CN113222484A - Method and system for generating marketing task based on big data analysis - Google Patents

Method and system for generating marketing task based on big data analysis Download PDF

Info

Publication number
CN113222484A
CN113222484A CN202110774651.6A CN202110774651A CN113222484A CN 113222484 A CN113222484 A CN 113222484A CN 202110774651 A CN202110774651 A CN 202110774651A CN 113222484 A CN113222484 A CN 113222484A
Authority
CN
China
Prior art keywords
marketing
marketed
big data
product
determining
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
Application number
CN202110774651.6A
Other languages
Chinese (zh)
Inventor
张莹
周明智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Entertainment Interactive Technology Beijing Co ltd
Original Assignee
Entertainment Interactive Technology Beijing Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Entertainment Interactive Technology Beijing Co ltd filed Critical Entertainment Interactive Technology Beijing Co ltd
Priority to CN202110774651.6A priority Critical patent/CN113222484A/en
Publication of CN113222484A publication Critical patent/CN113222484A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • 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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities

Abstract

The invention discloses a method and a system for generating a marketing task based on big data analysis, wherein the method comprises the following steps: acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed; acquiring second big data of an object having a competitive or mutual profit relationship with the object to be marketed; performing data fusion on the first big data and the second big data, and performing data cleaning to obtain practical big data; performing data analysis on the practical big data based on a deep neural network to obtain an analysis result; determining marketing content and a marketing propagation mode according to the analysis result; adopting the determined marketing propagation mode to carry out marketing propagation on the marketing content to form a marketing task for the object to be marketed; and performing task allocation on the marketing task based on the attribute characteristics of the object to be marketed. Therefore, the scheme can automatically generate the marketing task, can also improve the efficiency and the precision and improve the success rate of marketing.

Description

Method and system for generating marketing task based on big data analysis
Technical Field
The invention relates to the technical field of big data, in particular to a method and a system for generating a marketing task based on big data analysis.
Background
Big data is more and more widely applied, and big data-based marketing is an important field of big data application. Marketing based on big data needs analysis processing of massive user big data, the process of the analysis processing is called user portrait, and the user portrait results in that a series of labels are marked on the user, and the gender, age, consumption capability, interests and hobbies of the user are identified. The marketing process is to filter the target users based on the tags and then to send the specified content to the target users in an appropriate manner.
However, in the prior art, the marketing based on big data cannot realize the automatic generation of the marketing task, and manual intervention is needed to realize the generation of the marketing task, so a solution is urgently needed to solve the technical problem.
Disclosure of Invention
The invention provides a method and a system for generating a marketing task based on big data analysis, which are used for solving the technical problem that the marketing task cannot be automatically generated in the prior art.
The invention provides a method for generating a marketing task based on big data analysis, which comprises the following steps:
acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
acquiring second big data of an object having a competitive or mutual profit relationship with the object to be marketed;
performing data fusion on the first big data and the second big data, and performing data cleaning to obtain practical big data;
performing data analysis on the practical big data based on a deep neural network to obtain an analysis result;
determining marketing content and a marketing propagation mode according to the analysis result;
adopting the determined marketing propagation mode to carry out marketing propagation on the marketing content to form a marketing task for the object to be marketed;
and performing task allocation on the marketing task based on the attribute characteristics of the object to be marketed.
Optionally, the acquiring the first big data related to the object to be marketed includes:
determining self-positioning of an object to be marketed and first network public opinion information;
determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
determining KPI indexes of an object to be marketed and positioning information of a product to be marketed in the market;
the obtaining of the second big data of the object having competition or mutual interest relation with the object to be marketed comprises:
determining competitive objects and/or mutual interest objects of the objects to be marketed;
determining second network public opinion information of competitive objects and/or mutual interest objects;
relevant product information of competing objects and/or mutually beneficial objects is determined.
Optionally, in the determining marketing content and marketing propagation manner according to the analysis result, the method for determining marketing content includes:
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a character content with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a picture with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a video or a short video with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a spreading title to guide public opinion;
the marketing propagation mode determining method comprises the following steps:
putting the marketing content as articles on each platform;
putting the marketing content as an advertisement on each website or ground promotion platform with a spreading degree;
performing official response on the marketing content to improve the spreading degree;
and receiving feedback of the user and performing interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
Optionally, after the marketing transmission is performed on the marketing content by using the determined marketing transmission mode to form a marketing task for the object to be marketed, the method includes:
a marketing task detection model is constructed in advance;
inputting the formed marketing tasks into the model, and determining grade values of the marketing tasks;
if the grading value is lower than a preset value, respectively acquiring third big data and fourth big data based on an object to be marketed and an object having a competition or mutual profit relationship with the object to be marketed, and generating a new marketing task according to the newly acquired third big data and fourth big data;
inputting the generated new marketing tasks into the model until the grading value of the marketing tasks is equal to or higher than a preset value, and setting the corresponding marketing tasks as final marketing tasks;
after the task allocation is carried out on the marketing task based on the attribute characteristics of the object to be marketed, the method comprises the following steps:
determining the completion condition and marketing efficiency of the marketing task;
evaluating the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency;
and adjusting the task allocation according to the evaluation.
Optionally, the inputting the formed marketing task into the model, and determining a rating value of the marketing task includes:
determining a matching degree relation between a user and a product aiming at the marketing task;
according to the matching degree relation, determining the matching degree between the user and the product based on the following formula:
Figure DEST_PATH_IMAGE001
Figure 260693DEST_PATH_IMAGE002
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure DEST_PATH_IMAGE003
for the u-th user matrix, the user matrix,
Figure 36888DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 754308DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 680676DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 419349DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 648336DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 446528DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 301220DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 501258DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 166725DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 452213DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 845017DEST_PATH_IMAGE015
respectively being a matrix of degree of matchVariance, variance of user matrix and variance of product matrix, I is shorthand for indicating function; pi is a product symbol;
determining a rating value for the marketing task based on the degree of matching;
assessing the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency, comprising:
determining the estimated scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the real scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the true score similarity of each member and the adjacent members;
updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 40506DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 1509DEST_PATH_IMAGE017
the estimated score for the member update is updated,
Figure 898927DEST_PATH_IMAGE018
in order to estimate the score of the object,
Figure DEST_PATH_IMAGE019
in order to be a true score,
Figure 377313DEST_PATH_IMAGE020
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and when the number of members with the estimated scores higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is reasonable.
The invention also provides a system for generating marketing tasks based on big data analysis, which comprises:
the system comprises a first big data acquisition unit, a second big data acquisition unit and a marketing unit, wherein the first big data acquisition unit is used for acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
the second big data acquisition unit is used for acquiring second big data of an object having competition or mutual profit relation with the object to be marketed by a user;
the data fusion cleaning unit is used for carrying out data fusion on the first big data and the second big data and cleaning the data to obtain practical big data;
the data analysis unit is used for carrying out data analysis on the practical big data based on the deep neural network to obtain an analysis result;
the determining unit is used for determining marketing content and marketing propagation modes according to the analysis result;
the marketing task generating unit is used for carrying out marketing propagation on the marketing content by adopting the determined marketing propagation mode to form a marketing task aiming at a to-be-marketed object;
and the task allocation unit is used for allocating tasks to the marketing tasks based on the attribute characteristics of the objects to be marketed.
Optionally, the first big data unit includes:
the first network public opinion information determining subunit is used for determining the self-positioning of the object to be marketed and the first network public opinion information;
the information determining subunit is used for determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
the positioning information determining subunit is used for determining KPI (Key performance indicator) of the object to be marketed and positioning information of the product to be marketed in the market;
the second big data unit includes:
the competitive object determining subunit is used for determining a competitive object and/or a mutual interest object of the object to be marketed;
the second network public opinion information determining subunit is used for determining second network public opinion information of the competitive object and/or the mutual interest object;
and the related product information determining subunit is used for determining related product information of the competitive object and/or the mutual interest object.
Optionally, the determining unit includes:
the text content subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into text content with spreading performance;
the picture subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a picture with spreading property;
the video subunit is used for making key information or hotspot information of marketing promotion of the object to be marketed or the product to be marketed into a video or a short video with spreading performance;
the title subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a spreading title to guide public opinion;
the article releasing subunit is used for releasing the marketing content as an article on each platform;
the advertisement putting subunit is used for putting the marketing content as an advertisement on each website or ground promotion platform with the spreading degree;
the response subunit is used for carrying out official response on the marketing content to improve the propagation degree;
and the interactive feedback subunit receives the feedback of the user and carries out interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
Optionally, the method further includes:
the marketing task detection model construction unit is used for constructing a marketing task detection model in advance;
the grading value determining unit is used for inputting the formed marketing tasks into the model after marketing propagation is carried out on the marketing contents by adopting the determined marketing propagation mode to form marketing tasks aiming at objects to be marketed, and determining the grading value of the marketing tasks;
if the grading value is lower than a preset value, a user respectively acquires third big data and fourth big data based on an object to be marketed and an object having a competition or mutual interest relationship with the object to be marketed, and generates a new marketing task according to the newly acquired third big data and fourth big data;
the final marketing task determining unit is used for inputting the generated new marketing task into the model until the grading value of the marketing task is equal to or higher than a preset value, and setting the corresponding marketing task as the final marketing task;
the marketing efficiency determining unit is used for determining the completion condition and the marketing efficiency of the marketing task after the marketing task is subjected to task allocation based on the attribute characteristics of the object to be marketed;
the evaluation unit is used for evaluating the rationality of the distribution of the marketing tasks based on the completion condition and the marketing efficiency;
and the adjusting unit is used for adjusting the reasonability of the task allocation according to the evaluation.
Optionally, the scoring level value determining unit includes:
the matching degree relation determining subunit is used for determining the matching degree relation between the user and the product aiming at the marketing task;
the matching degree determining subunit is used for determining the matching degree between the user and the product according to the matching degree relation based on the following formula:
Figure 551942DEST_PATH_IMAGE021
Figure 545830DEST_PATH_IMAGE022
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure 946856DEST_PATH_IMAGE023
for the u th useThe matrix of users is a matrix of users,
Figure 556829DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure 710598DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 13404DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 370567DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 49810DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 58086DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 531793DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 641831DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 718240DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 721969DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 241943DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 963911DEST_PATH_IMAGE015
the variance of the matching degree matrix, the variance of the user matrix and the product momentVariance of the array, I is shorthand for indicating function; pi is a product symbol;
a grading value determination subunit, configured to determine a grading value of the marketing task based on the matching degree;
the evaluation unit includes:
the pre-estimation scoring determining subunit is used for determining the pre-estimation scoring of the marketing task completion and the marketing efficiency of each member in the team of the object to be marketed;
the real score determining subunit is used for determining the real score of each member in the team of the object to be marketed for completing the marketing task and the marketing efficiency;
the similarity determining subunit is used for determining the real score similarity of each member and the adjacent members;
and the estimated score updating subunit is used for updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 846941DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 439596DEST_PATH_IMAGE017
the estimated score for the member update is updated,
Figure 130472DEST_PATH_IMAGE018
in order to estimate the score of the object,
Figure 464370DEST_PATH_IMAGE019
in order to be a true score,
Figure 23527DEST_PATH_IMAGE020
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and the rationality judging subunit is used for judging that the distribution of the marketing tasks is rational when the number of the members with the estimated scores higher than the preset value reaches a preset percentage.
The invention provides a method for generating a marketing task based on big data analysis, which can automatically generate the marketing task of an object to be marketed by analyzing big data based on big data and a deep neural network technology, automatically generate the marketing task by acquiring the relevant big data of the object to be marketed on a plurality of platforms and taking the big data as a data analysis basis, does not need human interference, and only needs to collect the big data intelligently and learn and analyze the big data through a deep bible network technology to realize the automatic generation of the marketing task.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method for generating marketing tasks based on big data analysis in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for generating a marketing task based on big data analysis according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1:
an embodiment of the present invention provides a method for generating a marketing task based on big data analysis, and fig. 1 is a flowchart of a method for generating a marketing task based on big data analysis in an embodiment of the present invention, please refer to fig. 1, where the method includes the following steps:
step S101, acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
step S102, second big data of an object having competition or mutual interest relation with the object to be marketed is obtained;
step S103, performing data fusion on the first big data and the second big data, and performing data cleaning to obtain practical big data;
step S104, carrying out data analysis on the practical big data based on a deep neural network to obtain an analysis result;
step S105, determining marketing content and marketing propagation mode according to the analysis result;
step S106, marketing and propagating the marketing content by adopting the determined marketing and propagating mode to form a marketing task for the object to be marketed;
and S107, distributing the marketing tasks based on the attribute characteristics of the object to be marketed.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the relevant big data of the object to be marketed is collected and the relevant big data of the object having a competitive relationship or a mutual interest relationship with the object to be marketed is also collected, namely, the first big data and the second big data are collected and determined through the omnibearing big data, wherein the object to be marketed can be an enterprise or an individual, can be marketing or individual marketing of the enterprise, and can also be marketing of products of the enterprise or marketing of individual products.
The big data acquired through collection are subjected to fusion processing, data after fusion processing are cleaned, and due to the fact that the big data are collected through multiple platforms in a multidimensional mode, repeated or obviously wrong data cannot be found, the repeated or obviously wrong data are cleaned, reliability of the big data is guaranteed, and accuracy of marketing tasks is improved.
After the big data are cleaned, the big data are analyzed based on learning of the deep neural network, marketing content and a marketing transmission mode for the object to be marketed are determined, the marketing content and the marketing transmission mode are determined according to the object to be marketed and have the characteristic of personalized uniqueness, the marketing task is automatically generated based on the big data, different big data are collected for different marketing objects, and different personalized marketing tasks are automatically formulated according to the different big data.
In addition, after the marketing task is generated, the marketing task can be distributed based on the attribute characteristics of the object to be marketed. In actual operation, the generated marketing tasks are automatically distributed by combining the responsibility of the team members, the team members complete the distributed corresponding tasks according to the responsibility and skills of the team members, and all the team members complete the marketing tasks together.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment can be used for automatically generating the marketing task of the object to be marketed by analyzing the big data based on the big data and the deep neural network technology, acquiring the relevant big data of the object to be marketed on a plurality of platforms, taking the big data as a data analysis basis, automatically generating the marketing task, and not needing human interference, and only needing to collect the big data through intelligence and learn and analyze the big data through the deep bible network technology to realize automatically generating the marketing task.
Example 2:
on the basis of embodiment 1, the acquiring of the first big data related to the object to be marketed comprises:
determining self-positioning of an object to be marketed and first network public opinion information;
determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
determining KPI indexes of an object to be marketed and positioning information of a product to be marketed in the market;
the obtaining of the second big data of the object having competition or mutual interest relation with the object to be marketed comprises:
determining competitive objects and/or mutual interest objects of the objects to be marketed;
determining second network public opinion information of competitive objects and/or mutual interest objects;
relevant product information of competing objects and/or mutually beneficial objects is determined.
The working principle of the technical scheme is as follows: the present embodiment adopts a scheme of a gathering process of the first big data and a gathering process of the second big data. The first big data comprises self-positioning and first network public opinion information of the object to be marketed, key information and/or hot spot information of marketing promotion of the product to be marketed which is determined based on the self-positioning and the first network public opinion information, and also comprises KPI (Key performance indicator) of the object to be marketed and positioning information of the product to be marketed in the market. The second big data comprises competitive objects and/or mutual interest objects of the objects to be marketed, second network public opinion information of the competitive objects and/or mutual interest objects, and related product information of the competitive objects and/or mutual interest objects.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment includes the network public opinion information through specific limitation on the first big data and the second big data, and due to the characteristics of the network era, the network public opinion information is important data in the big data collection process, the network public opinion information includes the self condition comment degree of an enterprise and the comment degree related to a competitive enterprise or a mutual interest enterprise, and the comment degree can be good comment or negative comment and the like. In addition, key information and/or hotspot information of marketing promotion of the product to be marketed is determined based on the self-positioning and the first network public opinion information, and the key information and the characteristic information are taken as key reference information of marketing content and a marketing transmission mode, so that data and information basis is provided for automatically generating the marketing content and the marketing transmission mode. Therefore, the scheme provided by the embodiment can obtain the big data of each platform to the maximum extent, and the collected big data is used as a data base for subsequent data analysis and automatic generation of marketing contents and marketing propagation modes.
Example 3:
on the basis of the embodiment 2, in the determining of the marketing content and the marketing propagation manner according to the analysis result, the method for determining the marketing content includes:
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a character content with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a picture with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a video or a short video with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a spreading title to guide public opinion;
the marketing propagation mode determining method comprises the following steps:
putting the marketing content as articles on each platform;
putting the marketing content as an advertisement on each website or ground promotion platform with a spreading degree;
performing official response on the marketing content to improve the spreading degree;
and receiving feedback of the user and performing interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is a generation process of marketing content and marketing propagation modes. Specifically, the marketing content includes written text content, picture content, video content, and content such as title or public opinion guided word operation, and the core content or hot content of the object to be marketed is promoted through the marketing content to achieve the marketing purpose.
In addition, the marketing propagation mode comprises propagation means such as article issuing, advertisement putting, official response and user interaction, and marketing content is popularized on each platform.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment is adopted to automatically generate the marketing task without human interference through big data analysis and insight, and the performance of enterprise self and competitive product comparison is combined, and the KPI (Key Performance indicator) of the marketing purpose of the enterprise is combined, so that the efficiency and the accuracy of the generation of the marketing task can be improved, and the success rate of marketing is further improved.
Example 4:
on the basis of the embodiment 1, after the marketing transmission is performed on the marketing content by adopting the determined marketing transmission mode to form a marketing task for a subject to be marketed, the method includes:
a marketing task detection model is constructed in advance;
inputting the formed marketing tasks into the model, and determining grade values of the marketing tasks;
if the grading value is lower than a preset value, respectively acquiring third big data and fourth big data based on an object to be marketed and an object having a competition or mutual profit relationship with the object to be marketed, and generating a new marketing task according to the newly acquired third big data and fourth big data;
inputting the generated new marketing tasks into the model until the grading value of the marketing tasks is equal to or higher than a preset value, and setting the corresponding marketing tasks as final marketing tasks;
after the task allocation is carried out on the marketing task based on the attribute characteristics of the object to be marketed, the method comprises the following steps:
determining the completion condition and marketing efficiency of the marketing task;
evaluating the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency;
and adjusting the task allocation according to the evaluation.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that a marketing task detection model is constructed, the accuracy and the reasonableness of the automatically generated marketing task can be pre-judged, and the marketing task is adjusted according to the pre-judgment, so that the accuracy of the marketing task is improved. Specifically, a grading value of the marketing task can be determined in the model, pre-judgment is performed based on the grading value, if the grading value is lower than a preset value, third big data and fourth big data are respectively obtained based on an object to be marketed and an object having a competition or mutual profit relationship with the object to be marketed, a new marketing task is generated according to the newly obtained third big data and fourth big data, and then the generated new marketing task is input into the model until the grading value of the marketing task is equal to or higher than the preset value, and the corresponding marketing task is set as a final marketing task. The marketing task automatically generated is adjusted according to the pre-judgment of the model, and the accuracy of the marketing task is improved.
In addition, this embodiment can also judge and adjust the rationality of automatic allocation task, and is concrete, confirms the completion condition and the marketing efficiency of marketing task, then based on completion condition and marketing efficiency are right the rationality of the allocation of marketing task is evaluateed, finally according to the evaluation is right the task allocation carries out rationality adjustment. Therefore, the rationality of marketing task distribution can be guaranteed by adopting the scheme, the marketing task can be smoothly and effectively completed, and the marketing success rate is improved.
The beneficial effects of the above technical scheme are: according to the scheme provided by the embodiment, on one hand, the accuracy and the reasonableness of the automatically generated marketing task can be pre-judged by constructing the marketing task detection model, and the marketing task is adjusted according to the pre-judgment, so that the accuracy of the marketing task is improved. On the other hand, the rationality of the automatic distribution tasks can be judged and adjusted, the rationality of the distribution of the marketing tasks can be guaranteed, the marketing tasks can be smoothly and effectively completed, and the success rate of marketing is improved.
Example 5:
on the basis of embodiment 4, the inputting the formed marketing tasks into the model, and the determining the grade value of the marketing tasks comprise:
determining a matching degree relation between a user and a product aiming at the marketing task;
according to the matching degree relation, determining the matching degree between the user and the product based on the following formula:
Figure 611635DEST_PATH_IMAGE024
Figure 598045DEST_PATH_IMAGE025
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure 153660DEST_PATH_IMAGE023
for the u-th user matrix, the user matrix,
Figure 250929DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure 959122DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 850855DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 159345DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 935672DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 357426DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 78781DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 218776DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 798793DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 340633DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 229960DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 732617DEST_PATH_IMAGE015
the variance of the matching degree matrix, the variance of the user matrix and the variance of the product matrix are respectively, and I is the abbreviation of an indication function; pi is a product symbol;
determining a rating value for the marketing task based on the degree of matching;
assessing the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency, comprising:
determining the estimated scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the real scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the true score similarity of each member and the adjacent members;
updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 975379DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 496359DEST_PATH_IMAGE017
the estimated score for the member update is updated,
Figure 166375DEST_PATH_IMAGE018
in order to estimate the score of the object,
Figure 421907DEST_PATH_IMAGE019
in order to be a true score,
Figure 202781DEST_PATH_IMAGE020
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and when the number of members with the estimated scores higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is reasonable.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is a process of determining the grading value of the marketing task and a process of evaluating the distribution reasonableness of the marketing task based on the completion condition and the marketing efficiency. Specifically, according to the matching degree relation, the matching degree between the user and the product is determined based on a formula, and then the grading value of the marketing task is determined based on the matching degree. The formula that adopts this embodiment to provide can accurate definite user and the product degree of matching between, and then grades to the marketing task of automatic generation, if the degree of matching is high between user and the product then explains that the formulation of marketing task is reasonable and accurate, but under the not high condition of degree of matching between user and the product, then explains that the formulation of marketing task has the part that can improve, consequently, can further judge whether need adjust the improvement to the marketing task based on the degree of matching between user and the product.
And in addition, evaluating the rationality of distribution of the marketing tasks based on the completion condition and the marketing efficiency, wherein the evaluation comprises the steps of determining that each member in the team of the object to be marketed completes the marketing tasks and the estimated score and the real score of the marketing efficiency, updating the estimated score according to the estimated score, the real score and the similarity, and when the number of the updated members with the estimated score higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is rational. Generally, 85% of the members in the team who have the updated estimated score higher than the preset value can be set to determine that the distribution of the marketing task is reasonable.
The beneficial effects of the above technical scheme are: according to the scheme provided by the embodiment, the matching degree between the user and the product is determined based on the formula according to the matching degree relation, then the grading value of the marketing task is determined based on the matching degree, whether the marketing task needs to be adjusted and improved can be further judged based on the matching degree between the user and the product, the marketing task which is automatically generated is adjusted according to the pre-judgment of the model, and the accuracy of the marketing task is improved. In addition, the estimated score is updated according to the estimated score, the real score and the similarity, when the number of members of the updated estimated score higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is set to be reasonable, the rationality of the automatic distribution tasks is judged and adjusted, the rationality of the distribution of the marketing tasks can be guaranteed, the marketing tasks can be smoothly and effectively completed, and the success rate of marketing is improved.
Example 6:
fig. 2 is a schematic structural diagram of a system for generating a marketing task based on big data analysis according to an embodiment of the present invention, and please refer to fig. 2, the system includes the following structural parts:
a first big data acquisition unit 201, configured to acquire first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
a second big data acquiring unit 202, configured to acquire second big data of an object having a competitive or mutual interest relationship with the object to be marketed;
the data fusion cleaning unit 203 is used for performing data fusion on the first big data and the second big data, and performing data cleaning to obtain practical big data;
the data analysis unit 204 is used for performing data analysis on the practical big data based on a deep neural network to obtain an analysis result;
a determining unit 205, configured to determine marketing content and a marketing propagation manner according to the analysis result;
the marketing task generating unit 206 is configured to perform marketing propagation on the marketing content by using the determined marketing propagation manner, so as to form a marketing task for a target to be marketed;
and the task allocation unit 207 is used for allocating tasks to the marketing tasks based on the attribute characteristics of the objects to be marketed.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the relevant big data of the object to be marketed is collected and the relevant big data of the object having a competitive relationship or a mutual interest relationship with the object to be marketed is also collected, namely, the first big data and the second big data are collected and determined through the omnibearing big data, wherein the object to be marketed can be an enterprise or an individual, can be marketing or individual marketing of the enterprise, and can also be marketing of products of the enterprise or marketing of individual products.
The big data acquired through collection are subjected to fusion processing, data after fusion processing are cleaned, and due to the fact that the big data are collected through multiple platforms in a multidimensional mode, repeated or obviously wrong data cannot be found, the repeated or obviously wrong data are cleaned, reliability of the big data is guaranteed, and accuracy of marketing tasks is improved.
After the big data are cleaned, the big data are analyzed based on learning of the deep neural network, marketing content and a marketing transmission mode for the object to be marketed are determined, the marketing content and the marketing transmission mode are determined according to the object to be marketed and have the characteristic of personalized uniqueness, the marketing task is automatically generated based on the big data, different big data are collected for different marketing objects, and different personalized marketing tasks are automatically formulated according to the different big data.
In addition, after the marketing task is generated, the marketing task can be distributed based on the attribute characteristics of the object to be marketed. In actual operation, the generated marketing tasks are automatically distributed by combining the responsibility of the team members, the team members complete the distributed corresponding tasks according to the responsibility and skills of the team members, and all the team members complete the marketing tasks together.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment can be used for automatically generating the marketing task of the object to be marketed by analyzing the big data based on the big data and the deep neural network technology, acquiring the relevant big data of the object to be marketed on a plurality of platforms, taking the big data as a data analysis basis, automatically generating the marketing task, and not needing human interference, and only needing to collect the big data through intelligence and learn and analyze the big data through the deep bible network technology to realize automatically generating the marketing task.
Example 7:
on the basis of embodiment 6, the first big data unit includes:
the first network public opinion information determining subunit is used for determining the self-positioning of the object to be marketed and the first network public opinion information;
the information determining subunit is used for determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
the positioning information determining subunit is used for determining KPI (Key performance indicator) of the object to be marketed and positioning information of the product to be marketed in the market;
the second big data unit includes:
the competitive object determining subunit is used for determining a competitive object and/or a mutual interest object of the object to be marketed;
the second network public opinion information determining subunit is used for determining second network public opinion information of the competitive object and/or the mutual interest object;
and the related product information determining subunit is used for determining related product information of the competitive object and/or the mutual interest object.
The working principle of the technical scheme is as follows: the present embodiment adopts a scheme of gathering the first big data and gathering the second big data. The first big data comprises self-positioning and first network public opinion information of the object to be marketed, key information and/or hot spot information of marketing promotion of the product to be marketed which is determined based on the self-positioning and the first network public opinion information, and also comprises KPI (Key performance indicator) of the object to be marketed and positioning information of the product to be marketed in the market. The second big data comprises competitive objects and/or mutual interest objects of the objects to be marketed, second network public opinion information of the competitive objects and/or mutual interest objects, and related product information of the competitive objects and/or mutual interest objects.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment includes the network public opinion information through specific limitation on the first big data and the second big data, and due to the characteristics of the network era, the network public opinion information is important data in the big data collection process, the network public opinion information includes the self condition comment degree of an enterprise and the comment degree related to a competitive enterprise or a mutual interest enterprise, and the comment degree can be good comment or negative comment and the like. In addition, key information and/or hotspot information of marketing promotion of the product to be marketed is determined based on the self-positioning and the first network public opinion information, and the key information and the characteristic information are taken as key reference information of marketing content and a marketing transmission mode, so that data and information basis is provided for automatically generating the marketing content and the marketing transmission mode. Therefore, the scheme provided by the embodiment can obtain the big data of each platform to the maximum extent, and the collected big data is used as a data base for subsequent data analysis and automatic generation of marketing contents and marketing propagation modes.
Example 8:
on the basis of embodiment 7, the determination unit includes:
the text content subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into text content with spreading performance;
the picture subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a picture with spreading property;
the video subunit is used for making key information or hotspot information of marketing promotion of the object to be marketed or the product to be marketed into a video or a short video with spreading performance;
the title subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a spreading title to guide public opinion;
the article releasing subunit is used for releasing the marketing content as an article on each platform;
the advertisement putting subunit is used for putting the marketing content as an advertisement on each website or ground promotion platform with the spreading degree;
the response subunit is used for carrying out official response on the marketing content to improve the propagation degree;
and the interactive feedback subunit receives the feedback of the user and carries out interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is a generation process of marketing content and marketing propagation modes. Specifically, the marketing content includes written text content, picture content, video content, and content such as title or public opinion guided word operation, and the core content or hot content of the object to be marketed is promoted through the marketing content to achieve the marketing purpose.
In addition, the marketing propagation mode comprises propagation means such as article issuing, advertisement putting, official response and user interaction, and marketing content is popularized on each platform.
The beneficial effects of the above technical scheme are: the scheme provided by the embodiment is adopted to automatically generate the marketing task without human interference through big data analysis and insight, and the performance of enterprise self and competitive product comparison is combined, and the KPI (Key Performance indicator) of the marketing purpose of the enterprise is combined, so that the efficiency and the accuracy of the generation of the marketing task can be improved, and the success rate of marketing is further improved.
Example 9:
on the basis of embodiment 6, the method further comprises the following steps:
the marketing task detection model construction unit is used for constructing a marketing task detection model in advance;
the grading value determining unit is used for inputting the formed marketing tasks into the model after marketing propagation is carried out on the marketing contents by adopting the determined marketing propagation mode to form marketing tasks aiming at objects to be marketed, and determining the grading value of the marketing tasks;
if the grading value is lower than a preset value, a user respectively acquires third big data and fourth big data based on an object to be marketed and an object having a competition or mutual interest relationship with the object to be marketed, and generates a new marketing task according to the newly acquired third big data and fourth big data;
the final marketing task determining unit is used for inputting the generated new marketing task into the model until the grading value of the marketing task is equal to or higher than a preset value, and setting the corresponding marketing task as the final marketing task;
the marketing efficiency determining unit is used for determining the completion condition and the marketing efficiency of the marketing task after the marketing task is subjected to task allocation based on the attribute characteristics of the object to be marketed;
the evaluation unit is used for evaluating the rationality of the distribution of the marketing tasks based on the completion condition and the marketing efficiency;
and the adjusting unit is used for adjusting the reasonability of the task allocation according to the evaluation.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that a marketing task detection model is constructed, the accuracy and the reasonableness of the automatically generated marketing task can be pre-judged, and the marketing task is adjusted according to the pre-judgment, so that the accuracy of the marketing task is improved. Specifically, a grading value of the marketing task can be determined in the model, pre-judgment is performed based on the grading value, if the grading value is lower than a preset value, third big data and fourth big data are respectively obtained based on an object to be marketed and an object having a competition or mutual profit relationship with the object to be marketed, a new marketing task is generated according to the newly obtained third big data and fourth big data, and then the generated new marketing task is input into the model until the grading value of the marketing task is equal to or higher than the preset value, and the corresponding marketing task is set as a final marketing task. The marketing task automatically generated is adjusted according to the pre-judgment of the model, and the accuracy of the marketing task is improved.
In addition, this embodiment can also judge and adjust the rationality of automatic allocation task, and is concrete, confirms the completion condition and the marketing efficiency of marketing task, then based on completion condition and marketing efficiency are right the rationality of the allocation of marketing task is evaluateed, finally according to the evaluation is right the task allocation carries out rationality adjustment. Therefore, the rationality of marketing task distribution can be guaranteed by adopting the scheme, the marketing task can be smoothly and effectively completed, and the marketing success rate is improved.
The beneficial effects of the above technical scheme are: according to the scheme provided by the embodiment, on one hand, the accuracy and the reasonableness of the automatically generated marketing task can be pre-judged by constructing the marketing task detection model, and the marketing task is adjusted according to the pre-judgment, so that the accuracy of the marketing task is improved. On the other hand, the rationality of the automatic distribution tasks can be judged and adjusted, the rationality of the distribution of the marketing tasks can be guaranteed, the marketing tasks can be smoothly and effectively completed, and the success rate of marketing is improved.
Example 10:
on the basis of embodiment 9, the rating value determining unit includes:
the matching degree relation determining subunit is used for determining the matching degree relation between the user and the product aiming at the marketing task;
the matching degree determining subunit is used for determining the matching degree between the user and the product according to the matching degree relation based on the following formula:
Figure 109426DEST_PATH_IMAGE001
Figure 825709DEST_PATH_IMAGE002
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure 427592DEST_PATH_IMAGE023
for the u-th user matrix, the user matrix,
Figure 139721DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure 510659DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 663423DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 487022DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 999912DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 366303DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 549022DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 250131DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 442078DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 397396DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 16596DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 939421DEST_PATH_IMAGE015
the variance of the matching degree matrix, the variance of the user matrix and the variance of the product matrix are respectively, and I is the abbreviation of an indication function; pi is a product symbol;
a grading value determination subunit, configured to determine a grading value of the marketing task based on the matching degree;
the evaluation unit includes:
the pre-estimation scoring determining subunit is used for determining the pre-estimation scoring of the marketing task completion and the marketing efficiency of each member in the team of the object to be marketed;
the real score determining subunit is used for determining the real score of each member in the team of the object to be marketed for completing the marketing task and the marketing efficiency;
the similarity determining subunit is used for determining the real score similarity of each member and the adjacent members;
and the estimated score updating subunit is used for updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 810425DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 744883DEST_PATH_IMAGE017
the estimated score for the member update is updated,
Figure 662548DEST_PATH_IMAGE018
in order to estimate the score of the object,
Figure 213615DEST_PATH_IMAGE019
in order to be a true score,
Figure DEST_PATH_IMAGE026
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and the rationality judging subunit is used for judging that the distribution of the marketing tasks is rational when the number of the members with the estimated scores higher than the preset value reaches a preset percentage.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is a process of determining the grading value of the marketing task and a process of evaluating the distribution reasonableness of the marketing task based on the completion condition and the marketing efficiency. Specifically, according to the matching degree relation, the matching degree between the user and the product is determined based on a formula, and then the grading value of the marketing task is determined based on the matching degree. The formula that adopts this embodiment to provide can accurate definite user and the product degree of matching between, and then grades to the marketing task of automatic generation, if the degree of matching is high between user and the product then explains that the formulation of marketing task is reasonable and accurate, but under the not high condition of degree of matching between user and the product, then explains that the formulation of marketing task has the part that can improve, consequently, can further judge whether need adjust the improvement to the marketing task based on the degree of matching between user and the product.
And in addition, evaluating the rationality of distribution of the marketing tasks based on the completion condition and the marketing efficiency, wherein the evaluation comprises the steps of determining that each member in the team of the object to be marketed completes the marketing tasks and the estimated score and the real score of the marketing efficiency, updating the estimated score according to the estimated score, the real score and the similarity, and when the number of the updated members with the estimated score higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is rational. Generally, 85% of the members in the team who have the updated estimated score higher than the preset value can be set to determine that the distribution of the marketing task is reasonable.
The beneficial effects of the above technical scheme are: according to the scheme provided by the embodiment, the matching degree between the user and the product is determined based on the formula according to the matching degree relation, then the grading value of the marketing task is determined based on the matching degree, whether the marketing task needs to be adjusted and improved can be further judged based on the matching degree between the user and the product, the marketing task which is automatically generated is adjusted according to the pre-judgment of the model, and the accuracy of the marketing task is improved. In addition, the estimated score is updated according to the estimated score, the real score and the similarity, when the number of members of the updated estimated score higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is set to be reasonable, the rationality of the automatic distribution tasks is judged and adjusted, the rationality of the distribution of the marketing tasks can be guaranteed, the marketing tasks can be smoothly and effectively completed, and the success rate of marketing is improved.
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 (10)

1. A method for generating marketing tasks based on big data analysis is characterized by comprising the following steps:
acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
acquiring second big data of an object having a competitive or mutual profit relationship with the object to be marketed;
performing data fusion on the first big data and the second big data, and performing data cleaning to obtain practical big data;
performing data analysis on the practical big data based on a deep neural network to obtain an analysis result;
determining marketing content and a marketing propagation mode according to the analysis result;
adopting the determined marketing propagation mode to carry out marketing propagation on the marketing content to form a marketing task for the object to be marketed;
and performing task allocation on the marketing task based on the attribute characteristics of the object to be marketed.
2. The method for generating marketing tasks based on big data analysis of claim 1, wherein the obtaining of the first big data related to the object to be marketed comprises:
determining self-positioning of an object to be marketed and first network public opinion information;
determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
determining KPI indexes of an object to be marketed and positioning information of a product to be marketed in the market;
the obtaining of the second big data of the object having competition or mutual interest relation with the object to be marketed comprises:
determining competitive objects and/or mutual interest objects of the objects to be marketed;
determining second network public opinion information of competitive objects and/or mutual interest objects;
relevant product information of competing objects and/or mutually beneficial objects is determined.
3. The method for generating marketing tasks based on big data analysis according to claim 2, wherein the method for determining marketing content and marketing transmission mode according to the analysis result comprises:
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a character content with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a picture with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a video or a short video with spreading performance;
key information or hot spot information of marketing promotion of an object to be marketed or a product to be marketed is made into a spreading title to guide public opinion;
the marketing propagation mode determining method comprises the following steps:
putting the marketing content as articles on each platform;
putting the marketing content as an advertisement on each website or ground promotion platform with a spreading degree;
performing official response on the marketing content to improve the spreading degree;
and receiving feedback of the user and performing interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
4. The method for generating marketing tasks based on big data analysis according to claim 1, wherein the marketing and propagating the marketing contents by using the determined marketing and propagating manner, after the marketing task for the object to be marketed is formed, comprises:
a marketing task detection model is constructed in advance;
inputting the formed marketing tasks into the model, and determining grade values of the marketing tasks;
if the grading value is lower than a preset value, respectively acquiring third big data and fourth big data based on an object to be marketed and an object having a competition or mutual profit relationship with the object to be marketed, and generating a new marketing task according to the newly acquired third big data and fourth big data;
inputting the generated new marketing tasks into the model until the grading value of the marketing tasks is equal to or higher than a preset value, and setting the corresponding marketing tasks as final marketing tasks;
after the task allocation is carried out on the marketing task based on the attribute characteristics of the object to be marketed, the method comprises the following steps:
determining the completion condition and marketing efficiency of the marketing task;
evaluating the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency;
and adjusting the task allocation according to the evaluation.
5. The method for generating marketing tasks based on big data analysis of claim 4, wherein the inputting the formed marketing tasks into the model, determining the rating values of the marketing tasks, comprises:
determining a matching degree relation between a user and a product aiming at the marketing task;
according to the matching degree relation, determining the matching degree between the user and the product based on the following formula:
Figure 41871DEST_PATH_IMAGE001
Figure 871287DEST_PATH_IMAGE002
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure 523985DEST_PATH_IMAGE003
for the u-th user matrix, the user matrix,
Figure 362628DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure 198429DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 464325DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 338740DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 715495DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 195018DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 428553DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 977215DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 954398DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 288428DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 630547DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 479555DEST_PATH_IMAGE015
the variance of the matching degree matrix, the variance of the user matrix and the variance of the product matrix are respectively, and I is the abbreviation of an indication function; pi is a product symbol;
determining a rating value for the marketing task based on the degree of matching;
assessing the rationality of the distribution of the marketing tasks based on the completion and marketing efficiency, comprising:
determining the estimated scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the real scores of the marketing tasks and the marketing efficiency of each member in the team of the object to be marketed;
determining the true score similarity of each member and the adjacent members;
updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 932533DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 137380DEST_PATH_IMAGE017
the estimated score for the member update is updated,
Figure 712718DEST_PATH_IMAGE018
in order to estimate the score of the object,
Figure 986705DEST_PATH_IMAGE019
in order to be a true score,
Figure 305691DEST_PATH_IMAGE020
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and when the number of members with the estimated scores higher than the preset value reaches the preset percentage, the distribution of the marketing tasks is reasonable.
6. A system for generating marketing tasks based on big data analytics, comprising:
the system comprises a first big data acquisition unit, a second big data acquisition unit and a marketing unit, wherein the first big data acquisition unit is used for acquiring first big data related to an object to be marketed; the marketing object comprises a business or a person to be marketed;
the second big data acquisition unit is used for acquiring second big data of an object having competition or mutual profit relation with the object to be marketed by a user;
the data fusion cleaning unit is used for carrying out data fusion on the first big data and the second big data and cleaning the data to obtain practical big data;
the data analysis unit is used for carrying out data analysis on the practical big data based on the deep neural network to obtain an analysis result;
the determining unit is used for determining marketing content and marketing propagation modes according to the analysis result;
the marketing task generating unit is used for carrying out marketing propagation on the marketing content by adopting the determined marketing propagation mode to form a marketing task aiming at a to-be-marketed object;
and the task allocation unit is used for allocating tasks to the marketing tasks based on the attribute characteristics of the objects to be marketed.
7. The big data analytics-based marketing task generating system of claim 6, wherein the first big data unit comprises:
the first network public opinion information determining subunit is used for determining the self-positioning of the object to be marketed and the first network public opinion information;
the information determining subunit is used for determining key information and/or hot spot information of marketing promotion of the product to be marketed based on the self-positioning and the first network public opinion information;
the positioning information determining subunit is used for determining KPI (Key performance indicator) of the object to be marketed and positioning information of the product to be marketed in the market;
the second big data unit includes:
the competitive object determining subunit is used for determining a competitive object and/or a mutual interest object of the object to be marketed;
the second network public opinion information determining subunit is used for determining second network public opinion information of the competitive object and/or the mutual interest object;
and the related product information determining subunit is used for determining related product information of the competitive object and/or the mutual interest object.
8. The big data analytics-based marketing task generating system of claim 7, wherein the determining unit comprises:
the text content subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into text content with spreading performance;
the picture subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a picture with spreading property;
the video subunit is used for making key information or hotspot information of marketing promotion of the object to be marketed or the product to be marketed into a video or a short video with spreading performance;
the title subunit is used for making key information or hot spot information of marketing promotion of the object to be marketed or the product to be marketed into a spreading title to guide public opinion;
the article releasing subunit is used for releasing the marketing content as an article on each platform;
the advertisement putting subunit is used for putting the marketing content as an advertisement on each website or ground promotion platform with the spreading degree;
the response subunit is used for carrying out official response on the marketing content to improve the propagation degree;
and the interactive feedback subunit receives the feedback of the user and carries out interactive feedback on the feedback aiming at the marketing content or the product to be marketed so as to improve the propagation degree.
9. The big data analytics-based marketing task generating system of claim 6, further comprising:
the marketing task detection model construction unit is used for constructing a marketing task detection model in advance;
the grading value determining unit is used for inputting the formed marketing tasks into the model after marketing propagation is carried out on the marketing contents by adopting the determined marketing propagation mode to form marketing tasks aiming at objects to be marketed, and determining the grading value of the marketing tasks;
the new marketing task generating unit is used for respectively acquiring third big data and fourth big data based on the object to be marketed and an object having competition or mutual profit relation with the object to be marketed if the grading value of the grading is lower than a preset value by a user, and generating a new marketing task according to the newly acquired third big data and fourth big data;
the final marketing task determining unit is used for inputting the generated new marketing task into the model until the grading value of the marketing task is equal to or higher than a preset value, and setting the corresponding marketing task as the final marketing task;
the marketing efficiency determining unit is used for determining the completion condition and the marketing efficiency of the marketing task after the marketing task is subjected to task allocation based on the attribute characteristics of the object to be marketed;
the evaluation unit is used for evaluating the rationality of the distribution of the marketing tasks based on the completion condition and the marketing efficiency;
and the adjusting unit is used for adjusting the reasonability of the task allocation according to the evaluation.
10. The big data analysis-based marketing task generating system of claim 9, wherein the rating value determining unit comprises:
the matching degree relation determining subunit is used for determining the matching degree relation between the user and the product aiming at the marketing task;
the matching degree determining subunit is used for determining the matching degree between the user and the product according to the matching degree relation based on the following formula:
Figure 348733DEST_PATH_IMAGE021
Figure 298234DEST_PATH_IMAGE022
wherein, U is a user matrix, U =1, 2, 3.. N, V is a product matrix, j =1, 2, 3.. M, R is a matching degree matrix between the user and the product,
Figure 856255DEST_PATH_IMAGE003
for the u-th user matrix, the user matrix,
Figure 165882DEST_PATH_IMAGE004
for the jth product matrix, the product matrix,
Figure 329010DEST_PATH_IMAGE005
is a matching degree matrix between the user u and the product j,
Figure 246151DEST_PATH_IMAGE006
is a conditional probability between the user and the product,
Figure 494729DEST_PATH_IMAGE007
in the form of a normal distribution of the signals,
Figure 155518DEST_PATH_IMAGE008
is a transposed matrix of the U,
Figure 173152DEST_PATH_IMAGE009
when the user u is matched with the product j, the value is 1, otherwise, the value is 0;
Figure 212259DEST_PATH_IMAGE010
is the posterior probability of the user and the product,
Figure 744872DEST_PATH_IMAGE011
is the probability of the user or users,
Figure 412613DEST_PATH_IMAGE012
is the probability of the product or the like,
Figure 19175DEST_PATH_IMAGE013
is a gaussian distribution of the users and is,
Figure 543697DEST_PATH_IMAGE014
is a gaussian distribution of the product and is,
Figure 501289DEST_PATH_IMAGE015
the variance of the matching degree matrix, the variance of the user matrix and the variance of the product matrix are respectively, and I is the abbreviation of an indication function; pi is a product symbol;
a grading value determination subunit, configured to determine a grading value of the marketing task based on the matching degree;
the evaluation unit includes:
the pre-estimation scoring determining subunit is used for determining the pre-estimation scoring of the marketing task completion and the marketing efficiency of each member in the team of the object to be marketed;
the real score determining subunit is used for determining the real score of each member in the team of the object to be marketed for completing the marketing task and the marketing efficiency;
the similarity determining subunit is used for determining the real score similarity of each member and the adjacent members;
and the estimated score updating subunit is used for updating the estimated score of each member based on the following formula according to the estimated score, the real score and the similarity of the real score:
Figure 503880DEST_PATH_IMAGE023
wherein the content of the first and second substances,
Figure 745375DEST_PATH_IMAGE024
the estimated score for the member update is updated,
Figure 378481DEST_PATH_IMAGE025
in order to estimate the score of the object,
Figure 823369DEST_PATH_IMAGE026
in order to be a true score,
Figure 629651DEST_PATH_IMAGE027
n, wherein n is the number of all calculated similarities, i =1, 2.. n is the true score similarity of the current member and the adjacent members;
and the rationality judging subunit is used for judging that the distribution of the marketing tasks is rational when the number of the members with the estimated scores higher than the preset value reaches a preset percentage.
CN202110774651.6A 2021-07-09 2021-07-09 Method and system for generating marketing task based on big data analysis Pending CN113222484A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110774651.6A CN113222484A (en) 2021-07-09 2021-07-09 Method and system for generating marketing task based on big data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110774651.6A CN113222484A (en) 2021-07-09 2021-07-09 Method and system for generating marketing task based on big data analysis

Publications (1)

Publication Number Publication Date
CN113222484A true CN113222484A (en) 2021-08-06

Family

ID=77081595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110774651.6A Pending CN113222484A (en) 2021-07-09 2021-07-09 Method and system for generating marketing task based on big data analysis

Country Status (1)

Country Link
CN (1) CN113222484A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116703469A (en) * 2023-08-03 2023-09-05 北京未来聚典信息技术有限公司 Marketing activity optimizing popularization method and system based on generation model

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107203910A (en) * 2017-05-27 2017-09-26 科技谷（厦门）信息技术有限公司 A kind of big data intelligent accurate marketing system
CN107526754A (en) * 2016-09-26 2017-12-29 广州速鸿信息科技有限公司 A kind of user's portrait platform method for building up based on big data
CN110942337A (en) * 2019-10-31 2020-03-31 天津中科智能识别产业技术研究院有限公司 Accurate tourism marketing method based on internet big data
CN111461806A (en) * 2019-01-21 2020-07-28 深圳增强现实技术有限公司 Marketing cloud service platform based on AR, AR intelligent device, system and method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107526754A (en) * 2016-09-26 2017-12-29 广州速鸿信息科技有限公司 A kind of user's portrait platform method for building up based on big data
CN107203910A (en) * 2017-05-27 2017-09-26 科技谷（厦门）信息技术有限公司 A kind of big data intelligent accurate marketing system
CN111461806A (en) * 2019-01-21 2020-07-28 深圳增强现实技术有限公司 Marketing cloud service platform based on AR, AR intelligent device, system and method
CN110942337A (en) * 2019-10-31 2020-03-31 天津中科智能识别产业技术研究院有限公司 Accurate tourism marketing method based on internet big data

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116703469A (en) * 2023-08-03 2023-09-05 北京未来聚典信息技术有限公司 Marketing activity optimizing popularization method and system based on generation model

Similar Documents

Publication Publication Date Title
US9875441B2 (en) Question recommending method, apparatus and system
CN102708131B (en) By consumer's automatic classification in fine point
Rosas et al. The use of concept mapping for scale development and validation in evaluation
Morrison et al. Knowledge and information networks in an Italian wine cluster
US9654593B2 (en) Discovering signature of electronic social networks
CN109241440A (en) It is a kind of based on deep learning towards implicit feedback recommended method
CN106126582A (en) Recommend method and device
CN108363821A (en) A kind of information-pushing method, device, terminal device and storage medium
CN110222975A (en) A kind of loss customer analysis method, apparatus, electronic equipment and storage medium
CN101149829A (en) Client data centralized processing method and system
CN102222299A (en) Inventory management
CN108334575A (en) A kind of recommendation results sequence modification method and device, electronic equipment
CN108416630A (en) A kind of determination method and device of target audience
CN112612942B (en) Social big data-based fund recommendation system and method
CN109102329A (en) A kind of data sampling and processing and analysis application method and device
Srba et al. Utilizing non-qa data to improve questions routing for users with low qa activity in cqa
CN111581516A (en) Investment product recommendation method and related device
CN109657962A (en) A kind of appraisal procedure and system of the volume assets of brand
CN112669113A (en) Product recommendation method and device, storage medium and electronic device
CN102243659B (en) Webpage junk detection method based on dynamic Bayesian model
CN113222484A (en) Method and system for generating marketing task based on big data analysis
CN114581140A (en) Recommendation method and device for advertising floor and electronic equipment
CN105978729A (en) System and method for pushing mobile phone information based on user surfing log and position
Stewart The evolution of market research
Lu et al. Social media strategy for Batik SMEs using customer knowledge management

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210806

RJ01 Rejection of invention patent application after publication