CN111598310A - Book popularity prediction method and equipment based on time series analysis - Google Patents
Book popularity prediction method and equipment based on time series analysis Download PDFInfo
- Publication number
- CN111598310A CN111598310A CN202010345025.0A CN202010345025A CN111598310A CN 111598310 A CN111598310 A CN 111598310A CN 202010345025 A CN202010345025 A CN 202010345025A CN 111598310 A CN111598310 A CN 111598310A
- Authority
- CN
- China
- Prior art keywords
- book
- heat
- time series
- series analysis
- analysis model
- 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
- 238000012731 temporal analysis Methods 0.000 title claims abstract description 60
- 238000000700 time series analysis Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000011156 evaluation Methods 0.000 claims abstract description 37
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 13
- 230000015654 memory Effects 0.000 claims description 16
- 230000001186 cumulative effect Effects 0.000 claims description 10
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 abstract description 4
- 201000004569 Blindness Diseases 0.000 abstract description 3
- 238000012552 review Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 230000002349 favourable effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 235000019633 pungent taste Nutrition 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001744 unit root test Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a book popularity prediction method and equipment based on time series analysis, wherein the method comprises the following steps: defining a heat evaluation standard for book resources, and calculating the heat value of the book in a certain period according to the heat evaluation standard; selecting the heat value of the book in a plurality of periods to obtain a book heat time sequence; detecting the book heat time sequence, selecting a stable and non-white noise sequence to deduce parameters of the time sequence analysis model, and constructing the time sequence analysis model; and predicting the heat of the book at the future moment based on the time series analysis model, and carrying out rationality evaluation on the time series analysis model. The invention defines a new heat evaluation standard for book heat based on a statistical method, and applies a time series model to book heat value prediction, thereby avoiding errors possibly caused by blindness and subjectivity for book topic selection argument of a publishing company and future trend prediction.
Description
Technical Field
The invention relates to the technical field of book publishing big data, in particular to a book popularity prediction method and equipment based on time series analysis.
Background
With the development of innovative technologies such as big data, artificial intelligence and the like, the book publishing industry faces huge challenges and opportunities, particularly book questions are important for book publishing and publishing, and nowadays, a publishing company has an independent and standardized book question-selecting and argumentation system on the book question-selecting argumentation, and the system is an important admission system for the publishing company to evaluate and judge whether the choice of the questions is right or not in economic benefit and social benefit evaluation on the book questions.
At present, the conventional method is adopted by a publishing company for setting and demonstrating book topics, relevant information and data of the topics are collected, sorted and analyzed, and the value and expected benefit of the topics are subjectively evaluated in a manual processing mode. These are all built on manual information and data collection and sorting, and have inaccuracy and incompleteness.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a book popularity prediction method and equipment based on time series analysis.
The embodiment of the invention provides a book popularity prediction method based on time series analysis, which comprises the following steps:
defining a heat evaluation standard for book resources, and calculating the heat value of the book in a certain period according to the heat evaluation standard;
selecting the heat value of the book in a plurality of periods to obtain a book heat time sequence;
detecting the book heat time sequence, selecting a stable and non-white noise sequence to deduce parameters of a time sequence analysis model, and constructing the time sequence analysis model;
and predicting the heat of the book at the future moment based on the time series analysis model, and carrying out rationality evaluation on the time series analysis model.
According to the embodiment of the invention, at least the following technical effects are achieved:
the method makes up for subjectivity and incompleteness of traditional book title selection in book publishing industry, defines a new popularity evaluation standard for book popularity based on a statistical method, and applies a time series model to book popularity prediction, thereby avoiding errors possibly caused by blindness and subjectivity for book title argument of publishing company and future trend prediction.
According to some embodiments of the present invention, the defining a popularity evaluation criterion for the book resources, and calculating a popularity value of the book in a certain period according to the popularity evaluation criterion includes:
defining heat evaluation standards comprising cumulative book feedback and sales scores, periodic book feedback and sales scores, author heat scores and good score scores, and assigning different weight values to each heat evaluation standard;
and carrying out weighted summation on the heat evaluation standards of the books to obtain the heat value of the books in a certain period.
According to some embodiments of the invention, the performing the rationality assessment on the time series analysis model comprises:
calculating an error between a fitting value generated by the time series analysis model and an actual value, and if the error is smaller than a preset range, meeting the rationality requirement; and if the error is larger than the preset range, adjusting the model until the error between the fitting value generated by refitting the time sequence analysis model and the actual value is smaller than the preset range, and forecasting the heat of the book at the future moment again based on the time sequence analysis model.
According to some embodiments of the invention, the parameters of the time series analysis model are derived according to a Bayesian information criterion or a Chichi information criterion.
According to some embodiments of the invention, the book resource is sourced from an elastic search, solr, or lucene full text search engine.
Some embodiments of the present invention provide a book popularity prediction apparatus based on time series analysis, comprising at least one control processor and a memory for communicative connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of book popularity prediction based on time series analysis as described above.
Some embodiments of the present invention provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a method of book popularity prediction based on time series analysis as described above.
According to the embodiment of the invention, at least the following technical effects are achieved:
the invention provides book popularity prediction equipment based on time series analysis and a computer readable storage medium, and achieves the same beneficial effects as the method.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart of a book popularity prediction method based on time series analysis according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of book data statistics provided by an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating an implementation of a time series analysis mode according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a book popularity prediction apparatus based on time series analysis according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Referring to fig. 1, an embodiment of the present invention provides a book popularity prediction method based on time series analysis, including the following steps:
s100, defining a heat degree evaluation standard for book resources, and calculating a heat degree value of a book in a certain period according to the heat degree evaluation standard;
the method specifically comprises the following steps:
s101, defining heat evaluation standards including cumulative book feedback and sales scores, periodic book feedback and sales scores, author heat scores and good score scores, and assigning different weight values to each heat evaluation standard;
s102, weighting and summing the book heat evaluation criteria to obtain the heat value of the book in a certain period.
As an alternative embodiment, the full book popularity value is set to 100 points, and the calculation formula is as follows:
book popularity ═ cumulative book feedback and sales score × 50% + periodic book feedback and sales score × 30% + author popularity score × 10% + good score × 10%
(1) Cumulative book feedback and sales scores are calculated as follows:
x is cumulative book feedback and sales index (number of comments + number of collections) × 1+ sales data × 5+ number of book reviews × 3
In the above formula, the number of reviews, the number of collections, the sales data, and the number of reviews of books are obtained by searching an elastic search full-text search engine, x is the cumulative book feedback and sales index, and base is a base number (related to sales volume), such as popular children books, where base is 10000; book of economy, base 1000; other categories may take different values depending on the actual situation. score the result calculated is the cumulative book feedback and sales score.
(2) The periodic book feedback and sales scores are calculated as follows:
x is the period book feedback and sale index (number of comments + collection number) x 1+ sale data x 5+ book comment number x 3
(3) The author heat score was calculated as follows:
author hotness score ═ reader number index × 70% + good rating index for all books by this author × 30%
Wherein, the reader number index is calculated as follows:
in the above formula, x is the number of readers of the book, max is the maximum number of readers of the single book stored in the elastic search, and min is the minimum number of readers of the single book stored in the elastic search. fn (x) is the calculated reader number index.
The evaluation formula of the favorable rating index of all books by the author is as follows:
fn (x) (cumulative number of reviews of all books by the author/cumulative number of reviews of all books by the author) × 100
In the above formula, the accumulated favorable scores of all books of the author and the accumulated comment quantity of all books can be obtained by querying the elastic search, and fn (x) is the calculated favorable scores of all books of the author.
(4) The good score is calculated as follows:
good score (five stars + four stars)/(five stars + four stars + three stars + two stars + one star) × 100
The number of book reviews from five stars to one star in the book can be obtained by inquiring an elastic search engine, a solr or a lucene full-text search engine and the like.
The book popularity evaluation standard is constructed for the first time, the book popularity evaluation standard is very pertinent and applicable in the book publishing field, the book feedback and sales index, the author popularity index and the goodness index which are proposed around the book popularity evaluation standard are all index quantification dimensions unique and peculiar to the book publishing field, and the book category which basically covers the book publishing field can effectively quantify and faithfully reflect the book popularity index constitution and evaluation results in terms of application.
S200, selecting the heat value of the book in a plurality of periods to obtain a book heat time sequence;
the book popularity time sequence can be calculated based on the popularity evaluation standard formula, in the practical application process, different popularity values in different time interval ranges can be obtained by calculating the actual conditions in different time granularity ranges (such as time interval ranges of days, weeks, months and the like), and the book popularity time sequence can be obtained by sequencing the different popularity values according to time. For example, a book popularity time series is obtained by selecting popularity values of 30 periods (one period per month).
S300, detecting the book heat time sequence, selecting a stable and non-white noise sequence to deduce parameters of the time sequence analysis model, and constructing the time sequence analysis model;
specifically, the method comprises the following steps:
the time series analysis model herein uses an ARIMA model.
Firstly, white noise detection is carried out on a time sequence by adopting an ADF (unit root test) detection method, and stationarity detection is carried out on a non-white noise sequence. In the process of carrying out stationarity prediction, differential operation is carried out on the non-stationary time series, so that the d (differential order) value of the input parameter of the model is determined. When white noise detection is carried out, if the p-value is more than 0.05, the time sequence is considered to be a white noise time sequence, the analysis of the white noise sequence is stopped, and if the p-value is far less than 0.05, the time sequence is considered to be a non-white noise time sequence.
The input parameters of the time series analysis model are derived according to a Bayesian Information Criterion (BIC) or an Akaichi Information Criterion (AIC).
In the above, the order of the difference is determined, and then a series of different values of BIC are calculated according to different values of p and q by using a Bayesian Information Criterion (BIC), and the value of p and q with the minimum BIC is preferred.
And finally, constructing a time series analysis model.
S400, predicting the heat of the book at a future moment based on the time series analysis model, and carrying out rationality evaluation on the time series analysis model.
Specifically, predicting the popularity of the book at a future time includes: and predicting the heat degree at a specific time in the future in a short distance.
Specifically, the rationality evaluation of the time series analysis model includes:
calculating the error between a fitting value generated by the time series analysis model and an actual value, and if the error is smaller than a preset range, meeting the rationality requirement; and if the error is larger than the preset range, adjusting the input parameters until the error between the fitting value generated by the time series analysis model through refitting and the actual value is smaller than the preset range, and predicting the heat of the book at the future moment again based on the time series analysis model.
The method makes up for subjectivity and incompleteness of traditional book title selection in book publishing industry, defines a new popularity evaluation standard for book popularity based on a statistical method, and applies a time series model to book popularity prediction, thereby avoiding errors possibly caused by blindness and subjectivity for book title argument of publishing company and future trend prediction.
For convenience of understanding, referring to fig. 2 and 3, an embodiment is illustrated, and the specific flow is as follows:
(1) the data source is as follows: original data such as internet books and e-commerce sales are stored in a distributed file system HDFS, then through an ETL (Extract-Transform-Load) process, which is used for describing a process of extracting (Extract), converting (Transform) and loading (Load) the data from a source end to a destination end, comment, collection, sales, book review, full-text retrieval information and the like of the books are stored in an elastic search, all information of a single book is stored in HBase, and then the elastic search can be inquired through an aggregation and statistical analysis interface to provide an interface for book heat calculation.
(2) Defining a heat evaluation standard, and obtaining the book heat value of each book according to the heat evaluation standard.
(3) Building book hotDegree time series: taking a book of financing XXX published by a certain publishing company as an example of a prediction object, automatically deducing 30 default actual book heat values according to the book heat calculation formula, and constructing a book heat time sequence (x) of the book with months as a time variable by using the 30 book heat values1,x2,x3,…,x30) The order here is (3.99, 45.48, 50.87.., 1.73).
(4) Performing stationarity detection and white noise detection on the book heat time sequence: by adopting an ADF (element root test) method, H0 of the ADF test assumes that an element root exists in a time sequence, and the test results of the element root in the time sequence are obtained: the method comprises the following steps of (1) counting a value t, p-value, critical ADF (automatic document feeder) check values under 1%, 5% and 10% confidence intervals, if the value of the p-value is smaller than the critical value of the 1%, 5% and 10% confidence intervals, rejecting an original hypothesis correspondingly with the probability of 99%, 95% and 90%, taking the critical value of the 5% confidence interval as a standard in the embodiment, calculating whether the ADF check p-value of the book heat time sequence is smaller than the critical value of the 5% confidence interval as the standard, and if so, determining the ADF check p-value is a stable sequence; otherwise, it is a non-stationary time series. Then a white noise check is performed and if the p-value is greater than 0.05, the time series is considered to be a white noise time series.
The stability of the book heat time sequence (3.99, 45.48, 50.87.,. 1.73) is tested by the ADF method, and the stability test results of the book heat time sequence are shown in the following table 1:
TABLE 1
As can be seen from Table 1, in the first Test results, the Test-Static Value (t-statistic) was less than 1%, the cut-off Value at the confidence intervals of 5% and 10%, but the p-Value was greater than 0.05, so the sequence was a non-stationary time sequence. 1 order ofThe difference d is 1, a time sequence after the difference is obtained (41.49, 5.39., -11.91), the time sequence is checked again, and the Test-Static Value is less than 1%, the critical Value under the confidence interval of 5% and 10% and the p-Value is less than 0.05 according to the numerical Value of the result of the check again (wherein the p-Value 5.1934854387004333e in the result of the check again is less than 0.05)-5) And the requirement of the stable time sequence is met, so that the book popularity time sequence after the difference is the stable time sequence.
(5) Deriving parameter values for the time series analysis model: a complete derivation of the time-series analysis model is performed (since the time-series analysis model is well known in the art and is relatively complex, the present embodiment only describes the result, and does not discuss the mathematical model and formula in a detailed classification). The method of AIC (Chi information criterion) is adopted to deduce parameter values (p, d, q) in a known time series analysis model formula (ARIMA), and the derivation results of the model parameter values are shown in the following table 2:
p | d | q | AIC |
3 | 1 | 2 | 1534.64385321 |
3 | 1 | 1 | 1467.09814278 |
2 | 1 | 2 | 1398.88.42321 |
2 | 1 | 1 | 987.343772175 |
1 | 1 | 0 | 1102.10971042 |
1 | 1 | 1 | 1056.39067223 |
TABLE 2
Among them, d ═ 1 is known. According to the requirements of the time series analysis experiment method, when the AIC is taken as the minimum value of 987.343772175, the parameter values (p, d, q) are the optimal values, namely: p is 2 and q is 1. The parameter values (p, d, q) are derived to obtain a time series analysis model that conforms to the book popularity prediction.
(6) According to the input parameters of the model, an ARIMA model is constructed: when the model is used for forward (future) prediction, the longer the prediction period, the larger the error, the month is taken as a time interval in the example, and the heat value of the next month in the book heat time sequence is predicted.
Substituting the derived parameter values (p, d and q) into the time series analysis model to obtain a complete time series analysis model conforming to the prediction object, analyzing and calculating the book heat time series (41.49, 5.39., -11.91) through the obtained time series analysis model to obtain the book heat estimation result, namely the fitting value, whether the fitting value is proper or not, and needing to be checked, wherein the verification is actually to verify the constructed model, and details are not described here.
(7) Evaluating the rationality of constructing a time series book popularity prediction model: and (4) evaluating whether the book heat prediction model is reasonable or not according to the error between the book heat prediction value (fitting value) and the actual calculation value. The calculation formula is as follows:
absolute error | actual value-fitted value |
For visual embodiment, the actual value and the fitting value are compared, the comparison is reasonable within a set error range, and a book heat trend fitting graph and an actual graph (constructed according to the actual heat of the book) are constructed according to the comparison and judgment, so that the trends are generally consistent and are proper. The book heat fitting condition of nearly 11 months of financing XXX is obtained according to the actual value and the fitting value of the time series analysis model, as shown in the following table 3:
TABLE 3
Where AE ═ actual value-fitted value |; APE ═ actual value-fitted value |/actual value.
It is reasonable to set the absolute error between the fitting value and the actual value within ± 15%, and as can be seen from the above table, the model prediction is reasonable (the absolute error between the fitting value and the actual value of the data is within a reasonable range) with the error within the set range. If the relative error is larger than 15%, the model needs to be readjusted, specifically: and (4) returning to the step (4) to perform re-inspection on the known non-stationary sequence, taking different differences (d is 2 or d is 3, and the like), performing re-inspection on the time sequence after the difference to determine whether the time sequence is a stationary sequence, if the time sequence is a stationary sequence, determining the difference value of the stationary sequence as the value of d, deriving p and q parameter values in the time sequence analysis model by using an AIC (interactive aided learning) method to obtain an adjusted time analysis model, and inspecting the reasonability of the model until the absolute error is within 15%, determining that the model is reasonable, and predicting, wherein details are not described herein.
Referring to FIG. 4, an embodiment of the present invention provides an embodiment of the present invention, which provides a book popularity prediction apparatus based on time series analysis;
the book popularity prediction device based on time series analysis can be any type of intelligent terminal, such as a mobile phone, a tablet computer, a personal computer and the like.
Specifically, the book popularity prediction apparatus based on time series analysis includes: one or more control processors and memory, one control processor being exemplified in fig. 4. The control processor and the memory may be connected by a bus or other means, as exemplified by the bus connection in fig. 4.
The memory is a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the book popularity prediction device based on time series analysis in the embodiment of the present invention; the control processor implements the book popularity prediction method based on time series analysis of the above-described method embodiments by running non-transitory software programs, instructions, and modules stored in the memory.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes a memory remotely located from the control processor, and the remote memories may be connected to the book popularity prediction apparatus based on time series analysis via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory, and when executed by the one or more control processors, perform the book popularity prediction method based on time series analysis in the above-described method embodiments, such as steps S100 to S400 in fig. 1.
Embodiments of the present invention further provide a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, which are executed by one or more control processors, for example, by one of the control processors in fig. 4, and may cause the one or more control processors to execute the book popularity prediction method based on time-series analysis in the above-described method embodiments, for example, steps S100 to S400 in fig. 1.
Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by software plus a general hardware platform. Those skilled in the art will appreciate that all or part of the processes of the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (7)
1. A book popularity prediction method based on time series analysis is characterized by comprising the following steps:
defining a heat evaluation standard for book resources, and calculating the heat value of the book in a certain period according to the heat evaluation standard;
selecting the heat value of the book in a plurality of periods to obtain a book heat time sequence;
detecting the book heat time sequence, selecting a stable and non-white noise sequence to deduce parameters of a time sequence analysis model, and constructing the time sequence analysis model;
and predicting the heat of the book at the future moment based on the time series analysis model, and carrying out rationality evaluation on the time series analysis model.
2. The book popularity prediction method based on time series analysis as claimed in claim 1, wherein the method for book popularity assessment is defined for book resources, and the popularity value of the book in a certain period is calculated according to the popularity assessment, comprising the steps of:
defining heat evaluation standards comprising cumulative book feedback and sales scores, periodic book feedback and sales scores, author heat scores and good score scores, and assigning different weight values to each heat evaluation standard;
and carrying out weighted summation on the heat evaluation standards of the books to obtain the heat value of the books in a certain period.
3. The book popularity prediction method based on time series analysis according to any one of claims 1 or 2, characterized in that the time series analysis model is subjected to rationality evaluation, and the method comprises the following steps:
calculating an error between a fitting value generated by the time series analysis model and an actual value, and if the error is smaller than a preset range, meeting the rationality requirement; and if the error is larger than the preset range, adjusting the model until the error between the fitting value generated by refitting the time sequence analysis model and the actual value is smaller than the preset range, and forecasting the heat of the book at the future moment again based on the time sequence analysis model.
4. The book popularity prediction method based on time series analysis as claimed in claim 3, wherein: and deducing parameters of the time series analysis model according to a Bayesian information criterion or a Chi information criterion.
5. The method of claim 1, wherein the book resource is derived from an elastic search engine, solr or lucene full text search engine.
6. A book popularity prediction device based on time series analysis is characterized in that: comprises at least one control processor and a memory for communicative connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of book popularity prediction based on time series analysis as claimed in any one of claims 1 to 5.
7. A computer-readable storage medium characterized by: the computer-readable storage medium stores computer-executable instructions for causing a computer to execute a book popularity prediction method based on time series analysis according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010345025.0A CN111598310A (en) | 2020-04-27 | 2020-04-27 | Book popularity prediction method and equipment based on time series analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010345025.0A CN111598310A (en) | 2020-04-27 | 2020-04-27 | Book popularity prediction method and equipment based on time series analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111598310A true CN111598310A (en) | 2020-08-28 |
Family
ID=72189454
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010345025.0A Pending CN111598310A (en) | 2020-04-27 | 2020-04-27 | Book popularity prediction method and equipment based on time series analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111598310A (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611726B1 (en) * | 1999-09-17 | 2003-08-26 | Carl E. Crosswhite | Method for determining optimal time series forecasting parameters |
JP2010020442A (en) * | 2008-07-09 | 2010-01-28 | Toshiba Corp | Method and device for creating prediction scenario of future demand regarding transaction object |
US20100318484A1 (en) * | 2009-06-15 | 2010-12-16 | Bernardo Huberman | Managing online content based on its predicted popularity |
CN102591929A (en) * | 2011-12-23 | 2012-07-18 | 深圳职业技术学院 | Library data processing system and data processing method thereof |
CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机***有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
CN105183718A (en) * | 2015-09-25 | 2015-12-23 | 苏州天梯卓越传媒有限公司 | Hotspot topic obtaining method for publishing industry and system thereof |
JP6124232B1 (en) * | 2016-11-15 | 2017-05-10 | シーロムパートナーズ税理士法人 | Financial forecasting system, financial forecasting method, and financial forecasting program |
CN106934046A (en) * | 2017-03-16 | 2017-07-07 | 天闻数媒科技(北京)有限公司 | A kind of distribution of publications analysis system and method |
CN107103038A (en) * | 2017-03-24 | 2017-08-29 | 武汉理工数字传播工程有限公司 | A kind of Subject Selection system based on big data |
CN107767191A (en) * | 2017-12-05 | 2018-03-06 | 广东技术师范学院 | A kind of method based on medical big data prediction medicine sales trend |
CN108416636A (en) * | 2018-03-30 | 2018-08-17 | 大连理工大学 | A kind of ARIMA and support vector regression fusion method of prediction drug sales volume |
CN109670922A (en) * | 2018-12-29 | 2019-04-23 | 北京工业大学 | Books are worth discovery method on a kind of line based on composite character |
CN110399502A (en) * | 2019-06-18 | 2019-11-01 | 东华大学 | A kind of learning value evaluation method of subject books |
CN110555578A (en) * | 2018-06-01 | 2019-12-10 | 北京京东尚科信息技术有限公司 | sales prediction method and device |
-
2020
- 2020-04-27 CN CN202010345025.0A patent/CN111598310A/en active Pending
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611726B1 (en) * | 1999-09-17 | 2003-08-26 | Carl E. Crosswhite | Method for determining optimal time series forecasting parameters |
JP2010020442A (en) * | 2008-07-09 | 2010-01-28 | Toshiba Corp | Method and device for creating prediction scenario of future demand regarding transaction object |
US20100318484A1 (en) * | 2009-06-15 | 2010-12-16 | Bernardo Huberman | Managing online content based on its predicted popularity |
CN102591929A (en) * | 2011-12-23 | 2012-07-18 | 深圳职业技术学院 | Library data processing system and data processing method thereof |
CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机***有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
CN105183718A (en) * | 2015-09-25 | 2015-12-23 | 苏州天梯卓越传媒有限公司 | Hotspot topic obtaining method for publishing industry and system thereof |
JP6124232B1 (en) * | 2016-11-15 | 2017-05-10 | シーロムパートナーズ税理士法人 | Financial forecasting system, financial forecasting method, and financial forecasting program |
CN106934046A (en) * | 2017-03-16 | 2017-07-07 | 天闻数媒科技(北京)有限公司 | A kind of distribution of publications analysis system and method |
CN107103038A (en) * | 2017-03-24 | 2017-08-29 | 武汉理工数字传播工程有限公司 | A kind of Subject Selection system based on big data |
CN107767191A (en) * | 2017-12-05 | 2018-03-06 | 广东技术师范学院 | A kind of method based on medical big data prediction medicine sales trend |
CN108416636A (en) * | 2018-03-30 | 2018-08-17 | 大连理工大学 | A kind of ARIMA and support vector regression fusion method of prediction drug sales volume |
CN110555578A (en) * | 2018-06-01 | 2019-12-10 | 北京京东尚科信息技术有限公司 | sales prediction method and device |
CN109670922A (en) * | 2018-12-29 | 2019-04-23 | 北京工业大学 | Books are worth discovery method on a kind of line based on composite character |
CN110399502A (en) * | 2019-06-18 | 2019-11-01 | 东华大学 | A kind of learning value evaluation method of subject books |
Non-Patent Citations (11)
Title |
---|
刘自强等: "基于时间序列模型的研究热点分析预测方法研究", 《情报理论与实践》 * |
刘自强等: "基于时间序列模型的研究热点分析预测方法研究", 《情报理论与实践》, no. 05, 31 December 2016 (2016-12-31) * |
曾文等: "基于图书出版行业大数据的选题决策分析模型研究", 《情报学报》 * |
曾文等: "基于图书出版行业大数据的选题决策分析模型研究", 《情报学报》, no. 08, 24 August 2018 (2018-08-24), pages 813 - 821 * |
李雁翎等: "五维图书评价体系及分析模型的建构", 《情报科学》 * |
李雁翎等: "五维图书评价体系及分析模型的建构", 《情报科学》, no. 08, 5 August 2013 (2013-08-05) * |
林海等: "基于Holt-Winters时间序列的图书选题预测模型", 《数字技术与应用》 * |
林海等: "基于Holt-Winters时间序列的图书选题预测模型", 《数字技术与应用》, no. 03, 15 March 2017 (2017-03-15), pages 51 - 53 * |
柯源: "出版社资源的配置研究", 《北京印刷学院学报》 * |
柯源: "出版社资源的配置研究", 《北京印刷学院学报》, no. 05, 26 October 2007 (2007-10-26) * |
韩钦;: "时间序列分析模型在图书选题上的应用研究――以图书热度为预测研究对象", 出版广角, no. 03, pages 28 - 31 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108073568B (en) | Keyword extraction method and device | |
CN108280670B (en) | Seed crowd diffusion method and device and information delivery system | |
US20180053092A1 (en) | Method and System for Innovation Management and Optimization Under Uncertainty | |
CN111159564A (en) | Information recommendation method and device, storage medium and computer equipment | |
CN110647696B (en) | Business object sorting method and device | |
Yang et al. | Tag-based expert recommendation in community question answering | |
CN106095942B (en) | Strong variable extracting method and device | |
US9280739B2 (en) | Computer implemented system for automating the generation of a business decision analytic model | |
CN105095411A (en) | Method and system for predicting APP ranking based on App quality | |
WO2017071474A1 (en) | Method and device for processing language data items and method and device for analyzing language data items | |
CN111695024A (en) | Object evaluation value prediction method and system, and recommendation method and system | |
CN112383828B (en) | Quality of experience prediction method, equipment and system with brain-like characteristics | |
CN111737473A (en) | Text classification method, device and equipment | |
CN112766402A (en) | Algorithm selection method and device and electronic equipment | |
CN113254810A (en) | Search result output method and device, computer equipment and readable storage medium | |
Nagahara et al. | Toward data-driven production simulation modeling: dispatching rule identification by machine learning techniques | |
CN108509588B (en) | Lawyer evaluation method and recommendation method based on big data | |
CN114490786A (en) | Data sorting method and device | |
Zhang et al. | Product improvement in a big data environment: A novel method based on text mining and large group decision making | |
CN113065790A (en) | Method and system for evaluating patent value | |
CN112966964A (en) | Product matching method, device, equipment and storage medium based on design requirements | |
CN110852322B (en) | Method and device for determining region of interest | |
Shen et al. | Predicting usefulness of Yelp reviews with localized linear regression models | |
WO2020057237A1 (en) | Influence detection method applicable to object of interest, and electronic terminal and storage medium | |
WO2018044955A1 (en) | Systems and methods for measuring collected content significance |
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: 20200828 |
|
RJ01 | Rejection of invention patent application after publication |