CN109272367B - Information processing method and device - Google Patents

Information processing method and device Download PDF

Info

Publication number
CN109272367B
CN109272367B CN201710581430.0A CN201710581430A CN109272367B CN 109272367 B CN109272367 B CN 109272367B CN 201710581430 A CN201710581430 A CN 201710581430A CN 109272367 B CN109272367 B CN 109272367B
Authority
CN
China
Prior art keywords
target
information
description information
characteristic value
judgment matrix
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
Application number
CN201710581430.0A
Other languages
Chinese (zh)
Other versions
CN109272367A (en
Inventor
王雪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201710581430.0A priority Critical patent/CN109272367B/en
Publication of CN109272367A publication Critical patent/CN109272367A/en
Application granted granted Critical
Publication of CN109272367B publication Critical patent/CN109272367B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses an information processing method and device. One embodiment of the method comprises: acquiring target article information on a preset website, wherein the target article information comprises at least one piece of target description information for describing a target article; analyzing each item label description information in at least one piece of target description information respectively to generate a characteristic data set of each item label description information; respectively generating a characteristic value of each item label description information based on the characteristic data set of each item label description information; generating a characteristic value of the target article information based on the characteristic value of the item label description information; and matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result. The embodiment realizes the information processing rich in pertinence.

Description

Information processing method and device
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of internet technologies, and in particular, to an information processing method and apparatus.
Background
With the popularization of the internet, the advantages of online shopping are more prominent, and the scale of users who shop on the internet is also increasing. When a user purchases goods by using a network, the user needs to acquire a large amount of goods information from the network and analyze the acquired large amount of goods information so as to select and purchase the goods required by the user. Since the item information directly affects the selection of the user for the item, it is important to process the item information in a targeted manner in order to ensure the authenticity, effectiveness, richness, and the like of the item information displayed to the user.
Disclosure of Invention
An object of the embodiments of the present application is to provide an improved information processing method and apparatus, so as to solve the technical problems mentioned in the above background.
In a first aspect, an embodiment of the present application provides an information processing method, where the method includes: acquiring target article information on a preset website, wherein the target article information comprises at least one piece of target description information for describing a target article; analyzing each item label description information in at least one piece of target description information respectively to generate a characteristic data set of each item label description information; respectively generating a characteristic value of each item label description information based on the characteristic data set of each item label description information; generating a characteristic value of the target article information based on the characteristic value of the item label description information; and matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result.
In some embodiments, generating the feature value of each item label description information based on the feature data set of each item label description information respectively includes: for each piece of target description information in at least one piece of target description information, respectively obtaining the weight corresponding to each feature data in the feature data set of the target description information, and generating the feature value of the target description information based on the feature data set of the target description information and the weight corresponding to each feature data.
In some embodiments, before obtaining the weight corresponding to each feature data in the feature data set of the target description information, the method further includes: acquiring a first judgment matrix corresponding to the feature data set of the target description information, wherein elements in the first judgment matrix are used for representing the relative importance degree between two feature data in the feature data set of the target description information; and generating weights corresponding to all the characteristic data in the characteristic data set of the target description information based on all the elements in the first judgment matrix.
In some embodiments, before obtaining the first determination matrix corresponding to the feature data set of the target description information, the method further includes: acquiring a first candidate judgment matrix corresponding to the characteristic data set of the target description information and a preset first reference parameter; performing the following first determining step: generating a first detection parameter based on the maximum eigenvalue of the first candidate judgment matrix and the order of the first candidate judgment matrix, determining whether the ratio of the first detection parameter to the first reference parameter is smaller than a first preset threshold, and if so, taking the first candidate judgment matrix as the first judgment matrix; and in response to the fact that the ratio of the first detection parameter to the first reference parameter is not smaller than a first preset threshold value, outputting first prompt information to prompt correction of the first candidate judgment matrix, taking the corrected first candidate judgment matrix as the first candidate judgment matrix, and continuing to execute the first determining step.
In some embodiments, generating the feature value of the target description information based on the feature data set of the target description information and the weight corresponding to each feature data includes: acquiring a feature data set of description information with the same category as the target description information in reference article information on a preset website, wherein the reference article information is article information of an article with the same category as the target article; standardizing the feature data set of the target description information by using the obtained feature data set and the length of a preset standard mapping interval to obtain a standardized feature data set of the target description information; the feature value of the target description information is generated based on the normalized feature data set of the target description information and the weight corresponding to each feature data.
In some embodiments, generating the feature value of the target item information based on the feature value of the item description information includes: respectively acquiring weights corresponding to the characteristic values of the item label description information; and generating a characteristic value of the target article information based on the characteristic value of each item label description information and the weight corresponding to the characteristic value of each item label description information.
In some embodiments, before obtaining the weight corresponding to the feature value of each item label description information, the method further includes: acquiring a second judgment matrix corresponding to at least one piece of target description information, wherein elements in the second judgment matrix are used for representing the relative importance degree between two pieces of target description information in the at least one piece of target description information; and generating a weight corresponding to the characteristic value of each item label description information in the at least one piece of target description information based on each element in the second judgment matrix.
In some embodiments, before obtaining the second decision matrix corresponding to at least one piece of object description information, the method further includes: acquiring a second candidate judgment matrix corresponding to at least one piece of target description information and a preset second reference parameter; performing the following second determining step: generating a second detection parameter based on the maximum eigenvalue of the second candidate judgment matrix and the order of the second candidate judgment matrix, determining whether the ratio of the second detection parameter to the second reference parameter is smaller than a second preset threshold, and if so, taking the second candidate judgment matrix as the second judgment matrix; and in response to the determination that the ratio of the second detection parameter to the second reference parameter is not less than the second preset threshold, outputting second prompt information to prompt the correction of the second candidate judgment matrix, taking the corrected second candidate judgment matrix as the second candidate judgment matrix, and continuing to execute the second determination step.
In some embodiments, the target item information includes target item information for each preset time point within a preset time period; and generating a characteristic value of the target article information based on the characteristic value of the description information of each item label, including: generating a characteristic value of the target article information at each preset time point based on the characteristic value of each item label description information of the target article information at each preset time point; acquiring a pre-constructed function related to a time point; generating weights corresponding to characteristic values of the target article information at all preset time points based on the functions related to the time points; and generating the characteristic value of the target item information based on the characteristic value of the target item information at each preset time point and the weight corresponding to the characteristic value of the target item information at each preset time point.
In some embodiments, processing the target item information based on the matching result includes: determining the category of the target article information based on the matching result, wherein each preset characteristic value interval in the preset characteristic value interval set corresponds to the category of one article information; determining whether the category of the target item information is a preset category; and if the target article information is in the preset category, outputting third prompt information or deleting the target article information from a preset website, wherein the third prompt information is used for prompting the target article information to be modified.
In a second aspect, an embodiment of the present application provides an information processing apparatus, including: the system comprises a target article information acquisition unit, a target article information acquisition unit and a target article information acquisition unit, wherein the target article information acquisition unit is configured to acquire target article information on a preset website, and the target article information comprises at least one piece of target description information for describing a target article; the characteristic data generating unit is configured to analyze each item label description information in at least one piece of target description information respectively and generate a characteristic data set of each item label description information; the target description information characteristic value generating unit is configured to generate a characteristic value of each item label description information based on a characteristic data set of each item label description information; the target article information characteristic value generating unit is configured to generate a characteristic value of the target article information based on the characteristic value of each item label description information; and the target article information processing unit is configured to match the characteristic value of the target article information in a preset characteristic value interval set and process the target article information based on a matching result.
In some embodiments, the target description information feature value generation unit includes: and the target description information characteristic value generating subunit is configured to, for each piece of target description information in at least one piece of target description information, respectively acquire a weight corresponding to each piece of characteristic data in the characteristic data set of the target description information, and generate a characteristic value of the target description information based on the characteristic data set of the target description information and the weight corresponding to each piece of characteristic data.
In some embodiments, the target description information feature value generation unit further includes: a first judgment matrix obtaining subunit, configured to obtain a first judgment matrix corresponding to the feature data set of the target description information, where an element in the first judgment matrix is used to represent a relative importance degree between two feature data in the feature data set of the target description information; and the characteristic data weight generation subunit is configured to generate weights corresponding to the characteristic data in the characteristic data set of the target description information based on the elements in the first judgment matrix.
In some embodiments, the target description information feature value generation unit further includes: a first candidate judgment matrix obtaining subunit configured to obtain a first candidate judgment matrix corresponding to the feature data set of the target description information and a preset first reference parameter; a first determination step execution subunit configured to execute the following first determination steps: generating a first detection parameter based on the maximum eigenvalue of the first candidate judgment matrix and the order of the first candidate judgment matrix, determining whether the ratio of the first detection parameter to the first reference parameter is smaller than a first preset threshold, and if so, taking the first candidate judgment matrix as the first judgment matrix; and the first candidate judgment matrix correction subunit is configured to output first prompt information to prompt correction of the first candidate judgment matrix in response to determining that the ratio between the first detection parameter and the first reference parameter is not smaller than a first preset threshold, and continue to execute the first determination step by taking the corrected first candidate judgment matrix as the first candidate judgment matrix.
In some embodiments, the target description information characteristic value generation subunit includes: the characteristic data acquisition module is configured to acquire a characteristic data set of description information, which is the same as the type of the target description information, in reference article information on a preset website, wherein the reference article information is the article information of an article, which is the same as the type of the target article; the standardization processing module is configured to utilize the acquired feature data set and the length of a preset standard mapping interval to standardize the feature data set of the target description information to obtain a standardized feature data set of the target description information; and the target description information characteristic value generation module is configured to generate a characteristic value of the target description information based on the normalized characteristic data set of the target description information and the weight corresponding to each characteristic data.
In some embodiments, the target item information characteristic value generation unit includes: the object description information characteristic value weight acquiring subunit is configured to acquire weights corresponding to characteristic values of the item description information respectively; and the target article information characteristic value generating subunit is configured to generate the characteristic value of the target article information based on the characteristic value of each item label description information and the weight corresponding to the characteristic value of each item label description information.
In some embodiments, the target item information characteristic value generation unit further includes: a second decision matrix obtaining subunit, configured to obtain a second decision matrix corresponding to the at least one piece of target description information, where an element in the second decision matrix is used to represent a relative importance degree between two pieces of target description information in the at least one piece of target description information; and the target description information characteristic value weight generating subunit is configured to generate a weight corresponding to the characteristic value of each item of target description information in the at least one piece of target description information based on each element in the second judgment matrix.
In some embodiments, the target item information characteristic value generation unit further includes: a second candidate judgment matrix obtaining subunit configured to obtain a second candidate judgment matrix corresponding to the at least one piece of target description information and a preset second reference parameter; a second determination step execution subunit configured to execute the following second determination step: generating a second detection parameter based on the maximum eigenvalue of the second candidate judgment matrix and the order of the second candidate judgment matrix, determining whether the ratio of the second detection parameter to the second reference parameter is smaller than a second preset threshold, and if so, taking the second candidate judgment matrix as the second judgment matrix; and the second candidate judgment matrix correction subunit is configured to output second prompt information to prompt correction of the second candidate judgment matrix in response to a determination that the ratio between the second detection parameter and the second reference parameter is not smaller than a second preset threshold, and continue to execute the second determination step by taking the corrected second candidate judgment matrix as the second candidate judgment matrix.
In some embodiments, the target item information includes target item information for each preset time point within a preset time period; and the target item information characteristic value generation unit is further configured to: generating a characteristic value of the target article information at each preset time point based on the characteristic value of each item label description information of the target article information at each preset time point; acquiring a pre-constructed function related to a time point; generating weights corresponding to characteristic values of the target article information at all preset time points based on the functions related to the time points; and generating the characteristic value of the target item information based on the characteristic value of the target item information at each preset time point and the weight corresponding to the characteristic value of the target item information at each preset time point.
In some embodiments, the target item information processing unit includes: the target article information category determining subunit is configured to determine a category of the target article information based on the matching result, wherein each preset characteristic value interval in the preset characteristic value interval set corresponds to a category of article information; a preset category determination subunit configured to determine whether the category of the target item information is a preset category; and the target article information processing subunit is configured to output third prompt information or delete the target article information from the preset website if the target article information processing subunit is in the preset category, wherein the third prompt information is used for prompting to modify the target article information.
In a third aspect, an embodiment of the present application provides a server, where the server includes: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.
According to the information processing method and device provided by the embodiment of the application, the feature data set of each item description information is generated by analyzing at least one piece of target description information included in the target article information on the preset website; then generating a characteristic value of the item label description information based on the characteristic data set of the item label description information; then generating a characteristic value of the target article information based on the characteristic value of the item label description information; and finally, matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result. Thereby realizing the information processing with rich pertinence.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of an information processing method according to the present application;
FIG. 3 is a flow diagram of yet another embodiment of an information processing method according to the present application;
FIG. 4 is a flow diagram of one embodiment of a method of generating weights corresponding to feature data according to the present application;
FIG. 5 is a flow diagram of one embodiment of a method of generating weights corresponding to feature values of target description information according to the present application;
FIG. 6 is a schematic block diagram of one embodiment of an information processing apparatus according to the present application;
FIG. 7 is a block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the information processing method or information processing apparatus of the present application may be applied.
As shown in fig. 1, system architecture 100 may include a database server 101, a server 102, and a network 103. Network 103 is the medium used to provide communication links between database server 101 and server 102. Network 103 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The database server 101 may be a background database server of the website, and is used for storing the item information on the website.
The server 102 may provide various services. For example, the server 102 may acquire target item information on a website from the database server 101, perform processing such as analysis on data such as the target item information, and perform processing on the target item information based on a processing result (for example, a matching result of a feature value of the target item information in a preset feature value interval set).
It should be noted that the information processing method provided in the embodiment of the present application is generally executed by the server 102, and accordingly, the information processing apparatus is generally disposed in the server 102.
It should be understood that the number of database servers, and networks in FIG. 1 is merely illustrative. There may be any number of database servers, and networks, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of an information processing method according to the present application is shown. The information processing method comprises the following steps:
step 201, obtaining target item information on a preset website.
In the present embodiment, the electronic device (for example, the server 102 shown in fig. 1) on which the information processing method operates may acquire target item information on a preset website (for example, a certain electronic commerce website) from a database server (for example, the database server 101 shown in fig. 1) through a wired connection manner or a wireless connection manner. The target item information may include at least one piece of target description information describing the target item. The target description information may include, but is not limited to, a target item host, a target item detail map, a target item name, target item configuration information, target item function information, target item review information, and the like.
Step 202, analyzing each item label description information in at least one piece of target description information respectively, and generating a feature data set of each item label description information.
In this embodiment, for each piece of target description information in at least one piece of target description information, the electronic device may analyze the piece of target description information, so as to generate a feature data set of the target description information. Wherein each feature data may be used to represent a feature of the object description information. By way of example, if the target description information is a target item host, the feature data of the target description information may include, but is not limited to, the number of target item hosts, the clarity of the target item hosts, the degree to which the target item hosts conform to physical objects, and so forth.
Step 203, generating a feature value of each item label description information based on the feature data set of each item label description information.
In this embodiment, for each piece of object description information in the at least one piece of object description information, the electronic device may generate a feature value of the object description information by using a feature data set of the object description information. Wherein, the characteristic value of the object description information can be used to represent the overall characteristic of the object description information. As an example, the electronic device may add respective feature data in a feature data set of the target description information, and take the resultant sum as a feature value of the target description information.
And step 204, generating a characteristic value of the target article information based on the characteristic value of the description information of each item label.
In this embodiment, the electronic device may generate the feature value of the target item information by using the feature value of each item label description information included in the target item information. The characteristic value of the target item information may be used to represent an overall characteristic of the target item information. As an example, the electronic device may add feature values of the item label description information included in the target item information, and use the resultant sum as the feature value of the target item information.
And step 205, matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on the matching result.
In this embodiment, the electronic device may pre-divide a plurality of characteristic value intervals, where one characteristic value interval corresponds to one article information processing method. At this time, the electronic device may match the feature value of the target article information with each preset feature value interval in the preset feature value interval set, if the feature value of the target article information falls within one of the preset feature value intervals, the matching is successful, and the target article information is processed by using an article information processing method corresponding to the preset feature value interval with which the matching is successful.
In some optional implementations of this embodiment, the electronic device may first determine a category of the target item information based on the matching result; then determining whether the category of the target article information is a preset category; and if the type is the preset type, outputting third prompt information or deleting the target article information from the preset website. Each preset characteristic value interval in the preset characteristic value interval set can correspond to a type of article information. The preset categories are typically categories that do not comply with the relevant regulations. The third prompting message can be used for prompting the modification of the target article information.
As an example, if the category of the target item information is a preset category, the electronic device may send an email to a website maintainer or a target item information uploader, where the content of the email is used to prompt the website maintainer or the target item information uploader to modify the target item information.
As another example, if the category of the target item information is a preset category, the electronic device may send a deletion instruction to the database server to cause the database server to delete the target item information.
According to the information processing method provided by the embodiment of the application, at least one piece of target description information included in target article information on a preset website is analyzed, so that a feature data set of each item of target description information is generated; then generating a characteristic value of the item label description information based on the characteristic data set of the item label description information; then generating a characteristic value of the target article information based on the characteristic value of the item label description information; and finally, matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result. Thereby realizing the information processing with rich pertinence.
With further reference to FIG. 3, a flow 300 of yet another embodiment of an information processing method is shown. The process 300 of the information processing method includes the following steps:
step 301, obtaining target item information on a preset website.
In the present embodiment, the electronic device (for example, the server 102 shown in fig. 1) on which the information processing method operates may acquire target item information on a preset website (for example, a certain electronic commerce website) from a database server (for example, the database server 101 shown in fig. 1) through a wired connection manner or a wireless connection manner. The target item information may include at least one piece of target description information describing the target item. The target description information may include, but is not limited to, a target item host, a target item detail map, a target item name, target item configuration information, target item function information, target item review information, and the like.
Step 302, analyzing each item label description information in at least one piece of target description information respectively, and generating a feature data set of each item label description information.
In this embodiment, for each piece of target description information in at least one piece of target description information, the electronic device may analyze the piece of target description information, so as to generate a feature data set of the target description information. Wherein each feature data may be used to represent a feature of the object description information.
Step 303, for each piece of target description information in at least one piece of target description information, respectively obtaining a weight corresponding to each feature data in the feature data set of the target description information.
In this embodiment, for each piece of target description information in at least one piece of target description information, the electronic device may respectively obtain weights corresponding to each feature data in the feature data set of the target description information.
Here, the electronic device may acquire the weight corresponding to the feature data in various ways. As an example, the electronic device may query the first weight table to obtain weights corresponding to respective feature data in the feature data set of the target description information. The first weight table may be used to store the feature data and the weight corresponding to the feature data.
Step 304, generating a feature value of the target description information based on the feature data set of the target description information and the weight corresponding to each feature data.
In this embodiment, the electronic device may generate the feature value of the target description information by using the feature data set of the target description information and the weight corresponding to each feature data.
As an example, the electronic device may generate the characteristic value S of the target description information by the following formula:
Figure BDA0001352401290000111
wherein i is more than or equal to 1 and less than or equal to a, i is an integer, a is the number of all feature data in the feature data set of the target description information, W is the weight corresponding to the feature dataiIs the weight corresponding to the ith feature data, s is the feature data, siIs the ith characteristic data.
In some optional implementations of this embodiment, the electronic device may generate the feature value of the target description information by:
firstly, a feature data set of description information in reference article information on a preset website, wherein the description information is the same as the target description information in category, is obtained.
The reference item information may be item information of an item of the same type as the target item.
Then, the feature data set of the target description information is standardized by using the obtained feature data set and the length of a preset standard mapping interval, so that a standardized feature data set of the target description information is obtained.
As an example, the electronic device may obtain each normalized feature data s 'by'i：
Figure BDA0001352401290000121
Figure BDA0001352401290000122
Wherein i is more than or equal to 1 and less than or equal to a, i is an integer, a is the number of all feature data in the feature data set of the target description information, s is feature data, s isiFor the ith feature data, μ is an average value of feature data of the same category as the feature data s in the plurality of feature data sets obtained, and μiFor the ith feature data s in the obtained multiple feature data setsiThe mean value of the feature data with the same category, delta is the variance of the feature data with the same category as the feature data s in the acquired plurality of feature data sets, and deltaiFor the ith feature data s in the obtained multiple feature data setsiVariance of class-identical feature data, Y being a normalization parameter, YiIs the ith normalization parameter, YminIs all YiMinimum value of (1), YmaxIs all YiL is the length of the preset standard mapping interval.
Finally, a feature value of the object description information is generated based on the normalized feature data set of the object description information and the weight corresponding to each feature data.
As an example, the electronic device may generate the characteristic value S of the target description information by the following formula:
Figure BDA0001352401290000123
wherein W is the weight corresponding to the characteristic data, WiIs the weight corresponding to the ith characteristic data, s 'is normalized characteristic data, s'iIs the ith normalized feature data.
Step 305, the weights corresponding to the feature values of the item label description information are respectively obtained.
In this embodiment, the electronic device may obtain weights corresponding to feature values of the item label description information.
Here, the electronic device may acquire the weight corresponding to the feature value of the target description information in various ways. As an example, the electronic device may query the second weight table to obtain the weight corresponding to the feature value of the target description information. The second weight table may be configured to store the feature value of the target description information and the weight corresponding to the feature value of the target description information.
Step 306, generating a feature value of the target item information based on the feature value of each item label description information and the weight corresponding to the feature value of each item label description information.
In this embodiment, the electronic device may generate the feature value of the target item information by using the feature value of each item label description information and the weight corresponding to the feature value of each item label description information.
As an example, the electronic device may generate the characteristic value WIQI of the target item information by the following formula:
Figure BDA0001352401290000131
wherein m is more than or equal to 1 and less than or equal to b, m is an integer, b is the number of all target description information included in the target item information, W 'is the weight corresponding to the characteristic value of the target description information, W'mIs the weight corresponding to the characteristic value of the mth target description information, S is the characteristic value of the target description information, SmThe characteristic value of the mth object description information is obtained.
In some optional implementations of this embodiment, the target item information may include target item information at each preset time point within a preset time period. At this time, the electronic device may generate the characteristic value of the target item information by:
first, the feature value of the target item information at each preset time point is generated based on the feature value of each item label description information of the target item information at each preset time point.
Thereafter, a pre-constructed function associated with the point in time is obtained.
The function related to the time point may be a decreasing function, and the function related to the time point is as follows, for example:
Figure BDA0001352401290000132
n is more than or equal to 1 and less than or equal to c, n is an integer, c is the number of all preset time points in a preset time period, delta t is the difference between the preset time point and the current time point, and delta tnIs the difference between the nth predetermined point in time and the current point in time, G is a gravity factor, typically having a value of 1.8, f (Δ t) is the function value of the function associated with the predetermined point in time, f (Δ t)n) Is the function value of the function associated with the nth predetermined point in time.
Then, based on the function related to the time points, a weight corresponding to the characteristic value of the target item information at each preset time point is generated.
As an example, the electronic device may generate the weight W corresponding to the feature value of the target item information at each preset time point by the following formula "n：
Figure BDA0001352401290000141
Wherein W 'is the weight corresponding to the characteristic value of the target item information at the preset time point, W'nIs the n-thAnd presetting the weight corresponding to the characteristic value of the target article information at the time point.
And finally, generating the characteristic value of the target article information based on the characteristic value of the target article information at each preset time point and the weight corresponding to the characteristic value of the target article information at each preset time point.
As an example, the electronic device may generate the characteristic value BTWIQI of the target item information by the following formula:
Figure BDA0001352401290000142
wherein, WIQI is the characteristic value of the target item information at the preset time point, WIQInThe characteristic value of the target item information at the nth preset time point.
And 307, matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result.
In this embodiment, the electronic device may pre-divide a plurality of characteristic value intervals, where one characteristic value interval corresponds to one article information processing method. At this time, the electronic device may match the feature value of the target article information with each preset feature value interval in the preset feature value interval set, if the feature value of the target article information falls within one of the preset feature value intervals, the matching is successful, and the target article information is processed by using an article information processing method corresponding to the preset feature value interval with which the matching is successful.
As can be seen from fig. 3, compared with the embodiment corresponding to fig. 2, the flow 300 of the information processing method in the present embodiment highlights steps 303 and 306. Therefore, the characteristic value of the target description information and the characteristic value of the target article information generated by the scheme described in the embodiment are more real and objective.
With further reference to FIG. 4, a flow 400 of one embodiment of a method of generating weights corresponding to feature data is illustrated. The process 400 of the method for generating weights corresponding to feature data includes the following steps:
step 401, obtaining a first candidate judgment matrix corresponding to the feature data set of the target description information and a preset first reference parameter.
In this embodiment, the electronic device may acquire a first candidate determination matrix corresponding to the feature data set of the target description information and a preset first reference parameter.
In some alternative implementations of the present embodiment, a person skilled in the art may construct the first candidate decision matrix according to a relative importance degree between any two feature data in the feature data set. As an example, for a target item host:
firstly, a calibration table is established, which is specifically shown in table 1:
Figure BDA0001352401290000151
TABLE 1
Then, a target item main icon table is established, as shown in table 2:
main graph of target object Degree of conformity with the real object Number of Definition of
Degree of conformity with the real object 1 6 4
Number of 1/6 1 1/3
Definition of 1/4 3 1
TABLE 2
And finally, constructing a first candidate judgment matrix H of the main graph of the target object:
Figure BDA0001352401290000152
in some optional implementations of the embodiment, the electronic device may obtain the first reference parameter by querying the reference parameter table. In general, the first reference parameter is related to the rank of the first candidate decision matrix, and the reference parameter table is shown in table 3 as an example:
order of matrix 1 2 3 4 5 6
Reference parameter 0 0 0.53 0.89 1.12 1.24
TABLE 3
Step 402, generating a first detection parameter based on the maximum eigenvalue of the first candidate judgment matrix and the rank of the first candidate judgment matrix.
In this embodiment, the electronic device may generate the first detection parameter using the maximum eigenvalue of the first candidate determination matrix and the rank of the first candidate determination matrix. The maximum eigenvalue of the first candidate judgment matrix is the eigenvalue with the maximum value among all eigenvalues of the first candidate judgment matrix.
Here, for the first candidate decision matrix H, if the number λ and the non-zero column vector x make the relation: if Hx is satisfied, the number λ is an eigenvalue of the first candidate decision matrix H, and the non-zero column vector x is an eigenvector of the first candidate decision matrix H corresponding to the eigenvalue λ. The order of the first candidate judgment matrix H is the same as the dimension of the non-zero column vector x.
As an example, the electronic device may generate the first detection parameter CI by the following formula:
Figure BDA0001352401290000161
wherein λ ismaxAnd a is the number of all the feature data in the feature data set of the target description information, namely the order of the first candidate judgment matrix.
In step 403, it is determined whether the ratio between the first detected parameter and the first reference parameter is smaller than a first preset threshold.
In this embodiment, the electronic device may calculate a ratio between the first detection parameter and the first reference parameter, and compare the obtained ratio with a first preset threshold (e.g., 0.10); if the value is smaller than the first preset threshold, go to step 404; if not, go to step 404'.
In step 404, the first candidate judgment matrix is used as the first judgment matrix.
In this embodiment, in a case that the ratio between the first detection parameter and the first reference parameter is smaller than the first preset threshold, the electronic device may use the first candidate determination matrix as the first determination matrix, and continue to perform step 405.
In step 404', a first prompt message is output to prompt the first candidate judgment matrix to be corrected, and the corrected first candidate judgment matrix is used as the first candidate judgment matrix.
In an embodiment, in a case that a ratio between the first detection parameter and the first reference parameter is not less than a first preset threshold, the electronic device may first output first prompt information to prompt a person skilled in the art to correct the first candidate determination matrix; the corrected first candidate judgment matrix is then used as the first candidate judgment matrix, and the step 402 is executed again.
In step 405, a first judgment matrix corresponding to the feature data set of the target description information is obtained.
In this embodiment, the electronic device may acquire a first determination matrix corresponding to the feature data set of the target description information. Wherein, the elements in the first judgment matrix can be used for characterizing the relative importance degree between two feature data in the feature data set of the target description information.
Step 406, based on each element in the first determination matrix, generating a weight corresponding to each feature data in the feature data set of the target description information.
In this embodiment, the electronic device may generate, by using each element in the first determination matrix, a weight corresponding to each feature data in the feature data set of the target description information.
As an example, the electronic device may generate the weight W corresponding to each feature data by the following formulai：
Figure BDA0001352401290000171
Wherein i is greater than or equal to 1 and less than or equal to a, i is an integer, j is greater than or equal to 1 and less than or equal to a, j is an integer, a is the number of all feature data in the feature data set of the target description information, i.e. the order of the first candidate judgment matrix, k is an element of the first candidate judgment matrix, k is the number of the first candidate judgment matrix, andijdetermining the elements of the ith row and the jth column of the matrix for the first candidate, wherein W is the weight corresponding to the characteristic data, and W isiThe weight corresponding to the ith characteristic data.
With further reference to FIG. 5, a flow 500 of one embodiment of a method of generating weights corresponding to feature values of target description information is illustrated. The process 500 of the method for generating weights corresponding to feature values of target description information includes the following steps:
step 501, obtaining a second candidate judgment matrix corresponding to at least one piece of target description information and a preset second reference parameter.
In this embodiment, the electronic device may acquire a second candidate determination matrix corresponding to at least one piece of target description information and a preset second reference parameter. Wherein, a person skilled in the art may construct the second candidate judgment matrix according to the relative importance degree between any two object description information in the at least one object description information. The electronic device may obtain the second reference parameter by querying the reference parameter table. Typically, the second reference parameter is related to the order of the second candidate decision matrix.
It should be noted that, the method for constructing the second candidate determination matrix may refer to the method for constructing the first candidate determination matrix, and details are not described here.
Step 502, generating a second detection parameter based on the maximum eigenvalue of the second candidate judgment matrix and the rank of the second candidate judgment matrix.
In this embodiment, the electronic device may generate the second detection parameter using the maximum eigenvalue of the second candidate determination matrix and the rank of the second candidate determination matrix. And the maximum eigenvalue of the second candidate judgment matrix is the eigenvalue with the maximum value among all the eigenvalues of the second candidate judgment matrix.
It should be noted that, the generation method of the second detection parameter may refer to the generation method of the first detection parameter, and is not described herein again.
Step 503, determining whether the ratio between the second detected parameter and the second reference parameter is smaller than a second preset threshold.
In this embodiment, the electronic device may calculate a ratio between the second detection parameter and the second reference parameter, and compare the obtained ratio with a second preset threshold (e.g., 0.10); if the value is less than the second preset threshold, go to step 504; if not, go to step 504'.
Step 504, the second candidate judgment matrix is used as the second judgment matrix.
In this embodiment, in the case that the ratio between the second detection parameter and the second reference parameter is smaller than the second preset threshold, the electronic device may regard the second candidate determination matrix as the second determination matrix, and continue to perform step 505.
In step 504', a second prompt message is output to prompt the second candidate judgment matrix to be corrected, and the corrected second candidate judgment matrix is used as the second candidate judgment matrix.
In an embodiment, in a case that a ratio between the second detection parameter and the second reference parameter is not less than a second preset threshold, the electronic device may first output second prompt information to prompt a person skilled in the art to correct the second candidate determination matrix; the corrected second candidate decision matrix is then used as the second candidate decision matrix, and the process returns to execute step 502.
Step 505, a second judgment matrix corresponding to at least one piece of target description information is obtained.
In this embodiment, the electronic device may acquire a second determination matrix corresponding to at least one piece of target description information. Wherein the elements in the second decision matrix may be used to characterize a relative degree of importance between two pieces of object description information in the at least one piece of object description information.
Step 506, based on each element in the second decision matrix, generating a weight corresponding to a feature value of each item label description information in the at least one piece of target description information.
In this embodiment, the electronic device may generate, by using each element in the second determination matrix, a weight corresponding to a feature value of each item of target description information in the at least one piece of target description information.
It should be noted that, the method for generating the weight corresponding to the feature value of the target description information may refer to the method for generating the weight corresponding to the feature data, and details are not repeated here.
With further reference to fig. 6, as an implementation of the method shown in the above figures, the present application provides an embodiment of an information processing apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 6, the information processing apparatus 600 of the present embodiment may include: a target item information acquisition unit 601, a feature data generation unit 602, a target description information feature value generation unit 603, a target item information feature value generation unit 604, and a target item information processing unit 605. The target item information acquiring unit 601 is configured to acquire target item information on a preset website, where the target item information includes at least one piece of target description information describing a target item; a feature data generating unit 602 configured to analyze each item label description information in the at least one piece of target description information, and generate a feature data set of each item label description information; a target description information feature value generation unit 603 configured to generate a feature value of each item label description information based on a feature data set of each item label description information; a target item information feature value generation unit 604 configured to generate a feature value of the target item information based on a feature value of each item label description information; the target item information processing unit 605 is configured to match the feature value of the target item information in a preset feature value interval set, and process the target item information based on the matching result.
In the present embodiment, in the information processing apparatus 600: specific processing of the target item information obtaining unit 601, the feature data generating unit 602, the target description information feature value generating unit 603, the target item information feature value generating unit 604, and the target item information processing unit 605 and technical effects thereof may refer to relevant descriptions of step 201, step 202, step 203, step 204, and step 205 in the corresponding embodiment of fig. 2, which are not described herein again.
In some optional implementations of this embodiment, the target description information feature value generating unit 603 may include: and a target description information feature value generating subunit (not shown in the figure) configured to, for each piece of target description information in at least one piece of target description information, respectively obtain a weight corresponding to each feature data in the feature data set of the target description information, and generate a feature value of the target description information based on the feature data set of the target description information and the weight corresponding to each feature data.
In some optional implementation manners of this embodiment, the target description information feature value generating unit 603 may further include: a first judgment matrix obtaining subunit (not shown in the figure), configured to obtain a first judgment matrix corresponding to the feature data set of the target description information, where an element in the first judgment matrix is used to represent a relative importance degree between two feature data in the feature data set of the target description information; and a feature data weight generating subunit (not shown in the figure) configured to generate, based on each element in the first determination matrix, a weight corresponding to each feature data in the feature data set of the target description information.
In some optional implementation manners of this embodiment, the target description information feature value generating unit 603 may further include: a first candidate judgment matrix obtaining subunit (not shown in the figure) configured to obtain a first candidate judgment matrix corresponding to the feature data set of the target description information and a preset first reference parameter; a first determining step performing subunit (not shown in the figure) configured to perform the following first determining step: generating a first detection parameter based on the maximum eigenvalue of the first candidate judgment matrix and the order of the first candidate judgment matrix, determining whether the ratio of the first detection parameter to the first reference parameter is smaller than a first preset threshold, and if so, taking the first candidate judgment matrix as the first judgment matrix; a first candidate judgment matrix modification subunit (not shown in the figure), configured to, in response to determining that the ratio between the first detection parameter and the first reference parameter is not smaller than the first preset threshold, output first prompt information to prompt modification of the first candidate judgment matrix, and continue to execute the first determining step by using the modified first candidate judgment matrix as the first candidate judgment matrix.
In some optional implementations of this embodiment, the target description information feature value generating subunit may include: a feature data obtaining module (not shown in the figure) configured to obtain a feature data set of description information in reference article information on a preset website, the description information being the same as the type of the target article, wherein the reference article information is the article information of the article which is the same as the type of the target article; a normalization processing module (not shown in the figure) configured to perform normalization processing on the feature data set of the target description information by using the obtained feature data set and the length of the preset standard mapping interval to obtain a normalized feature data set of the target description information; and an object description information feature value generation module (not shown in the figure) configured to generate a feature value of the object description information based on the normalized feature data set of the object description information and the weight corresponding to each feature data.
In some optional implementations of this embodiment, the target item information characteristic value generating unit 604 may include: a target description information feature value weight obtaining subunit (not shown in the figure), configured to obtain weights corresponding to feature values of the item description information, respectively; and a target item information feature value generation subunit (not shown in the figure) configured to generate a feature value of the target item information based on the feature value of each item label description information and the weight corresponding to the feature value of each item label description information.
In some optional implementations of this embodiment, the target item information characteristic value generating unit 604 may further include: a second decision matrix obtaining subunit (not shown in the figure), configured to obtain a second decision matrix corresponding to the at least one piece of target description information, where an element in the second decision matrix is used to represent a relative importance degree between two pieces of target description information in the at least one piece of target description information; and a target description information feature value weight generating subunit (not shown in the figure) configured to generate, based on each element in the second decision matrix, a weight corresponding to the feature value of each item of label description information in the at least one piece of target description information.
In some optional implementations of this embodiment, the target item information characteristic value generating unit 604 may further include: a second candidate judgment matrix obtaining subunit (not shown in the figure) configured to obtain a second candidate judgment matrix corresponding to the at least one piece of target description information and a preset second reference parameter; a second determining step executing subunit (not shown in the figure) configured to execute the following second determining step: generating a second detection parameter based on the maximum eigenvalue of the second candidate judgment matrix and the order of the second candidate judgment matrix, determining whether the ratio of the second detection parameter to the second reference parameter is smaller than a second preset threshold, and if so, taking the second candidate judgment matrix as the second judgment matrix; and a second candidate judgment matrix modification subunit (not shown in the figure), configured to, in response to determining that the ratio between the second detection parameter and the second reference parameter is not smaller than the second preset threshold, output second prompt information to prompt modification of the second candidate judgment matrix, and take the modified second candidate judgment matrix as the second candidate judgment matrix to continue to execute the second determination step.
In some optional implementations of this embodiment, the target item information includes target item information at each preset time point within a preset time period; and the target item information characteristic value generating unit 604 may be further configured to: generating a characteristic value of the target article information at each preset time point based on the characteristic value of each item label description information of the target article information at each preset time point; acquiring a pre-constructed function related to a time point; generating weights corresponding to characteristic values of the target article information at all preset time points based on the functions related to the time points; and generating the characteristic value of the target item information based on the characteristic value of the target item information at each preset time point and the weight corresponding to the characteristic value of the target item information at each preset time point.
In some optional implementations of this embodiment, the target item information processing unit 605 may include: a target item information category determining subunit (not shown in the figures), configured to determine a category of the target item information based on the matching result, where each preset characteristic value interval in the preset characteristic value interval set corresponds to a category of item information; a preset category determining subunit (not shown in the figure) configured to determine whether the category of the target item information is a preset category; and a target article information processing subunit (not shown in the figure), configured to, if the target article information processing subunit is in the preset category, output third prompt information or delete the target article information from the preset website, where the third prompt information is used for prompting to modify the target article information.
Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, according to an embodiment 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 can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application.
It should be noted that the computer readable medium mentioned above in the present application may 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 application, 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 this application, 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 application. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a target article information acquisition unit, a feature data generation unit, a target description information feature value generation unit, a target article information feature value generation unit, and a target article information processing unit. Here, the names of these units do not constitute a limitation to the unit itself in some cases, and for example, the target item information acquisition unit may also be described as a "unit that acquires target item information on a preset website".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the server described in the above embodiments; or may exist separately and not be assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: acquiring target article information on a preset website, wherein the target article information comprises at least one piece of target description information for describing a target article; analyzing each item label description information in at least one piece of target description information respectively to generate a characteristic data set of each item label description information; respectively generating a characteristic value of each item label description information based on the characteristic data set of each item label description information; generating a characteristic value of the target article information based on the characteristic value of the item label description information; and matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result. The embodiment realizes the information processing rich in pertinence.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims (17)

1. An information processing method, characterized in that the method comprises:
acquiring target article information on a preset website, wherein the target article information comprises at least one piece of target description information for describing a target article;
analyzing each item label description information in the at least one piece of target description information respectively to generate a feature data set of each item label description information, wherein the feature data is used for representing one feature of the target description information;
respectively generating a characteristic value of each item label description information based on a characteristic data set of each item label description information, wherein the characteristic value of the target description information is used for representing the overall characteristic of the target description information;
generating a characteristic value of the target article information based on the characteristic value of the item label description information;
matching the characteristic value of the target article information in a preset characteristic value interval set, and processing the target article information based on a matching result;
wherein the processing the target item information based on the matching result includes:
determining the category of the target article information based on a matching result, wherein each preset characteristic value interval in the preset characteristic value interval set corresponds to the category of one article information;
determining whether the category of the target item information is a preset category;
if the target article information is the preset category, outputting third prompt information or deleting the target article information from the preset website, wherein the third prompt information is used for prompting to modify the target article information.
2. The method according to claim 1, wherein the generating a feature value of each item label description information based on the feature data set of each item label description information comprises:
for each piece of target description information in the at least one piece of target description information, respectively obtaining the weight corresponding to each feature data in the feature data set of the target description information, and generating the feature value of the target description information based on the feature data set of the target description information and the weight corresponding to each feature data.
3. The method according to claim 2, further comprising, before the obtaining the weight corresponding to each feature data in the feature data set of the target description information, respectively:
acquiring a first judgment matrix corresponding to the feature data set of the target description information, wherein elements in the first judgment matrix are used for representing the relative importance degree between two feature data in the feature data set of the target description information;
and generating weights corresponding to all the characteristic data in the characteristic data set of the target description information based on all the elements in the first judgment matrix.
4. The method according to claim 3, wherein before the obtaining the first determination matrix corresponding to the feature data set of the target description information, further comprising:
acquiring a first candidate judgment matrix corresponding to the characteristic data set of the target description information and a preset first reference parameter;
performing the following first determining step: generating a first detection parameter based on the maximum eigenvalue of a first candidate judgment matrix and the order of the first candidate judgment matrix, determining whether the ratio of the first detection parameter to the first reference parameter is smaller than a first preset threshold, and if so, taking the first candidate judgment matrix as the first judgment matrix;
and in response to the determination that the ratio of the first detection parameter to the first reference parameter is not less than the first preset threshold, outputting first prompt information to prompt the first candidate judgment matrix to be corrected, taking the corrected first candidate judgment matrix as the first candidate judgment matrix, and continuing to execute the first determination step.
5. The method according to claim 2, wherein the generating feature values of the object description information based on the feature data set of the object description information and the weights corresponding to the respective feature data comprises:
acquiring a feature data set of description information which is the same as the type of the target description information in reference article information on the preset website, wherein the reference article information is article information of an article which is the same as the type of the target article;
standardizing the feature data set of the target description information by using the obtained feature data set and the length of a preset standard mapping interval to obtain a standardized feature data set of the target description information;
the feature value of the target description information is generated based on the normalized feature data set of the target description information and the weight corresponding to each feature data.
6. The method according to claim 1, wherein the generating a feature value of the target item information based on a feature value of each item label description information comprises:
respectively acquiring weights corresponding to the characteristic values of the item label description information;
and generating the characteristic value of the target article information based on the characteristic value of each item label description information and the weight corresponding to the characteristic value of each item label description information.
7. The method according to claim 6, further comprising, before the obtaining the weight corresponding to the feature value of each item label description information, respectively:
acquiring a second judgment matrix corresponding to the at least one piece of target description information, wherein elements in the second judgment matrix are used for representing the relative importance degree between two pieces of target description information in the at least one piece of target description information;
and generating a weight corresponding to the characteristic value of each item label description information in the at least one piece of target description information based on each element in the second judgment matrix.
8. The method according to claim 7, wherein before said obtaining the second decision matrix corresponding to the at least one piece of object description information, further comprising:
acquiring a second candidate judgment matrix corresponding to the at least one piece of target description information and a preset second reference parameter;
performing the following second determining step: generating a second detection parameter based on the maximum eigenvalue of a second candidate judgment matrix and the order of the second candidate judgment matrix, determining whether the ratio between the second detection parameter and the second reference parameter is smaller than a second preset threshold, and if so, taking the second candidate judgment matrix as the second judgment matrix;
and in response to determining that the ratio of the second detection parameter to the second reference parameter is not less than the second preset threshold, outputting second prompt information to prompt correction of the second candidate judgment matrix, taking the corrected second candidate judgment matrix as the second candidate judgment matrix, and continuing to execute the second determining step.
9. The method according to claim 1, wherein the target item information includes target item information for respective preset time points within a preset time period; and
generating the characteristic value of the target item information based on the characteristic value of the description information of each item label, including:
generating a characteristic value of the target article information at each preset time point based on the characteristic value of each item label description information of the target article information at each preset time point;
acquiring a pre-constructed function related to a time point;
generating weights corresponding to characteristic values of the target article information at all preset time points based on the functions related to the time points;
and generating the characteristic value of the target item information based on the characteristic value of the target item information at each preset time point and the weight corresponding to the characteristic value of the target item information at each preset time point.
10. An information processing apparatus characterized in that the apparatus comprises:
the system comprises a target article information acquisition unit, a target article information acquisition unit and a target article information acquisition unit, wherein the target article information acquisition unit is configured to acquire target article information on a preset website, and the target article information comprises at least one piece of target description information for describing a target article;
the characteristic data generating unit is configured to analyze each item label description information in the at least one piece of target description information respectively and generate a characteristic data set of each item label description information, wherein the characteristic data is used for representing one characteristic of the target description information;
the target description information characteristic value generating unit is configured to generate a characteristic value of each item label description information based on a characteristic data set of each item label description information, wherein the characteristic value of the target description information is used for representing the overall characteristic of the target description information;
the target article information characteristic value generating unit is configured to generate a characteristic value of the target article information based on the characteristic value of each item label description information;
the target article information processing unit is configured to match the characteristic value of the target article information in a preset characteristic value interval set and process the target article information based on a matching result;
wherein the target item information processing unit includes:
the target article information category determining subunit is configured to determine a category of the target article information based on a matching result, where each preset characteristic value interval in the preset characteristic value interval set corresponds to a category of article information;
a preset category determination subunit configured to determine whether the category of the target item information is a preset category;
and the target article information processing subunit is configured to, if the target article information processing subunit is in the preset category, output third prompt information or delete the target article information from the preset website, where the third prompt information is used to prompt modification of the target article information.
11. The apparatus according to claim 10, wherein the target description information feature value generation unit includes:
and the target description information characteristic value generating subunit is configured to, for each piece of target description information in the at least one piece of target description information, respectively obtain a weight corresponding to each piece of characteristic data in the characteristic data set of the target description information, and generate a characteristic value of the target description information based on the characteristic data set of the target description information and the weight corresponding to each piece of characteristic data.
12. The apparatus according to claim 11, wherein the target description information feature value generation unit further includes:
a first judgment matrix obtaining subunit, configured to obtain a first judgment matrix corresponding to the feature data set of the target description information, where an element in the first judgment matrix is used to represent a relative importance degree between two feature data in the feature data set of the target description information;
and the characteristic data weight generating subunit is configured to generate a weight corresponding to each characteristic data in the characteristic data set of the target description information based on each element in the first judgment matrix.
13. The apparatus according to claim 12, wherein the target description information feature value generation unit further includes:
a first candidate judgment matrix obtaining subunit configured to obtain a first candidate judgment matrix corresponding to the feature data set of the target description information and a preset first reference parameter;
a first determination step execution subunit configured to execute the following first determination steps: generating a first detection parameter based on the maximum eigenvalue of a first candidate judgment matrix and the order of the first candidate judgment matrix, determining whether the ratio of the first detection parameter to the first reference parameter is smaller than a first preset threshold, and if so, taking the first candidate judgment matrix as the first judgment matrix;
a first candidate judgment matrix modification subunit configured to, in response to determining that the ratio between the first detection parameter and the first reference parameter is not smaller than the first preset threshold, output first prompt information to prompt modification of the first candidate judgment matrix, and continue to execute the first determining step with the modified first candidate judgment matrix as the first candidate judgment matrix.
14. The apparatus of claim 13, wherein the target description information feature value generation subunit comprises:
a feature data acquisition module configured to acquire a feature data set of description information in reference article information on the preset website, the description information being of the same type as the target description information, wherein the reference article information is article information of an article of the same type as the target article;
the standardization processing module is configured to utilize the acquired feature data set and the length of a preset standard mapping interval to standardize the feature data set of the target description information to obtain a standardized feature data set of the target description information;
and the target description information characteristic value generation module is configured to generate a characteristic value of the target description information based on the normalized characteristic data set of the target description information and the weight corresponding to each characteristic data.
15. The apparatus according to claim 10, wherein the target item information includes target item information at each preset time point within a preset time period; and
the target item information characteristic value generation unit is further configured to:
generating a characteristic value of the target article information at each preset time point based on the characteristic value of each item label description information of the target article information at each preset time point;
acquiring a pre-constructed function related to a time point;
generating weights corresponding to characteristic values of the target article information at all preset time points based on the functions related to the time points;
and generating the characteristic value of the target item information based on the characteristic value of the target item information at each preset time point and the weight corresponding to the characteristic value of the target item information at each preset time point.
16. A server, characterized in that the server comprises:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-9.
17. A computer-readable storage 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 1-9.
CN201710581430.0A 2017-07-17 2017-07-17 Information processing method and device Active CN109272367B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710581430.0A CN109272367B (en) 2017-07-17 2017-07-17 Information processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710581430.0A CN109272367B (en) 2017-07-17 2017-07-17 Information processing method and device

Publications (2)

Publication Number Publication Date
CN109272367A CN109272367A (en) 2019-01-25
CN109272367B true CN109272367B (en) 2021-11-09

Family

ID=65147786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710581430.0A Active CN109272367B (en) 2017-07-17 2017-07-17 Information processing method and device

Country Status (1)

Country Link
CN (1) CN109272367B (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104281956B (en) * 2014-10-27 2018-09-07 南京信息工程大学 The dynamic recommendation method for adapting to user interest variation based on temporal information
KR101596353B1 (en) * 2015-03-16 2016-02-22 주식회사 한국무역정보통신 Device and method for determining HS code
CN106096042A (en) * 2016-06-28 2016-11-09 乐视控股（北京）有限公司 Data message sorting technique and system

Also Published As

Publication number Publication date
CN109272367A (en) 2019-01-25

Similar Documents

Publication Publication Date Title
CN107506495B (en) Information pushing method and device
WO2019114391A1 (en) Information output method and apparatus
CN108520470B (en) Method and apparatus for generating user attribute information
CN109063190B (en) Method and device for processing data sequence
CN108388563B (en) Information output method and device
CN106897905B (en) Method and device for pushing information and electronic equipment
CN110555451A (en) information identification method and device
CN109711917B (en) Information pushing method and device
CN108933695B (en) Method and apparatus for processing information
CN110689395B (en) Method and device for pushing information
CN109685537B (en) User behavior analysis method, device, medium and electronic equipment
US20170142119A1 (en) Method for creating group user profile, electronic device, and non-transitory computer-readable storage medium
CN113743971A (en) Data processing method and device
WO2022156589A1 (en) Method and device for determining live broadcast click rate
CN110610365A (en) Method and device for identifying transaction request
CN108959289B (en) Website category acquisition method and device
CN109272367B (en) Information processing method and device
CN112308648A (en) Information processing method and device
CN109344327B (en) Method and apparatus for generating information
CN107357847B (en) Data processing method and device
CN110163701B (en) Method and device for pushing information
CN113869904B (en) Suspicious data identification method, device, electronic equipment, medium and computer program
CN111723274B (en) Method and device for processing information
CN113742564A (en) Target resource pushing method and device
KR20230009437A (en) User search category predictor

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