CN113743973A - Method and device for analyzing market hotspot trend - Google Patents
Method and device for analyzing market hotspot trend Download PDFInfo
- Publication number
- CN113743973A CN113743973A CN202011380611.5A CN202011380611A CN113743973A CN 113743973 A CN113743973 A CN 113743973A CN 202011380611 A CN202011380611 A CN 202011380611A CN 113743973 A CN113743973 A CN 113743973A
- Authority
- CN
- China
- Prior art keywords
- keyword
- keywords
- library
- emerging
- market
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000011218 segmentation Effects 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 16
- 230000002776 aggregation Effects 0.000 claims description 11
- 238000004220 aggregation Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims 1
- 238000005070 sampling Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for analyzing market hotspot tendency, and relates to the technical field of computers. One embodiment of the method comprises: acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are the first keywords of which the current market share ratio of the article is smaller than a set threshold value; and analyzing the search quantity of the emerging keywords within a set time length in the future to obtain the market hotspot trend. The method can achieve the purposes of predicting the emerging trend of products and further analyzing the market hot trend under the condition of rapidness and no sampling deviation, and the analysis result is more timely, comprehensive and accurate.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for analyzing market hotspot trends.
Background
Analysis and prediction of emerging trends in the market can help manufacturers to know the commodity attributes which can become market hotspots in the future, so that the commodities with the attributes can be distributed in advance, and the commodities with the attributes are configured to help the manufacturers to better become explosive products. The current market hotspot trend analysis and prediction method mainly learns the preference degree of a user to a specific commodity attribute through manual user research and development, and then gives final trend judgment based on the research and analysis result.
However, the existing user investigation method has the problems of long period and limited coverage, and the emerging trend becomes a hot spot already after the investigation result comes out, so that the advanced layout of manufacturers and merchants loses significance, the analysis and prediction result of the market hot spot trend is not timely enough, and the hysteresis is realized; on the other hand, research only covers a relatively small part of user groups, and the part of user groups cannot necessarily reflect the overall situation of the market, so that the analysis and prediction results of the market hotspot trends are not comprehensive and accurate.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for analyzing a market hot trend, so as to achieve the purpose of predicting a product emerging trend and further analyzing the market hot trend under the condition of fast speed and no sampling deviation, and the analysis result is more timely, comprehensive and accurate.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of analyzing a market hotspot tendency.
A method of analyzing market hotspot trends, comprising:
acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article;
selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold;
and analyzing the search quantity of the emerging keywords within a set time length in the future to obtain the market hotspot trend.
Optionally, the obtaining a first keyword library for describing the attention of the user and a second keyword library for describing the item includes:
performing word segmentation on data related to the user attention to obtain a first word segmentation set, and performing aggregation processing according to the similarity of words in the first word segmentation set to obtain a first keyword library for describing the user attention;
performing word segmentation on the article attribute data to obtain a second word segmentation set, and performing aggregation processing according to the similarity of words in the second word segmentation set to obtain a second keyword library for describing the article.
Optionally, selecting emerging keywords from the first keyword library includes:
acquiring the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set first threshold value with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for an article according to the second matching keyword, and acquiring the market ratio of the article;
and acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword according to the incidence relation.
Optionally, the obtaining of the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library includes:
judging whether each first keyword in the first keyword library is contained in the second keyword library;
if not, calculating the similarity between the first keyword and each second keyword in the second keyword library.
Optionally, the similarity between the keywords is obtained by:
obtaining semantic vectors of each keyword by using a language matching model;
and calculating the similarity between the keywords based on the semantic vectors.
Optionally, the analyzing the search volume of the emerging keyword within a set time duration in the future includes:
and analyzing the search quantity of the emerging keywords within a set time length in the future through a time series prediction model.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for analyzing market hotspot tendency.
An apparatus for analyzing market hotspot trends, comprising:
the data acquisition module is used for acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article;
the keyword selection module is used for selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold;
and the search volume analysis module is used for carrying out search volume analysis on the emerging keywords within a set time length in the future so as to obtain the market hotspot trend.
Optionally, the data obtaining module is further configured to:
performing word segmentation on data related to the user attention to obtain a first word segmentation set, and performing aggregation processing according to the similarity of words in the first word segmentation set to obtain a first keyword library for describing the user attention;
performing word segmentation on the article attribute data to obtain a second word segmentation set, and performing aggregation processing according to the similarity of words in the second word segmentation set to obtain a second keyword library for describing the article.
Optionally, the keyword selecting module is further configured to:
acquiring the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set first threshold value with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for an article according to the second matching keyword, and acquiring the market ratio of the article;
and acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword according to the incidence relation.
Optionally, the keyword selecting module is further configured to:
judging whether each first keyword in the first keyword library is contained in the second keyword library;
if not, calculating the similarity between the first keyword and each second keyword in the second keyword library.
Optionally, the similarity between the keywords is obtained by:
obtaining semantic vectors of each keyword by using a language matching model;
and calculating the similarity between the keywords based on the semantic vectors.
Optionally, the search volume analysis module is further configured to:
and analyzing the search quantity of the emerging keywords within a set time length in the future through a time series prediction model.
According to yet another aspect of the embodiments of the present invention, an electronic device for analyzing market hotspot trends is provided.
An electronic device for analyzing market hotspot trends, comprising: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for analyzing the market hotspot trend provided by the embodiment of the invention.
According to yet another aspect of embodiments of the present invention, a computer-readable medium is provided.
A computer readable medium, on which a computer program is stored, which when executed by a processor implements the method for analyzing market hotspot trends provided by embodiments of the present invention.
One embodiment of the above invention has the following advantages or benefits: the method comprises the steps of obtaining a first keyword library used for describing the attention of a user and a second keyword library used for describing an article; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are the first keywords of which the current market share ratio of the article is smaller than a set threshold value; the technical means of analyzing the search quantity of emerging keywords within a set time length in the future to obtain the market hotspot trend is realized, the prediction of the emerging hotspot trend of a product market is converted into the prediction of the search trend of the focus of a user, the future behaviors of the whole number of users on a certain keyword are predicted through a deep learning model, so that the aims of predicting the emerging trend of the product and further analyzing the market hotspot trend are fulfilled under the condition of no sampling deviation, and the analysis result is more timely, comprehensive and accurate.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a method for analyzing market hotspot trends according to an embodiment of the invention;
FIG. 2 is a system framework diagram of analyzing market hotspot trends, in accordance with one embodiment of the present invention;
FIG. 3 is a schematic diagram of an implementation of a search prediction model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the main modules of an apparatus for analyzing market hotspot trends according to an embodiment of the invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to solve the technical problems in the prior art, the invention provides a method for analyzing the market hot-spot trend, which converts the prediction of the emerging hot-spot trend of the product market into the prediction of the searching trend of the user focus of attention and predicts the future behaviors of all users on a certain keyword through a deep learning model, so that the aims of predicting the emerging trend of the product and further analyzing the market hot-spot trend are fulfilled under the condition of fast speed without sampling deviation, and the analysis result is more timely, comprehensive and accurate.
Fig. 1 is a schematic diagram of main steps of a method for analyzing market hotspot tendency according to an embodiment of the invention. As shown in fig. 1, the method for analyzing a market hotspot trend of the embodiment of the invention mainly includes the following steps S101 to S103.
Step S101: acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article;
step S102: selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are the first keywords of which the current market share ratio of the article is smaller than a set threshold value;
step S103: and analyzing the search quantity of the emerging keywords within a set time length in the future to obtain the market hotspot trend.
According to an embodiment of the present invention, when the first keyword library for describing the user attention is obtained, the data related to the user attention may be specifically subjected to word segmentation processing to obtain a first word segmentation set, and aggregation processing is performed according to similarity of words in the first word segmentation set to obtain the first keyword library for describing the user attention. Specifically, first, data related to the user attention is acquired, for example: searching data, question and answer data, comment data and the like, and then segmenting the data, specifically, segmenting a sentence included in the data into a plurality of words through a commonly used segmentation tool (for example, jieba segmentation), wherein the words form a first segmentation set. Then, words with the same meaning are aggregated to obtain a first keyword library, specifically, when the words are aggregated, semantic vectors of the words are obtained through a language matching model (for example, a BERT model, which is essentially a new word2Vec and is used for generating a correlation model of word vectors), then similarity between the words is calculated based on a distance between the semantic vectors, the words with the similarity reaching a certain threshold can be aggregated into the same word as a first keyword, and finally, a first keyword library A for describing user attention is obtained.
Similarly, when a second keyword library for describing the article is obtained, the article attribute data may be specifically subjected to word segmentation processing to obtain a second word segmentation set, and aggregation processing is performed according to the similarity of words in the second word segmentation set to obtain the second keyword library for describing the article. Specifically, the item attribute data is, for example, a product title or product detailed description information. Firstly, acquiring article attribute data, then performing word segmentation on the article attribute data, and performing aggregation processing to obtain a second keyword library B for describing articles.
After the first keyword bank A and the second keyword bank B are obtained, emerging keywords can be selected from the first keyword bank A through comparison analysis of the first keyword bank A and the second keyword bank B. According to the technical scheme of the invention, the emerging keywords refer to keywords with relatively less current market share of the items, that is, of all the first keywords included in the first keyword library a, the current market share of the items related to the emerging keywords is relatively less, and although the users have paid attention to the items, the attention degree is smaller or the attention amount is less, so that the items are likely to become hot spots of future markets.
According to an embodiment of the present invention, when selecting an emerging keyword from the first keyword library, the method may specifically include the following steps:
acquiring the similarity of each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set similarity threshold with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for the article according to the second matching keyword, and acquiring the market ratio of the article;
and according to the incidence relation, acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword.
In a specific embodiment, assuming that the similarity between a certain first keyword a1 in the first keyword library a and two second keywords B1 and B2 in the second keyword library B reaches 90% and 85%, respectively, and both exceed a preset similarity threshold 80%, the first keyword a1, the second keywords B1 and the second keywords B2 are used as a group of first keywords and second keywords whose similarities meet the preset similarity threshold, the first keyword a1 is used as a first matching keyword, the second keywords B1 and B2 are used as second matching keywords, and an association relationship between the first matching keyword and the second matching keyword is established. In a specific implementation, the second matching keyword associated with a certain first matching keyword may include one second keyword or may include a plurality of second keywords. If the similarity between the first keyword a2 in the first keyword library a and any second keyword in the second keyword library B is less than the set similarity threshold, the first keyword a2 is an invalid first keyword.
After the incidence relation between the first matching keyword and the second matching keyword is established, the corresponding article can be searched according to the second matching keyword, and the market ratio of the article is obtained. In this embodiment, for the second matching keywords B1 and B2 associated with the first matching keyword a1, B1 and B2 are used to match with the item attribute data, respectively, and the item corresponding to the item attribute data including B1 or B2 is taken as the found item, and then the market share of these items is calculated. When calculating the market proportion, the number of the articles can be according to the number of the articles, namely: the number of item attribute data M is compared to the total number of items of the same type N. For example: assuming that the item attribute data is an item title, the number of item titles containing B1 or B2 in the item title is M, and the total number of items of the same type is N, the market share of the items is M/N. Similarly, in calculating the market share, the number of these items may be: the number of item attribute data M is a market share for these items. The way of calculating the market share is not limited to the way listed in the embodiments of the present invention, and can be flexibly selected according to the application requirements, which is not limited by the present invention.
After the market share of the articles is obtained, the articles with the market share smaller than the set threshold value can be obtained, and further, second matching keywords of the articles can be obtained. And obtaining corresponding first matching keywords according to the incidence relation between the first matching keywords and the second matching keywords, and taking the first matching keywords as emerging keywords. After the market share of the items is obtained, the market shares of the items may be ranked from small to large, and the first matching keywords corresponding to a predetermined number (for example, 500) of items ranked in the top may be used as the new keywords.
According to one embodiment, when obtaining the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library, the method may specifically include:
judging whether each first keyword in the first keyword library is contained in the second keyword library;
if not, calculating the similarity between the first keyword and each second keyword in the second keyword library.
In specific implementation, for each first keyword in the first keyword library, it may be first searched from the second keyword library whether there is a same second keyword, and if there is a same second keyword, it indicates that the similarity between the first keyword and the second keyword in the second keyword library is 100%, and at this time, it is not necessary to calculate the similarity between the first keyword and other second keywords in the second keyword library. Then, the first keyword and the second keyword can be used as a first matching keyword and a second matching keyword to execute subsequent operations. Otherwise, if the second keyword library does not contain the first keyword, the similarity between the first keyword and each second keyword in the second keyword library needs to be calculated.
According to the technical scheme of the invention, the similarity between the keywords can be obtained in the following modes:
obtaining semantic vectors of each keyword by using a language matching model;
similarity between keywords is calculated based on the semantic vector.
Here, the similarity between the keywords may be a similarity between the first keyword and the second keyword. A language matching model (e.g., BERT model, which is essentially a new word2Vec, and is used to generate a correlation model of word vectors) is used to obtain semantic vectors for each keyword, and then similarity between the keywords is calculated based on a distance between the semantic vectors.
According to the embodiment of the invention, when the emerging keywords are analyzed for the search quantity within the set time length in the future, the time series prediction model can be used for analyzing the search quantity within the set time length in the future for the emerging keywords. Examples of the time series prediction model include an LSTM (long-short term memory) model, an ARMA (Autoregressive Moving Average model), an ARIMA (Autoregressive Integrated Moving Average model), and a differential Integrated Moving Average Autoregressive model.
FIG. 2 is a system block diagram of analyzing market hotspot trends, in accordance with one embodiment of the present invention. In the embodiment of the present invention, taking the analysis of the commodity data collected by the e-commerce platform as an example, as shown in fig. 2, the system for analyzing the market hotspot trend in the embodiment of the present invention mainly includes three modules: the device comprises a keyword generation module, an emerging keyword generation module and a search amount prediction module. The functions of the modules are respectively as follows:
1. a keyword generation module, configured to generate, for data related to the user attention, for example: the method comprises the steps that commodity question-answer data, historical search data, search quantity data of the commodity question-answer data, historical comment data of the historical search data, and the like are subjected to word segmentation and then aggregated to obtain a first keyword bank A for describing the attention of a user; and item attribute data such as: the commodity titles, commodity detailed information and the like are subjected to word segmentation processing and then are aggregated to obtain a second keyword library B for describing the articles;
2. and the emerging keyword generation module is used for matching the first keyword library A which is generated in the keyword generation module and used for describing the attention of the user with the second keyword library B used for describing the articles, and selecting the first keywords corresponding to the articles with relatively less current market occupation as the emerging keywords according to the market occupation condition of the articles. Specifically, for each first keyword in the first keyword library a, judging whether the first keyword is contained in the second keyword library; if not, calculating the similarity between the first keyword and each second keyword in the second keyword library, thereby obtaining the similarity between each first keyword in the first keyword library A and each second keyword in the second keyword library B; regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set similarity threshold with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword; searching for the article according to the second matching keyword, and acquiring the market ratio of the article; according to the incidence relation, acquiring a first matching keyword corresponding to an article with a market ratio smaller than a set threshold value as an emerging keyword;
3. and the search quantity prediction module is used for predicting the future search quantity of the emerging keywords obtained by mining the emerging keyword generation module so as to judge the emerging trend and the market hotspot trend of the product and provide an auxiliary decision for customizing the product. In one embodiment of the present invention, the search volume of a keyword in the past year and half (flexibly settable), search user figures, market macro-economic data, and the like are used as training data to predict the search volume of the keyword in the next three months (flexibly settable). Specifically, the method comprises the following steps: for a certain keyword k, assuming that the time starting point is t, and the total search volume of three consecutive months after t is taken as
Using user portrait (sex ratio, average age, average passenger unit price, etc.) and market macro economy data about keyword k three months before t
Thereby constructing a training set. And training the training set based on the time series prediction model LSTM to obtain a search volume prediction model, and then analyzing and predicting the market hotspot trend by using the search volume prediction model.
Fig. 3 is a schematic diagram illustrating an implementation principle of the search quantity prediction model according to an embodiment of the present invention. As shown in fig. 3, the search quantity prediction model is trained based on the time series prediction model LSTM model. In the embodiment of the invention
And
as an input, in
For output, updating parameters of the LSTM model based on the training set to finally obtain a search quantity prediction model, so that the search quantity prediction model can predict the keywords i to be predicted
FIG. 4 is a schematic diagram of the main modules of an apparatus for analyzing market hotspot trends according to an embodiment of the present invention. As shown in fig. 4, the apparatus 400 for analyzing market hotspot tendency of the embodiment of the present invention mainly includes a data acquisition module 401, a keyword selection module 402, and a search volume analysis module 403.
A data obtaining module 401, configured to obtain a first keyword library used for describing a user attention and a second keyword library used for describing an item;
a keyword selection module 402, configured to select an emerging keyword from the first keyword library according to the first keyword library and the second keyword library, where the emerging keyword is a first keyword for which a current market share of an article is smaller than a set threshold;
and a search volume analysis module 403, configured to perform search volume analysis on the emerging keywords within a set time duration in the future to obtain a market hotspot trend.
According to an embodiment of the present invention, the data obtaining module 401 may further be configured to:
performing word segmentation on data related to the user attention to obtain a first word segmentation set, and performing aggregation processing according to the similarity of words in the first word segmentation set to obtain a first keyword library for describing the user attention;
performing word segmentation on the article attribute data to obtain a second word segmentation set, and performing aggregation processing according to the similarity of words in the second word segmentation set to obtain a second keyword library for describing the article.
According to another embodiment of the present invention, the keyword selecting module 402 may further be configured to:
acquiring the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set first threshold value with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for an article according to the second matching keyword, and acquiring the market ratio of the article;
and acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword according to the incidence relation.
According to another embodiment of the present invention, the keyword selecting module 402 may further be configured to:
judging whether each first keyword in the first keyword library is contained in the second keyword library;
if not, calculating the similarity between the first keyword and each second keyword in the second keyword library.
According to another embodiment of the present invention, the similarity between keywords is obtained by:
obtaining semantic vectors of each keyword by using a language matching model;
and calculating the similarity between the keywords based on the semantic vectors.
According to still another embodiment of the present invention, the search volume analysis module 403 may be further configured to:
and analyzing the search quantity of the emerging keywords within a set time length in the future through a time series prediction model.
According to the technical scheme of the embodiment of the invention, a first keyword library for describing the attention of a user and a second keyword library for describing an article are obtained; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are the first keywords of which the current market share ratio of the article is smaller than a set threshold value; the technical means of analyzing the search quantity of emerging keywords within a set time length in the future to obtain the market hotspot trend is realized, the prediction of the emerging hotspot trend of a product market is converted into the prediction of the search trend of the focus of a user, the future behaviors of the whole number of users on a certain keyword are predicted through a deep learning model, so that the aims of predicting the emerging trend of the product and further analyzing the market hotspot trend are fulfilled under the condition of no sampling deviation, and the analysis result is more timely, comprehensive and accurate.
Fig. 5 illustrates an exemplary system architecture 500 of a method of analyzing market hotspot trends or an apparatus for analyzing market hotspot trends to which embodiments of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as a shopping-type application, a web browser application, a search-type application, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server that provides various services, such as a back-office management server (for example only) that supports market hotspot trend query requests sent by users using the terminal devices 501, 502, 503. The background management server can perform the following steps according to the received market hotspot trend query request: acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold; and performing search quantity analysis and other processing on the emerging keywords within a set time length in the future, and feeding back processing results (such as market hotspot trends or emerging product trends, which are only examples) to the terminal equipment.
It should be noted that the method for analyzing the market hotspot tendency provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the apparatus for analyzing the market hotspot tendency is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device or server implementing an embodiment of the invention is shown. The terminal device or the server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware. The described units or modules may also be provided in a processor, and may be described as: a processor comprises a data acquisition module, a keyword selection module and a search quantity analysis module. Where the names of these units or modules do not in some cases constitute a limitation of the units or modules themselves, for example, the data acquisition module may also be described as a "module for acquiring a first keyword library for describing the user's attention and a second keyword library for describing an item".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold; and analyzing the search quantity of the emerging keywords within a set time length in the future to obtain the market hotspot trend.
According to the technical scheme of the embodiment of the invention, a first keyword library for describing the attention of a user and a second keyword library for describing an article are obtained; selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are the first keywords of which the current market share ratio of the article is smaller than a set threshold value; the technical means of analyzing the search quantity of emerging keywords within a set time length in the future to obtain the market hotspot trend is realized, the prediction of the emerging hotspot trend of a product market is converted into the prediction of the search trend of the focus of a user, the future behaviors of the whole number of users on a certain keyword are predicted through a deep learning model, so that the aims of predicting the emerging trend of the product and further analyzing the market hotspot trend are fulfilled under the condition of no sampling deviation, and the analysis result is more timely, comprehensive and accurate.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of analyzing market hotspot trends, comprising:
acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article;
selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold;
and analyzing the search quantity of the emerging keywords within a set time length in the future to obtain the market hotspot trend.
2. The method of claim 1, wherein obtaining a first keyword library for describing a user's attention and a second keyword library for describing an item comprises:
performing word segmentation on data related to the user attention to obtain a first word segmentation set, and performing aggregation processing according to the similarity of words in the first word segmentation set to obtain a first keyword library for describing the user attention;
performing word segmentation on the article attribute data to obtain a second word segmentation set, and performing aggregation processing according to the similarity of words in the second word segmentation set to obtain a second keyword library for describing the article.
3. The method of claim 1, wherein selecting emerging keywords from the first keyword library comprises:
acquiring the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set similarity threshold value with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for an article according to the second matching keyword, and acquiring the market ratio of the article;
and acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword according to the incidence relation.
4. The method of claim 3, wherein obtaining the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library comprises:
judging whether each first keyword in the first keyword library is contained in the second keyword library;
if not, calculating the similarity between the first keyword and each second keyword in the second keyword library.
5. The method according to claim 3 or 4, characterized in that the similarity between keywords is obtained by:
obtaining semantic vectors of each keyword by using a language matching model;
and calculating the similarity between the keywords based on the semantic vectors.
6. The method of claim 1, wherein analyzing the search volume for the emerging keywords for a set length of time in the future comprises:
and analyzing the search quantity of the emerging keywords within a set time length in the future through a time series prediction model.
7. An apparatus for analyzing market hotspot trends, comprising:
the data acquisition module is used for acquiring a first keyword library for describing the attention of a user and a second keyword library for describing an article;
the keyword selection module is used for selecting emerging keywords from the first keyword library according to the first keyword library and the second keyword library, wherein the emerging keywords are first keywords with the current market share of the article being smaller than a set threshold;
and the search volume analysis module is used for carrying out search volume analysis on the emerging keywords within a set time length in the future so as to obtain the market hotspot trend.
8. The apparatus of claim 7, wherein the keyword extraction module is further configured to:
acquiring the similarity between each first keyword in the first keyword library and each second keyword in the second keyword library;
regarding each first keyword, taking the first keyword as a first matching keyword, taking a second keyword with the similarity meeting a set similarity threshold value with the first keyword as a second matching keyword, and establishing an incidence relation between the first matching keyword and the second matching keyword;
searching for an article according to the second matching keyword, and acquiring the market ratio of the article;
and acquiring a first matching keyword corresponding to the article with the market ratio smaller than a set threshold value as an emerging keyword according to the incidence relation.
9. An electronic device for analyzing market hotspot trends, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011380611.5A CN113743973A (en) | 2020-11-30 | 2020-11-30 | Method and device for analyzing market hotspot trend |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011380611.5A CN113743973A (en) | 2020-11-30 | 2020-11-30 | Method and device for analyzing market hotspot trend |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113743973A true CN113743973A (en) | 2021-12-03 |
Family
ID=78728128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011380611.5A Pending CN113743973A (en) | 2020-11-30 | 2020-11-30 | Method and device for analyzing market hotspot trend |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743973A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023142448A1 (en) * | 2022-01-26 | 2023-08-03 | 北京沃东天骏信息技术有限公司 | Hotspot information processing method and apparatus, and server and readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040059115A (en) * | 2002-12-27 | 2004-07-05 | 징구 주식회사 | Internet advertising in search engine using keyword bidding |
| US20130036107A1 (en) * | 2011-08-07 | 2013-02-07 | Citizennet Inc. | Systems and methods for trend detection using frequency analysis |
| JP2014182445A (en) * | 2013-03-18 | 2014-09-29 | Mitsubishi Electric Corp | Information processing device and navigation device |
| CN107908616A (en) * | 2017-10-18 | 2018-04-13 | 北京京东尚科信息技术有限公司 | The method and apparatus of anticipation trend word |
| WO2018192496A1 (en) * | 2017-04-20 | 2018-10-25 | 腾讯科技（深圳）有限公司 | Trend information generation method and device, storage medium and electronic device |
| CN108984554A (en) * | 2017-06-01 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining keyword |
| JP2018206190A (en) * | 2017-06-07 | 2018-12-27 | 日本電信電話株式会社 | Trend evaluation device and trend evaluation method |
| CN109271574A (en) * | 2018-08-28 | 2019-01-25 | 麒麟合盛网络技术股份有限公司 | A kind of hot word recommended method and device |
| CN110490712A (en) * | 2019-08-21 | 2019-11-22 | 浙江中国轻纺城网络有限公司 | A kind of commodity class heading search method, system and storage medium |
| CN110766486A (en) * | 2018-07-09 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for determining item category |
-
2020
- 2020-11-30 CN CN202011380611.5A patent/CN113743973A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040059115A (en) * | 2002-12-27 | 2004-07-05 | 징구 주식회사 | Internet advertising in search engine using keyword bidding |
| US20130036107A1 (en) * | 2011-08-07 | 2013-02-07 | Citizennet Inc. | Systems and methods for trend detection using frequency analysis |
| JP2014182445A (en) * | 2013-03-18 | 2014-09-29 | Mitsubishi Electric Corp | Information processing device and navigation device |
| WO2018192496A1 (en) * | 2017-04-20 | 2018-10-25 | 腾讯科技（深圳）有限公司 | Trend information generation method and device, storage medium and electronic device |
| CN108984554A (en) * | 2017-06-01 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining keyword |
| JP2018206190A (en) * | 2017-06-07 | 2018-12-27 | 日本電信電話株式会社 | Trend evaluation device and trend evaluation method |
| CN107908616A (en) * | 2017-10-18 | 2018-04-13 | 北京京东尚科信息技术有限公司 | The method and apparatus of anticipation trend word |
| CN110766486A (en) * | 2018-07-09 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for determining item category |
| CN109271574A (en) * | 2018-08-28 | 2019-01-25 | 麒麟合盛网络技术股份有限公司 | A kind of hot word recommended method and device |
| CN110490712A (en) * | 2019-08-21 | 2019-11-22 | 浙江中国轻纺城网络有限公司 | A kind of commodity class heading search method, system and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| D\'ANGELO, N等: "Predicting Growth in English and French Vocabulary: The Facilitating Effects of Morphological and Cognate Awareness", 《DEVELOPMENTAL PSYCHOLOGY》, vol. 53, no. 7, 4 July 2017 (2017-07-04), pages 1242 - 1255 * |
| 李斌;吴庆涛;: "基于灰色理论的网络搜索频度数据分析", 计算机与现代化, no. 09, 28 September 2018 (2018-09-28), pages 98 - 104 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023142448A1 (en) * | 2022-01-26 | 2023-08-03 | 北京沃东天骏信息技术有限公司 | Hotspot information processing method and apparatus, and server and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679217B (en) | Associated content extraction method and device based on data mining | |
| CN109522483B (en) | Method and device for pushing information | |
| CN108804450B (en) | Information pushing method and device | |
| CN109145280A (en) | The method and apparatus of information push | |
| CN107832338B (en) | Method and system for recognizing core product words | |
| US20200045122A1 (en) | Method and apparatus for pushing information | |
| CN106919711B (en) | Method and device for labeling information based on artificial intelligence | |
| CN108121814B (en) | Search result ranking model generation method and device | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN111754278A (en) | Article recommendation method and device, computer storage medium and electronic equipment | |
| CN115033801B (en) | Article recommendation method, model training method and electronic equipment | |
| CN112330382B (en) | Item recommendation method, device, computing equipment and medium | |
| CN112328889A (en) | Method and device for determining recommended search terms, readable medium and electronic equipment | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN117909560A (en) | Search method, training device, training equipment, training medium and training program product | |
| CN111782850B (en) | Object searching method and device based on hand drawing | |
| CN112650942A (en) | Product recommendation method, device, computer system and computer-readable storage medium | |
| CN113743973A (en) | Method and device for analyzing market hotspot trend | |
| CN113360816A (en) | Click rate prediction method and device | |
| US20230085684A1 (en) | Method of recommending data, electronic device, and medium | |
| CN113495991A (en) | Recommendation method and device | |
| CN110852078A (en) | Method and device for generating title | |
| CN115238676A (en) | Method and device for identifying hot spots of bidding demands, storage medium and electronic equipment | |
| CN114445179A (en) | Service recommendation method and device, electronic equipment and computer readable medium | |
| CN111368036B (en) | Method and device for searching information |
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 |