CN107886357A - The method and system of content value is judged based on user behavior data - Google Patents
The method and system of content value is judged based on user behavior data Download PDFInfo
- Publication number
- CN107886357A CN107886357A CN201711079164.8A CN201711079164A CN107886357A CN 107886357 A CN107886357 A CN 107886357A CN 201711079164 A CN201711079164 A CN 201711079164A CN 107886357 A CN107886357 A CN 107886357A
- Authority
- CN
- China
- Prior art keywords
- content
- index
- work
- data
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of method that content value is judged based on user behavior data, the consumer behaviour data carried out according to user to works content are that works establish good-looking exponential model；The consumer behaviour data are gathered and by the data transfer to the good-looking exponential model, to obtain the good-looking index of works；Establish the relation of good-looking index and content value；The good-looking index of acquisition is matched to judge content value with content value；In method provided by the invention, pouplarity of the works content in potential user group can be reacted based on the good-looking index that user behavior data is drawn, the growth trend of user behavior can be predicted, also serves as the data of content value price according to so that the content value index drawn has higher reliability；On the other hand present invention also offers a kind of system for realizing the above method, the data auxiliary IP both parties drawn by system judge the zone of reasonableness of content business price.
Description
Technical Field
The invention belongs to the technical field of electronic reading, and relates to content value judgment mainly based on novel and assisted by short stories, cartoons and cartoons, in particular to a method for judging content value based on user behavior data and a system for implementing the method.
Background
With the continuous progress of social economy, the consumption demand of people on the spiritual culture level is more and more vigorous, the culture (content) consumption market is larger and larger, the forms of culture (content) products are more and more abundant, and the development of the culture industry is driven to become a great trend by taking IP as a kernel. The Intellectual Property (IP) is a cross-platform, which can exist in different forms such as cartoons, novels, movies, toys, games, etc., and can be switched at will, and drives the development of the popular cultural industry by the diversified development and popularization of popular IP.
Therefore, the IP value can be used as the embodiment of the extension of the cultural industry chain; assessment of IP value is critical to reduce authoring risk and reducing distribution risk.
At present, the IP value is mostly judged according to the IP value transfer condition, the IP value transfer is mainly the transfer and flow of vermicelli (or users), the users and the flow have a recognized price range in the industry, the setting of the actual content, the number of words and the like are factors related to the IP ductility, and the IP price is also influenced. Because the number of fans and the flow are difficult to be accurately measured, the potential primary IP is difficult to be found and received because enough fans and flow are not accumulated, and the enterprises can miss the opportunity to buy before, and the IP with large fans and flow is high in price and small in number, so that most of small and medium-sized enterprises cannot buy the new IP.
In view of the above, the present invention is particularly proposed.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art, and provide a method for judging content value based on user behavior data, which can more intuitively reflect the popularity of the work content in a target user group, is favorable for predicting the growth trend of user behavior, and provides a reliable data basis for pricing the content value of the work.
In order to solve the technical problems, the invention adopts the technical scheme that:
a method for determining content value based on user behavior data comprises
Establishing a good-looking index model for the work according to consumer behavior data of the content of the work performed by a user;
collecting the consumer behavior data and transmitting the data to the goodness index model to obtain the goodness index of the product;
establishing a relationship between the goodness-of-view index and the content value;
and matching the obtained good-looking index with the content value to judge the content value.
Further, in the method for determining a content value based on user behavior data, the method includes: the establishing of the relationship between the goodness index and the content value comprises the following steps:
and establishing a summation model according to the goodness index of the work, the author premium index of the work and the content volume of the work.
Further, in the method for determining a content value based on user behavior data, the method includes: in the process of establishing the goodness index model for the work according to the consumer behavior data of the content of the work by the user, a calculation formula in the goodness index model is as follows:
wherein r represents the content consumption progress, and q represents the number of people who finish the content consumption progress; r represents the total content amount of the digital content of the work; and Q represents the maximum value of Q when R is smaller, wherein the value range of R is more than 10 and more than 0,r, the value of R is not more than R, and the value of Q is less than Q.
Further, in the method for determining a content value based on user behavior data, the method includes: the method for collecting the consumer behavior data comprises the following steps:
dividing the category of the works according to the content of the works, and dividing a target user according to the gender and age of the user;
establishing data acquisition dimensions according to consumer behaviors of users on different work categories;
according to the category of the content of the work, data acquisition is carried out according to the corresponding data acquisition dimension, and consumer behavior data of the user on the content of the work is acquired; and acquiring the target user number of the consumer behavior data.
Further, in the method for determining a content value based on user behavior data, the method includes: the work category at least comprises character content, audio/video content and game content; the setting up data collection dimensions according to consumer behavior of a user on the category of the work includes: aiming at the consumer behavior of the text content, the reading progress of the user is used as sampling data, aiming at the consumer behavior of the audio and video content, the continuous playing time of the user is used as the sampling data, and aiming at the consumer behavior of the game work, the continuous using time of the user is used as the sampling data.
Further, in the method for determining a content value based on user behavior data, the method includes: the matching the obtained goodness index with the content value to determine the content value includes:
obtaining the goodness index of the work output by the goodness index model;
acquiring the author price overflow index and the content volume of the work;
in the summation model, the following calculation is performed:
V＝A+αC+λN；
wherein V is a digital content value index, A is an author premium index, C is a content volume of a work, and N is a goodwill index of the work; alpha is the content value coefficient of the work, and lambda is the value coefficient of the goodness index.
Further, in the method for determining a content value based on user behavior data, the method includes: also comprises
Acquiring relevant single-dimension index data of the work to serve as reference data for content value judgment; the obtained relevant single-dimensional index data of the work are input into a weighting model, and a calculation formula in the weighting model is as follows:
where θ is the weighted average of the relevant single-dimensional indices, f 1 、f 2 ……f k Representing related single-dimensional index data, x 1 、x 2 ……x k Representing weights corresponding to single-dimensional metric data.
In another aspect, the present invention also provides a system for determining content value based on user behavior data, comprising
The first modeling module: the system is used for establishing an goodness index model for the work according to consumer behavior data of the content of the work by a user;
a data acquisition module: the system comprises a first modeling module, a second modeling module and a database, wherein the first modeling module is used for acquiring consumer behavior data of a user on the content of a work to transmit to the first modeling module so as to acquire a goodness index;
further comprising a second modeling module: the method is used for establishing the relation between the goodness-of-look index and the content value and matching the obtained goodness-of-look index with the content value to judge the content value.
Further, in the system for determining a content value based on user behavior data as described above: the establishing of the relationship between the goodness-of-look index and the content value in the second modeling module comprises the following steps: and acquiring the goodness index, the author premium index of the product and the content data of the product to establish a summation model.
Further, in the system for determining a content value based on user behavior data as described above: also comprises
A data matching module: the system is used for matching the work category of the work according to the content of the work and matching the target user according to the gender and the age of the user; the system is also used for setting up data acquisition dimensions according to consumer behaviors of users on different work categories; and the result matched by the data matching module is transmitted to the data acquisition module in a data form.
After adopting the technical scheme, compared with the prior art, the invention has the following beneficial effects:
in the method for judging the content value based on the user behavior data, the goodness index obtained based on the user behavior data can reflect the popularity of the work content in a target user group, can predict the growth trend of the user behavior, and can also be used as a data basis for pricing the content value so that the obtained content value index has higher reliability; the content value index obtained by looking at the index and integrating other related data can provide an IP value pricing reference basis supported by data for an IP demand party; on the other hand, the invention also provides a system for realizing the method, and the data obtained by the system assists the IP buyer and the IP seller to judge the reasonable range of the content transaction price and price the IP.
Drawings
FIG. 1 is a graph of the number of persons who finished reading 5363 two works in A, B in a method of determining content value based on user behavior data according to the present invention;
fig. 2 is a block diagram illustrating a system for determining content value based on user behavior data according to the present invention.
Detailed Description
The invention will be further described with reference to the following drawings and specific examples to aid in understanding the contents of the invention.
A method for determining content value based on user behavior data comprises
Establishing an goodness index model for the work according to consumer behavior data of the content of the work by a user;
collecting the consumer behavior data and transmitting the data to the goodness-of-view index model to obtain the goodness-of-view index of the work;
establishing a relationship between the goodness-of-view index and the content value;
and matching the obtained goodness index with the content value to judge the content value.
In the method, the works mainly take novel works as main parts, and short stories, cartoons, games and other works as auxiliary parts; the goodness index is set for the works, so that a relatively uniform comparison basis exists among the works, and the goodness index set for the works can be used as a measuring basis among the works of different categories (such as novel categories and game categories) and different subject matters of the same category (such as swordsman, hallucinations, speech conditions and other subject matters).
The goodness index model is established according to consumer behavior data of a user on the content of the work, the consumer behavior data comprises consumption behavior data (reading, commenting, sharing, voting and the like) and post-purchase behavior data (such as praise, forwarding, goodness, repurchasing, customer satisfaction and the like), and as the consumption behavior can more directly reflect the reaction of the user on the current content of the work than the post-purchase behavior, the goodness index model is also beneficial to evaluating the value of the early-stage work in the creation, the goodness index model is mainly established according to the consumption behavior data of the user on the content of the work;
the data acquisition method for the content consumption behavior of the works by the user comprises the following steps:
1. classifying the content of the work into categories, and classifying the gender and the age of a user;
the classification of the work content comprises word content, audio and video content, game content and the like so as to collect consumption behavior data of users aiming at different types of work content; the users are divided by sex and age to form different target user groups, so that the popularity of the work content in a certain target user group can be conveniently judged, and the market prospect of a certain work in which target user groups is better can be judged by comparing the popularity of the work in different target user groups.
2. Setting up data acquisition dimensions according to consumption behaviors of users on works of different work categories; specifically comprises
Aiming at the consumption behaviors of the text contents, taking the reading progress of a user as sampling data, aiming at the consumption behaviors of the audio and video contents, taking the continuous playing time of the user as the sampling data, and aiming at the consumption behaviors of the game works, taking the continuous using time of the user as the sampling data; and establishing corresponding data acquisition dimensions according to the category to which the content of the work belongs, and taking the data acquisition dimensions as sampling data to obtain a more accurate goodness-of-view index calculation result.
3. Acquiring consumption behavior data of a user on the content of the work and the number of target users of the consumption behavior data;
and according to the category of the content of the work after the content of the work is classified, performing data acquisition according to the corresponding data acquisition dimension, acquiring consumption behavior data of the user on the content of the work, and transmitting the acquired consumption behavior data to the goodness-of-look index model for calculating the goodness-of-look index.
In the method, the goodness-of-look index model calculates the goodness-of-look index based on a required target user as a reference according to consumption behavior data of the user on the content of the work, and a calculation formula is as follows;
wherein r represents a content consumption progress such as the reading progress (in words or pages), continuous playing time (i.e., viewing duration, in duration), continuous use time (in duration) as described above; q represents the number of people completed at the progress of the content consumption; r represents the total content quantity of the digital content of the work, such as the total word number or the total chapter or the total duration of the work presented by the digital content; and Q represents the maximum value of Q when r is small, wherein the value range of r is as follows: 10> < r >0; in the above formula, the value of R is not more than R, and the value of Q is less than Q.
The goodness index can be obtained by the calculation formula of the goodness index, and the goodness index can be used for reflecting the fluctuation relation among the consumption behaviors of the users, the content of the works and the number of the users; in practical application, by taking a literal work (the expression form is digital content) as an example, the number of readers is continuously increased from the beginning to the end of creation, and readers continuously interrupt and give up continuously consuming the content of the work due to personal preference and other reasons when reading, watching or listening to the work; counting the number of finished people of each consumption progress from 1% to 100% of the reading completion degree, and then, increasing the total number of finished people continuously along with the improvement of the progress, but the trend of the growth rate does not continuously increase all the time, according to the IP requirement, by taking a target user group (female readers, age 18-20 years) of specified gender and age group as the basis, the inventor of the application draws the song shown in the figure 1 by taking the number of finished people as a horizontal coordinate and taking the capacity as a vertical coordinate through reading consumption behavior data of the target user group on two similar works A, B obtained from a certain reading service platform; from the graph of fig. 1, it is apparent that the curve of the number of persons who finish reading of story a is lower in the falling tendency than story B, and thus story a is more popular with readers than story B.
Through data fitting, the inventor finds that the curve meets the characteristics of a function y = k (1- (x-a)/b) ^ n + c (wherein k, a, b and c are constants), so that a calculation formula of an index n is a good-looking index formula of the content of the work in the method; therefore, the goodness-of-view index in the method reflects the attenuation trend of the number of people who finish content consumption, so that the content value of the story A is higher and the quality is higher in comparison with the goodness-of-view index.
Therefore, in the method, the goodness index is set for the work according to the consumption behavior data of the user to the content of the work, the goodness index can intuitively embody the popularity of the content of the current work in a target user group, and the growth trend of the user behavior can be predicted; for the curve reflected by the goodness index, the longitudinal comparison can reflect the quality change of different progresses (paragraphs or chapters and the like) of the work, and the transverse comparison can reflect the popularity of the content authored by the author in the target user so as to measure the authoring level of the author. Therefore, the good-looking index can be used as a judgment basis for the value-added potential of the growth-type works, the popular population and audience quantity of the contents of the works can be judged, and a more accurate and reliable reference basis is provided for IP pricing of an IP demand party.
Besides the written works given in the above embodiments, the goodness-of-look index of the method of the present invention can also be calculated for audio-video and game works as long as corresponding data acquisition dimensions are selected for different types of works, and the goodness-of-look index of the content of the works can also be obtained, so as to obtain the change trend of the popularity of the works, which is used as the basis for judging the value of the works.
In the method, the users are divided into gender and age, the gender and the age range can be designated as the target users according to different IP requirements and aiming at the content types of the works, the popularity of one work in a certain target user group is obtained, the calculation of the good-looking index has certain flexibility, and the target group is allowed to be selectively screened so as to be matched with an IP demand party to pertinently evaluate the content value of the work.
Particularly, for works in the process of creation, according to the advancement of chapters, plots and the like, the reading amount can keep increasing, but the increasing rate also has the condition of increasing or slowing down, and meanwhile, the vermicelli amount can be subjected to the condition of accumulation or later loss, so that the good-looking indexes can clearly reflect the conditions in the method provided by the invention as the evaluation standard of the works:
(1) For IP, the higher the look-good index, the lower the reader churn rate, thus causing more new readers and retaining old readers, facilitating the exploration of hot and potential IP;
(2) For an author, the goodness index can be calculated according to the unit consumption progress (such as each chapter), according to the calculation result, the author can know the user preference more clearly, the powder dropping point of the work is judged, and the content consumption behavior data of the user generates the reference value for creation;
(3) For an IP demand party, based on the development trend of the work reflected by the goodness index, the market judgment basis can be provided for the IP demand party, and the IP demand party can grasp the opportunity for purchase; the addition model constructed based on the goodness index can assist an IP demand party in judging the IP value.
In the method of the present invention, the establishing of the relationship between the goodness-of-look index and the content value, and the matching of the obtained goodness-of-look index and the content value to determine the content value includes:
establishing a summation model according to the goodness index, the author premium index of the works and the content volume of the works to obtain a digital content value index V, specifically:
obtaining the goodness index of the work output by the goodness index model;
acquiring the author price overflow index and the content volume of the work;
the calculation was performed as follows:
V＝A+αC+λN；
wherein A is the author premium index, C is the content volume of the work, and N is the goodwill index of the work; alpha is a content value coefficient of the work, and lambda is a good-looking index value coefficient; and setting corresponding coefficient values according to the content classification of the work.
Because of the market influence of different authors, the authors can feed the premium index according to the IP market feedback, and the premium index obtained from the market is input into a summation model to obtain the content value; in the method, the goodness index reflects the popularity of the content of the work in the user group, the overflow index of the author and the content volume of the work are integrated to obtain the content value index of the work, and the content value index can be used as a pricing basis of the content value to assist IP buyers and sellers in judging the reasonable range of the content trading price and pricing the IP.
The method further comprises the step of obtaining relevant single-dimension index data of the work to serve as reference data for content value judgment.
In order to judge the content value of the work more accurately, data records such as the number of fans, the amount of praise, the forwarding amount, the number of votes, the amount of comments and the like of the digital content are used as relevant single-dimensional index data according to the goodness index model, and the data records are used as auxiliary parameters of the goodness index and the content value index and input into the weighting model, so that the content value and the value-added potential of the work are judged.
The calculation formula of the relevant single-dimension index data of the works in the weighting model is as follows:
where θ is the weighted average of the relevant single-dimensional indices, f 1 、f 2 ……f k Representing related single-dimensional index data, x 1 、x 2 ……x k Representing weights corresponding to the single-dimensional index data; according to the emphasis reference requirement of an IP demand side, solving a weighted average theta of relevant single-dimensional indexes; if the IP demand side focuses on considering the number of fans, votes, comments and the like of a work, the IP demand side only needs to calculate the weighted average of the relevant indexes. According to the formula, the acquired user consumption behavior data and post-purchase behavior data are allowed to be input in the weighting model, multi-dimensional user behavior data can be covered, the preference degree of the user to the content of the work can be accurately reflected, and the content value of the work can be more effectively obtained in an auxiliary mode.
Wherein the right of each single dimension index can be set according to the requirement of an IP operator in the concrete implementation; for example, the right of the fan number of all works on a certain reading service platform is 10%, the voting number is 13%, and the comment amount is 11% … …; under an addition model for evaluating content value, appropriate weight is set as a standard for a relevant single-dimensional index of a work, an obtained weighted average calculation result also has a measured value, the higher the relevant single-dimensional index data is, the higher the popularity of the work is reflected in an auxiliary manner, the higher the value is, and when the IP value of the work is judged, the relevant single-dimensional index data and the content value index show an addition relation. In the method, the content value index is obtained according to the goodness index, the market value of the author and the content volume of the work, and the related single-dimensional index data are integrated, so that the content value of the work can be more accurately judged.
The evaluation factors of the goodness index (including the consumption progress, the number of people completing, and the like) and related single-dimensional index data (such as the vermicelli amount, the evaluation amount, and the like) are collected through a platform server, namely, service platforms of the works such as novel, cartoon, games, and the like, such as a language game APP, and the data can be further obtained through an API (Application Programming Interface) accessed to each novel reading platform; the relevant calculation is carried out by acquiring user data (such as gender, age and the like in the data registered by the user) recorded by the platform server and consumption behavior data (consumption progress, completion number and the like) of the work by the user.
In the method, the goodness index model also allows the collected post-purchase behavior data of the user on the content of the work to be calculated, appropriate post-purchase behavior data is added into the r value of the goodness index calculation formula, and the obtained value can also be used as reference data for judging the value of the content of the work.
The invention relates to a method for judging content value based on user behavior data (namely consumer behavior data), which is applicable to contents in any stage (creation and completion), and obtains a good-looking index aiming at IP (Internet protocol) requirements of a demand party by acquiring user portrait data in a certain stage, such as requirements: science fiction subject, 100 characters finished, female reader, 18-20 years old. By the method, a good-looking index curve of a certain product meeting the requirement aiming at the requirement is obtained, so that an IP demander can select a product which is most matched with the requirement from a large number of products.
Based on the popularity and the content value index reflected by the obtained good-looking index, the method can be used for assisting in pricing the IP of the work in real time according to the price range of the transfer and the flow confirmation of the industry to the vermicelli (or the user), and is favorable for providing the possibility of early showing for the author; at the present stage, no uniform and definite standard exists for pricing of IP values, and based on the goodness index, the content value index and the like of the method, the IP value pricing supported by data is provided for an IP demand party conveniently, and the curve of the goodness index can also be used as a reference basis for future trends of the IP, so that the method has certain accuracy; meanwhile, the method can reflect which part of the work content is more popular based on the reflected user behavior data, provide creation direction guidance for an author and provide reading reference for a user.
On the other hand, as shown in fig. 2, the present invention also provides a system for implementing the method for determining content value based on user behavior data, the system includes
The first modeling module: the system is used for establishing an goodness index model for the work according to consumer behavior data of the content of the work by a user;
a data acquisition module: the system comprises a first modeling module, a second modeling module and a database, wherein the first modeling module is used for acquiring consumer behavior data of a user on the content of a work to transmit to the first modeling module so as to acquire a goodness index;
a second modeling module: the system is used for establishing the relation between the good-looking index and the content value, and matching the obtained good-looking index with the content value to judge the content; the second modeling module establishes the relationship between the goodness-of-view index and the content value, and comprises the following steps: and acquiring the goodness index, the author premium index of the product and the content data of the product to establish a summation model.
Further, the system also comprises a data matching module: the system is used for matching the content category of the work according to the content of the work and matching the target user according to the gender and the age of the user; the system is also used for setting up data acquisition dimensions according to consumer behaviors of the user on the content of the work; and the result matched by the data matching module is transmitted to the data acquisition module in a data form.
The data matching module is used for classifying the content of the works and classifying the gender and the age of the user, wherein the classification of the content of the works comprises the content of characters, the content of audios and videos, the content of games and the like, so that consumption behavior data of the user are collected aiming at the content of the works of different classes; dividing the gender and the age of the user to form different target user groups; and establishing a data acquisition dimension according to the consumption behavior of the user on the content of the work, wherein the reading progress of the user is taken as sampling data for the consumption behavior of the text content, the continuous playing time of the user is taken as the sampling data for the consumption behavior of the audio and video content, and the continuous using time of the user is taken as the sampling data for the consumption behavior of the game work.
The data matching module transmits the matching result, namely the data acquisition condition (the type of the work, the target user, the acquisition dimension and the like) to the data acquisition module according to the requirement of the IP demand side so as to acquire the data of the consumption behavior.
The data acquisition module acquires consumption behavior data (including content consumption progress, number of people completed in the content consumption progress, content amount of the work and the like) of the target user on the content of the work according to the matching result, and transmits the consumption behavior data to the first modeling module.
After acquiring the consumption behavior data of the target user on the content of the work, the first modeling module calculates according to the following formula;
wherein r represents a content consumption progress such as the reading progress (in words or pages), continuous playing time (i.e., viewing duration, in duration), continuous use time (in duration) as described above; q represents the number of people completed at the progress of the content consumption; r represents the total content quantity of the digital content of the work, such as the total word number or the total chapter or the total duration of the work presented by the digital content; q represents the maximum value of Q when r is small (the value range of r is 10> r > 0) and the maximum value of Q (namely the maximum value of Q in the range of r is small); in the above formula, the value of R is not more than R, and the value of Q is less than Q.
The first modeling module transmits the result of the calculation of the goodness-of-look index to the second modeling module.
After the second modeling module obtains the goodness index, a summation model is established with the author premium index of the work and the content data of the work to obtain a digital content value index V, wherein the summation model is carried out according to the following formula:
V＝A+αC+λN；
wherein A is the author premium index, C is the content volume of the work, and N is the goodwill index of the work; alpha is the content value coefficient of the work, and lambda is the value coefficient of the good look index; the values of alpha and lambda are classified according to the content of the work and have different coefficient values.
The data of the content volume, the author price-premium index and the like of the works in the second modeling module are provided through the data acquisition module.
Furthermore, the system of the present invention further includes a third modeling module, where the third modeling module is configured to obtain the relevant single-dimensional index data of the work and calculate a weighted average of the relevant single-dimensional index data according to a calculation formula as follows:
where θ is the weighted average of the relevant single-dimensional indices, f 1 、f 2 ……f k The index data of the relevant single dimension is represented and comprises data such as the number of fans of digital content, the amount of praise, the amount of forwarding, the number of votes cast, the amount of comments and the like, and the data is provided by an acquisition data acquisition module; x is the number of 1 、x 2 ……x k Representing the right corresponding to the single-dimension index data, wherein the right of the single-dimension index can be set according to the requirement of an IP operator in specific implementation; for example, the right of the number of fans of all works on a certain reading service platform is 10%, the number of votes is 13%, and the amount of comments is 11%. According to the emphasis reference requirement of the IP demand side, the third modeling module is enabled to calculate the weighted average theta of the related single-dimensional indexes; if the IP demand side pays attention to the number of fans, votes, comments and the like of a work, the weighted average of the related indexes is obtained.
The system for judging the content value based on the user behavior data can provide data basis for pricing the content value of the work through the good-looking index output by the first modeling module and the content value index output by the second modeling module, and assist IP buyers and sellers in judging the reasonable range of the content transaction price and pricing the IP. Meanwhile, the weighted average value of the related single-dimensional index data provided by the third modeling module can be used as an auxiliary parameter of the goodness-of-look index and the content value index to judge the content value and the value-added potential of the product.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for determining content value based on user behavior data, characterized by: comprises that
Establishing an goodness index model for the work according to consumer behavior data of the content of the work by a user;
collecting the consumer behavior data and transmitting the data to the goodness index model to obtain the goodness index of the product;
establishing a relationship between the goodness-of-view index and the content value;
and matching the obtained good-looking index with the content value to judge the content value.
2. The method of claim 1, wherein the method comprises: the establishing of the relationship between the goodness index and the content value comprises the following steps:
and establishing a summation model according to the goodness index of the work, the author premium index of the work and the content volume of the work.
3. The method of claim 1, wherein the method comprises: in the process of establishing the goodness index model for the work according to the consumer behavior data of the content of the work by the user, a calculation formula in the goodness index model is as follows:
wherein r represents the content consumption progress, and q represents the number of people who finish the content consumption progress; r represents the total content amount of the digital content of the work; and Q represents the maximum value of Q when R is smaller, wherein the value range of R is more than 10 and more than 0,r, the value of R is not more than R, and the value of Q is less than Q.
4. The method of claim 3, wherein the method comprises: the method for collecting the consumer behavior data comprises the following steps:
dividing the category of the works according to the content of the works, and dividing a target user according to the gender and age of the user;
setting data acquisition dimensions according to consumer behaviors of users on different work categories;
according to the category of the content of the work, data acquisition is carried out according to the corresponding data acquisition dimension, and consumer behavior data of the user on the content of the work is acquired; and acquiring the target user number of the consumer behavior data.
5. The method of claim 4, wherein the method comprises: the work category at least comprises text content, audio and video content and game content; the setting up a data collection dimension according to consumer behavior of a user on a category of the work includes: aiming at the consumer behavior of the text content, the reading progress of the user is used as sampling data, aiming at the consumer behavior of the audio and video content, the continuous playing time of the user is used as the sampling data, and aiming at the consumer behavior of the game work, the continuous using time of the user is used as the sampling data.
6. The method of determining content value based on user behavior data according to any one of claims 2-5, wherein: the matching the obtained goodness index with the content value to determine the content value includes:
obtaining the goodness index of the work output by the goodness index model;
acquiring the author price overflow index and the content volume of the work;
in the summation model, the calculation is performed according to the following formula:
V＝A+αC+λN；
wherein V is a digital content value index, A is an author premium index, C is a content amount of a work, and N is a goodness index of the work; alpha is the content value coefficient of the work, and lambda is the value coefficient of the goodness index.
7. The method of determining content value based on user behavior data according to any one of claims 1-5, wherein: also comprises
Acquiring relevant single-dimension index data of the work to serve as reference data for content value judgment; the obtained relevant single-dimensional index data of the work are input into a weighting model, and a calculation formula in the weighting model is as follows:
where θ is the weighted average of the relevant single-dimensional indices, f 1 、f 2 ……f k Representing related single-dimensional index data, x 1 、x 2 ……x k Representing weights corresponding to single-dimensional metric data.
8. A system for determining content value based on user behavior data, characterized by: comprises that
The first modeling module: the system is used for establishing an goodness index model for the work according to consumer behavior data of the content of the work by a user;
a data acquisition module: the system comprises a first modeling module, a second modeling module and a data processing module, wherein the first modeling module is used for acquiring consumer behavior data of a user on the content of a work and transmitting the consumer behavior data to the first modeling module so as to acquire a good-looking index;
further comprising a second modeling module: and the method is used for establishing the relation between the good-looking index and the content value and matching the obtained good-looking index with the content value to judge the content value.
9. The system for determining content value based on user behavior data as claimed in claim 8, wherein: the establishing of the relationship between the goodness-of-look index and the content value in the second modeling module comprises the following steps: and acquiring the goodness index, the author premium index of the product and the content data of the product to establish a summation model.
10. The system for determining content value based on user behavior data as claimed in claim 8, wherein: also comprises
A data matching module: the system is used for matching the work category of the work according to the content of the work and matching the target user according to the gender and the age of the user; the system is also used for setting up data acquisition dimensions according to consumer behaviors of users on different work categories; and the result matched by the data matching module is transmitted to the data acquisition module in a data form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711079164.8A CN107886357A (en) | 2017-11-06 | 2017-11-06 | The method and system of content value is judged based on user behavior data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711079164.8A CN107886357A (en) | 2017-11-06 | 2017-11-06 | The method and system of content value is judged based on user behavior data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107886357A true CN107886357A (en) | 2018-04-06 |
Family
ID=61778909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711079164.8A Pending CN107886357A (en) | 2017-11-06 | 2017-11-06 | The method and system of content value is judged based on user behavior data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886357A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298592A (en) * | 2019-07-02 | 2019-10-01 | 北京星和汇科技有限公司 | A kind of virtual personal value evaluating method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101568921A (en) * | 2006-12-22 | 2009-10-28 | 雅虎公司 | Dynamic pricing models for digital content |
| CN102567477A (en) * | 2011-06-16 | 2012-07-11 | 北京亿赞普网络技术有限公司 | Website value evaluation method and device |
| CN103679507A (en) * | 2013-12-06 | 2014-03-26 | 冯志刚 | Method and system for grading and ranking works or commodities |
| CN104317959A (en) * | 2014-11-10 | 2015-01-28 | 北京字节跳动网络技术有限公司 | Data mining method and device based on social platform |
| CN104361063A (en) * | 2014-11-04 | 2015-02-18 | 北京字节跳动网络技术有限公司 | User interest discovering method and device |
| US9100722B2 (en) * | 2008-01-16 | 2015-08-04 | Apple Inc. | Filtering and tailoring multimedia content based on observed user behavior |
| CN104951956A (en) * | 2014-03-31 | 2015-09-30 | Tcl集团股份有限公司 | Film ranking method and device |
| CN106056297A (en) * | 2016-05-31 | 2016-10-26 | 叶波 | Film and television big data evaluation decision aiding system and method |
| CN106339502A (en) * | 2016-09-18 | 2017-01-18 | 电子科技大学 | Modeling recommendation method based on user behavior data fragmentation cluster |
| CN106469177A (en) * | 2015-08-21 | 2017-03-01 | 中国传媒大学 | Internet film user satisfaction analysis method based on structural equation model and system |
| CN106779827A (en) * | 2016-12-02 | 2017-05-31 | 上海晶樵网络信息技术有限公司 | A kind of Internet user's behavior collection and the big data method of analysis detection |
| CN106909618A (en) * | 2017-01-13 | 2017-06-30 | 广州薏生网络科技有限公司 | A kind of article of healthy class from media propagates the computational methods of combined influence power |
| CN107229666A (en) * | 2016-12-30 | 2017-10-03 | 北京字节跳动科技有限公司 | A kind of interest heuristic approach and device based on commending system |
-
2017
- 2017-11-06 CN CN201711079164.8A patent/CN107886357A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101568921A (en) * | 2006-12-22 | 2009-10-28 | 雅虎公司 | Dynamic pricing models for digital content |
| US9100722B2 (en) * | 2008-01-16 | 2015-08-04 | Apple Inc. | Filtering and tailoring multimedia content based on observed user behavior |
| CN102567477A (en) * | 2011-06-16 | 2012-07-11 | 北京亿赞普网络技术有限公司 | Website value evaluation method and device |
| CN103679507A (en) * | 2013-12-06 | 2014-03-26 | 冯志刚 | Method and system for grading and ranking works or commodities |
| CN104951956A (en) * | 2014-03-31 | 2015-09-30 | Tcl集团股份有限公司 | Film ranking method and device |
| CN104361063A (en) * | 2014-11-04 | 2015-02-18 | 北京字节跳动网络技术有限公司 | User interest discovering method and device |
| CN104317959A (en) * | 2014-11-10 | 2015-01-28 | 北京字节跳动网络技术有限公司 | Data mining method and device based on social platform |
| CN106469177A (en) * | 2015-08-21 | 2017-03-01 | 中国传媒大学 | Internet film user satisfaction analysis method based on structural equation model and system |
| CN106056297A (en) * | 2016-05-31 | 2016-10-26 | 叶波 | Film and television big data evaluation decision aiding system and method |
| CN106339502A (en) * | 2016-09-18 | 2017-01-18 | 电子科技大学 | Modeling recommendation method based on user behavior data fragmentation cluster |
| CN106779827A (en) * | 2016-12-02 | 2017-05-31 | 上海晶樵网络信息技术有限公司 | A kind of Internet user's behavior collection and the big data method of analysis detection |
| CN107229666A (en) * | 2016-12-30 | 2017-10-03 | 北京字节跳动科技有限公司 | A kind of interest heuristic approach and device based on commending system |
| CN106909618A (en) * | 2017-01-13 | 2017-06-30 | 广州薏生网络科技有限公司 | A kind of article of healthy class from media propagates the computational methods of combined influence power |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298592A (en) * | 2019-07-02 | 2019-10-01 | 北京星和汇科技有限公司 | A kind of virtual personal value evaluating method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Budzinski et al. | Merger simulation in competition policy: A survey | |
| CN108921398B (en) | Shop quality evaluation method and device | |
| Siering et al. | What drives the helpfulness of online product reviews? From stars to facts and emotions | |
| CN108133013A (en) | Information processing method, device, computer equipment and storage medium | |
| CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
| KR102038237B1 (en) | Credit score model training method, credit score calculation method, apparatus and server | |
| CN103106600A (en) | Commodity information push system and commodity information push method | |
| CN112015721A (en) | E-commerce platform storage database optimization method based on big data | |
| CN111222410A (en) | Shop and merchant consumption behavior analysis guiding marketing system based on face recognition | |
| CN105956882A (en) | Method and device for getting procurement demand | |
| CN106127521A (en) | A kind of information processing method and data handling system | |
| WO2023000491A1 (en) | Application recommendation method, apparatus and device, and computer-readable storage medium | |
| CN111079941A (en) | Credit information system combining expert experience model and supervised machine learning algorithm | |
| CN111611496A (en) | Product recommendation method and device | |
| CN106204100A (en) | A kind of data processing method and data handling system | |
| KR102297332B1 (en) | Electronic device and how to calculate influence of influencer on electronic devices | |
| CN115860870A (en) | Commodity recommendation method, system and device and readable medium | |
| US20220122178A1 (en) | Data display method and apparatus, terminal device, and storage medium | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| TWI657395B (en) | Opinion leader related network-based trading system, method, and storage medium | |
| CN107886357A (en) | The method and system of content value is judged based on user behavior data | |
| CN116501840B (en) | NLP intelligent analysis method for guest acquisition marketing | |
| KR20210003421A (en) | Method and sever for sorting user preferred post | |
| CN116739654A (en) | Information acquisition device and system | |
| CN110889716A (en) | Method and device for identifying potential registered user |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |