CN112579663A - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN112579663A CN112579663A CN201910942436.5A CN201910942436A CN112579663A CN 112579663 A CN112579663 A CN 112579663A CN 201910942436 A CN201910942436 A CN 201910942436A CN 112579663 A CN112579663 A CN 112579663A
- Authority
- CN
- China
- Prior art keywords
- label
- weight value
- user
- preset
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The invention discloses an information processing method and device, wherein the method comprises the following steps: determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first label and the total number of times that the user triggers the preset object provided with the preset label; and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user. The method and the system can accurately mine the customers with marketing value.
Description
Technical Field
The present invention relates to the field of electronic information, and in particular, to an information processing method and apparatus.
Background
Mining the customers with marketing value from the customers is an important step in customer marketing. For example, for any one wechat public number, the wechat user concerned about the wechat public number is the wechat fan of the wechat public number, and the wechat fan interested in a certain product can be mined out from the wechat fans of the wechat public number as the marketing value user of the product.
The accuracy of mining the customers with marketing value from the customers directly influences the marketing result. Wherein, the accuracy of mining the customers with marketing value from the customers refers to the interest degree of the customers mined from the customers in the preset products.
Therefore, a method of accurately mining marketing-valued customers from customers is required.
Disclosure of Invention
In view of the above, the present invention provides an information processing method and apparatus that overcomes or at least partially solves the above problems.
The application provides an information processing method, which comprises the following steps:
determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; the initial weight value is related to a triggering mode of triggering the preset object by the user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels;
updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the weight value of the first label represents the interest degree of the user in the product indicated by the first label in historical time; the first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with the tag;
and determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
Optionally, after determining an initial weight value of a first tag when it is detected that a user triggers a preset object provided with the first tag, the method further includes:
and under the condition that the corresponding relation among the user, the first label and the weight value of the first label does not exist, generating the corresponding relation among the user, the first label and the weight value of the first label, wherein the weight value of the first label in the generated corresponding relation is the initial weight value of the first label.
Optionally, the updating the weight value of the first tag according to at least the initial weight value, the weight value of the first tag, the first ratio, and the inverse document frequency index includes:
weighting and calculating the initial weight value and the weight value of the first label to obtain a weighted result value;
multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value;
multiplying the weighted result value by the multiplied result value to obtain a calculation result;
and updating the weight value of the first label by adopting the calculation result.
Optionally, in a case that there is no correspondence between the user, the first tag, and the weight value of the first tag, after generating the correspondence between the user, the first tag, and the weight value of the first tag, the method further includes:
storing the corresponding relation in a preset file;
the updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index specifically comprises:
updating the weight value of the first label in the preset file at least according to the initial weight value, the weight value of the first label in the preset file, a first ratio and an inverse document frequency index;
the method comprises the following steps of determining users meeting preset conditions as marketing users according to the weight value of each label of each user, specifically:
and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user in the preset file.
Optionally, before determining, according to the weight value of each label of each user in the preset file, that the user meeting the preset condition is the marketing user, the method further includes:
updating the weight value of each label of each user in the preset file according to a preset decay period value every other preset time;
optionally, updating the weight value of any one of the tags of any one of the users in the preset file according to the decay period value includes:
calculating the attenuation coefficient value according to the decay period value and a preset first formula;
calculating to obtain a result value according to the preset time length, the attenuation coefficient value, the weight value of the label in the preset file and a preset second formula;
and updating the weight value of the label in the preset file by adopting the result value.
The present application also provides an information processing apparatus including:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; the initial weight value is related to a triggering mode of triggering the preset object by the user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels;
the updating module is used for updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the weight value of the first label represents the interest degree of the user in the product indicated by the first label in historical time; the first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with the tag;
and the second determining module is used for determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
Optionally, the method further includes:
a generating module, configured to generate a correspondence relationship among the weight values of the user, the first tag, and the first tag when there is no correspondence relationship among the weight values of the user, the first tag, and the first tag, where the weight value of the first tag in the generated correspondence relationship is an initial weight value of the first tag.
Optionally, the updating module is configured to update the weight value of the first tag according to at least the initial weight value, the weight value of the first tag, the first ratio, and the inverse document frequency index, and includes:
the updating module is specifically configured to perform weighting and calculation on the initial weight value and the weight value of the first tag to obtain a weighted result value;
multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value;
multiplying the weighted result value by the multiplied result value to obtain a calculation result;
and updating the weight value of the first label by adopting the calculation result.
Optionally, the method further includes:
the storage module is used for storing the corresponding relation in a preset file;
the updating module is specifically configured to update the weight value of the first tag in the preset file at least according to the initial weight value, the weight value of the first tag in the preset file, a first ratio, and an inverse document frequency index;
the second determining module is specifically configured to determine, according to the weight value of each label of each user in the preset file, that a user meeting a preset condition is a marketing user.
Optionally, the method further includes:
and the decay updating module is used for updating the weighted value of each label of each user in the preset file according to a preset decay period value at preset time intervals before the second determining module determines the user meeting the preset condition as the marketing user according to the weighted value of each label of each user in the preset file.
Optionally, the decay updating module is configured to update the weight value of any one of the tags of any one of the users in the preset file according to a preset decay period value at intervals of a preset duration, and includes:
the decay updating module is specifically used for calculating the decay coefficient value according to the decay period value and a preset first formula;
calculating to obtain a result value according to the preset time length, the attenuation coefficient value, the weight value of the label in the preset file and a preset second formula;
and updating the weight value of the label in the preset file by adopting the result value.
The present application also provides a storage medium including a stored program, wherein the program executes any one of the above-described information processing methods.
The application also provides a device, which comprises at least one processor, at least one memory connected with the processor, and a bus; the processor and the memory complete mutual communication through the bus; the processor is used for calling the program instructions in the memory so as to execute any one of the information processing methods.
By means of the technical scheme, in the information processing method provided by the invention, under the condition that a user is detected to trigger a preset object provided with a first label, an initial weight value of the first label is determined; and updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index, and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user.
In one aspect, the weight value of the first label characterizes a level of interest of the user in the product indicated by the first label over a historical time.
On the other hand, the initial weight value of the first label is related to a triggering mode of triggering the preset object by the user, and the triggering mode represents the interest degree of the user in the product indicated by the first label. Therefore, the initial weight value of the first tag represents the current level of interest of the user in the product indicated by the first tag in the current trigger mode.
The first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with the preset tag, and therefore the first ratio represents the degree of interest of the user in the product indicated by the first tag from the perspective of all tags concerned by the user.
The inverse document frequency index represents the attention degree of the product indicated by the first label from the perspective of all users who trigger the preset object provided with the preset label.
In summary, the weight value of the first tag is updated at least according to the initial weight value, the weight value of the first tag, the first ratio and the inverse document frequency index, so that the weight value of the first tag can comprehensively reflect the interest degree of the user in the product indicated by the first tag from multiple angles, the interest degree of the user in the product indicated by the first tag can be objectively reflected by the weight value of the first tag, and then the user meeting the preset condition is determined to be the marketing user according to the weight value of each tag of each user, so that the accuracy of the determined marketing user is higher, and then the related information of the product indicated by the tag is pushed to the user, and the required marketing result can be realized.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating an information processing method provided in an embodiment of the present application;
FIG. 2 is a flow chart illustrating a further information processing method provided by an embodiment of the present application;
fig. 3 is a schematic structural diagram illustrating an information processing apparatus according to an embodiment of the present application;
fig. 4 shows a schematic structural diagram of an apparatus provided in an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the application takes the WeChat public number as an example, and introduces a process for determining WeChat vermicelli with marketing value from the WeChat vermicelli of the WeChat public number. Of course, the information processing method provided by the embodiment of the application is not only suitable for the scenes of screening the WeChat fans with marketing value from the WeChat fans, but also suitable for other scenes.
In the embodiment of the present application, the micro page, the purchase link, and the like pushed in the wechat public number are referred to as preset objects, and of course, in practice, the preset objects may be other contents besides the micro page and the purchase link, and the embodiment does not limit the specific contents of the preset objects.
In the embodiment of the application, the labels are determined by the products pushed by the preset object, and the labels corresponding to different products are different. For example, in a WeChat article, a vehicle of a model A5 is described, and a worker previously sets a label a of the vehicle of the model A5, and the worker may add the label a to the WeChat article. For example, the transaction interface linked by one purchase link is information on a B5 model car, the staff member previously sets the label B of the B5 model car, and the staff member may add the label B to the purchase link. Therefore, the label added to the preset object is determined according to the product related to the preset object, and the labels corresponding to different products are different. In the embodiment of the present application, the label set in advance by the worker according to the product to be analyzed is referred to as a preset label.
The purpose of the embodiment of the application is as follows: counting the triggering condition of the WeChat vermicelli on the preset object provided with any preset label to obtain the weight value of the label of the WeChat vermicelli, and obtaining the interest degree of the WeChat vermicelli on the product indicated by the label, and further determining the WeChat vermicelli meeting the preset condition from the WeChat vermicelli as a user with marketing value according to the interest degree of the WeChat vermicelli on the product indicated by the preset label. Specifically, a process of determining a user having a marketing value from WeChat fans is as follows as an information processing method shown in FIG. 1.
Fig. 1 is an information processing method provided in an embodiment of the present application, including the following steps:
and S101, collecting network data.
In this step, the data generated by the WeChat fans in the process of using the WeChat is collected and is called network data.
Specifically, the implementation process of collecting network data is the prior art, and is not described herein again.
And S102, carrying out data cleaning on the collected network data to obtain cleaned network data.
The purpose of data cleaning of the collected network data in the step is to filter impurity data in the collected network data. Specifically, the specific implementation process of data cleansing is the prior art, and is not described herein again.
S103, judging whether target network data exists in the cleaned network data, if so, executing S104, and if not, executing S101.
In this step, the target network data is data representing that the user triggers a preset object provided with the first tag.
S104, determining the initial weight value of the first label from the preset corresponding relation between the triggering mode and the initial weight value of the label.
In this embodiment, the first tag is any one of preset tags.
In this embodiment, the triggering manner may include: browsing, ordering, rating, collecting, searching, etc. Taking the preset object as the micro page as an example, the user can search the micro page, browse the micro page, and collect the micro page.
The triggering modes of the user on the preset object provided with any label are different, which indicates that the user has different interest degrees in the product indicated by the label. Therefore, in this embodiment, an initial weight value is set in advance for each trigger mode of any tag, where the higher the trigger mode representing the higher level of interest of the user in the product indicated by the tag is, the larger the initial weight value set for the tag is. For example, the initial weight value of the tab a is 30 when the micro page provided with the tab a is browsed, and the initial weight value of the tab a is 40 when the micro page provided with the tab a is collected.
In this step, when it is detected that a user triggers a preset object provided with a first tag, an initial weight value of the first tag in the trigger mode is determined from a preset corresponding relationship between the trigger mode and the initial weight value of the tag.
S105, judging whether the corresponding relation among the user, the first label and the weight value of the first label exists in the preset file, if not, executing S106, and if so, executing S107.
In this embodiment, the preset file is used to record the user, the tag in the preset object triggered by the user, and the weight value of the tag, that is, the preset file stores the correspondence between the user, the tag, and the weight value of the tag. Specifically, the preset file may be a preset table, and certainly, in practice, the preset file may also be a file in other forms, and the embodiment does not limit the specific content of the preset file.
The purpose of this step is: and judging whether the user is a preset object with a first label for the first time, if so, executing S106, and if not, executing S107.
S106, generating a corresponding relation among the user, the first label and the weight value of the first label in a preset file.
When the corresponding relation between the user and the first label does not exist in the preset file, the fact that the user is the preset object provided with the first label is triggered for the first time is indicated, and therefore the corresponding relation among the user, the first label and the weight value of the first label is generated in the preset file. In the correspondence generated in this step, the weight value of the first label is the initial weight value of the first label.
And S107, updating the weight value of the first label of the user in a preset file.
And when the corresponding relation between the user and the first label exists in the preset file, the user is indicated not to trigger the preset object provided with the first label for the first time. In this step, the weight value of the first tag of the user in the preset file needs to be replaced according to the weight value of the first tag (the weight value of the first tag) currently existing in the preset file and the initial weight value of the first tag obtained by the current trigger of the user.
Specifically, the formula for updating the weight value of the first tag of the user is as shown in the following formula (1):
wherein a represents the updated weight value of the first label of the user, n has a value of 2, k represents a variable having values of 1 and 2, and b1A weight value of the first label representing the user in a preset file, b2And the initial weight value of the first label obtained by the current trigger of the user is represented. Phi denotesThe degree of decay is a fixed value, and c represents the attention value of the tag.
Specifically, the attention value of the first tag of the user is calculated as shown in the following formula (2):
TF-IDF(P,T)＝TF(P,T)×IDF(P,T) (2)
in the formula, TF-IDF (P, T) represents the attention degree value of the first tag of the user, TF (P, T) represents the individual purity of the first tag of the user, and for the convenience of description, is referred to as a first ratio, and IDF (P, T) is an inverse document frequency index, and represents the overall scarcity of the first tag of the user. Specifically, the formula for calculating TF (P, T) is shown in the following formula (3), and the formula for calculating IDF (P, T) is shown in the following formula (4).
Wherein W (P, T) represents the total number of times the user triggers the preset object provided with the first tag. T isiDenotes a preset tag, where i ═ 1,2,3.. M denotes the total number of preset tags. W (P, T)i) Indicates that the user has triggered the setting of the tag TiThe number of times of the preset object is set,
indicating the total number of times the user triggers a preset object provided with a preset tag.
For example, the preset tags include: label T1Label T2And a label T3Wherein the user has triggered the setting of the tag T1The number of times of the preset object is 3, the user has triggered the setting of the tag T2Is 0 (i.e., the user has not triggered the set tag T)2Preset object of) the user has triggered the setting of the tag T3The number of times of the preset object of (1) is 4. Then M takes the value 3, W (P, T)1) Is 3, W (P, T)2) Is 0, W (P, T)3) The value of (a) is 4,
is W (P, T)1)、W(P,T2) And W (P, T)3) The sum of the amounts is 7.
In the formula, Σ W (P)i,Tj) Representing the total number of users who triggered the preset object provided with the preset tag. Sigma W (P)iAnd T) represents the total number of users who triggered the preset object provided with the first tag.
For example, the preset tags include: label T1Label T2And a label T3Assume that the first tag is tag T1，Trigger over-set with tag T1The user of the preset object is a user P1、User P2And user P3Triggered over setting with a tag T2The user of the preset object is a user P1User P2And user P4Triggered over setting with a tag T3The user of the preset object is a user P1User P2Then Σ W (P)i,Tj) Is 4, Σ W (P)iAnd T) has a value of 3.
Wherein, the acquisition mode of W (P, T): the total times that the user triggers the preset object provided with the first label can be counted under the condition that the user triggers the preset object provided with the first label each time, and the counted total times are stored in a preset file.
∑W(P,Ti) The acquisition mode of (1): and adding values of W (P, T) corresponding to each preset label triggered by the user in the preset file.
∑W(Pi,Ti) The acquisition mode of (1): and counting the total number of the users recorded in the preset file.
∑W(PiAnd T) acquisition mode: and counting the total number of users forming the corresponding relation with the first label in the preset file.
For example, A user 2Triggering the preset object provided with the label a once to obtain that the initial weight value of the label a is 20, and generating a corresponding relation among the user A, the label a and the weight value of 20 in a preset file. Triggering the preset object provided with the label a for the second time by the user A to obtain that the initial weight value of the label a is 30, wherein in the step b1Has a value of 20, b2Is 30, the calculation is performed according to the above formula (2), and if the calculated weight value is 15, the weight value of the label a of the user in the preset file is replaced from 20 to 15. A, the user triggers the preset object provided with the label a for the third time to obtain that the initial weight value of the label a is 40, and in the step, b1Has a value of 15, b2Is 40, the calculation is performed according to the above formula (2), and if the weight value obtained by the calculation is 18, the weight value of the label a of the user in the preset file is replaced from 15 to 18.
It can be seen from formula (2) that the process of updating the weight value of the first tag of the user in the preset file includes: weighting and calculating the initial weight value of the first label and the weight value of the first label to obtain a weighted result value; multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value; multiplying the weighted result value by the multiplied result value to obtain a calculation result; and updating the weight value of the first label by adopting the calculation result.
In this embodiment, the preset file obtains the corresponding relationship between the tags of the multiple users, but the interest level of the user in the product indicated by the tag, which is represented by the weight value of any tag of any user in the preset file, decreases with the passage of time. For example, if the weight value of the tag a of the user a is 30 after 12 o 'clock in 2 month and 3, only the interest level of the user a in the tag a at 12 o' clock in 2 month and 3 can be represented as the interest level represented by the weight value 30. Assuming that the user does not trigger the preset object provided with the tag a from 12 o 'clock at 2 month 3 to 12 o' clock at 2 month 4, the weight value of the tag a of the user at 12 o 'clock at 2 month 4 is still 30, but the interest level represented by the weight value 30 cannot represent the interest level of the user at 12 o' clock at 2 month 4 on the product indicated by the tag a.
Therefore, in order to enable the weighted value of each label of each user in the preset file to objectively reflect the interest degree of the user in the product indicated by the label at the current moment, in the embodiment, a decay period is introduced. According to the decay period, the weight value of each label of each user in the preset file is updated (namely, the weight value of each user in the preset file is attenuated along with the time), so that the interest degree of the user in the product indicated by each label at the current moment can be objectively reflected by the weight value of each label of each user in the preset file.
Specifically, a step of updating the weight value of each tag of each user in the preset file by using a preset decay period value is performed as shown in the following step S108.
And S108, updating the weighted value of each label of each user in the preset file according to a preset decay period value every other preset time.
Specifically, the formula used for updating the weight value of any one of the tags of any one of the users is shown in the following formula (5).
The weight of the current period is the weight of the last period × e(-attenuation factor x interval time) (5)
The previous-stage weight represents a weight value of the label of the user in a preset file before the step is executed, the present-stage weight represents a weight value of the label in a preset file obtained after the step is executed, the interval time is preset duration, and a calculation formula of the attenuation coefficient is shown in a formula (6) below.
Wherein the decay period is a predetermined decay period value.
In this embodiment, the decay period value may be 7 days, and the preset time period may be 1 day. In practice, of course, the values of the decay period value and the preset duration may also be other values, and the values of the decay period value and the preset duration are not limited in this embodiment.
As can be seen from S108, in this embodiment, the process of updating the weighted values of the tags of each user in the preset file according to the preset decay period value includes: calculating an attenuation coefficient value according to a preset decay period value and a preset first formula; and calculating to obtain a result value according to the preset time length, the attenuation coefficient value, the weight value of the label in the preset file and a preset second formula, and updating the weight value of the label in the preset file by adopting the result value. The preset first formula is the formula (6), and the preset second formula is the formula (5).
S109, according to the weight value of each label of each user in the preset file, determining the label meeting the preset condition as a target label.
In this step, the preset condition may be that the weight value is greater than a preset threshold. Namely, the label with the weight value larger than the preset threshold value is determined as the target label from the preset file.
And S110, taking the user corresponding to the target label in the preset file as a marketing user.
Because the target label is a label with a weight value larger than a preset threshold, the user corresponding to the target label represents: and the user who is interested in the product indicated by the target label to a degree greater than the preset interest degree. Therefore, in the step, the user corresponding to the target label in the preset file is used as the marketing user, and the required marketing effect can be achieved.
The purpose of the above S109 to S110 is: and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user in the preset file.
And S111, under the condition that a preset instruction is received, pushing information of the product indicated by the corresponding label to the marketing user.
In this step, the corresponding tag of any marketing user is the tag corresponding to the marketing user in the target tags.
In this embodiment, network data is collected, data cleaning is performed on the collected network data, and data processing is performed on the cleaned data. Because the collected network data is objective data and the data obtained by cleaning the collected network data is also objective data, the embodiment performs data processing on the objective data to obtain marketing users, and pushes the information of products indicated by corresponding labels to the marketing users after obtaining the marketing users, so that the accuracy of marketing to WeChat fans is improved.
The embodiment has the following beneficial effects:
has the beneficial effects of,
In one aspect, the weight value of the first label characterizes a level of interest of the user in the product indicated by the first label over a historical time.
On the other hand, the initial weight value of the first label is related to a triggering mode of triggering the preset object by the user, and the triggering mode represents the interest degree of the user in the product indicated by the first label. Therefore, the initial weight value of the first tag represents the current level of interest of the user in the product indicated by the first tag in the current trigger mode.
The first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with any tag, and therefore, the first ratio represents the degree of interest of the user in the product indicated by the first tag from the perspective of all tags concerned by the user.
The inverse document frequency index is a value calculated according to a preset formula and is a ratio of the total number of users who trigger the preset object provided with the tag to the total number of users who trigger the preset object provided with the first tag, and therefore the inverse document frequency index reflects the attention degree of the product indicated by the first tag from the perspective of all users who trigger the preset object provided with the tag.
In summary, the weight value of the first tag is updated at least according to the initial weight value, the weight value of the first tag, the first ratio and the inverse document frequency index, so that the weight value of the first tag can comprehensively reflect the interest degree of the user in the product indicated by the first tag from multiple angles, the interest degree of the user in the product indicated by the first tag can be objectively reflected by the weight value of the first tag, and then the user meeting the preset condition is determined as the marketing user according to the weight value of each tag of each user, so that the accuracy of the determined marketing user is high, and further, related information of the product indicated by the tag is pushed to the marketing user, and a required marketing result can be realized.
Has the beneficial effects of,
In this embodiment, every preset time length, the weight value of each tag of each user in the preset file is updated according to a preset decay period value, so that the weight value of each tag of each user in the preset file is obtained, the interest degree of the user in the product indicated by the tag at the current moment can be objectively reflected by the weight value of each tag of each user in the preset file, and further, the accuracy of the weight value of each tag of each user in the preset file is higher. Therefore, according to the weight value of each label of each user in the preset file, the user meeting the preset condition is determined to be the marketing user, and the accuracy of the determined marketing user is further improved.
Fig. 2 is a further information processing method provided in the embodiment of the present application, including the following steps:
s201, under the condition that a user is detected to trigger a preset object provided with a first label, determining an initial weight value of the first label.
The specific implementation manner of this step may refer to S104, which is not described herein again.
S202, updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index.
For a specific implementation manner of this step, reference may be made to S105 and S107, which are not described herein again.
And S203, determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
For a specific implementation manner of this step, reference may be made to S109 and S110, which is not described herein again.
Fig. 3 is an information processing apparatus according to an embodiment of the present application, including: a first determination module 301, an update module 302, and a second determination module 303.
The first determining module 301 is configured to determine an initial weight value of a first tag when it is detected that a user triggers a preset object provided with the first tag; the initial weight value is related to a triggering mode of triggering a preset object by a user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels.
An updating module 302, configured to update the weight value of the first tag at least according to the initial weight value, the weight value of the first tag, the first ratio, and the inverse document frequency index; the weighted value of the first label represents the interest degree of the user in the product indicated by the first label in the historical time; the first ratio represents a ratio between the total times of triggering the preset object provided with the first label by the user and the total times of triggering the preset object provided with the label by the user; the second determining module 303 is configured to determine, according to the weight value of each label of each user, that the user meeting the preset condition is a marketing user.
Optionally, the method further includes: the generating module 304 is configured to generate a corresponding relationship among the user, the first tag, and the weight value of the first tag under the condition that there is no corresponding relationship among the user, the first tag, and the weight value of the first tag, where the weight value of the first tag in the generated corresponding relationship is an initial weight value of the first tag.
Optionally, the updating module 302 is configured to update the weight value of the first tag according to at least the initial weight value, the weight value of the first tag, the first ratio, and the inverse document frequency index, and includes: an updating module 302, configured to perform weighting and calculation on the initial weight value and the weight value of the first tag to obtain a weighted result value; multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value; multiplying the weighted result value by the multiplied result value to obtain a calculation result; and updating the weight value of the first label by adopting the calculation result.
Optionally, the method further includes: a saving module 305, configured to save the corresponding relationship in a preset file;
an updating module 302, configured to update a weight value of a first tag in a preset file according to at least the initial weight value, the weight value of the first tag in the preset file, the first ratio, and an inverse document frequency index; the second determining module 303 is specifically configured to determine, according to the weight value of each label of each user in the preset file, that the user meeting the preset condition is a marketing user.
Optionally, the method further includes: the decay updating module 306 is configured to update the weight value of each tag of each user in the preset file according to a preset decay period value at preset intervals before the second determining module determines that the user meeting the preset condition is the marketing user according to the weight value of each tag of each user.
Optionally, the decay updating module 306 is configured to update the weighted value of any tag of any user in the preset file according to a preset decay period value at intervals of a preset duration, where the updating module includes: a decay update module 306, specifically configured to calculate an attenuation coefficient value according to the decay period value and a preset first formula; calculating to obtain a result value according to a preset time length, an attenuation coefficient value, a weight value of the label in a preset file and a preset second formula; and updating the weight value of the label in the preset file by using the result value.
The information processing device comprises a processor and a memory, wherein the first determining module, the updating module, the second determining module and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and the information processing method is realized by adjusting kernel parameters.
An embodiment of the present invention provides a storage medium having a program stored thereon, the program implementing the information processing method when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the information processing method is executed when the program runs.
An embodiment of the present invention provides an apparatus, as shown in fig. 4, the apparatus includes at least one processor, and at least one memory and a bus connected to the processor; the processor and the memory complete mutual communication through a bus; the processor is used for calling the program instructions in the memory so as to execute the information processing method. The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; the initial weight value is related to a triggering mode of triggering the preset object by the user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels;
updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the weight value of the first label represents the interest degree of the user in the product indicated by the first label in historical time; the first ratio represents a ratio between the total number of times that the user triggers a preset object provided with the first tag and the total number of times that the user triggers a preset object provided with any one tag;
and determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
Optionally, after determining an initial weight value of a first tag when it is detected that a user triggers a preset object provided with the first tag, the method further includes:
and under the condition that the corresponding relation among the user, the first label and the weight value of the first label does not exist, generating the corresponding relation among the user, the first label and the weight value of the first label, wherein the weight value of the first label in the generated corresponding relation is the initial weight value of the first label.
Optionally, the updating the weight value of the first tag according to at least the initial weight value, the weight value of the first tag, the first ratio, and the inverse document frequency index includes:
weighting and calculating the initial weight value and the weight value of the first label to obtain a weighted result value;
multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value;
multiplying the weighted result value by the multiplied result value to obtain a calculation result;
and updating the weight value of the first label by adopting the calculation result.
Optionally, in a case that there is no correspondence between the user, the first tag, and the weight value of the first tag, after generating the correspondence between the user, the first tag, and the weight value of the first tag, the method further includes:
storing the corresponding relation in a preset file;
the updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index specifically comprises:
updating the weight value of the first label in the preset file at least according to the initial weight value, the weight value of the first label in the preset file, a first ratio and an inverse document frequency index;
the method comprises the following steps of determining users meeting preset conditions as marketing users according to the weight value of each label of each user, specifically:
and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user in the preset file.
Optionally, before determining, according to the weight value of each label of each user, that the user meeting the preset condition is a marketing user, the method further includes:
and updating the weight value of each label of each user in the preset file according to a preset decay period value every other preset time.
Optionally, updating the weight value of any tag of any user in the preset file according to the decay period value to obtain the weight value of the tag, including:
calculating the attenuation coefficient value according to the decay period value and a preset first formula;
calculating to obtain a result value according to the preset time length, the attenuation coefficient value, the weight value of the label in the preset file and a preset second formula;
and updating the weight value of the label in the preset file by adopting the result value.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. An information processing method characterized by comprising:
determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; the initial weight value is related to a triggering mode of triggering the preset object by the user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels;
updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the weight value of the first label represents the interest degree of the user in the product indicated by the first label in historical time; the first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with the tag;
and determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
2. The method according to claim 1, wherein after determining an initial weight value of a first tag in a case that a user is detected to trigger a preset object provided with the first tag, the method further comprises:
and under the condition that the corresponding relation among the user, the first label and the weight value of the first label does not exist, generating the corresponding relation among the user, the first label and the weight value of the first label, wherein the weight value of the first label in the generated corresponding relation is the initial weight value of the first label.
3. The method of claim 1 or 2, wherein the updating the weight value of the first tag according to at least the initial weight value, the weight value of the first tag, a first ratio, and an inverse document frequency index comprises:
weighting and calculating the initial weight value and the weight value of the first label to obtain a weighted result value;
multiplying the first ratio by the inverse document frequency index to obtain a multiplication result value;
multiplying the weighted result value by the multiplied result value to obtain a calculation result;
and updating the weight value of the first label by adopting the calculation result.
4. The method of claim 2, wherein after generating the correspondence among the weight values of the user, the first tag, and the first tag in the absence of the correspondence among the weight values of the user, the first tag, and the first tag, the method further comprises:
storing the corresponding relation in a preset file;
the updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index specifically comprises:
updating the weight value of the first label in the preset file at least according to the initial weight value, the weight value of the first label in the preset file, a first ratio and an inverse document frequency index;
the method comprises the following steps of determining users meeting preset conditions as marketing users according to the weight value of each label of each user, specifically:
and determining the users meeting the preset conditions as marketing users according to the weight value of each label of each user in the preset file.
5. The method according to claim 4, wherein before determining the users meeting the preset condition as marketing users according to the weighted value of each label of each user in the preset file, the method further comprises:
and updating the weight value of each label of each user in the preset file according to a preset decay period value every other preset time.
6. The method of claim 5, wherein updating the weight value of any tag of any user in the preset file according to the decay period value comprises:
calculating the attenuation coefficient value according to the decay period value and a preset first formula;
calculating to obtain a result value according to the preset time length, the attenuation coefficient value, the weight value of the label in the preset file and a preset second formula;
and updating the weight value of the label in the preset file by adopting the result value.
7. An information processing apparatus characterized by comprising:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining an initial weight value of a first label under the condition that a user is detected to trigger a preset object provided with the first label; the initial weight value is related to a triggering mode of triggering the preset object by the user; the triggering mode represents the interest degree of the user in the product indicated by the first label; the first label is any one of preset labels;
the updating module is used for updating the weight value of the first label at least according to the initial weight value, the weight value of the first label, the first ratio and the inverse document frequency index; the weight value of the first label represents the interest degree of the user in the product indicated by the first label in historical time; the first ratio represents a ratio between the total number of times that the user triggers the preset object provided with the first tag and the total number of times that the user triggers the preset object provided with the tag;
and the second determining module is used for determining the users meeting the preset conditions as marketing users according to the weight values of the labels of each user.
8. The apparatus of claim 7, further comprising:
a generating module, configured to generate a correspondence relationship among the weight values of the user, the first tag, and the first tag when there is no correspondence relationship among the weight values of the user, the first tag, and the first tag, where the weight value of the first tag in the generated correspondence relationship is an initial weight value of the first tag.
9. A storage medium comprising a stored program, wherein the program executes the information processing method according to any one of claims 1 to 6.
10. An apparatus comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to call program instructions in the memory to perform the information processing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910942436.5A CN112579663A (en) | 2019-09-30 | 2019-09-30 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910942436.5A CN112579663A (en) | 2019-09-30 | 2019-09-30 | Information processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112579663A true CN112579663A (en) | 2021-03-30 |
Family
ID=75116350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910942436.5A Pending CN112579663A (en) | 2019-09-30 | 2019-09-30 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579663A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9031951B1 (en) * | 2012-04-02 | 2015-05-12 | Google Inc. | Associating interest and disinterest keywords with similar and dissimilar users |
| US20160371271A1 (en) * | 2015-06-18 | 2016-12-22 | International Business Machines Corporation | Identification of Target Audience for Content Delivery in Social Networks by Quantifying Semantic Relations and Crowdsourcing |
| CN107341245A (en) * | 2017-07-06 | 2017-11-10 | 广州优视网络科技有限公司 | Data processing method, device and server |
| CN108595599A (en) * | 2018-04-19 | 2018-09-28 | 广州优视网络科技有限公司 | Using label generating method, device, storage medium and computer equipment |
| CN109446412A (en) * | 2018-09-25 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device, equipment and medium based on web page tag |
| CN109828989A (en) * | 2019-01-31 | 2019-05-31 | 泰康保险集团股份有限公司 | Client's marketing method and device |
-
2019
- 2019-09-30 CN CN201910942436.5A patent/CN112579663A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9031951B1 (en) * | 2012-04-02 | 2015-05-12 | Google Inc. | Associating interest and disinterest keywords with similar and dissimilar users |
| US20160371271A1 (en) * | 2015-06-18 | 2016-12-22 | International Business Machines Corporation | Identification of Target Audience for Content Delivery in Social Networks by Quantifying Semantic Relations and Crowdsourcing |
| CN107341245A (en) * | 2017-07-06 | 2017-11-10 | 广州优视网络科技有限公司 | Data processing method, device and server |
| CN108595599A (en) * | 2018-04-19 | 2018-09-28 | 广州优视网络科技有限公司 | Using label generating method, device, storage medium and computer equipment |
| CN109446412A (en) * | 2018-09-25 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device, equipment and medium based on web page tag |
| CN109828989A (en) * | 2019-01-31 | 2019-05-31 | 泰康保险集团股份有限公司 | Client's marketing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805622B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
| CN110135915B (en) | Commodity recommendation method and system | |
| JP5838229B2 (en) | Send product information based on determined preference values | |
| CN106504011B (en) | A kind of methods of exhibiting and device of business object | |
| CN108549569B (en) | Method and equipment for searching information in application program | |
| TW201327233A (en) | Personalized information pushing method and device | |
| CN111639988B (en) | Broker recommendation method, device, electronic equipment and storage medium | |
| CN110413870A (en) | Method of Commodity Recommendation, device and server | |
| KR20140056731A (en) | Purchase recommendation service system and method | |
| CN110880127B (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| WO2020221022A1 (en) | Service object recommendation method | |
| WO2019184582A1 (en) | Electronic book consumption demand determining method, electronic device, and computer storage medium | |
| WO2012019001A2 (en) | Returning estimated value of search keywords of entire account | |
| CN110689402A (en) | Method and device for recommending merchants, electronic equipment and readable storage medium | |
| CN110659417A (en) | Information pushing method and system, electronic equipment and storage medium | |
| CN112613938A (en) | Model training method and device and computer equipment | |
| CN106874293B (en) | Data processing method and device | |
| CN110717788A (en) | Target user screening method and device | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
| US20170068962A1 (en) | Forecasting customer channel choice using cross-channel loyalty | |
| CN106919609B (en) | Product information pushing method and device | |
| US8122448B2 (en) | Estimation method and system | |
| CN110851708B (en) | Negative sample extraction method, device, computer equipment and storage medium | |
| CN110796505B (en) | Business object recommendation method and device |
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 |