CN112348417A - Marketing value evaluation method and device based on principal component analysis algorithm - Google Patents
Marketing value evaluation method and device based on principal component analysis algorithm Download PDFInfo
- Publication number
- CN112348417A CN112348417A CN202011403115.7A CN202011403115A CN112348417A CN 112348417 A CN112348417 A CN 112348417A CN 202011403115 A CN202011403115 A CN 202011403115A CN 112348417 A CN112348417 A CN 112348417A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- model
- obtaining
- marketing
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 125
- 238000000513 principal component analysis Methods 0.000 title claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012847 principal component analysis method Methods 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000012384 transportation and delivery Methods 0.000 description 3
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 2
- 244000046052 Phaseolus vulgaris Species 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000005252 bulbus oculi Anatomy 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/44—Statistical methods, e.g. probability models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Library & Information Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a marketing value evaluation method and device based on a principal component analysis algorithm, wherein the method comprises the following steps: obtaining first user information of which the level meets a preset requirement in a social contact platform; obtaining user portrait information according to the first user information; storing the user representation information in a base database; inputting the user portrait information into a first model, wherein the first model is a model which is established by using a principal component analysis algorithm and performing model training by taking data in the basic database as a sample; obtaining a first output result of the first model, wherein the first output result is a marketing value evaluation value of the first user; and obtaining a first instruction according to the marketing value evaluation value, wherein the first instruction is used for storing the marketing value evaluation value in the basic database. The technical problems that in the prior art, the evaluation dimension of the marketing value of the user of the social platform is single, and the accuracy of the evaluation result is low are solved.
Description
Technical Field
The invention relates to the technical field of component analysis, in particular to a marketing value evaluation method and device based on a principal component analysis algorithm.
Background
At present, principal component analysis is widely applied to many fields such as regional economic development evaluation, garment standard formulation, satisfaction evaluation, pattern recognition and the like, and is a common multivariate analysis method. Today, with the rapid development of social media, the use of KOL to improve advertising has become the most practical and common form of marketing for brand owners. KOL is a concept on marketing, generally defined as: persons who have more, more accurate product information, and are received or informed by the relevant group and have a greater impact on the purchasing behavior of that group. Public entertainment reaches a new height under the promotion of the internet, and the bean vermicelli and eyeball effect brought by the KOL is multiplied by the internet. KOL pronouns are chosen by almost all brands, thereby increasing awareness. At the same time, the KOL marketing difficulty also changes, and not all KOL impressions can receive value matching the impressions. It is therefore difficult to judge the marketing value of the social platform KOL from only the number of fans of the social platform KOL.
In the process of implementing the technical scheme of the invention in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:
the evaluation dimension of the marketing value of the user of the social platform is single, and the accuracy of the evaluation result is low.
Disclosure of Invention
The marketing value evaluation method and device based on the principal component analysis algorithm solve the technical problems that the evaluation dimension of the marketing value of a user of a social platform is single and the accuracy of an evaluation result is low in the prior art, and achieve the technical purpose that the marketing value of the user is evaluated in a multi-dimensional and accurate mode based on the principal component analysis algorithm.
The embodiment of the application provides a marketing value evaluation method based on a principal component analysis algorithm, wherein the method comprises the following steps: acquiring first user information according to a preset requirement, wherein the first user is a user meeting the preset requirement in the social platform; obtaining user portrait information according to the first user information; storing the user representation information in a base database; inputting the user portrait information into a first model, wherein the first model is a model which is established by using a principal component analysis algorithm and performing model training by taking data in the basic database as a sample; obtaining a first output result of the first model, wherein the first output result is a marketing value evaluation value of the first user; and obtaining a first instruction according to the marketing value evaluation value, wherein the first instruction is used for storing the marketing value evaluation value in the basic database.
In another aspect, the present application further provides a marketing value evaluation device based on a principal component analysis algorithm, wherein the device includes: the first obtaining unit is used for obtaining first user information according to a preset requirement, and the first user is a user meeting the preset requirement in the social platform; a second obtaining unit, configured to obtain user portrait information according to the first user information; a first storage unit to store the user representation information in a base database; the first input unit is used for inputting the user portrait information into a first model, and the first model is a model which is established by using a principal component analysis algorithm and is subjected to model training by taking data in the basic database as samples; a third obtaining unit, configured to obtain a first output result of the first model, where the first output result is a marketing value evaluation value of the first user; a fourth obtaining unit, configured to obtain a first instruction according to the marketing value assessment value, where the first instruction is used to store the marketing value assessment value in the basic database.
On the other hand, the embodiment of the present application further provides a marketing value evaluation device based on a principal component analysis algorithm, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
because the user portrait is established from multiple dimensions and is input into the principal component analysis model for training, the training model can continuously optimize learning and obtain experience to process more accurate data, so that more accurate evaluation value of the marketing value of the user is obtained, and the evaluation value is stored in the basic database. Through the principal component analysis method, the influence factors of the marketing value of the user are reasonably judged, and the most main influence factors are analyzed, so that a reasonable suggestion is provided for marketing planning of the social platform. The technical purpose of multi-dimensional and accurate evaluation of the marketing value of the user based on the principal component analysis algorithm is achieved.
The foregoing is a summary of the present disclosure, and embodiments of the present disclosure are described below to make the technical means of the present disclosure more clearly understood.
Drawings
Fig. 1 is a schematic flowchart of a marketing value evaluation method based on a principal component analysis algorithm according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a marketing value evaluation device based on a principal component analysis algorithm according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a first storage unit 13, a first input unit 14, a third obtaining unit 15, a fourth obtaining unit 16, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 305.
Detailed Description
The marketing value evaluation method and device based on the principal component analysis algorithm solve the technical problems that the evaluation dimension of the marketing value of a user of a social platform is single and the accuracy of an evaluation result is low in the prior art, and achieve the technical purpose that the marketing value of the user is evaluated in a multi-dimensional and accurate mode based on the principal component analysis algorithm. Hereinafter, example embodiments of the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
Today, with the rapid development of social media, the use of KOL to improve advertising has become the most practical and common form of marketing for brand owners. Public entertainment reaches a new height under the promotion of the internet, and the bean vermicelli and eyeball effect brought by the KOL is multiplied by the internet. KOL pronouns are chosen by almost all brands, thereby increasing awareness. Meanwhile, the KOL marketing difficulty also changes, not all KOL deliveries can obtain the value matched with the deliveries, and the delivery capacity of the social platform KOL is difficult to judge only from the number of fans of the social platform KOL. The technical problems that the evaluation dimension of the marketing value of the user of the social platform is single and the accuracy of the evaluation result is low exist in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a marketing value evaluation method based on a principal component analysis algorithm, wherein the method comprises the following steps: acquiring first user information according to a preset requirement, wherein the first user is a user meeting the preset requirement in the social platform; obtaining user portrait information according to the first user information; storing the user representation information in a base database; inputting the user portrait information into a first model, wherein the first model is a model which is established by using a principal component analysis algorithm and performing model training by taking data in the basic database as a sample; obtaining a first output result of the first model, wherein the first output result is a marketing value evaluation value of the first user; and obtaining a first instruction according to the marketing value evaluation value, wherein the first instruction is used for storing the marketing value evaluation value in the basic database.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a marketing value evaluation method based on a principal component analysis algorithm, where the method includes:
step S100: acquiring first user information according to a preset requirement, wherein the first user is a user meeting the preset requirement in the social platform;
specifically, in the embodiment of the application, the information of the first user is acquired by an information acquisition platform of a social platform, wherein the information includes related data such as the number of fans of the first user, regional information, identity information and interaction data. The preset requirement is level threshold information of a first user for marketing value evaluation preset by the platform, for example, a threshold value of the number of fans, a threshold value of interaction data and the like are set as the preset requirement, and then marketing value evaluation is performed on the users meeting the preset requirement. For example, the social platform such as a microblog and a KOL information acquisition platform of a microblog is used for crawling a KOL of the microblog, namely information data of a microblog large V user, from the microblog and storing the acquired KOL data information into the basic database.
Step S200: obtaining user portrait information according to the first user information;
specifically, the first user information obtained by the information acquisition platform of the social platform is used for establishing portrait information of the first user by a user portrait platform. The user portrait information is obtained by a user portrait platform of the social platform, is an effective tool for outlining customers and connecting customer appeal and design directions, and is used for classifying all user information. For example, the microblog KOL portrait platform performs domain portrait related analysis and fan portrait related analysis on the acquired microblog KOL information, so that the marketing value of the user is further analyzed. By establishing the portrait information of each user, the client information can be accurately mastered, and a foundation is laid for subsequent marketing value evaluation.
Step S300: storing the user representation information in a base database;
specifically, the basic database provides the first user basic information and fans and other related data of the social platform required by the user marketing value evaluation, and stores all data generated in the evaluation process. And after the user portrait information is obtained by a user portrait platform of the social platform, storing the user portrait information in the basic database for reading data from the basic database in the subsequent marketing value evaluation of the first user.
Step S400: inputting the user portrait information into a first model, wherein the first model is a model which is established by using a principal component analysis algorithm and performing model training by taking data in the basic database as a sample;
step S500: obtaining a first output result of the first model, wherein the first output result is a marketing value evaluation value of the first user;
specifically, the principal component analysis algorithm is a common mathematical statistical method, in which a set of variables possibly having correlation is converted into a set of linearly uncorrelated variables through orthogonal transformation, and the converted set of variables is called a principal component. The user portrait information comprises a plurality of variables, and when marketing value evaluation is carried out, evaluation complexity is increased, redundant repeated variables in the user portrait are eliminated through a principal component analysis method, and new variables are established as few as possible. And after the first user portrait information is read from the basic database by a social platform user marketing value evaluation analysis platform, inputting the user portrait information into the first model so as to obtain the marketing value evaluation value information of the first user. The first model is a model which is established by using a principal component analysis algorithm through model training by taking data in the basic database as samples. The first model is a machine learning model, after the user portrait information is input into the first model, the first model outputs marketing value evaluation value identification information of the first user to verify the marketing value evaluation value of the first user output by the first model, and if the output marketing value evaluation value of the first user is consistent with the marketing value evaluation value of the first user, the data supervised learning is finished, and then the next group of data supervised learning is carried out; and if the output marketing value evaluation value of the first user is inconsistent with the identified marketing value evaluation value of the first user, adjusting the first model by the first model, and performing supervised learning of the next group of data until the first model reaches an expected accuracy. For example, the microblog KOL marketing value evaluation analysis platform is used for reading information of microblog KOLs in various fields from a basic database, and further analyzing marketing values of the microblog KOLs in the various fields through the first model. Based on the characteristic that the first model can continuously optimize learning and obtain 'experience' to process data more accurately, the marketing value evaluation value of the first user can be obtained more accurately.
Step S600: and obtaining a first instruction according to the marketing value evaluation value, wherein the first instruction is used for storing the marketing value evaluation value in the basic database.
Specifically, after the marketing value evaluation value of the first user is obtained through the first model by the social platform user marketing value evaluation analysis platform, the obtained information of the marketing value evaluation value of the first user is stored in the basic database. And the subsequent management and analysis of data by the social platform are facilitated.
Further, before the inputting the user portrait information into the first model, embodiment S400 of the present application further includes:
step S401: obtaining model configuration parameters;
step S402: obtaining model training data according to the model configuration parameters and the basic database;
step S403: and obtaining first modeling information according to the model training data, wherein the first modeling information is used for performing the first model training by taking the model training data as a sample.
Specifically, the user marketing value evaluation system performs model training by establishing the first model, using data in an existing basic database as a sample, and performs modeling using the principal component analysis algorithm. Model configuration parameters of the first model are obtained by a data management center of the social platform. Obtaining model training data according to the model configuration parameters and the basic database, obtaining first modeling information according to the model training data, further obtaining the first model, and performing the first model training by using the model training data as a sample. The accuracy of the user marketing value evaluation system data acquisition is enhanced.
Further, step S200 in the embodiment of the present application further includes:
step S201: acquiring first text information according to the first user information;
step S202: obtaining a first user field category according to the first text information;
step S203: and storing the first user field type into the basic database.
Specifically, the purpose of text word segmentation is to perform word segmentation on a test text according to a certain rule through a mechanical word segmentation method, an artificial intelligence word segmentation method and the like, so that the feature value of the text is conveniently extracted, and a word group with feature value comparison is provided for the text. After the social platform user information acquisition platform acquires the data information of the first user, text word segmentation is carried out according to the published content of the first user on the social platform, and the category of the first user field is acquired through analysis. And respectively storing the obtained first user field types into the basic database. For example, the microblog KOL relates to a field portrait unit, the module is used for analyzing the popularization of the microblog KOL and relates to the field, and text word segmentation is mainly performed according to the released microblog of the microblog KOL to classify the field related to each microblog KOL.
Further, step S201 in the embodiment of the present application further includes:
step S2011: acquiring first fan information according to the first user information;
step S2012: acquiring first fan attribute information according to the first fan information;
step S2013: inputting the first fan attribute information into a second model, wherein the second model is a model which takes a large amount of fan attribute information as samples for training;
step S2014: obtaining a second output result of the second model, wherein the second output result is fan portrait information of the first user;
step S2015: and storing the fan portrait information into the basic database, wherein the user portrait information comprises the first user field category and the first user fan portrait information.
Specifically, the user portrait information is divided into a field portrait unit and a fan portrait unit. The fan portrait unit is obtained by inputting the first fan attribute information into the second training model, the second model is used for analyzing relevant attribute information of the fan social attribute, the age level, the consumption behavior and the like of the first user fan, the second model is used for analyzing and obtaining the fan portrait information, and the obtained first user fan portrait information is stored in the basic database. Wherein the second model is a clustering model, such as a random forest and a neural network. The cluster analysis refers to an analysis process of grouping a set of physical or abstract objects into a plurality of classes composed of similar objects, the random forest refers to a classifier which trains and predicts samples by using a plurality of trees, and the neural network model is a mathematical model or a calculation model which imitates the structure and the function of a biological neural network. For example, the microblog KOL fan imaging unit is used for analyzing relevant attribute information such as social attributes, age levels and consumption behaviors of microblog KOL fans, and storing the final image data of the microblog KOL fans into the basic database by using a clustering model (such as a random forest and a neural network).
Further, before obtaining the first execution instruction, step S203 in this embodiment of the present application further includes:
step S2031: obtaining a first marketing value evaluation value, a second marketing value evaluation value and an Nth marketing value evaluation value from the basic database, wherein N is a natural number greater than 1;
step S2032: obtaining corresponding user field categories according to the first marketing value evaluation value, the second marketing value evaluation value and the Nth marketing value evaluation value respectively;
step S2033: obtaining first classification information according to the user field category, wherein the first classification information is used for classifying the first marketing value evaluation value, the second marketing value evaluation value and the Nth marketing value evaluation value according to the user field to obtain a plurality of field marketing value evaluation value sets;
step S2034: ranking the marketing value evaluation values in the field marketing value evaluation value set to obtain a ranking list of the marketing value of each field;
step S2035: and obtaining first display information according to the marketing value ranking list in each field, wherein the first display information is used for displaying the marketing value ranking list in each field and storing the marketing value ranking list in the basic database.
Specifically, after the obtained user marketing value evaluation values and the user image information are stored in the basic database, the marketing value evaluation values of the N users are in one-to-one correspondence with the user field categories, and the marketing value evaluation values are classified according to the user field categories to obtain the plurality of field marketing value evaluation value sets. And ranking the marketing value evaluation values in the field marketing value evaluation value set to obtain a ranking list of the marketing value of each field, storing the ranking list into the basic database, and displaying the users through the social platform. For example, a microblog KOL marketing value scoring system is established, a marketing value ranking list of microblog KOLs in various fields is generated, a brand owner can be helped to greatly improve the probability of finding high-value microblog KOLs, and compared with methods that the brand owner selects only through the number of fans and the like, the method provided by the invention is more efficient and accurate, and the microblog KOLs are comprehensively evaluated for marketing value.
Further, step S202 in the embodiment of the present application further includes:
step S2021: obtaining first text word segmentation information according to the first text information;
step S2022: obtaining a first text vocabulary level and a first text vocabulary frequency according to the first text word segmentation information;
step S2023: and obtaining the first user field category according to the first text vocabulary level and the first text vocabulary frequency.
Specifically, the social platform user information acquisition platform performs word segmentation on the first text according to a certain rule through a mechanical word segmentation method, an artificial intelligence word segmentation method and the like, extracts characteristic values of the first text, including word level and word frequency information of the first text, and obtains the field category information of the first user by analyzing and counting the word level and the word frequency. For example, the field portrait unit of the microblog is used for analyzing popularization of the microblog KOL, and relates to the field, text word segmentation is mainly performed according to a microblog issued by the microblog KOL, statistics is performed according to vocabulary levels and frequency, and classification is performed on the field related to each microblog KOL.
In summary, the marketing value evaluation method based on the principal component analysis algorithm provided by the embodiment of the application has the following technical effects:
because the user portrait is established from multiple dimensions and is input into the principal component analysis model for training, the training model can continuously optimize learning and obtain experience to process more accurate data, so that more accurate evaluation value of the marketing value of the user is obtained, and the evaluation value is stored in the basic database. Through the principal component analysis method, the influence factors of the marketing value of the user are reasonably judged, and the most main influence factors are analyzed, so that a reasonable suggestion is provided for marketing planning of the social platform. The technical purpose of multi-dimensional and accurate evaluation of the marketing value of the user based on the principal component analysis algorithm is achieved.
Example two
Based on the same inventive concept as the marketing value evaluation method based on the principal component analysis algorithm in the foregoing embodiment, the present invention further provides a marketing value evaluation device based on the principal component analysis algorithm, as shown in fig. 2, the device includes:
the first obtaining unit 11 is configured to obtain first user information according to a preset requirement, where the first user is a user in the social platform, and the level of the first user meets the preset requirement;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain user portrait information according to the first user information;
a first storage unit 13, the first storage unit 13 being configured to store the user portrait information in a base database;
a first input unit 14, where the first input unit 14 is configured to input the user portrait information into a first model, where the first model is a model created by using a principal component analysis algorithm and performing model training using data in the basic database as a sample;
a third obtaining unit 15, where the third obtaining unit 15 is configured to obtain a first output result of the first model, where the first output result is a marketing value evaluation value of the first user;
a fourth obtaining unit 16, wherein the fourth obtaining unit 16 is configured to obtain a first instruction according to the marketing value assessment value, and the first instruction is configured to store the marketing value assessment value in the basic database.
Further, the apparatus further comprises:
a fifth obtaining unit, configured to obtain a model configuration parameter;
a sixth obtaining unit, configured to obtain model training data according to the model configuration parameters and the basic database;
a seventh obtaining unit, configured to obtain first modeling information according to the model training data, where the first modeling information is used to perform the first model training by using the model training data as a sample.
Further, the apparatus further comprises:
an eighth obtaining unit, configured to obtain first text information according to the first user information;
a ninth obtaining unit, configured to obtain a first user domain category according to the first text information;
a second storage unit to store the first user domain category in the base database.
Further, the apparatus further comprises:
a tenth obtaining unit, configured to obtain first fan information according to the first user information;
an eleventh obtaining unit, configured to obtain first fan attribute information according to the first fan information;
the second input unit is used for inputting the first fan attribute information into a second model, and the second model is trained by taking a large amount of fan attribute information as samples;
a twelfth obtaining unit, configured to obtain a second output result of the second model, where the second output result is fan portrait information of the first user;
and the third storage unit is used for storing the fan portrait information into the basic database, wherein the user portrait information comprises the first user field type and the first user fan portrait information.
Further, the apparatus further comprises:
a thirteenth obtaining unit configured to obtain a first marketing value evaluation value, a second marketing value evaluation value, and up to an nth marketing value evaluation value from the basic database, where N is a natural number greater than 1;
a fourteenth obtaining unit, configured to obtain corresponding user domain categories according to the first marketing value evaluation value, the second marketing value evaluation value, and up to an nth marketing value evaluation value, respectively;
a fifteenth obtaining unit, configured to obtain first classification information according to the user domain category, where the first classification information is used to classify the first marketing value evaluation value, the second marketing value evaluation value, and up to an nth marketing value evaluation value according to a user domain, so as to obtain a plurality of domain marketing value evaluation value sets;
a sixteenth obtaining unit, configured to rank the marketing value evaluation values in the field marketing value evaluation value sets, and obtain a ranking list of the marketing values in each field;
a seventeenth obtaining unit, configured to obtain first display information according to the marketing value ranking list in each field, where the first display information is used to display the marketing value ranking list in each field and is stored in the basic database.
Further, the apparatus further comprises:
an eighteenth obtaining unit, configured to obtain first text word segmentation information according to the first text information;
a nineteenth obtaining unit, configured to obtain a first text vocabulary level and a first text vocabulary frequency according to the first text word segmentation information;
a twentieth obtaining unit, configured to obtain the first user domain category according to the first text vocabulary level and the first text vocabulary frequency.
Further, the apparatus further comprises:
a twenty-first obtaining unit, configured to obtain the second model, where the second model is a clustering model.
Various changes and specific examples of the marketing value evaluation method based on the principal component analysis algorithm in the first embodiment of fig. 1 are also applicable to the marketing value evaluation device based on the principal component analysis algorithm in the present embodiment, and through the foregoing detailed description of the marketing value evaluation method based on the principal component analysis algorithm, those skilled in the art can clearly know the marketing value evaluation device based on the principal component analysis algorithm in the present embodiment, so for the brevity of the description, details are not described here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the marketing value evaluation method based on the principal component analysis algorithm in the foregoing embodiments, the present invention further provides a marketing value evaluation device based on the principal component analysis algorithm, on which a computer program is stored, which when executed by a processor implements the steps of any one of the foregoing marketing value evaluation methods based on the principal component analysis algorithm.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A marketing value evaluation method based on a principal component analysis algorithm, wherein the method comprises the following steps:
acquiring first user information according to a preset requirement, wherein the first user is a user meeting the preset requirement in the social platform;
obtaining user portrait information according to the first user information;
storing the user representation information in a base database;
inputting the user portrait information into a first model, wherein the first model is a model which is established by using a principal component analysis algorithm and performing model training by taking data in the basic database as a sample;
obtaining a first output result of the first model, wherein the first output result is a marketing value evaluation value of the first user;
and obtaining a first instruction according to the marketing value evaluation value, wherein the first instruction is used for storing the marketing value evaluation value in the basic database.
2. The method of claim 1, wherein said entering said user representation information into a first model comprises, prior to:
obtaining model configuration parameters;
obtaining model training data according to the model configuration parameters and the basic database;
and obtaining first modeling information according to the model training data, wherein the first modeling information is used for performing the first model training by taking the model training data as a sample.
3. The method of claim 1, wherein said obtaining user representation information based on said first user information comprises:
acquiring first text information according to the first user information;
obtaining a first user field category according to the first text information;
and storing the first user field type into the basic database.
4. The method of claim 3, wherein said obtaining user representation information based on said first user information further comprises:
acquiring first fan information according to the first user information;
acquiring first fan attribute information according to the first fan information;
inputting the first fan attribute information into a second model, wherein the second model is a model which takes a large amount of fan attribute information as samples for training;
obtaining a second output result of the second model, wherein the second output result is fan portrait information of the first user;
and storing the fan portrait information into the basic database, wherein the user portrait information comprises the first user field category and the first user fan portrait information.
5. The method of claim 3, wherein the method comprises:
obtaining a first marketing value evaluation value, a second marketing value evaluation value and an Nth marketing value evaluation value from the basic database, wherein N is a natural number greater than 1;
obtaining corresponding user field categories according to the first marketing value evaluation value, the second marketing value evaluation value and the Nth marketing value evaluation value respectively;
obtaining first classification information according to the user field category, wherein the first classification information is used for classifying the first marketing value evaluation value, the second marketing value evaluation value and the Nth marketing value evaluation value according to the user field to obtain a plurality of field marketing value evaluation value sets;
ranking the marketing value evaluation values in the field marketing value evaluation value set to obtain a ranking list of the marketing value of each field;
and obtaining first display information according to the marketing value ranking list in each field, wherein the first display information is used for displaying the marketing value ranking list in each field and storing the marketing value ranking list in the basic database.
6. The method of claim 3, wherein the obtaining a first user area category from the first textual information comprises:
obtaining first text word segmentation information according to the first text information;
obtaining a first text vocabulary level and a first text vocabulary frequency according to the first text word segmentation information;
and obtaining the first user field category according to the first text vocabulary level and the first text vocabulary frequency.
7. The method of claim 4, wherein the second model is a clustering model.
8. A marketing value evaluation apparatus based on a principal component analysis algorithm, wherein the apparatus comprises:
the first obtaining unit is used for obtaining first user information according to a preset requirement, and the first user is a user meeting the preset requirement in the social platform;
a second obtaining unit, configured to obtain user portrait information according to the first user information;
a first storage unit to store the user representation information in a base database;
the first input unit is used for inputting the user portrait information into a first model, and the first model is a model which is established by using a principal component analysis algorithm and is subjected to model training by taking data in the basic database as samples;
a third obtaining unit, configured to obtain a first output result of the first model, where the first output result is a marketing value evaluation value of the first user;
a fourth obtaining unit, configured to obtain a first instruction according to the marketing value assessment value, where the first instruction is used to store the marketing value assessment value in the basic database.
9. A device for assessing marketing value based on a principal component analysis algorithm, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403115.7A CN112348417A (en) | 2020-12-04 | 2020-12-04 | Marketing value evaluation method and device based on principal component analysis algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403115.7A CN112348417A (en) | 2020-12-04 | 2020-12-04 | Marketing value evaluation method and device based on principal component analysis algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112348417A true CN112348417A (en) | 2021-02-09 |
Family
ID=74428093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011403115.7A Pending CN112348417A (en) | 2020-12-04 | 2020-12-04 | Marketing value evaluation method and device based on principal component analysis algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348417A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598405A (en) * | 2021-02-20 | 2021-04-02 | 汇正(广州)企业管理咨询有限公司 | Business project data management method and system based on big data |
| CN113362108A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN113360717A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Intelligent thread processing method and system |
| CN113407913A (en) * | 2021-05-31 | 2021-09-17 | 南京触手科技有限公司 | Creative work management method and system based on digital watermark |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063945A (en) * | 2018-06-08 | 2018-12-21 | 广州亦云信息技术股份有限公司 | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system |
| CN109636128A (en) * | 2018-11-19 | 2019-04-16 | 国家电网有限公司客户服务中心 | A kind of optimization method of dot number and structure based on business hall measures of effectiveness |
| CN110334929A (en) * | 2019-06-25 | 2019-10-15 | 阿里巴巴集团控股有限公司 | Internet enterprises estimation method and system based on alternative data |
-
2020
- 2020-12-04 CN CN202011403115.7A patent/CN112348417A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063945A (en) * | 2018-06-08 | 2018-12-21 | 广州亦云信息技术股份有限公司 | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system |
| CN109636128A (en) * | 2018-11-19 | 2019-04-16 | 国家电网有限公司客户服务中心 | A kind of optimization method of dot number and structure based on business hall measures of effectiveness |
| CN110334929A (en) * | 2019-06-25 | 2019-10-15 | 阿里巴巴集团控股有限公司 | Internet enterprises estimation method and system based on alternative data |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598405A (en) * | 2021-02-20 | 2021-04-02 | 汇正(广州)企业管理咨询有限公司 | Business project data management method and system based on big data |
| CN113407913A (en) * | 2021-05-31 | 2021-09-17 | 南京触手科技有限公司 | Creative work management method and system based on digital watermark |
| CN113407913B (en) * | 2021-05-31 | 2022-04-12 | 南京触手科技有限公司 | Creative work management method and system based on digital watermark |
| CN113362108A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN113360717A (en) * | 2021-06-02 | 2021-09-07 | 北京国联视讯信息技术股份有限公司 | Intelligent thread processing method and system |
| CN113362108B (en) * | 2021-06-02 | 2023-12-29 | 北京国联视讯信息技术股份有限公司 | Accurate operation method and system based on artificial intelligence |
| CN113360717B (en) * | 2021-06-02 | 2024-05-14 | 北京国联视讯信息技术股份有限公司 | Intelligent clue processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hackeling | Mastering Machine Learning with scikit-learn | |
| CN112348417A (en) | Marketing value evaluation method and device based on principal component analysis algorithm | |
| CN112036550B (en) | Client intention identification method and device based on artificial intelligence and computer equipment | |
| CN111949787A (en) | Automatic question-answering method, device, equipment and storage medium based on knowledge graph | |
| Malik et al. | Applied unsupervised learning with R: Uncover hidden relationships and patterns with k-means clustering, hierarchical clustering, and PCA | |
| CN110263248B (en) | Information pushing method, device, storage medium and server | |
| EP2866421A1 (en) | Method and apparatus for identifying a same user in multiple social networks | |
| CN109299258A (en) | A kind of public sentiment event detecting method, device and equipment | |
| CN113722474A (en) | Text classification method, device, equipment and storage medium | |
| CN110598070A (en) | Application type identification method and device, server and storage medium | |
| CN112487284A (en) | Bank customer portrait generation method, equipment, storage medium and device | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN110162609A (en) | For recommending the method and device asked questions to user | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN114416929A (en) | Sample generation method, device, equipment and storage medium of entity recall model | |
| CN112598405B (en) | Business project data management method and system based on big data | |
| CN114398909A (en) | Question generation method, device, equipment and storage medium for dialogue training | |
| CN118014622A (en) | Advertisement pushing method and system based on user portrait | |
| CN113704623A (en) | Data recommendation method, device, equipment and storage medium | |
| CN111222566B (en) | User attribute identification method, device and storage medium | |
| Hidayat et al. | Determine Felder Silverman learning style model using literature based and K-means clustering | |
| CN110717787A (en) | User classification method and device | |
| CN112580348B (en) | Policy text relevance analysis method and system | |
| CN115129834A (en) | Question answering method and system | |
| KR20230049486A (en) | Political tendency analysis device and service providing method using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |