CN114419448B - Intelligent analysis method and system based on stream shot commodities - Google Patents
Intelligent analysis method and system based on stream shot commodities Download PDFInfo
- Publication number
- CN114419448B CN114419448B CN202210308349.6A CN202210308349A CN114419448B CN 114419448 B CN114419448 B CN 114419448B CN 202210308349 A CN202210308349 A CN 202210308349A CN 114419448 B CN114419448 B CN 114419448B
- Authority
- CN
- China
- Prior art keywords
- feature
- chain
- beat
- auction
- shot
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
Abstract
The invention discloses an intelligent analysis method and system based on a stream shot commodity, wherein the method comprises the following steps: acquiring data of historical auction information of a target object to obtain a historical auction atlas set; carrying out multi-feature classification on the images to obtain a first, a second and a third beat feature chain; obtaining a corresponding first common beat feature chain; acquiring flow beat characteristics of each link point and common beat characteristics of each link point; inputting a node feature association degree evaluation model to train one-to-one corresponding nodes, and obtaining a stream beat-common beat feature association degree set of each corresponding node as a first analysis feature; performing main feature extraction on the second flow characteristic chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow characteristic chain, and taking an extraction result as a third analysis feature; and inputting the first, second and third analysis characteristics into a characteristic standardization processing model for training to obtain the expected streaming environment information.
Description
Technical Field
The invention relates to the field of data processing, in particular to an intelligent analysis method and system based on a flow shot commodity.
Background
The "streaming auction" means that the auction transaction fails due to the price of the auction being too high. In the course of trading activity, the buyer and the seller can not reach an agreement, so that the trading action can not be successfully carried out, and the target of the auction can not obtain the amount of the desired deal.
In order to effectively process the commodities which are not auctioned in time in the auction, the auction needs to be performed again, however, in the prior art, the technical problem that the auction quality of a certain commodity which is taken out frequently is seriously influenced because the multi-characteristic data analysis cannot be performed on the commodity which is taken out frequently.
Disclosure of Invention
The invention aims to provide an intelligent analysis method and system based on a streaming shot commodity, which are used for solving the technical problem that in the prior art, as multi-feature data analysis cannot be carried out on a certain streaming shot commodity, the shooting quality of the shooting is seriously influenced due to multiple streaming shots.
In view of the above problems, the present invention provides a method and a system for intelligently analyzing a stream shot-based commodity.
In a first aspect, the present invention provides a method for intelligently analyzing a commodity based on stream shooting, which is characterized in that the method includes: based on big data, carrying out data acquisition on historical auction information of the target object to obtain a historical auction picture set of the target object; performing multi-feature classification on the historical auction picture collection to obtain a first stream-shot feature chain, a second stream-shot feature chain and a third stream-shot feature chain; obtaining a first popular beat feature chain corresponding to the first popular beat feature chain; acquiring flow beat characteristics of each link point on the first flow beat characteristic chain and common beat characteristics of each link node on the first common beat characteristic chain; respectively inputting the flow beat characteristics and the common beat characteristics of the chain nodes as input information into a node characteristic association degree evaluation model to train one-to-one corresponding nodes, obtaining a flow beat-common beat characteristic association degree set of each corresponding node, and taking the flow beat-common beat characteristic association degree set as a first analysis characteristic; performing main feature extraction on the second flow shooting feature chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow shooting feature chain, and taking an extraction result as a third analysis feature; inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain the expected streaming environment information of the target object.
In another aspect, the present invention further provides a system for intelligently analyzing a flow shot-based commodity, which is used for executing the method for intelligently analyzing the flow shot-based commodity according to the first aspect, wherein the system comprises: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring the historical auction information of a target object based on big data to obtain a historical auction atlas set of the target object; the first classification unit is used for performing multi-feature classification on the historical auction picture set to obtain a first stream beat feature chain, a second stream beat feature chain and a third stream beat feature chain; a first obtaining unit, configured to obtain a first ordinary beat feature chain corresponding to the first stream beat feature chain; a second obtaining unit, configured to obtain a flow shot feature of each link point on the first flow shot feature chain and a common shot feature of each link node on the first common shot feature chain; a first input unit, configured to input the flow beat features and the ordinary beat features of the chain nodes as input information to a node feature association degree evaluation model to perform training on nodes in a one-to-one correspondence manner, obtain a flow beat-ordinary beat feature association degree set of each corresponding node, and use the flow beat-ordinary beat feature association degree set as a first analysis feature; a first extraction unit, configured to perform main feature extraction on the second tap feature chain, take an extraction result as a second analysis feature, perform main feature extraction on the third tap feature chain, and take an extraction result as a third analysis feature; and the second input unit is used for inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain the expected streaming environment information of the target object.
In a third aspect, the present invention further provides an intelligent analysis system based on a flow shot commodity, including a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
In a fourth aspect, an electronic device, comprising a processor and a memory;
the memory is used for storing;
the processor is configured to execute the method according to any one of the first aspect above by calling.
In a fifth aspect, a computer program product comprises a computer program and/or instructions which, when executed by a processor, performs the steps of the method of any of the first aspect described above.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
through analyzing past auction data of the flow shot commodity, the flow shot commodity is compared with each key feature of a common shot commodity in the same period of the past one by one, the features of the shot commodity to be optimized are obtained through analysis, standardized fusion optimization is carried out on each feature of the shot commodity to be optimized, the expected auction environment meeting the flow shot commodity is finally analyzed, multi-azimuth analysis on the key features of the shot commodity is achieved, the expected auction environment suitable for the shot commodity is created, reasonable optimization is further carried out on the auction environment of the flow shot commodity, and the technical effect of the auction quality of the flow shot commodity is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without inventive effort.
FIG. 1 is a schematic flow chart of an intelligent analysis method based on a flow shot commodity according to the present invention;
FIG. 2 is a schematic flow chart illustrating key feature retrieval analysis performed on the historical access information set in the intelligent flow-shot commodity-based analysis method according to the present invention;
FIG. 3 is a schematic structural diagram of an intelligent analysis system based on a flow shot commodity according to the present invention;
fig. 4 is a schematic structural diagram of an exemplary electronic device of the present invention.
Description of the reference numerals:
the system comprises a first acquisition unit 11, a first classification unit 12, a first obtaining unit 13, a second obtaining unit 14, a first input unit 15, a first extraction unit 16, a second input unit 17, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.
Detailed Description
The invention provides an intelligent analysis method and system based on stream shot commodities, and solves the technical problem that in the prior art, as multi-characteristic data analysis cannot be carried out on a certain stream shot commodity, multiple stream shots occur on the shot commodity, and the auction quality of the shot commodity is seriously influenced. Through analyzing past auction data of the flow shot commodity, the flow shot commodity is compared with each key feature of a common shot commodity in the same period of the past one by one, the features of the shot commodity to be optimized are obtained through analysis, standardized fusion optimization is carried out on each feature of the shot commodity to be optimized, the expected auction environment meeting the flow shot commodity is finally analyzed, multi-azimuth analysis on the key features of the shot commodity is achieved, the expected auction environment suitable for the shot commodity is created, reasonable optimization is further carried out on the auction environment of the flow shot commodity, and the technical effect of the auction quality of the flow shot commodity is improved.
In the technical scheme of the invention, the acquisition, storage, use, processing and the like of the data all accord with relevant regulations of national laws and regulations.
The technical solutions in the present invention will be described below clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. It should be further noted that, for the convenience of description, only some but not all of the elements associated with the present invention are shown in the drawings.
The invention provides an intelligent analysis method based on a flow shot commodity, which is characterized by comprising the following steps: based on big data, carrying out data acquisition on historical auction information of the target object to obtain a historical auction picture set of the target object; performing multi-feature classification on the historical auction picture collection to obtain a first stream-shot feature chain, a second stream-shot feature chain and a third stream-shot feature chain; obtaining a first common beat feature chain corresponding to the first stream beat feature chain; acquiring flow beat characteristics of each link point on the first flow beat characteristic chain and common beat characteristics of each link node on the first common beat characteristic chain; respectively inputting the flow beat characteristics and the common beat characteristics of the chain nodes as input information into a node characteristic association degree evaluation model to train one-to-one corresponding nodes, obtaining a flow beat-common beat characteristic association degree set of each corresponding node, and taking the flow beat-common beat characteristic association degree set as a first analysis characteristic; performing main feature extraction on the second flow shooting feature chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow shooting feature chain, and taking an extraction result as a third analysis feature; inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain the expected streaming environment information of the target object.
Having described the general principles of the invention, reference will now be made in detail to various non-limiting embodiments of the invention, examples of which are illustrated in the accompanying drawings.
Example one
Referring to fig. 1, the present invention provides an intelligent analysis method based on a flow shot commodity, wherein the method is applied to an intelligent analysis system based on a flow shot commodity, and the method specifically includes the following steps:
step S100: based on big data, carrying out data acquisition on historical auction information of the target object to obtain a historical auction picture set of the target object;
step S200: performing multi-feature classification on the historical auction picture collection to obtain a first stream-shot feature chain, a second stream-shot feature chain and a third stream-shot feature chain;
further, step S200 includes:
step S210: acquiring the access amount of the historical auction information of the target object to obtain a historical access information set of the target object;
step S220: performing key feature retrieval analysis on the historical access information set, and performing descending order arrangement on analysis results to generate a historical retrieval feature sequence of the target object;
step S230: and sequentially performing feature retrieval classification on the historical auction picture set based on the historical retrieval feature sequence to obtain the first stream-shot feature chain, the second stream-shot feature chain and the third stream-shot feature chain.
Specifically, as shown in fig. 2, step S220 includes:
step S221: defining the historical access information set as original d-dimensional data, and carrying out standardization processing to obtain a standardized access information set of the target object as sample data;
step S222: constructing a covariance matrix of the sample data based on the standardized access information set;
step S223: calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
step S224: maximum value screening is carried out on the characteristic values and the characteristic vectors to obtain k characteristic vectors corresponding to the first k maximum characteristic values, wherein k is less than or equal to d;
step S225: constructing a mapping matrix W based on the k eigenvectors;
step S226: and converting the original d-dimensional data into a k-dimensional feature subspace based on the mapping matrix W.
Specifically, the "streaming auction" means that an auction transaction fails due to an excessively high price in the auction. In the trading activity, the buyer and the seller can not reach an agreement, so that the trading action can not be successfully carried out, and the amount of the wanted deal can not be obtained for the auction targets.
In order to effectively process the commodities which are not auctioned in time in the auction and need to be auctioned again, however, in the prior art, multi-characteristic data analysis cannot be performed on a certain flow shot commodity, so that multiple flow shots occur to the shot commodity, and the auction quality of the shot commodity is seriously influenced.
Specifically, the target object is a photographed article which is not called by the first auction, and may be a real estate, a stock, a land, and a common collection of a antique, and the like, and the historical auction picture set is an information set in the past auction process of the photographed article, and the collection of the antique may be explained here as an example, and exemplarily, the historical auction picture set is information including a base price of a auction, a group, a true or false degree of a collection, and a genre of a contemporary photographed article, and the like, which are collected by a certain antique in the past auction process, and by performing multi-feature classification on the historical auction picture set, a first auction feature chain, a second auction feature chain, and a third auction feature chain can be obtained, where the first auction feature chain, the second auction feature chain, and the third auction feature chain can be understood as a maximum feature set of a proposed auction of the collected article, specifically, the first stream auction feature chain can be understood as that the auction types of the collection which are taken during the auction process of the previous times and the collection taken during the same period include calligraphy and painting, ancient games, porcelain and the like, the second stream auction feature chain can be understood as that the audience groups of the collection under the auction process of the previous times are word and painting hobby groups or porcelain loving groups, and the third stream auction feature chain can be understood as that whether the starting price of the collection changes during the auction process of the previous times, and is stable or not, or slightly reduced or the like.
When the historical auction directory set is subjected to multi-feature classification, specifically, the historical auction information of the target object can be acquired, that is, the access amount of the collection in the past auction process is acquired, the historical access information set includes information such as the click amount of the collection and the reading duration of a single click amount, based on which the attention of audience groups to the collection is reflected from the side, and then the historical access information set is subjected to key feature retrieval analysis, that is, the audience groups retrieve the collection according to which key features, illustratively, the key features such as the shooting type, the unearthed age, the authenticity certificate, the expert evaluation and the starting price of the collection, and by descending the sequence arrangement, the most concerned search features of the audience groups and the first three searched search features related to the collection can be obtained, and obtaining the first stream beat feature chain, the second stream beat feature chain and the third stream beat feature chain through corresponding matching.
Specifically, when the key feature retrieval analysis is performed on the historical access information set, a computer algorithm can be applied to realize data processing, more specifically, the historical access information set can be defined as original d-dimensional data, the original data is subjected to standardization processing including data cleaning, data integration, data specification, data transformation and the like, so that the standardized access information set of the target object is obtained as sample data, and then based on the sample data, a covariance matrix of the sample data is constructed, and a formula can be based on 
The constitution is made wherein, among others,
for representing the degree of dispersion of two random variables, n represents the total number of data, i.e. the sample size,
and
respectively represent the mean values of the observed samples corresponding to two random variables, i.e. features j and k,
the ith sample value representing the feature j,
the ith sample value representing the feature k; in the normalized data, the mean value of the samples is 0, i.e., when
And
when all are 0, the covariance of the normalized data can be represented as:
wherein, in the step (A),
reflecting the degree of dispersion of the two random variables when the sample mean is 0. By calculating the eigenvalues and the corresponding eigenvectors of the covariance matrix, the eigenvectors corresponding to the first k largest eigenvalues can be selected, that is, the eigenvectors containing the most information are selected to form a subset, the importance of the eigenvectors is determined by the size of the eigenvalues, so that the k eigenvalues with the front size of the eigenvalue are selected as the selected eigenvalues, and the corresponding eigenvectors are used as the eigenvectors for constructing the mapping matrix. Furthermore, a mapping matrix W is constructed based on the k eigenvectors, i.e. the selected k eigenvectors form a matrix W with (d, k) dimension. The original d-dimensional data are converted into k-dimensional feature subspace based on the mapping matrix W, so that the extraction of key features of the historical access information set is realized, wherein the k-dimensional feature subspace contains spatial data including the first stream beat feature chain, the second stream beat feature chain and the third stream beat feature chain, and the data processing is realized based on a computer algorithm, so that the data processing process is faster and more accurate.
Step S300: obtaining a first popular beat feature chain corresponding to the first popular beat feature chain;
step S400: acquiring flow beat characteristics of each link point on the first flow beat characteristic chain and common beat characteristics of each link node on the first common beat characteristic chain;
specifically, after obtaining each auction run feature chain, a first auction feature chain corresponding to the first auction run feature chain may be obtained, where the first auction feature chain may be understood as an auction-type feature chain of other collections that are auctioned in the same period as the collection, and illustratively, the auction subject of the first period (i.e., the first node) is a calligraphy and painting collection, whereas the collection is a porcelain collection, and the auction subject of the second period (i.e., the second node) is a jade collection, whereas the collection is still a porcelain collection, which is different from the auction subject of each period, so that the collection cannot be auctioned out.
The first general-beat feature chain refers to a past auction type of a general-beat product (i.e., a first normal auction), and the first popular-beat feature chain refers to a self auction type of a popular-beat product (which has undergone at least one auction), and the description will be given by taking a porcelain collection as an example each time.
Step S500: respectively inputting the flow beat characteristics and the common beat characteristics of the chain nodes as input information into a node characteristic association degree evaluation model to train one-to-one corresponding nodes, obtaining a flow beat-common beat characteristic association degree set of each corresponding node, and taking the flow beat-common beat characteristic association degree set as a first analysis characteristic;
Further, step S500 includes:
step S510: obtaining a first node stream beat feature in the link node stream beat features and a first node common beat feature in the link node common beat features;
step S520: inputting the first node stream beat features and the first node common beat features into the node feature association degree evaluation model for training to obtain first feature association degrees of the link point stream beat features and the link node common beat features at the first nodes;
step S530: and traversing and training the nodes on the flow beat features of the chain nodes and the ordinary beat features of the chain nodes, and sequentially obtaining second feature association degrees at second nodes until the Nth feature association degree at the Nth node, wherein the Nth feature association degree is used as the flow beat-ordinary beat feature association degree set.
Specifically, after obtaining the flow beat features of each link point on the first flow beat feature chain and the common beat features of each link node on the first common beat feature chain, relevance evaluation may be performed on two features at any node based on a node feature relevance evaluation model, that is, training of one-to-one corresponding nodes is performed, so that a flow beat-common beat feature relevance set of each corresponding node is obtained.
Specifically, a first node flow shot feature in the chain node flow shot features and a first node common shot feature in the chain node common shot features are obtained, wherein the first node flow shot feature represents a collection type-porcelain class when the flow shot collection is auctioned in the first period, the first node common shot feature represents a collection type-calligraphy class accompanying a normal collection when the flow shot collection is auctioned in the first period, and the first node flow shot feature and the first node common shot feature which are input are trained based on the node feature association degree evaluation model, namely association degree evaluation training is carried out on the porcelain collection and the calligraphy and painting collection, so that a first feature association degree can be obtained.
By analogy, traversing training is carried out on the flow shot characteristics of each chain link point and each node on the common shot characteristics of each chain link point, the second characteristic association degree of a second node is sequentially obtained until the Nth characteristic association degree of an Nth node is obtained as the flow shot-common shot characteristic association degree set, illustratively, when the second node common shot characteristics of the second node are jadeware type collections, the difference still exists between the second node common shot characteristics and the porcelain type collections of the collections, but the first characteristic association degree set is reduced compared with the first characteristic association, the size set of the association degree of the shot types auctioned with each period of the porcelain type collections can be obtained by traversing training of the flow shot characteristics of each chain link point and each node on the common shot characteristics of each chain link point, the data in the collection can be screened until the shot type set with the maximum correlation degree of the porcelain type collections is obtained by screening, the collection is used as the first analysis characteristic, so that the collection is placed in a matching auction category for auction in the later auction process, and the auction quality of the auction is improved.
Step S600: performing main feature extraction on the second flow shooting feature chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow shooting feature chain, and taking an extraction result as a third analysis feature;
step S700: inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain the expected streaming environment information of the target object.
Further, step S700 includes:
step S710: based on the feature standardization processing model, carrying out primary standardization processing on the first analysis feature and the second analysis feature to obtain a first to-be-optimized environment vector of the target object;
step S720: based on the feature standardization processing model, carrying out secondary standardization processing on the second analysis feature and the third analysis feature to obtain a second to-be-optimized environment vector of the target object;
step S730: and carrying out three times of standardization processing on the first analysis characteristic and the third analysis characteristic based on the characteristic standardization processing model to obtain a third environment vector to be optimized of the target object.
Specifically, after the first analysis feature is summarized, the second stream shooting feature chain may be subjected to main feature extraction, and an extraction result is taken as a second analysis feature, performing main feature extraction on the third beat feature chain, taking an extraction result as a third analysis feature, wherein the second analysis characteristic represents the actual audience group distribution of the Tibetan in the process of auction of the past times, and comprises the distribution of different audience groups such as hobby calligraphy and painting groups, love porcelain groups and the like, the third analysis characteristic characterizes the starting price distribution information of the collection in the auction process of the past times, after obtaining the first analytical feature, the second analytical feature and the third analytical feature, the feature normalization processing model can be trained on the basis of the feature normalization processing model, so that the expected streaming environment information of the target object is obtained, namely, an expected auction environment is created for the subsequent auction of the collection.
Specifically, when the first analysis feature, the second analysis feature and the third analysis feature are input to a feature normalization processing model for training, based on a misalignment training, the input data can be trained more sufficiently, that is, based on the feature normalization processing model, the first analysis feature and the second analysis feature are normalized once, the first analysis feature and the second analysis feature are trained first to obtain a first environment vector to be optimized after one training, and for example, by normalizing the feature value of each item of input data with the synchronized item-taking type of the collection and the corresponding audience group, the auction environment matching the auction type of the collection and adapting to the audience group can be trained based on the feature normalization processing model, thereby improving the quality of the auction of the collection.
And thirdly, carrying out secondary standardization processing on the second analysis feature and the third analysis feature to obtain a second environment vector to be optimized of the target object, wherein the second environment vector to be optimized can be represented as an auction environment which is suitable for audience groups and has a base price for starting auction meeting expected requirements of the audience groups based on the feature standardization processing model, so that the auction quality of the Tibetan product is improved.
And finally, carrying out three times of standardization processing on the first analysis feature and the third analysis feature to obtain a third environment vector to be optimized of the target object, wherein the third environment vector to be optimized can be represented by training an auction environment which is matched with the auction type of the collection and meets the expected requirements of the audience group at the base price based on the feature standardization processing model, so as to improve the auction quality of the collection.
Further, the present application further includes step S800:
step S810: constructing a vector optimization platform;
step S820: uploading the first to-be-optimized environment vector, the second to-be-optimized environment vector and the third to-be-optimized environment vector to the vector optimization platform for fusion optimization among vectors, and generating expected streaming environment information of the target object;
Step S830: and performing environment creation of a subsequent auction link on the target object based on the expected streaming environment information.
Further, step S810 includes:
step S811: obtaining a three-dimensional data vector based on the characteristic standardization processing model;
step S812: respectively constructing a first dimension vector space, a second dimension vector space and a third dimension vector space according to the three-dimensional data vector;
step S813: and constructing the vector optimization platform based on the first dimension vector space, the second dimension vector space and the third dimension vector space.
Specifically, after the first to-be-optimized environment vector, the second to-be-optimized environment vector, and the third to-be-optimized environment vector are obtained, vector fusion needs to be performed on the first to-be-optimized environment vector, the second to-be-optimized environment vector, and the third to-be-optimized environment vector. Specifically, a vector optimization platform can be constructed, which provides a large platform for data fusion of the first environment vector to be optimized, the second environment vector to be optimized and the third environment vector to be optimized, and is used for optimizing data, by uploading the first environment vector to be optimized, the second environment vector to be optimized and the third environment vector to be optimized to the vector optimization platform for inter-vector fusion optimization, an auction environment which is in accordance with the auction type of the collection and is suitable for the auction environment of the audience group, is suitable for the audience group and has a shooting base price meeting the expected requirements of the audience group, and an auction environment which is in accordance with the auction type of the collection and has a shooting base price meeting the expected requirements of the audience group can be realized, and the three-terminal auction environments are effectively fused, so that the expected streaming environment information of the target object is generated, and finally, based on the expected streaming environment information, providing a good auction environment for the subsequent auction of the collection, and improving the auction quality of the collection.
In the process of constructing the vector optimization platform, specifically, a three-dimensional data vector can be obtained based on the characteristic standardization processing model, the three-dimensional data vector refers to three-dimensional data of the type of the synchronous shooting, the auction audience group and the starting price of the stream shooting commodity, further respectively constructing a first dimension vector space, a second dimension vector space and a third dimension vector space according to the three-dimensional data vector, wherein the first dimension vector space comprises data distribution of a contemporaneous auction type, the second dimension vector space comprises data distribution of an auction audience group, the third dimension vector space comprises data distribution of the shooting base price of the flow shooting commodity, and finally, based on the data distribution, the vector optimization platform is constructed, and an optimization platform is provided for data fusion of the first to-be-optimized environment vector, the second to-be-optimized environment vector and the third to-be-optimized environment vector.
In summary, the intelligent analysis method based on the stream shot commodities provided by the invention has the following technical effects:
1. through analyzing the past auction data of the flow auction commodity, the flow auction commodity is compared with each key feature of the common auction commodity in the same period of the past one by one, so that the auction features to be optimized of the commodity are obtained through analysis, through standardized fusion optimization of the auction features to be optimized, the expected auction environment meeting the flow auction commodity is finally analyzed, multi-azimuth analysis on the key features of the commodity is achieved, the expected auction environment suitable for the commodity is created, further, the auction environment of the flow auction commodity is reasonably optimized, and the technical effect of the auction quality of the flow auction commodity is improved.
2. By standardizing the types of the synchronized auction products of the Tibetan products and the corresponding audience groups, the characteristic values of all the input data are standardized, so that the auction types of the Tibetan products are fit for based on the characteristic standardization processing model, and the auction quality of the Tibetan products is improved.
Example two
Based on the same inventive concept as the intelligent analysis method based on the flow shot commodity in the foregoing embodiment, the present invention further provides an intelligent analysis system based on the flow shot commodity, please refer to fig. 3, where the system includes:
the first acquisition unit 11 is used for acquiring data of historical auction information of the target object based on big data to obtain a historical auction atlas set of the target object;
a first classification unit 12, where the first classification unit 12 is configured to perform multi-feature classification on the historical auction atlas set to obtain a first auction feature chain, a second auction feature chain, and a third auction feature chain;
a first obtaining unit 13, where the first obtaining unit 13 is configured to obtain a first ordinary beat feature chain corresponding to the first streaming beat feature chain;
A second obtaining unit 14, where the second obtaining unit 14 is configured to obtain a flow beat feature of each link point on the first flow beat feature chain, and a common beat feature of each link node on the first common beat feature chain;
a first input unit 15, where the first input unit 15 is configured to input the flow beat features of the chain nodes and the common beat features of the chain nodes as input information to a node feature association degree evaluation model to perform training on one-to-one corresponding nodes, obtain a flow beat-common beat feature association degree set of each corresponding node, and use the flow beat-common beat feature association degree set as a first analysis feature;
a first extraction unit 16, where the first extraction unit 16 is configured to perform main feature extraction on the second tap feature chain, take an extraction result as a second analysis feature, perform main feature extraction on the third tap feature chain, and take an extraction result as a third analysis feature;
a second input unit 17, where the second input unit 17 is configured to input the first analysis feature, the second analysis feature, and the third analysis feature into a feature standardization processing model for training, so as to obtain the expected flow shooting environment information of the target object.
Further, the system further comprises:
the second acquisition unit is used for acquiring the access amount of the historical auction information of the target object to obtain a historical access information set of the target object;
the first retrieval unit is used for performing key feature retrieval analysis on the historical access information set, and performing descending order arrangement on analysis results to generate a historical retrieval feature sequence of the target object;
and the second classification unit is used for sequentially performing feature retrieval classification on the historical auction picture set based on the historical retrieval feature sequence to obtain the first stream beat feature chain, the second stream beat feature chain and the third stream beat feature chain.
Further, the system further comprises:
a third obtaining unit, configured to define the historical access information set as original d-dimensional data, and perform normalization processing to obtain a normalized access information set of the target object as sample data;
a first construction unit to construct a covariance matrix of the sample data based on the standardized set of access information;
A first calculation unit for calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
the first screening unit is used for carrying out maximum value screening on the characteristic values and the characteristic vectors to obtain k characteristic vectors corresponding to the first k maximum characteristic values, wherein k is less than or equal to d;
a first constructing unit configured to construct a mapping matrix W based on the k eigenvectors;
a first conversion unit for converting the raw d-dimensional data into a k-dimensional feature subspace based on the mapping matrix W.
Further, the system further comprises:
a fourth obtaining unit, configured to obtain a first node flow beat feature in the chain link point flow beat features and a first node common beat feature in the chain link node common beat features;
a third input unit, configured to input the first node stream beat features and the first node common beat features into the node feature association degree evaluation model for training, so as to obtain first feature association degrees of the link point stream beat features and the link node common beat features at a first node;
A fifth obtaining unit, configured to perform traversal training on each node on the flow beat feature of each link point and the normal beat feature of each link point, and sequentially obtain a second feature association degree at a second node until an nth feature association degree at an nth node, where the second feature association degree is used as the flow beat-normal beat feature association degree set.
Further, the system further comprises:
the first processing unit is used for carrying out primary standardization processing on the first analysis feature and the second analysis feature based on the feature standardization processing model to obtain a first to-be-optimized environment vector of the target object;
the second processing unit is used for carrying out secondary standardization processing on the second analysis characteristic and the third analysis characteristic based on the characteristic standardization processing model to obtain a second environment vector to be optimized of the target object;
and the third processing unit is used for carrying out three times of standardization processing on the first analysis characteristic and the third analysis characteristic based on the characteristic standardization processing model to obtain a third environment vector to be optimized of the target object.
Further, the system further comprises:
a second construction unit for constructing a vector optimization platform;
a first optimization unit, configured to upload the first to-be-optimized environment vector, the second to-be-optimized environment vector, and the third to-be-optimized environment vector to the vector optimization platform for inter-vector fusion optimization, so as to generate expected streaming environment information of the target object;
a first creating unit, configured to create an environment of a subsequent auction link for the target object based on the information of the environment of the desired streaming.
Further, the system further comprises:
a sixth obtaining unit, configured to obtain a three-dimensional data vector based on the feature normalization processing model;
a third construction unit, configured to respectively construct a first dimension vector space, a second dimension vector space, and a third dimension vector space according to the three-dimensional data vector;
a fourth construction unit, configured to construct the vector optimization platform based on the first-dimension vector space, the second-dimension vector space, and the third-dimension vector space.
In the present description, each embodiment is described in a progressive manner, and the emphasis of each embodiment is on the difference from other embodiments, and the flow-shot-product-based intelligent analysis method and the specific example in the first embodiment of fig. 1 are also applicable to the flow-shot-product-based intelligent analysis system of the present embodiment, and through the foregoing detailed description of the flow-shot-product-based intelligent analysis method, those skilled in the art can clearly know that the flow-shot-product-based intelligent analysis system of the present embodiment is provided, so for the brevity of the description, detailed description is not repeated here. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The electronic device of the present invention is described below with reference to fig. 4.
Fig. 4 illustrates a schematic structural diagram of an electronic device according to the present invention.
Based on the inventive concept of the intelligent analysis method based on the flow shot commodities in the foregoing embodiments, the present invention further provides an intelligent analysis system based on the flow shot commodities, on which a computer program is stored, and the program, when executed by a processor, implements the steps of any one of the foregoing intelligent analysis methods based on the flow shot commodities.
Where in fig. 4 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The invention provides an intelligent analysis method based on a stream shot commodity, which is characterized by comprising the following steps: based on the big data, performing data acquisition on historical auction information of the target object to obtain a historical auction atlas set of the target object; performing multi-feature classification on the historical auction picture collection to obtain a first stream-shot feature chain, a second stream-shot feature chain and a third stream-shot feature chain; obtaining a first popular beat feature chain corresponding to the first popular beat feature chain; acquiring flow beat characteristics of each link point on the first flow beat characteristic chain and common beat characteristics of each link node on the first common beat characteristic chain; respectively inputting the flow beat characteristics and the common beat characteristics of the chain nodes as input information into a node characteristic association degree evaluation model to train one-to-one corresponding nodes, obtaining a flow beat-common beat characteristic association degree set of each corresponding node, and taking the flow beat-common beat characteristic association degree set as a first analysis characteristic; performing main feature extraction on the second flow shooting feature chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow shooting feature chain, and taking an extraction result as a third analysis feature; inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain the expected streaming environment information of the target object. The method solves the technical problem that in the prior art, due to the fact that multi-feature data analysis cannot be carried out on a certain article of flow shot, the article of shot is subjected to flow shot for many times, and the quality of the article of shot is seriously affected. Through analyzing past auction data of the flow shot commodity, the flow shot commodity is compared with each key feature of a common shot commodity in the same period of the past one by one, the features of the shot commodity to be optimized are obtained through analysis, standardized fusion optimization is carried out on each feature of the shot commodity to be optimized, the expected auction environment meeting the flow shot commodity is finally analyzed, multi-azimuth analysis on the key features of the shot commodity is achieved, the expected auction environment suitable for the shot commodity is created, reasonable optimization is further carried out on the auction environment of the flow shot commodity, and the technical effect of the auction quality of the flow shot commodity is improved.
The invention also provides an electronic device, which comprises a processor and a memory;
the memory is used for storing;
the processor is configured to execute the method according to any one of the first embodiment through calling.
The invention also provides a computer program product comprising a computer program and/or instructions which, when executed by a processor, carry out the steps of the method of any one of the above embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, it is intended that the present invention also encompass such modifications and variations.
Claims (10)
1. An intelligent analysis method based on stream shot commodities is characterized by comprising the following steps:
based on the big data, performing data acquisition on historical auction information of the stream-shot commodities to obtain a historical auction atlas set of the stream-shot commodities;
Performing multi-feature classification on the historical auction picture set to obtain a first stream-shot feature chain, a second stream-shot feature chain and a third stream-shot feature chain, wherein the first stream-shot feature chain is a picture type feature chain, the second stream-shot feature chain is an audience group feature chain, and the third stream-shot feature chain is an auction base price feature chain;
obtaining a first primary common beat feature chain corresponding to the first stream beat feature chain;
acquiring flow beat characteristics of each link point on the first flow beat characteristic chain and common beat characteristics of each link node on the first primary common beat characteristic chain;
respectively inputting the flow beat characteristics and the common beat characteristics of the chain nodes as input information into a node characteristic association degree evaluation model to train one-to-one corresponding nodes, obtaining a flow beat-common beat characteristic association degree set of each corresponding node, and taking the flow beat-common beat characteristic association degree set as a first analysis characteristic;
performing main feature extraction on the second flow shooting feature chain, taking an extraction result as a second analysis feature, performing main feature extraction on the third flow shooting feature chain, and taking an extraction result as a third analysis feature;
inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain expected streaming environment information of the streaming commodity, namely creating an expected auction environment for the subsequent auction.
2. The method of claim 1, wherein the multi-feature classifying the set of historical auction books comprises:
acquiring the access amount of the historical auction information of the stream-shot commodities to obtain a historical access information set of the stream-shot commodities;
performing key feature retrieval analysis on the historical access information set, and performing descending order arrangement on analysis results to generate a historical retrieval feature sequence of the flow shot commodity;
and sequentially performing feature retrieval classification on the historical auction picture set based on the historical retrieval feature sequence to obtain the first stream-shot feature chain, the second stream-shot feature chain and the third stream-shot feature chain.
3. The method of claim 2, wherein the performing a key feature retrieval analysis on the set of historical access information comprises:
defining the historical access information set as original d-dimensional data, and performing standardization processing to obtain a standardized access information set of the flow shooting commodity as sample data;
constructing a covariance matrix of the sample data based on the standardized access information set;
calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
Maximum value screening is carried out on the characteristic values and the characteristic vectors, k characteristic vectors corresponding to the first k maximum characteristic values are obtained, wherein k is less than or equal to d;
constructing a mapping matrix W based on the k eigenvectors;
and converting the original d-dimensional data into a k-dimensional feature subspace based on the mapping matrix W.
4. The method of claim 1, wherein the input to the node feature relevance assessment model performs training of one-to-one nodes, comprising:
obtaining a first node flow beat feature in the chain link point flow beat features and a first node common beat feature in the chain link point common beat features;
inputting the first node stream beat features and the first node common beat features into the node feature association degree evaluation model for training to obtain first feature association degrees of the link point stream beat features and the link node common beat features at first nodes;
and traversing and training the nodes on the flow beat features of the chain link points and the common beat features of the chain link points, and sequentially obtaining second feature association degrees at second nodes until the Nth feature association degree at the Nth node, wherein the N-th feature association degree serves as the flow beat-common beat feature association degree set.
5. The method of claim 1, wherein the method comprises:
based on the feature standardization processing model, carrying out primary standardization processing on the first analysis feature and the second analysis feature to obtain a first to-be-optimized environment vector of the flow shooting commodity;
based on the feature standardization processing model, carrying out secondary standardization processing on the second analysis feature and the third analysis feature to obtain a second to-be-optimized environment vector of the flow shot commodity;
and carrying out three times of standardization processing on the first analysis characteristic and the third analysis characteristic based on the characteristic standardization processing model to obtain a third environment vector to be optimized of the flow shot commodity.
6. The method of claim 5, wherein the method comprises:
constructing a vector optimization platform;
uploading the first to-be-optimized environment vector, the second to-be-optimized environment vector and the third to-be-optimized environment vector to the vector optimization platform for fusion optimization among vectors, and generating expected streaming environment information of the streaming commodity;
and based on the expected streaming environment information, performing environment creation of a subsequent auction link on the streaming commodity.
7. The method of claim 6, wherein said constructing a vector optimization platform comprises:
obtaining a three-dimensional data vector based on the characteristic standardization processing model;
respectively constructing a first dimension vector space, a second dimension vector space and a third dimension vector space according to the three-dimensional data vector;
and constructing the vector optimization platform based on the first dimension vector space, the second dimension vector space and the third dimension vector space.
8. An intelligent analysis system based on stream shot commodities, characterized in that the system comprises:
the first acquisition unit is used for acquiring data of historical auction information of the stream-shot commodities based on big data to obtain a historical auction atlas set of the stream-shot commodities;
the system comprises a first classification unit, a second classification unit and a third classification unit, wherein the first classification unit is used for performing multi-feature classification on the historical auction picture set to obtain a first auction feature chain, a second auction feature chain and a third auction feature chain, the first auction feature chain is a feature chain of a auction type, the second auction feature chain is a feature chain of an audience group, and the third auction feature chain is a feature chain of a base price for auction;
A first obtaining unit, configured to obtain a first primary common beat feature chain corresponding to the first stream beat feature chain;
a second obtaining unit, configured to obtain a flow shot feature of each link point on the first flow shot feature chain and a common shot feature of each link node on the first primary common shot feature chain;
a first input unit, configured to input the flow beat features and the common beat features of the chain nodes as input information to a node feature association degree evaluation model to perform training on nodes in a one-to-one correspondence manner, obtain a flow beat-common beat feature association degree set of each corresponding node, and use the flow beat-common beat feature association degree set as a first analysis feature;
a first extraction unit, configured to perform main feature extraction on the second beat feature chain, take an extraction result as a second analysis feature, perform main feature extraction on the third beat feature chain, and take an extraction result as a third analysis feature;
and the second input unit is used for inputting the first analysis characteristic, the second analysis characteristic and the third analysis characteristic into a characteristic standardization processing model for training to obtain expected flow shooting environment information of the flow shooting commodity, namely establishing an expected auction environment for the subsequent auction.
9. An electronic device comprising a processor and a memory;
the memory is used for storing;
the processor is used for executing the method of any one of claims 1-7 through calling.
10. A computer storage medium comprising computer programs and/or instructions, characterized in that the computer programs and/or instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210308349.6A CN114419448B (en) | 2022-03-28 | 2022-03-28 | Intelligent analysis method and system based on stream shot commodities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210308349.6A CN114419448B (en) | 2022-03-28 | 2022-03-28 | Intelligent analysis method and system based on stream shot commodities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114419448A CN114419448A (en) | 2022-04-29 |
| CN114419448B true CN114419448B (en) | 2022-06-14 |
Family
ID=81264587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210308349.6A Active CN114419448B (en) | 2022-03-28 | 2022-03-28 | Intelligent analysis method and system based on stream shot commodities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114419448B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819594A (en) * | 2021-01-07 | 2021-05-18 | 南京航空航天大学 | Privacy protection dynamic spectrum auction method based on alliance chain |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2637431C2 (en) * | 2015-10-12 | 2017-12-04 | Общество С Ограниченной Ответственностью "Яндекс" | Method and system of determining optimal value of auction parameter for digital object |
-
2022
- 2022-03-28 CN CN202210308349.6A patent/CN114419448B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819594A (en) * | 2021-01-07 | 2021-05-18 | 南京航空航天大学 | Privacy protection dynamic spectrum auction method based on alliance chain |
Non-Patent Citations (2)
| Title |
|---|
| 《Trusted UAV Network Coverage Using Blockchain, Machine Learning, and Auction Mechanisms》;Amjad Saeed Khan et al.;《IEEE Access》;20200622;第08卷;全文 * |
| 网上拍卖竞买者出价水平的动态演变模式研究;严明义;《统计研究》;20100315(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114419448A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yin et al. | Incomplete multi-view clustering via subspace learning | |
| Guo et al. | A stock market forecasting model combining two-directional two-dimensional principal component analysis and radial basis function neural network | |
| US20220215298A1 (en) | Method for training sequence mining model, method for processing sequence data, and device | |
| JP2013519138A (en) | Join embedding for item association | |
| US10909442B1 (en) | Neural network-based artificial intelligence system for content-based recommendations using multi-perspective learned descriptors | |
| CN110414550B (en) | Training method, device and system of face recognition model and computer readable medium | |
| US11645328B2 (en) | 3D-aware image search | |
| CN111695024A (en) | Object evaluation value prediction method and system, and recommendation method and system | |
| CN110443290B (en) | Product competition relationship quantitative generation method and device based on big data | |
| CN115860836A (en) | E-commerce service pushing method and system based on user behavior big data analysis | |
| Tkachenko et al. | Plackett-luce regression mixture model for heterogeneous rankings | |
| CN114419448B (en) | Intelligent analysis method and system based on stream shot commodities | |
| CN112749737A (en) | Image classification method and device, electronic equipment and storage medium | |
| Gorokhovatskyi et al. | Transforming image descriptions as a set of descriptors to construct classification features | |
| CN114780862B (en) | User interest vector extraction method, extraction model and computer system | |
| CN115860802A (en) | Product value prediction method, device, computer equipment and storage medium | |
| CN107423759B (en) | Comprehensive evaluation method, device and application of low-dimensional successive projection pursuit clustering model | |
| CN117009621A (en) | Information searching method, device, electronic equipment, storage medium and program product | |
| CN112650869B (en) | Image retrieval reordering method and device, electronic equipment and storage medium | |
| CN115114517A (en) | Collaborative filtering recommendation algorithm based on user attributes and item scores | |
| CN114529063A (en) | Financial field data prediction method, device and medium based on machine learning | |
| Virta et al. | Robust signal dimension estimation via SURE | |
| CN111695917A (en) | Commodity recommendation method, system, electronic device and storage medium | |
| CN115905887B (en) | Big data intelligent decision system based on data processing | |
| CN114281994B (en) | Text clustering integration method and system based on three-layer weighting model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |