CN112651582A - User category identification method for product loss user and related equipment - Google Patents
User category identification method for product loss user and related equipment Download PDFInfo
- Publication number
- CN112651582A CN112651582A CN201910959099.0A CN201910959099A CN112651582A CN 112651582 A CN112651582 A CN 112651582A CN 201910959099 A CN201910959099 A CN 201910959099A CN 112651582 A CN112651582 A CN 112651582A
- Authority
- CN
- China
- Prior art keywords
- user
- product loss
- intention
- value
- level
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000013210 evaluation model Methods 0.000 claims abstract description 39
- 238000010992 reflux Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 11
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000000611 regression analysis Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a user category identification method, a system, electronic equipment and a computer readable storage medium for a product loss user, wherein the method comprises the following steps: acquiring user data of a product loss user; determining the value level of a product loss user according to consumption data in user data; substituting a target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value; a user category corresponding to both the intent level and the value level of the return is determined for recalling the product loss users in a targeted recall manner corresponding to the user category. The application introduces a data analysis processing technology to process the user data, so that the corresponding reasonable targeted recall scheme is adopted for different types of product loss users, the waste of manpower recall cost is avoided, and the recall rate and the recall efficiency are effectively guaranteed.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method, a system, an electronic device, and a computer-readable storage medium for identifying a user category of a product loss user.
Background
Data is a carrier for recording a large amount of information, and the importance of data is not questionable in the current network era and big data era. Data processing and analysis are important in many business applications of enterprises.
User data is a type of important data in enterprise operations. The method has important guiding significance for carrying out targeted processing and analysis on the user data by combining specific business requirements of enterprises, and can play a great role in recovering lost users of products. However, most of the prior art can recall lost users indiscriminately and does not combine scientific and reasonable data processing analysis. In view of the limited recall force of non-manual recall modes such as short messages, in-station messages, mails and the like, the recall rate of the prior art uniformly adopting the modes is obviously lower; on the other hand, the prior art which uniformly adopts the manual voice recall mode has the problems of wasting a large amount of manpower recall cost and low efficiency.
In view of the above, it is an important need for those skilled in the art to provide a solution to the above technical problems.
Disclosure of Invention
The application aims to provide a user category identification method, a system, an electronic device and a computer readable storage medium for a product loss user, so as to provide scientific and reasonable guidance basis for recalling of the product loss user, improve the recall rate and recall efficiency and reduce the recall cost.
In order to solve the above technical problem, in a first aspect, the present application discloses a user category identification method for a product loss user, including:
acquiring user data of the product loss user;
determining the value level of the product loss user according to consumption data in the user data;
substituting the target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user;
determining a reflow intention level corresponding to the reflow intention probability value;
determining a user category corresponding to both the intent to reflow level and the value level for recalling the product loss users in a targeted recall manner corresponding to the user category.
In a second aspect, the present application further discloses a user category identification system for a product loss user, comprising:
the data acquisition module is used for acquiring user data of the product loss user;
the first processing module is used for determining the value level of the product loss user according to consumption data in the user data;
the model establishing module is used for establishing a backflow intention evaluation model of the backflow intention probability relative to the target attribute field in advance;
the second processing module is used for substituting the target attribute field in the user data into the backflow intention evaluation model and calculating the backflow intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value;
and the category identification module is used for determining a user category corresponding to the reflow intention level and the value level so as to recall the product loss users according to a target recall mode corresponding to the user category.
In a third aspect, the present application also discloses an electronic device, including:
a memory for storing a computer program;
a processor for executing said computer program to implement the steps of any of the product attrition users' user category identification methods as described above.
In a fourth aspect, the present application further discloses a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, is adapted to implement the steps of any one of the product loss user category identification methods described above.
The user category identification method for the product loss user comprises the following steps: acquiring user data of the product loss user; determining the value level of the product loss user according to consumption data in the user data; substituting the target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value; determining a user category corresponding to both the intent to reflow level and the value level for recalling the product loss users in a targeted recall manner corresponding to the user category.
Therefore, the method and the device introduce a data analysis processing technology to process the user data, determine the value level and the backflow intention level of the product loss user from a data level, further identify the user category of the product loss user and serve as a guidance basis for user recall, so that a corresponding reasonable targeted recall scheme can be adopted for different categories of product loss users. The application not only avoids the waste of manpower recall cost, but also effectively ensures recall rate and recall efficiency. The user category identification system, the electronic device and the computer-readable storage medium for the product loss user provided by the application also have the beneficial effects.
Drawings
In order to more clearly illustrate the technical solutions in the prior art and the embodiments of the present application, the drawings that are needed to be used in the description of the prior art and the embodiments of the present application will be briefly described below. Of course, the following description of the drawings related to the embodiments of the present application is only a part of the embodiments of the present application, and it will be obvious to those skilled in the art that other drawings can be obtained from the provided drawings without any creative effort, and the obtained other drawings also belong to the protection scope of the present application.
Fig. 1 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application;
fig. 2 is a flowchart of a user category identification method for a product loss user according to an embodiment of the present disclosure;
FIG. 3 is a diagram of a search interface for background user data of a game product according to an embodiment of the present disclosure;
fig. 4 is a detailed recording page diagram of user data disclosed in an embodiment of the present application;
FIG. 5 is a flowchart of another method for identifying a user category of a product loss user according to an embodiment of the present disclosure;
FIG. 6 is a flowchart of another method for identifying user categories of users with product loss according to the embodiment of the present application;
FIG. 7 is a diagram of a variable structure of a reflow intention evaluation model in an embodiment of an application scenario disclosed in the present application;
fig. 8 is a block diagram illustrating a structure of a user category identification system for a product loss user according to an embodiment of the present disclosure.
Detailed Description
The core of the application is to provide a user category identification method, a system, an electronic device and a computer readable storage medium for a product loss user, so as to provide scientific and reasonable guidance basis for recalling of the product loss user, improve the recall rate and recall efficiency and reduce the recall cost.
In order to more clearly and completely describe the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
User data is a type of important data in enterprise operations. The method has important guiding significance for carrying out targeted processing and analysis on the user data by combining specific business requirements of enterprises, and can play a great role in recovering lost users of products. However, most of the prior art recalls lost users indiscriminately and does not combine with scientific and reasonable data processing and analysis, so that not only is the efficiency low, but also a great deal of manpower recall cost is wasted, or the recall condition is not ideal. In view of this, the present application provides a user category identification method for a product loss user, which can effectively solve the above problems.
For convenience of understanding, the following describes an electronic device to which the user category identification method for the product loss user is applied, and may specifically refer to fig. 1.
As can be seen from fig. 1, the electronic device 10 may include: a processor 11, a memory 12, a communication interface 13, an input unit 14 and a display 15 and a communication bus 16. The processor 11, the memory 12, the communication interface 13, the input unit 14 and the display 15 all communicate with each other through a communication bus 16.
In the embodiment of the present application, the processor 11 may be a Central Processing Unit (CPU), an application specific integrated circuit, a digital signal processor, an off-the-shelf programmable gate array, or other programmable logic device. The processor may call a program stored in the memory 12. Specifically, the processor may perform operations performed by the electronic device side in any of the user category identification method embodiments described below.
The memory 12 is used for storing one or more programs, which may include program codes including computer operation instructions, and in this embodiment, at least a program for implementing a certain user class identification method described below is stored in the memory.
In one possible implementation, the memory 12 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function (such as obtaining user data of a product loss user), and the like; the stored data area may store data created during use of the electronic device 10, such as a value level, a reflow intention level, and the like.
In addition, the memory 12 may also include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid state storage device.
The communication interface 13 may be an interface of a communication module, such as an interface of a GSM module.
The present application may also include a display 14 and an input unit 15, and the like.
Of course, the structure of the electronic device shown in fig. 1 does not constitute a limitation of the electronic device in the embodiment of the present application, and in practical applications, the electronic device may include more or less components than those shown in fig. 1, or some components may be combined.
The electronic device 10 in fig. 1 may be a terminal (e.g., a PC), or may be a server with higher performance than a normal terminal.
In this embodiment of the application, the electronic device 10 may receive, by using a network according to the communication interface 13, user data of a product loss user sent by other external devices; user data of the product loss user can also be obtained through the input unit 14 (such as a keyboard, a touch screen, a voice input device, and the like).
Accordingly, the processor 11 in the electronic device 10 may receive the user data from the communication interface 13 or the input unit 14 via the communication bus 16 and call the program stored in the memory 12 to determine the value level of the product losing user according to the consumption data in the user data; substituting a target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value; and then determining the user categories corresponding to the return intention level and the value level, thereby realizing the purpose of providing scientific and reasonable basis for the users who recall the lost products.
Referring to fig. 2, an embodiment of the present application discloses a user category identification method for a product loss user, which mainly includes the following steps:
s11: user data of a product loss user is obtained.
The product may be various software application products, such as games, video players, and the like. And once the continuous unregistered days of the user, namely the lost days, exceed a certain value, the user can be regarded as a product lost user. For example, in the case of a game product, the user may be regarded as a lost user after the number of consecutive unregistered days exceeds 7 days.
Since the user establishes the account, various information data and activities under the product account form user data to be recorded, including personal information data, friend data, product use records, consumption data, customer service records and the like.
Each type of user data may further specifically include a plurality of attribute fields, for example, the personal information data reflects social attribute information of the user, and specifically may include attribute fields such as user age, user gender, user position, user location, and the like; for another example, the customer service record reflects customer service attribute information of the user, and specifically may include attribute fields such as number of times of customer service orders and solvability of customer service problems; the product usage record reflects account attribute information of the user, and specifically may include attribute fields such as account level, elapsed days, and the like.
For example, referring to fig. 3, fig. 3 is a diagram of a search interface of background user data of a game product according to an embodiment of the present application, specifically showing that the search result is user data with an account ID of 12345. After the account is selected and clicked, a user data detail page of the user can be further viewed, which can be specifically referred to in fig. 4.
S12: and determining the value level of the product loss user according to the consumption data in the user data.
In particular, in the prior art, indiscriminate recalls are performed for users with lost products, so that the pertinence is poor, and the recall quality is seriously influenced. Therefore, the embodiment of the application identifies the categories of the product loss users based on the user data, so that various product loss users can be effectively recalled in a targeted manner according to different situations.
The consumption data of the user is important data of the user during the use of the product, the value and the consumption capacity of the user are visually reflected, and meanwhile the love degree and the reflow intention of the user on the product are reflected to a certain extent. Therefore, the value rating is performed on the product loss users according to the consumption data of the users. It is readily understood that the more energy a user is consuming, the higher the corresponding value level. The consumption data includes, but is not limited to, attribute fields such as total consumption amount and consumption times.
In a simple embodiment, the product loss users can be classified into two value levels by using only one preset value threshold, and step S12 may specifically include: if the total consumption amount is higher than a preset value threshold value, determining the value level of the product loss user as a first value level; and if the total consumption amount is not higher than the preset value threshold value, determining the value level of the product loss user as a second value level.
Of course, those skilled in the art may also set a plurality of value thresholds to distinguish the product loss users into a plurality of value levels, which is not further limited in the present application.
S13: and substituting the target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user.
The reflow intention probability value is the probability value that the lost users are successfully recalled. It should be noted that, in order to scientifically and reasonably evaluate the reflux intention of the product loss user, a reflux intention evaluation model is established in advance, and based on the model, after relevant user data of the product loss user is substituted, the reflux intention probability value of the product loss user can be determined.
Specifically, the reflow intention evaluation model is a mathematical model of the reflow intention with respect to multiple variables, and may be established based on regression analysis, but of course, other methods such as cluster analysis may also be adopted. The multivariate, namely target attribute fields are some attribute fields in the user data which are associated with the reflow intention of the user, and collectively reflect the social attribute information, account attribute information or customer service attribute information of the user. The specific attribute fields can be set as target attribute fields by those skilled in the art according to the specific characteristics of the product and the actual application of the product.
S14: and determining the reflow intention level corresponding to the reflow intention probability value.
The reflow intention probability value is a reflow intention evaluation result obtained from a data level based on data analysis, objectively reflects the possibility that a user with product loss is successfully recalled, and can provide scientific and reasonable guidance opinions for the user recall. Based on the probability value of the return intention, the method and the device can distinguish the grades of the return possibility of the users so as to carry out reasonable and targeted return on different categories of the users with lost products.
In a simple embodiment, the product loss users can be classified into two reflow intention levels by using only one preset probability threshold, and the step S14 may specifically include: if the reflow intention probability value is higher than the preset probability threshold value, determining the reflow intention level of the product loss user as a first reflow intention level; and if the reflow intention probability value is not higher than the preset probability threshold value, determining the reflow intention level of the product loss user as a second reflow intention level.
Of course, those skilled in the art may set a plurality of probability thresholds to distinguish the product loss users into a plurality of reflow intention levels, which is not further limited in the present application.
S15: a user category corresponding to both the intent level and the value level of the return is determined for recalling the product loss users in a targeted recall manner corresponding to the user category.
Specifically, when the category identification is performed on the product loss user, the method is specifically based on two-level evaluation results: a reflow intention level and a value level. It is readily understood that the reflow intent level directly reflects the ease with which the product attrition user is successfully recalled, while the value level directly reflects the user value that the product attrition user brings after being successfully recalled.
Based on the two level evaluation results, different product loss users can be finely classified, and therefore different types of user recalls can be further performed for different types of product loss users. For example, the product loss users may be classified into four categories according to the aforementioned preset value threshold and preset probability threshold. And further, corresponding labels can be set for the product loss users of each category: users belonging to both the first value level and the first refluence intention level may be identified as high value reflexes; users belonging to both the first value level and the second reflow intention level may be identified as high value difficult reflow; users belonging to both the second value level and the first reflow intention level may be identified as low value reflow-prone; users belonging to both the second value level and the second reflow intent level may be identified as low value difficult reflow.
It should be noted that the common recall modes specifically include non-manual recall modes such as short messages, tips messages, in-station messages, online activities, and the like, and manual recall modes of manual voices. When different types of product loss users are recalled, based on the user type identification result, a manual recall mode can be only used for the product loss users of important types, and the balance between labor cost and recall rate is realized. For example, as a specific example, the target recall manner corresponding to the first price level may include an artificial voice recall; the target recall profile corresponding to the second value level may not include an artificial voice recall.
The user category identification method for the product loss user provided by the embodiment of the application comprises the following steps: acquiring user data of a product loss user; determining the value level of a product loss user according to consumption data in user data; substituting a target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value; a user category corresponding to both the intent level and the value level of the return is determined for recalling the product loss users in a targeted recall manner corresponding to the user category.
Therefore, the method and the device introduce a data analysis processing technology to process the user data, determine the value level and the backflow intention level of the product loss user from a data level, further identify the user category of the product loss user and serve as a guidance basis for user recall, so that a corresponding reasonable targeted recall scheme can be adopted for different categories of product loss users. The application not only avoids the waste of manpower recall cost, but also effectively ensures recall rate and recall efficiency.
On the basis of the above, as a specific embodiment, the pre-established reflow intention assessment model includes a plurality of reflow intention assessment models corresponding to the respective value levels one to one; the step S13 may be specifically: and substituting the target attribute field of the product loss user with the same value level into the corresponding backflow intention evaluation model, and calculating the backflow intention probability value of the product loss user with the current value level.
Specifically, in the embodiment, the corresponding reflow intention evaluation models can be respectively established for the users with different value levels of product loss, so as to obtain more precise and accurate reflow intention probability values.
The process of establishing the reflow intention evaluation model based on the regression analysis will be described below. Referring to fig. 5, an embodiment of the present application discloses a method for establishing a reflow intention evaluation model, which mainly includes the following steps:
s21: and establishing a logistic stewart regression model of the reflow intention probability with respect to the target attribute field.
Specifically, let a variable p represent the probability of the intention to reflow, and the range of p is [0,1 ]](ii) a Let variable xiThe quantized value, x, representing the target attribute fieldiThe value range of (a) is determined by the attribute of the target attribute field of the corresponding category and the quantization rule thereof. Then, the probability formula for p ═ 1 is:
wherein X ═ X1x2…]T；W＝[β1β2…]T；βiIs the regression coefficient of the corresponding target attribute field. The logistic regression model (logistic model) of the reflow intention probability with respect to the target attribute field is:
where ε is the random error.
S22: and obtaining a user data sample and a sample backflow result of the product loss user sample.
S23: and determining parameter values in the logistic stewart regression model according to the user data samples and the sample backflow results.
Specifically, in order to determine the parameter values in the logistic stet regression model, the method takes product loss user samples as analysis objects, and substitutes user data and backflow results of the product loss user samples as user data samples and sample backflow results into the logistic stet regression model to determine the values of the parameters. The determination of the parameter value may specifically adopt various fitting methods, which is not further limited in this application.
S24: and calculating the relative influence value of each target attribute field on the reflow intention probability.
It should be noted that, in step S23, the logistic regression model is already preliminarily established. Further, in this embodiment, the logistic stewart regression model established in step S23 may be optimized and updated on the basis of the above contents.
In the preliminarily established logistic regression model, the number of the target attribute fields contained in the model is high, and few of the target attribute fields have weak influence on the reflow probability. Therefore, the method and the device can remove some unnecessary target attribute fields by calculating the relative influence values of the target attribute fields on the reflow intention probability.
As a specific embodiment, the relative influence value may specifically be: target attribute field corresponding quantization value xiIs compared to the rate of change of its induced reflux probability value p.
S25: and removing the target attribute field with the relative influence value lower than the preset influence threshold value.
It is easy to understand that, after the target attribute field with a relatively low influence value is removed, the corresponding regression coefficient is also removed.
S26: determining parameter values in the updated reflow intention evaluation model.
Since some expressions in the original logistic regression model are removed, in order to ensure the accuracy of the model, the parameter values in the reflow intention evaluation model need to be recalculated so as to update the reflow intention evaluation model.
Referring to fig. 6, an embodiment of the present application discloses another user category identification method for a product loss user, which mainly includes:
s31: user data of a product loss user is obtained.
S32: judging whether the product loss user is an effective user or not according to the user data; if not, go to S33; if yes, the process proceeds to S34.
S33: recalling the product loss users according to a target recall mode corresponding to the invalid users; proceed to S38.
Specifically, in view of the situation that part of the product loss users may be invalid users, the method and the system also identify the invalid users and set a corresponding target recall mode. For invalid users, such as users who select a cover number, recall manners such as in-station messages, tips messages, online activities and the like cannot reach the users, so that the manners can be avoided when the invalid users are recalled specifically in the application.
S34: determining the value level of a product loss user according to consumption data in user data; proceed to S35.
S35: substituting a target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user; proceed to S36.
S36: determining a reflow intention level corresponding to the reflow intention probability value; proceed to S37.
S37: a user category corresponding to both the intent level and the value level of the return is determined for recalling the product loss users in a targeted recall manner corresponding to the user category.
S38: and obtaining a backflow result of the product loss user.
S39: and merging the product loss users into the product loss user sample, and updating the backflow intention evaluation model according to the updated product loss user sample.
Specifically, in order to further improve the return intention assessment model and improve the accuracy of the identification result, the user category identification method provided by this embodiment may further track the subsequent actual return result after recalling the product loss users of each category, so as to bring the product loss users into the product loss user sample, and further optimize and update the return intention assessment model by enriching the sample capacity.
The following describes an exemplary embodiment of the present application by taking a user category identification of a game product losing user as an example.
First, a sample of product losing users of the game product is obtained by collecting a large number of recall survey records of losing users of the game product. And then, according to a logistic stett regression analysis method, establishing a reflow intention evaluation model of the game product according to the user data of the product loss user sample and the sample reflow result.
In the process of establishing the model, thirty or more target attribute fields in user data are specifically selected as related variables to construct a logistic Stent regression model, wherein the logistic Stent regression model comprises user age, user gender, user occupation, lost days, game level, game fighting force value, total consumption, game virtual currency balance, user points, user penalty records, customer service order taking times, customer service problem solvability and the like. After the relevant variables are determined, the magnitude of each parameter value in the backflow intention assessment model can be fit and determined according to the final backflow result of each user in the product loss user sample.
In order to optimize the reflow intention evaluation model, the present embodiment further calculates the relative influence of each target attribute field on the reflow intention probability, and further deletes the target attribute field with lower relative influence, such as the user occupation, and only retains the target attribute field having significant influence on the reflow intention probability in the model.
After the screening optimization, eight significantly-influential target attribute fields are retained, as can be seen in particular in fig. 7, including: reflecting the user age and the user gender of the social attribute information of the user; reflecting the consumption total amount, the game grade, the game fighting force value and the loss days of the account attribute information; reflecting the number of times of customer service orders of the customer service attribute information of the user and the solvability of the customer service problem.
The variables after the eight target attribute fields are quantized are sequentially marked as xiThen the logistic regression model becomes:
Logit(p)＝β0+β1x1+β2x2+β3x3+β4x4+β5x5+β6x6+β7x7+β8x8+ε。
and (4) performing parameter fitting again by using the product loss sample, and determining the parameter values in the model one by one again. The optimized evaluation model of the reflow intention is obtained as follows:
Logit(p)＝-6.8e-0.0512393x1+0.2660933x2-0.8x3+0.008774x4-0.8x5-0.0056803x6+0.2077715x7+0.0529246x8-0.1334708。
after the reflow intention evaluation model is established, the category of the product loss user to be analyzed can be identified.
The system automatically loads user data of product loss users, identifies effective users, extracts consumption data of the effective users, and determines value levels of the effective users according to a preset value threshold; and quantizing the eight target attribute fields in the user data and inputting the eight target attribute fields into a backflow intention evaluation model, calculating backflow intention probability values of effective users, and further determining backflow intention levels of the effective users.
In this embodiment, a preset value threshold with a size of 100000 is specifically set, so that the product loss users are divided into two value levels; and a preset probability threshold value of 0.7 is set, and the product loss users are divided into two backflow intention levels. Thus, valid users can be specifically identified as four classes.
The user category identification result can be used as guide data in the process of recalling the lost user. As a specific example, the embodiments of the present application implement product attrition user recalls with specific reference to table 1. The target recall patterns corresponding to different categories of product loss users are specifically shown in table 1.
TABLE 1
Referring to fig. 8, an embodiment of the present application discloses a user category identification system for a product loss user, which mainly includes:
a data obtaining module 41, configured to obtain user data of a product loss user;
a first processing module 42, configured to determine, according to consumption data in the user data, a value level of a product losing user;
the model establishing module 43 is used for establishing a backflow intention evaluation model of the backflow intention probability with respect to the target attribute field in advance;
the second processing module 44 is configured to substitute the target attribute field in the user data into the backflow intention assessment model, and calculate a backflow intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value;
and the category identification module 45 is used for determining a user category corresponding to both the reflow intention level and the value level so as to recall the product loss users according to a target recall mode corresponding to the user category.
Therefore, the user category identification system of the product loss users, disclosed in the embodiment of the application, introduces a data analysis processing technology to process user data, determines the value level and the backflow intention level of the product loss users from a data layer, and further can identify the user categories of the product loss users and serve as a guide basis for user recall, so that a corresponding reasonable targeted recall scheme can be adopted for different categories of product loss users. The application not only avoids the waste of manpower recall cost, but also effectively ensures recall rate and recall efficiency.
For the specific content of the user category identification system of the product churn user, reference may be made to the detailed description of the user category identification method of the product churn user, and details thereof will not be repeated here.
On the basis of the above content, in a specific implementation manner of the user category identification system of the product loss user disclosed in the embodiment of the present application, the model building module 43 is specifically configured to: pre-establishing a plurality of backflow intention evaluation models which are respectively in one-to-one correspondence with the value levels;
the second processing module 44 is specifically configured to: and substituting the target attribute field of the product loss user with the same value level into the corresponding backflow intention evaluation model, and calculating the backflow intention probability value of the product loss user with the current value level.
On the basis of the above content, in a specific implementation manner of the user category identification system for a product loss user disclosed in the embodiment of the present application, the model building module 43 specifically includes:
the model establishing unit is used for establishing a logistic stewart regression model of the reflux intention probability about the target attribute field;
the sample acquisition unit is used for acquiring a user data sample and a sample backflow result of the product loss user sample;
and the parameter determining unit is used for determining the parameter value in the logistic stewart regression model according to the user data sample and the sample backflow result.
On the basis of the above, as a specific implementation manner, in the user category identification system of the product loss user disclosed in the embodiment of the present application, the model building module 43 further includes:
the model optimization unit is used for calculating the relative influence value of each target attribute field on the reflux intention probability; removing the target attribute field with the relative influence value lower than a preset influence threshold value; determining parameter values in the updated reflow intention evaluation model.
On the basis of the above content, as a specific implementation manner, in the user category identification system of the product loss user disclosed in the embodiment of the present application, the model optimization unit is further configured to:
after the product loss users are recalled according to a target recall mode corresponding to the user category, obtaining a reflux result of the product loss users; merging the product loss users into a product loss user sample; and updating the backflow intention evaluation model according to the updated product loss user sample.
On the basis of the above, as a specific implementation manner, in the user category identification system of the product loss user disclosed in the embodiment of the present application, the first processing module 42 is specifically configured to:
if the total consumption amount is higher than a preset value threshold value, determining the value level of the product loss user as a first value level; the target recall mode corresponding to the first price level comprises artificial voice recall;
if the total consumption amount is not higher than a preset value threshold value, determining the value level of the product loss user as a second value level; the target recall style corresponding to the second value level does not include an artificial voice recall.
On the basis of the above, as a specific implementation manner, in the user category identification system for a product loss user disclosed in the embodiment of the present application, the data obtaining module 41 is further configured to:
after user data of a product loss user is obtained, judging whether the product loss user is an effective user or not according to the user data; and the product losing users are recalled conveniently according to the target recall mode corresponding to the invalid users after the product losing users are judged to be the invalid users.
Further, the present application discloses a computer-readable storage medium, in which a computer program is stored, and the computer program is used for implementing the steps of any one of the product loss user category identification methods described above when being executed by a processor.
For the details of the computer-readable storage medium, reference may be made to the foregoing detailed description of the user category identification method for the product loss user, and details thereof will not be repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the equipment disclosed by the embodiment, the description is relatively simple because the equipment corresponds to the method disclosed by the embodiment, and the relevant parts can be referred to the method part for description.
It is further noted that, throughout this document, relational terms such as "first" and "second" are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, 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 a process, method, article, or apparatus that comprises the element.
The technical solutions provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall into the protection scope of the present application.
Claims (10)
1. A user category identification method for a product loss user is characterized by comprising the following steps:
acquiring user data of the product loss user;
determining the value level of the product loss user according to consumption data in the user data;
substituting the target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user;
determining a reflow intention level corresponding to the reflow intention probability value;
determining a user category corresponding to both the intent to reflow level and the value level for recalling the product loss users in a targeted recall manner corresponding to the user category.
2. The user category identification method according to claim 1, wherein the pre-established reflow intention evaluation model includes a plurality of reflow intention evaluation models that are respectively in one-to-one correspondence with respective value levels;
substituting the target attribute field in the user data into a pre-established reflux intention evaluation model, and calculating the reflux intention probability value of the product loss user, wherein the method comprises the following steps:
and substituting the target attribute field of the product loss user with the same value level into the corresponding backflow intention evaluation model, and calculating the backflow intention probability value of the product loss user with the current value level.
3. The method according to claim 1, wherein the reflow intention evaluation model is created by:
establishing a logistic stewart regression model of the reflux intention probability about the target attribute field;
obtaining a user data sample and a sample reflux result of a product loss user sample;
and determining parameter values in the logistic stewart regression model according to the user data sample and the sample backflow result.
4. The user class identification method of claim 3, further comprising, after the determining the parameter values in the logistic regression model:
calculating the relative influence value of each target attribute field on the reflow intention probability;
removing the target attribute field with the relative influence value lower than a preset influence threshold value;
determining parameter values in the updated reflow intention evaluation model.
5. The user category identification method of claim 4, further comprising, after said recalling said product attrition users in a targeted recall manner corresponding to said user category:
obtaining a backflow result of the product loss user;
incorporating the product churn user into the product churn user sample;
and updating the backflow intention assessment model according to the updated product loss user sample.
6. The method according to any one of claims 1 to 5, wherein the determining the value level of the product attrition user according to the consumption data in the user data comprises:
if the total consumption amount is higher than a preset value threshold value, determining the value level of the product loss user as a first value level; the target recall mode corresponding to the first price level comprises artificial voice recall;
if the total consumption amount is not higher than the preset value threshold value, determining the value level of the product loss user as a second value level; and the target recall mode corresponding to the second price level does not comprise artificial voice recall.
7. The method according to claim 6, further comprising, after the obtaining the user data of the product attrition user:
judging whether the product loss user is an effective user or not according to the user data;
if yes, executing the step of determining the value level of the product loss user according to consumption data in the user data;
and if not, recalling the product losing users according to a target recall mode corresponding to the invalid users.
8. A user category identification system for a product churn user, comprising:
the data acquisition module is used for acquiring user data of the product loss user;
the first processing module is used for determining the value level of the product loss user according to consumption data in the user data;
the model establishing module is used for establishing a backflow intention evaluation model of the backflow intention probability relative to the target attribute field in advance;
the second processing module is used for substituting the target attribute field in the user data into the backflow intention evaluation model and calculating the backflow intention probability value of the product loss user; determining a reflow intention level corresponding to the reflow intention probability value;
and the category identification module is used for determining a user category corresponding to the reflow intention level and the value level so as to recall the product loss users according to a target recall mode corresponding to the user category.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the user category identification method of a product attrition user as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the steps of the method for user category identification of a product attrition user as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959099.0A CN112651582B (en) | 2019-10-10 | 2019-10-10 | User category identification method and related equipment for product loss user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959099.0A CN112651582B (en) | 2019-10-10 | 2019-10-10 | User category identification method and related equipment for product loss user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112651582A true CN112651582A (en) | 2021-04-13 |
| CN112651582B CN112651582B (en) | 2024-04-26 |
Family
ID=75342870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910959099.0A Active CN112651582B (en) | 2019-10-10 | 2019-10-10 | User category identification method and related equipment for product loss user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651582B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343089A (en) * | 2021-06-11 | 2021-09-03 | 北京完美赤金科技有限公司 | User recall method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833063A (en) * | 2017-11-30 | 2018-03-23 | 上海科瓴医疗科技有限公司 | Pharmacy member is lost in early warning and intelligent interfering system and method |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN109583651A (en) * | 2018-12-03 | 2019-04-05 | 焦点科技股份有限公司 | A kind of method and apparatus for insuring electric business platform user attrition prediction |
| US20190182059A1 (en) * | 2017-12-12 | 2019-06-13 | Facebook, Inc. | Utilizing machine learning from exposed and non-exposed user recall to improve digital content distribution |
-
2019
- 2019-10-10 CN CN201910959099.0A patent/CN112651582B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833063A (en) * | 2017-11-30 | 2018-03-23 | 上海科瓴医疗科技有限公司 | Pharmacy member is lost in early warning and intelligent interfering system and method |
| US20190182059A1 (en) * | 2017-12-12 | 2019-06-13 | Facebook, Inc. | Utilizing machine learning from exposed and non-exposed user recall to improve digital content distribution |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN109583651A (en) * | 2018-12-03 | 2019-04-05 | 焦点科技股份有限公司 | A kind of method and apparatus for insuring electric business platform user attrition prediction |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343089A (en) * | 2021-06-11 | 2021-09-03 | 北京完美赤金科技有限公司 | User recall method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112651582B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837931B (en) | Customer churn prediction method, device and storage medium | |
| US20200364506A1 (en) | Article Recommendation Method and Apparatus, Computer Device, and Storage Medium | |
| CN110619506B (en) | Post image generation method, post image generation device and electronic equipment | |
| CN105095411B (en) | A kind of APP rankings prediction technique and system based on APP mass | |
| CN108665148B (en) | Electronic resource quality evaluation method and device and storage medium | |
| CN110334356A (en) | Article matter method for determination of amount, article screening technique and corresponding device | |
| CN111461180A (en) | Sample classification method and device, computer equipment and storage medium | |
| CN110659388A (en) | To-be-recommended information screening method and device, electronic equipment and storage medium | |
| CN111915156B (en) | Service pushing method based on user value, electronic equipment and storage medium | |
| CN108322317A (en) | A kind of account identification correlating method and server | |
| CN113643070A (en) | Intelligent information pushing method and system based on big data | |
| CN112435047A (en) | Marketing outbound data recommendation method based on buried point data | |
| CN107977855B (en) | Method and device for managing user information | |
| CN111324370A (en) | Method and device for carrying out risk processing on to-be-on-line small program | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| WO2019242453A1 (en) | Information processing method and device, storage medium, and electronic device | |
| CN112651582A (en) | User category identification method for product loss user and related equipment | |
| CN115271282A (en) | Customer value determination method and device based on fuzzy logic | |
| CN111882113A (en) | Enterprise mobile banking user prediction method and device | |
| CN112565902B (en) | Video recommendation method and device and electronic equipment | |
| CN112433993A (en) | Network data processing and analyzing system based on computer | |
| CN110690987B (en) | Account information management method, device and equipment | |
| CN116433324A (en) | Product recommendation method, device, medium and computer equipment | |
| Parra et al. | Comparison of Online Platforms for the Review Process of Conference Paper | |
| CN108460475A (en) | Poor student's prediction technique and device based on network playing by students behavior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40042608 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |