted products and the like.
The server calls a preset webpage crawler or crawler, crawls initial product data on a platform webpage, extracts stored historical product data from a preset database, and performs data cleaning, data stipulation and data conversion on the initial product data and the historical product data to obtain product data to be processed. The server performs semantic recognition and numerical recognition on the product data to be processed according to the data types of the character strings and the numerical values through a preset recognition model to obtain a recognition result, and classifies the product data to be processed into initial text type data (the data types corresponding to the character strings) and initial numerical type data (the data types corresponding to the numerical values) according to the recognition result, wherein the recognition model comprises an algorithm and a network structure for character string recognition and numerical value recognition, and the server can also perform character string fuzzy matching on the product data to be processed through a preset regular expression to obtain the corresponding initial text type data.
102. And carrying out semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and carrying out numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data.
The server sequentially performs feature extraction, word vector conversion, statistical analysis and classification on the initial text type data through a preset language model bert to obtain candidate text data, for example: the characteristics extracted by the characteristics are the historical sale condition characteristics of the product, the historical purchase client condition characteristics of the product, the attribute characteristics of the product, the employee age characteristics, the sale mode characteristics and the purchase mode characteristics of a company selling the product, and the client condition characteristics comprise client attribute characteristics, constellation characteristics, age characteristics and gender characteristics; statistical analysis includes the ratio of the seats to the sheep, the ratio of the numbers of the department-aged sales personnel to the senior-aged sales personnel to the number of the school-aged sales personnel to the senior-aged sales personnel to purchase the product, and the like; the classification may be according to the type of results of the statistical analysis.
The server performs feature extraction, feature scaling, feature characterization, abnormal value identification and feature discretization on initial numerical data through a feedback neural network model in a preset Artificial Neural Network (ANN) model to obtain numerical features, and performs prediction, statistical analysis and numerical classification on the numerical features to obtain candidate numerical data, for example: forecast, statistically analyze activity conversion rate data, product subsidy rate data, commission rate data, management income rate data, etc.; the numerical classification may be a classification according to the type of the result of the prediction, statistical analysis.
103. And carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and customer group positioning information.
The server labels the candidate text data according to the type of statistical analysis through a preset labeling algorithm and a labeling tool to obtain first data to be summarized, for example: and performing customer attribute, purchased attribute proportion, salesperson proportion and the like on the candidate text data. The server labels the candidate numerical data according to the numerical classification type through a preset labeling algorithm and a labeling tool to obtain second data to be summarized, for example: conversion rate data for performing an activity on the candidate value data, subsidy rate data for the product, commission rate data, and a notation for managing revenue rate data. And creating a user portrait according to the first data to be summarized, the second data to be summarized and the corresponding client information (so as to realize summarization), and obtaining data after the mark summary, wherein the mark summary comprises product attributes and client group positioning information, the client group positioning information refers to information of a client principle to be treated, and the client group positioning information comprises but is not limited to client group consumption capacity analysis information, client group consumption product trend information, client group consumption demand information and the like.
104. And storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain target product data.
The server classifies the data after the marks are gathered into multiple types of data according to preset attribute categories, writes the multiple types of data into preset forms Excel respectively to obtain multiple forms, and stores the multiple forms into a preset product database according to preset storage proportions and storage spaces, so that target product data are obtained. The preset attribute categories include basic attributes and non-basic attributes, for example: basic attributes such as insurance, loan financing, investment financing, credit card and life, and non-basic attributes such as customer operation, company operation, channel speciality, channel region, product operation and product association.
In the embodiment of the invention, the initial text type data is subjected to semantic escaping and semantic classification by performing semantic identification and numerical identification on the product data to be processed, the initial numerical type data is subjected to numerical processing, the candidate text data and the candidate numerical data are subjected to classification type marking and summarizing, the data to be processed is stored in the preset product database according to the preset attribute type, the product type classification and the numerical data classification based on the text type data of the product data to be processed in multiple classification modes are realized, the product data to be processed is subjected to systematic analysis and planning, the accuracy of classification and marking of the product data to be processed is improved, and the accuracy of the product data processed based on intelligent recommendation is improved.
Referring to fig. 2, another embodiment of the method for processing product data according to the embodiment of the present invention includes:
201. and acquiring product data to be processed, and classifying the product data to be processed according to the data type to obtain initial text type data and initial numerical type data.
Specifically, the server acquires product data to be processed, and performs semantic recognition on the product data to be processed through a preset semantic recognition model to obtain recognition data; and calling a preset character type decision tree and a preset digital type decision tree according to the data type, and respectively matching and extracting the identification data to obtain initial text type data and initial numerical type data.
The product data to be processed may include, but is not limited to, image data, voice data, and text data, among others. The server extracts product data to be processed after data preprocessing from a preset database, sequentially performs target frame detection, target frame segmentation, target frame image recognition and semantic recognition of a target frame image on the image data in the product data to be processed through a target detection algorithm, an image segmentation algorithm, an image recognition algorithm and a semantic recognition algorithm in a preset semantic recognition model to obtain first data, performs voice recognition and semantic recognition on the voice data in the product data to be processed through a voice recognition algorithm in the semantic recognition model to obtain second data, performs semantic recognition on the text data in the product data to be processed through a hidden Markov model in the semantic recognition model to obtain third data, and determines the first data, the second data and the third data as recognition data.
The server calls a preset character type decision tree according to the data type, similarity calculation, threshold judgment and data extraction are sequentially carried out on the identification data, initial text type data corresponding to the product data to be processed are obtained, the server calls a preset digital type decision tree according to the data type, similarity calculation, threshold judgment and data extraction are sequentially carried out on the identification data, and initial numerical type data corresponding to the product data to be processed are obtained.
202. And carrying out semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and carrying out numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data.
The server sequentially performs feature extraction, word vector conversion, statistical analysis and classification on the initial text type data through a preset language model bert to obtain candidate text data, for example: the characteristics extracted by the characteristics are the historical sale condition characteristics of the product, the historical purchase client condition characteristics of the product, the attribute characteristics of the product, the employee age characteristics, the sale mode characteristics and the purchase mode characteristics of a company selling the product, and the client condition characteristics comprise client attribute characteristics, constellation characteristics, age characteristics and gender characteristics; the statistical analysis is the proportion of young people and old people who buy the product, and the like.
Specifically, the server converts the data type of the initial numerical data into a preset data type through a preset artificial neural network model to obtain converted numerical data; acquiring a target field of the converted numerical data, and identifying and acquiring a field name corresponding to the target field in a preset field table; the conversion numerical type data and the field name are determined as candidate numerical data.
The server performs feature extraction and feature classification on initial numerical data through a self-organizing neural network algorithm in a preset artificial neural network model to obtain numerical data to be processed, converts the data type of the numerical data to be processed into a preset data type to realize uniform conversion of the data type of the initial numerical data into the same type to obtain converted numerical data, extracts a target field of the converted numerical data, generates a target key of the target field, and performs key-value pair matching on field names in a preset field table according to the target key to obtain candidate numerical data, wherein the candidate numerical data can comprise the converted numerical data and the field names corresponding to the converted numerical data. The method and the device realize systematic analysis and planning of product data to be processed based on numerical data, thereby improving the accuracy of the product data processed based on intelligent recommendation.
203. And carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and customer group positioning information.
Specifically, the server labels the product types of the candidate text data through a preset labeling algorithm, and performs labeling numerical calculation and numerical labeling on the candidate numerical data to obtain data to be summarized; acquiring customer information of product data to be processed, and classifying the data to be summarized according to the customer information to obtain summarized data; the summarized data is converted into a high-density subgraph.
The server labels the candidate text data according to the product type through a preset labeling algorithm and a labeling tool (such as: BasicFinder for Gauss), for example: and marking the product attributes, the product sales types, the product sales client group types and the like on the candidate text data, calculating and predicting the candidate numerical data by the server according to a preset marking numerical rule to obtain a value to be marked, and marking the value to be marked to the candidate numerical data by a preset marking algorithm and a marking tool so as to obtain the data to be summarized.
The method comprises the steps that a server obtains client information of product data to be processed and a hash table corresponding to the client information, the data to be summarized are classified and written into the corresponding hash tables to obtain summarized data, sub high-density subgraphs are generated according to the data (namely the summarized data) in the hash tables to obtain a plurality of sub high-density subgraphs, the incidence relation among the data in the hash tables is obtained, the sub high-density subgraphs are connected according to the incidence relation to obtain a main high-density subgraph, namely the summarized data are marked, and therefore the subsequent quick retrieval and arrangement of the product data to be processed are facilitated.
204. And storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain target product data.
Specifically, the server classifies the data after the marks are gathered according to preset attribute categories to obtain classified data; writing the classified data into a preset hash table to obtain data to be stored, and carrying out fragmentation processing on the data to be stored to obtain fragmented data; and creating an index of the fragment data to obtain index data, and writing the index data into a preset storage file of a preset product database to obtain target product data.
After the server obtains the classified data, the classified data are respectively written into hash tables corresponding to preset attribute categories to obtain data to be stored, each hash table is divided into a plurality of sub-tables, namely the data to be stored are subjected to fragmentation processing to obtain fragmentation data, indexes among the sub-tables are created to obtain indexes corresponding to the hash tables respectively, the indexes corresponding to the hash tables are related to each other to obtain index data, and the index data are stored into preset storage files of a preset product database, so that target product data are obtained, and the retrieval efficiency and the retrieval accuracy of the target product data are improved.
205. And acquiring user retrieval information, and matching corresponding client group data from the target product data according to the user retrieval information, wherein the user retrieval information comprises user information and/or product scene information.
The method comprises the steps that a user inputs user retrieval information on a preset interface, the preset interface sends the user retrieval information to a server, the server receives the user retrieval information, key information of the user retrieval information is extracted, target product data in a preset database is retrieved according to the key information, and corresponding client group data are obtained and comprise client groups to which the user belongs and client product data of the client groups, wherein the user information comprises at least one of user income information, life province and city information, family income information, family expenditure information, family member information, purchased financing product information, liability information and the like. Product scenario information is for example: education and child care, health care, vehicle and trip, small and micro management, wealth management and the like.
206. And performing product attribute clustering analysis on the customer group data through a preset clustering algorithm to obtain the target product attribute.
The server performs product attribute clustering analysis on the client group data through a preset clustering algorithm, namely an Expectation Maximization (EM) clustering algorithm based on a Gaussian Mixture Model (GMM), so as to calculate product attributes meeting user retrieval information (current state), obtain a plurality of candidate product attributes, obtain a numerical value labeled in target product data corresponding to each candidate product attribute, perform weighted summation on the numerical value to obtain a target value, and determine the candidate product attribute corresponding to a target value larger than a preset threshold value as the target product attribute so as to improve the accuracy of the target product attribute.
207. And according to the target product attribute, carrying out full search and screening on the preset product data in the preset product database to obtain recommended product data.
The server calls a preset search engine, full search is conducted on preset product data in a preset product database based on the target product attributes, candidate product data are obtained, the candidate product data comprise product data corresponding to a plurality of candidate products respectively, the preset product data comprise product attributes and attribute values, normalization processing is conducted on the attribute values to obtain normalization values, the candidate product data are sorted according to the sequence of the normalization values from large to small to obtain sequence data, corresponding candidate product data in the sequence data are extracted according to a preset ranking range, and accordingly recommended product data are obtained.
According to the method, corresponding client group data are matched from target product data according to user retrieval information, product attribute cluster analysis is carried out on the client group data through a preset clustering algorithm, and the preset product data in a preset product database are searched and screened in a full-scale mode according to the target product attributes, so that accurate matching of recommended product data required by users is achieved, labor cost is reduced, matching efficiency of the product data is improved, the recommended product data required by the users can be analyzed from a multi-dimensional angle, the recommended product data required by the users can be deeply mined, and intelligent recommendation accuracy of the processed product data is improved on the basis of improving accuracy of the product data processed based on intelligent recommendation.
Specifically, the server searches and screens the preset product data in the preset product database in a full amount according to the target product attribute to obtain recommended product data, then obtains interested product data based on the recommended product data, updates the preset product database according to the interested product data, and optimizes the execution process of the target product data.
The method comprises the steps that after a server obtains recommended product data, the recommended product data are rendered to a preset display page, a user clicks interested recommended product data on the preset display page, namely interesting product data, the preset display page records and sends the interesting product data to the server, the server receives the interesting product data, relevant fields or field values of interesting products are written in label content of the interesting product data, the interesting product data written in the label content replace original interesting product data in a preset product database, the preset product database is updated, and according to the interesting product data, the execution process of target product data, the applied optimized data label algorithm rules and the applied model network structure and algorithm are optimized and adjusted. By updating the preset product database according to the interested product data and optimizing the execution process of the target product data, the accuracy of the product data after intelligent recommendation processing is improved, and the retrieval accuracy and the retrieval efficiency of the target product data are improved.
In the embodiment of the invention, the product type classification and the numerical data classification based on the text type data of the product data to be processed in various classification modes are realized, the systematic analysis and planning are carried out on the product data to be processed, the accuracy of the classification and the labeling of the product data to be processed is improved, so the accuracy of the product data after the intelligent recommendation processing is improved, the corresponding client group data is matched from the target product data according to the retrieval information of the user, the product attribute clustering analysis is carried out on the client group data through the preset clustering algorithm, the total search and the screening are carried out on the preset product data in the preset product database according to the target product attribute, the accurate matching of the recommended product data required by the user is realized, the matching efficiency of the product data is improved, the recommended product data required by the user can be analyzed from multiple dimensions, and the recommended product data required by the user is deeply mined, so that the intelligent recommendation accuracy of the processed product data is improved on the basis of improving the accuracy of the product data processed based on intelligent recommendation.
With reference to fig. 3, the above describes a method for processing product data in an embodiment of the present invention, and a processing device for processing product data in an embodiment of the present invention is described below, where an embodiment of the processing device for product data in an embodiment of the present invention includes:
the classification module 301 is configured to acquire product data to be processed, and classify the product data to be processed according to data types to obtain initial text type data and initial numerical type data;
the first processing module 302 is configured to perform semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and perform numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
the second processing module 303 is configured to perform classification type labeling and summarization on the candidate text data and the candidate numerical data, where the labeled and summarized data includes product attributes and guest group location information;
and the storage module 304 is configured to store the data after the marks are aggregated into a preset product database according to the preset attribute category, so as to obtain target product data.
The function implementation of each module in the processing apparatus for product data corresponds to each step in the processing method embodiment for product data, and the function and implementation process thereof are not described in detail herein.
In the embodiment of the invention, the initial text type data is subjected to semantic escaping and semantic classification by performing semantic identification and numerical identification on the product data to be processed, the initial numerical type data is subjected to numerical processing, the candidate text data and the candidate numerical data are subjected to classification type marking and summarizing, the data to be processed is stored in the preset product database according to the preset attribute type, the product type classification and the numerical data classification based on the text type data of the product data to be processed in multiple classification modes are realized, the product data to be processed is subjected to systematic analysis and planning, the accuracy of classification and marking of the product data to be processed is improved, and the accuracy of the product data processed based on intelligent recommendation is improved.
Referring to fig. 4, another embodiment of the apparatus for processing product data according to the embodiment of the present invention includes:
the classification module 301 is configured to acquire product data to be processed, and classify the product data to be processed according to data types to obtain initial text type data and initial numerical type data;
the first processing module 302 is configured to perform semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and perform numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
the second processing module 303 is configured to perform classification type labeling and summarization on the candidate text data and the candidate numerical data, where the labeled and summarized data includes product attributes and guest group location information;
the storage module 304 is configured to store the data after the mark aggregation to a preset product database according to a preset attribute category, so as to obtain target product data;
the matching module 305 is configured to obtain user search information, and match corresponding client group data from target product data according to the user search information, where the user search information includes user information and/or product scenario information;
the cluster analysis module 306 is used for performing product attribute cluster analysis on the customer group data through a preset clustering algorithm to obtain target product attributes;
and the searching and screening module 307 is configured to perform full searching and screening on the preset product data in the preset product database according to the target product attribute to obtain recommended product data.
Optionally, the second processing module 303 may be further specifically configured to:
carrying out product type labeling on the candidate text data through a preset labeling algorithm, and carrying out labeling numerical calculation and numerical labeling on the candidate numerical data to obtain data to be summarized;
acquiring customer information of product data to be processed, and classifying the data to be summarized according to the customer information to obtain summarized data;
the summarized data is converted into a high-density subgraph.
Optionally, the storage module 304 may be further specifically configured to:
classifying the data after the marks are gathered according to preset attribute categories to obtain classified data;
writing the classified data into a preset hash table to obtain data to be stored, and carrying out fragmentation processing on the data to be stored to obtain fragmented data;
and creating an index of the fragment data to obtain index data, and writing the index data into a preset storage file of a preset product database to obtain target product data.
Optionally, the classification module 301 may be further specifically configured to:
acquiring product data to be processed, and performing semantic recognition on the product data to be processed through a preset semantic recognition model to obtain recognition data;
and calling a preset character type decision tree and a preset digital type decision tree according to the data type, and respectively matching and extracting the identification data to obtain initial text type data and initial numerical type data.
Optionally, the first processing module 302 may be further specifically configured to:
converting the data type of the initial numerical data into a preset data type through a preset artificial neural network model to obtain converted numerical data;
acquiring a target field of the converted numerical data, and identifying and acquiring a field name corresponding to the target field in a preset field table;
the conversion numerical type data and the field name are determined as candidate numerical data.
Optionally, the processing apparatus of the product data further includes:
and the update optimization module 308 is configured to acquire interest product data based on the recommended product data, update the preset product database according to the interest product data, and optimize an execution process of the target product data.
The functional implementation of each module and each unit in the processing apparatus for product data corresponds to each step in the processing method embodiment for product data, and the functions and implementation processes thereof are not described in detail herein.
In the embodiment of the invention, the product type classification and the numerical data classification based on the text type data of the product data to be processed in various classification modes are realized, the systematic analysis and planning are carried out on the product data to be processed, the accuracy of the classification and the labeling of the product data to be processed is improved, so the accuracy of the product data after the intelligent recommendation processing is improved, the corresponding client group data is matched from the target product data according to the retrieval information of the user, the product attribute clustering analysis is carried out on the client group data through the preset clustering algorithm, the total search and the screening are carried out on the preset product data in the preset product database according to the target product attribute, the accurate matching of the recommended product data required by the user is realized, the matching efficiency of the product data is improved, the recommended product data required by the user can be analyzed from multiple dimensions, and the recommended product data required by the user is deeply mined, so that the intelligent recommendation accuracy of the processed product data is improved on the basis of improving the accuracy of the product data processed based on intelligent recommendation.
Fig. 3 and fig. 4 describe the processing apparatus of the product data in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the following describes the processing apparatus of the product data in the embodiment of the present invention in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a product data processing device according to an embodiment of the present invention, where the product data processing device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations in the processing device 500 for product data. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the processing device 500 for the product data.
The product data processing device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the processing device configuration of the product data shown in fig. 5 does not constitute a limitation of the processing device of the product data, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the method of processing product data.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit 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 invention may be embodied in the form of a software product, which is stored in a storage medium and includes 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 invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing product data is characterized by comprising the following steps:
the method comprises the steps of obtaining product data to be processed, classifying the product data to be processed according to data types, and obtaining initial text type data and initial numerical type data;
performing semantic escaping and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and passenger group positioning information;
and storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain target product data.
2. The method for processing product data according to claim 1, wherein the classifying type labeling and summarizing the candidate text data and the candidate numerical data comprises:
carrying out product type labeling on the candidate text data through a preset labeling algorithm, and carrying out labeling numerical calculation and numerical labeling on the candidate numerical data to obtain data to be summarized;
acquiring customer information of the product data to be processed, and classifying the data to be summarized according to the customer information to obtain summarized data;
converting the summarized data into a high-density subgraph.
3. The method for processing product data according to claim 1, wherein the step of storing the data after the mark aggregation into a preset product database according to a preset attribute category to obtain target product data comprises:
classifying the data after the marks are gathered according to preset attribute categories to obtain classified data;
writing the classified data into a preset hash table to obtain data to be stored, and carrying out fragmentation processing on the data to be stored to obtain fragmented data;
and creating an index of the fragment data to obtain index data, and writing the index data into a preset storage file of a preset product database to obtain target product data.
4. The product data processing method according to claim 1, wherein the obtaining of the product data to be processed and the classifying of the product data to be processed according to data types to obtain initial text type data and initial numerical type data comprises:
acquiring product data to be processed, and performing semantic recognition on the product data to be processed through a preset semantic recognition model to obtain recognition data;
and calling a preset character type decision tree and a preset digital type decision tree according to the data type, and respectively matching and extracting the identification data to obtain initial text type data and initial numerical type data.
5. The method for processing product data according to claim 1, wherein the numerically processing the initial numerical data through a preset artificial neural network model to obtain candidate numerical data comprises:
converting the data type of the initial numerical data into a preset data type through a preset artificial neural network model to obtain converted numerical data;
acquiring a target field of the converted numerical data, and identifying and acquiring a field name corresponding to the target field in a preset field table;
and determining the conversion numerical data and the field name as candidate numerical data.
6. The method for processing product data according to any one of claims 1 to 5, wherein the step of storing the aggregated data of the marks into a preset product database according to a preset attribute category, and after obtaining the target product data, further comprises:
acquiring user retrieval information, and matching corresponding client group data from the target product data according to the user retrieval information, wherein the user retrieval information comprises user information and/or product scene information;
performing product attribute clustering analysis on the customer group data through a preset clustering algorithm to obtain target product attributes;
and according to the target product attribute, carrying out full search and screening on the preset product data in the preset product database to obtain recommended product data.
7. The method for processing product data according to claim 6, wherein after the full search and screening of the preset product data in the preset product database according to the target product attribute to obtain recommended product data, the method further comprises:
and obtaining interested product data based on the recommended product data, updating the preset product database according to the interested product data, and optimizing the execution process of the target product data.
8. A product data processing apparatus, characterized in that the product data processing apparatus comprises:
the classification module is used for acquiring product data to be processed and classifying the product data to be processed according to data types to obtain initial text type data and initial numerical type data;
the first processing module is used for performing semantic meaning transfer and semantic classification on the initial text type data through a preset language model to obtain candidate text data, and performing numerical processing on the initial numerical type data through a preset artificial neural network model to obtain candidate numerical data;
the second processing module is used for carrying out classification type marking and summarizing processing on the candidate text data and the candidate numerical data, wherein the marked and summarized data comprises product attributes and passenger group positioning information;
and the storage module is used for storing the data after the marks are gathered into a preset product database according to the preset attribute category to obtain the target product data.
9. A processing apparatus of product data, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause a processing device of the product data to perform the processing method of the product data according to any one of claims 1 to 7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a method of processing product data according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036535.4A CN112818215A (en) | 2021-01-12 | 2021-01-12 | Product data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036535.4A CN112818215A (en) | 2021-01-12 | 2021-01-12 | Product data processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112818215A true CN112818215A (en) | 2021-05-18 |
Family
ID=75868850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110036535.4A Pending CN112818215A (en) | 2021-01-12 | 2021-01-12 | Product data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112818215A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095604A (en) * | 2021-06-09 | 2021-07-09 | 平安科技（深圳）有限公司 | Fusion method, device and equipment of product data and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633030A (en) * | 2017-09-04 | 2018-01-26 | 深圳市华傲数据技术有限公司 | Credit estimation method and device based on data model |
| CN111625578A (en) * | 2020-05-26 | 2020-09-04 | 辽宁大学 | Feature extraction method suitable for time sequence data in cultural science and technology fusion field |
| CN112131449A (en) * | 2020-09-21 | 2020-12-25 | 西北大学 | Implementation method of cultural resource cascade query interface based on elastic search |
-
2021
- 2021-01-12 CN CN202110036535.4A patent/CN112818215A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633030A (en) * | 2017-09-04 | 2018-01-26 | 深圳市华傲数据技术有限公司 | Credit estimation method and device based on data model |
| CN111625578A (en) * | 2020-05-26 | 2020-09-04 | 辽宁大学 | Feature extraction method suitable for time sequence data in cultural science and technology fusion field |
| CN112131449A (en) * | 2020-09-21 | 2020-12-25 | 西北大学 | Implementation method of cultural resource cascade query interface based on elastic search |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095604A (en) * | 2021-06-09 | 2021-07-09 | 平安科技（深圳）有限公司 | Fusion method, device and equipment of product data and storage medium |
| CN113095604B (en) * | 2021-06-09 | 2021-09-10 | 平安科技（深圳）有限公司 | Fusion method, device and equipment of product data and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019214245A1 (en) | Information pushing method and apparatus, and terminal device and storage medium | |
| CN107066599B (en) | Similar listed company enterprise retrieval classification method and system based on knowledge base reasoning | |
| US7389306B2 (en) | System and method for processing semi-structured business data using selected template designs | |
| CN111445028A (en) | AI-driven transaction management system | |
| CN111767716B (en) | Method and device for determining enterprise multi-level industry information and computer equipment | |
| CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
| CN109558541B (en) | Information processing method and device and computer storage medium | |
| US8185536B2 (en) | Rank-order service providers based on desired service properties | |
| CN115002200B (en) | Message pushing method, device, equipment and storage medium based on user portrait | |
| US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
| CN113051291A (en) | Work order information processing method, device, equipment and storage medium | |
| CN113420018A (en) | User behavior data analysis method, device, equipment and storage medium | |
| CN114254201A (en) | Recommendation method for science and technology project review experts | |
| CN115098650A (en) | Comment information analysis method based on historical data model and related device | |
| KR20210033294A (en) | Automatic manufacturing apparatus for reports, and control method thereof | |
| CN111754208A (en) | Automatic screening method for recruitment resumes | |
| CN115187066A (en) | Risk identification method and device, electronic equipment and storage medium | |
| CN113837824A (en) | Information pushing method and system | |
| CN113591476A (en) | Data label recommendation method based on machine learning | |
| CN112818215A (en) | Product data processing method, device, equipment and storage medium | |
| CN107609921A (en) | A kind of data processing method and server | |
| Lo et al. | An emperical study on application of big data analytics to automate service desk business process | |
| CN112506930B (en) | Data insight system based on machine learning technology | |
| Fan et al. | Spatially enabled customer segmentation using a data classification method with uncertain predicates | |
| CN114065763A (en) | Event extraction-based public opinion analysis method and device and related components |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40046357 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |