CN114741605A - Method and device for recommending annuity products, electronic equipment and readable medium - Google Patents
Method and device for recommending annuity products, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN114741605A CN114741605A CN202210446820.8A CN202210446820A CN114741605A CN 114741605 A CN114741605 A CN 114741605A CN 202210446820 A CN202210446820 A CN 202210446820A CN 114741605 A CN114741605 A CN 114741605A
- Authority
- CN
- China
- Prior art keywords
- annuity
- user
- plans
- aggregate
- plan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 239000013598 vector Substances 0.000 claims abstract description 65
- 230000002776 aggregation Effects 0.000 claims description 35
- 238000004220 aggregation Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 24
- 230000006399 behavior Effects 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a recommendation method and device of annuity products, electronic equipment and a readable medium, and the recommendation method comprises the following steps: generating a feature vector of a user based on behavior feature information and label feature information of the user; determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the list of recommended annuity collection plans includes at least one chronologically arranged annuity collection plan; and adjusting the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list based on the similarity and/or popularity of the annuity aggregate plans to obtain a target annuity aggregate plan list and sending the target annuity aggregate plan list to the user. The user can easily find the annuity set plan meeting the preference of the user in the target annuity set plan list, and the recommendation accuracy is high.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and an apparatus for recommending annuals, an electronic device, and a computer-readable medium.
Background
The enterprise annuity is a supplementary endowment insurance system which is independently established by enterprises and workers thereof. The annual fund of the enterprise can provide an annual fund investment mode which accords with the preference for the enterprise and the employees in a mode of annual fund collective plan. At least one optional investment strategy may be included in the annuity aggregation plan. The user can choose the annual fund collection plan to join according to the preference of the user. However, because annuity aggregation plans are diverse, it is often difficult for a user to select an annuity aggregation plan that satisfies his preferences.
Disclosure of Invention
The embodiment of the invention provides a recommendation method and device of annuity products, electronic equipment and a computer readable storage medium, and aims to solve the problem of recommending an annuity set plan meeting the preference of a user.
The embodiment of the invention discloses a recommendation method of annuity products, which comprises the following steps:
generating a feature vector of a user based on behavior feature information and label feature information of the user;
determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the list of recommended annuity collection plans includes at least one chronologically arranged annuity collection plan;
and adjusting the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list based on the similarity and/or popularity of the annuity aggregate plans to obtain a target annuity aggregate plan list and sending the target annuity aggregate plan list to the user.
Optionally, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
and inputting the characteristic vector of the user and the product association table into a preset recommendation model, and acquiring a recommendation annuity set plan list output by the recommendation model.
Optionally, the recommendation model is trained in the following manner:
acquiring historical selection information for recording a historical selection annuity set plan of a user;
generating a training set based on the feature vector of the user, the product association table and the historical selection information;
and training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
Optionally, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
comparing similarity between users based on the feature vectors of the users;
for a user, determining an annuity collection plan associated with at least one user selected by other users similar to the user;
determining at least one annuity aggregation plan associated with a product similar to the annuity aggregation plan associated with the user based on the product association table;
and selecting at least one annual fund collection plan which is not selected by the user from the annual fund collection plans associated with the users and the annual fund collection plan associated with the product to generate a recommended annual fund collection plan list.
Optionally, the step of adjusting the ranking of the annuity aggregation plans in the recommended annuity aggregation plan list based on the similarity and popularity between the annuity aggregation plans includes:
determining the similarity between the annuity set plans according to a similarity matrix between the annuity set plans;
determining the interest degree of a user in the annuity collection plans in the recommended annuity collection plan list based on the similarity between the annuity collection plans;
adjusting the ranking of the annuity aggregation plan based on the level of interest.
Optionally, the method comprises:
and establishing a similarity matrix between the annuity set plans and carrying out normalization processing on the similarity matrix.
Optionally, the step of adjusting the ranking of the annuity aggregation plans in the recommended annuity aggregation plan list based on the similarity and popularity between the annuity aggregation plans includes:
decreasing the ranking of the annuity aggregate plans with high popularity in the recommended annuity aggregate plan list, and/or increasing the ranking of the annuity aggregate plans with low popularity in the recommended annuity aggregate plan list.
The embodiment of the invention discloses a recommendation device for annuity products, which comprises:
the user characteristic generation module is used for generating a characteristic vector of the user based on the behavior characteristic information and the label characteristic information of the user;
the recommending module is used for determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence;
and the adjusting module is used for adjusting the sequence of the annuity set plans in the recommended annuity set plan list based on the similarity and/or popularity among the annuity set plans to obtain a target annuity set plan list and sending the target annuity set plan list to the user.
Optionally, the recommending module includes:
and the model recommendation sub-module is used for inputting the feature vector of the user and the product association table into a preset recommendation model and acquiring a recommendation annuity set plan list output by the recommendation model.
Optionally, the recommendation model is obtained by training in the following manner:
the history acquisition module is used for acquiring history selection information for recording a user history selection annuity set plan;
a training set generating module, configured to generate a training set based on the feature vector of the user, the product association table, and the history selection information;
and the model training module is used for training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
Optionally, the recommendation module includes:
the similarity comparison submodule is used for comparing the similarity between the users based on the characteristic vectors of the users;
the association determination submodule is used for determining an annuity set plan associated with at least one user selected by other users similar to the user;
an association recommendation sub-module to determine at least one annuity aggregation plan associated with a product similar to the user-associated annuity aggregation plan based on the product association table;
and the list generation submodule is used for selecting at least one annuity set plan which is not selected by the user from the user related annuity set plans and the product related annuity set plans to generate a recommended annuity set plan list.
Optionally, the adjusting module includes:
the similarity comparison submodule is used for determining the similarity between the annuity set plans according to a similarity matrix between the annuity set plans;
the interest determination sub-module is used for determining the interest degree of the user in the annuity set plans in the recommended annuity set plan list based on the similarity between the annuity set plans;
and the adjusting sub-module is used for adjusting the sequence of the annuity set plan based on the interest degree.
Optionally, the method comprises:
and the normalization module is used for establishing a similarity matrix between the annuity set plans and carrying out normalization processing on the similarity matrix.
Optionally, the adjusting module includes:
and the sorting adjustment sub-module is used for reducing the sorting of the annual fund collection plans with high popularity in the recommended annual fund collection plan list and/or improving the sorting of the annual fund collection plans with low popularity in the recommended annual fund collection plan list.
The embodiment of the invention also discloses electronic equipment which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory finish mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the method according to the embodiment of the present invention when executing the program stored in the memory.
Also disclosed are one or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform a method according to an embodiment of the invention.
The embodiment of the invention has the following advantages:
according to the annuity product recommendation method, the characteristic vector of the user is generated based on the behavior characteristic information and the label characteristic information of the user, and the recommended annuity set plan list is determined based on the characteristic vector of the user and the product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence; the ranking of the annuity aggregate plans in the recommended annuity aggregate plan list is adjusted based on the similarity and/or popularity among the annuity aggregate plans to obtain a target annuity aggregate plan list and sent to the user, the recommended annuity aggregate plan list preferred by the user can be obtained, the user can easily find the annuity aggregate plan meeting the preference of the user in the target annuity aggregate plan list, and the recommendation accuracy is high.
Drawings
FIG. 1 is a flowchart illustrating the steps of a method for recommending annuity products provided in an embodiment of the present invention;
FIG. 2 is a flow chart illustrating steps of another annuity product recommendation method provided in an embodiment of the present invention;
fig. 3 is a block diagram showing a recommendation apparatus for annuity products according to an embodiment of the present invention;
FIG. 4 is a block diagram of an electronic device provided in an embodiment of the invention;
fig. 5 is a schematic diagram of a computer-readable medium provided in an embodiment of the invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Aiming at the problem of recommending the annuity aggregate plans meeting the preference of the user to the user, the embodiment of the invention determines the annuity aggregate plan list which is possibly interested by the user based on the characteristics of the user and the characteristics of products, and then adjusts the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list based on the similarity and/or popularity among the annuity aggregate plans to obtain the target annuity aggregate plan list, so that the user can easily find the annuity aggregate plans meeting the preference of the user in the target annuity aggregate plan list, and the recommendation accuracy is high.
Referring to fig. 1, a flowchart illustrating steps of a method for recommending annuity products provided in an embodiment of the present invention is shown, and specifically, the method may include the following steps:
specifically, in the process that the user uses the annuity service platform, under the condition that the user agrees, the personal information and the preference information provided by the user to the annuity service platform can be collected, and further extraction is carried out on the personal information and the preference information to obtain the label characteristic information.
Meanwhile, under the condition that the user agrees, operation records generated by the user in the process of using the annuity service platform can be collected, and behavior feature preference of the user is determined based on the user operation records to obtain behavior feature information.
Then, based on the behavior feature information and the label feature information of the user, a feature vector describing the features of the user is generated, thereby completing the construction of the user portrait,
in a specific implementation, the user may provide information associated with his or her individual, such as his or her age, occupation, region, etc., during the registration process, so that personal information may be obtained. In order to ensure that the investment of the user is matched with the personal ability and the preference of the user, the annuity service platform can provide risk assessment or questionnaire and the like for the user, collect information related to personal preference, such as income information, investment attitude, investment proportion and the like of the user, and further obtain preference information. Thereafter, a tag associated with the user feature may be extracted from the personal information and the preference information, resulting in tag feature information.
In the process that the user uses the annuity service platform, historical browsing records can be generated, user platform behaviors such as the time length for browsing the annuity products and the times for clicking the annuity products of the user on the annuity service platform can be recorded, and characteristics related to the user behaviors are extracted based on the user platform behaviors such as the historical browsing records, the time length for browsing the annuity products and the times for clicking the annuity products, so that behavior characteristic information is obtained.
Thereafter, a feature vector which is represented by a vector and records the tag feature information and the behavior feature information related information can be generated to construct a user portrait, so that an annuity collection plan meeting the preference of the user can be recommended to the user in the following process.
specifically, after obtaining the feature vector of the user, a recommended annuity set plan list may be further determined based on the feature vector of the user and the product association table, so as to determine an annuity set plan list including at least one sequentially arranged annuity set plan which may be of interest to the user.
The product association table may use the association between the annuity aggregation plans as a category, and records several annuity aggregation plans. So that a series of annuity aggregation plans that may be of interest to the user can be more easily determined based on the product association table.
In particular, the annuity service platform may tag sort the annuity collection plans. For example, annuity collection plans that contain only conservative investment strategies are categorized together; categorizing annuity collection plans with and only with integrated and aggressive investment strategies; the collective plan containing three investment strategies of integration, promotion and conservation is classified together. Thus, in the event that it is determined that the user prefers an annuity aggregation plan of a certain category, it is possible to further search for other annuity aggregation plans that may be of interest to the user based on the same category.
In specific implementation, the feature vector of the user and the product association table can be matched, an annuity aggregate plan associated with the feature vector of the user is searched, and then other annuity plans similar to the annuity aggregate plan are further searched based on the product association table, so that a recommended annuity aggregate plan list can be obtained.
The feature vector of the user and the product association table can also be used as input of the model, the input is input into the recommendation model, and the annuity set plan which is interested by the user is recommended through the recommendation model to obtain the recommended annuity set plan list.
In the recommended annuity aggregate plan list, the annuity aggregate plans can be arranged in sequence, and the sequence can be arranged according to the matching degree between the annuity aggregate plan and the feature vector of the user according to the actual requirement, so that the annuity aggregate plans more interesting to the user can be arranged at the front position as much as possible, and the user can more easily check the annuity aggregate plans more interesting to the user.
And 103, adjusting the sequence of the annuity set plans in the recommended annuity set plan list based on the similarity and/or popularity of the annuity set plans to obtain a target annuity set plan list and sending the target annuity set plan list to the user.
Specifically, after obtaining the recommended annuity aggregate plan list, in order to further improve the recommendation accuracy of the annuity aggregate plan, the ranking of the annuity aggregate plans in the recommended annuity aggregate plan list may be adjusted based on the similarity and/or popularity between the annuity aggregate plans, so that the annuity aggregate plans that may be interested by the user may be more easily arranged at the front positions of the annuity aggregate plans. Thereafter, the target annuity aggregate plan list can be sent to the user, so that the user can select the annuity aggregate plan which is interested in the user based on the target annuity aggregate plan list.
Specifically, based on the similarity between annuity collection plans, similar annuity collection plans preferred by the user can be placed at the front position in the target annuity collection plan list, so that the user can more easily view the annuity collection plans in which the user is interested. Meanwhile, the ranking of the annuity aggregate plans in the recommended annuity aggregate plan list is adjusted based on popularity, most of popular annuity aggregate plan products selected by users can be placed at the front position in the target annuity aggregate plan list, and users can more easily view the interested annuity aggregate plans. In addition, in order to reduce the problem of long-tailed exposure, the popular annuity aggregate plan can be properly sorted according to actual needs, so that the annuity aggregate plan product at the tail part can be more easily selected by the user.
According to the annuity product recommendation method, the characteristic vector of the user is generated based on the behavior characteristic information and the label characteristic information of the user, and the recommended annuity set plan list is determined based on the characteristic vector of the user and the product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence; the ranking of the annuity aggregate plans in the recommended annuity aggregate plan list is adjusted based on the similarity and/or popularity among the annuity aggregate plans to obtain a target annuity aggregate plan list and sent to the user, the recommended annuity aggregate plan list preferred by the user can be obtained, the user can easily find the annuity aggregate plan meeting the preference of the user in the target annuity aggregate plan list, and the recommendation accuracy is high.
Referring to fig. 2, a flowchart illustrating steps of a method for recommending annuity products provided in an embodiment of the present invention is shown, and specifically, the method may include the following steps:
specifically, in the process that the user uses the annuity service platform, under the condition that the user agrees, the personal information and the preference information provided by the user to the annuity service platform can be collected, and further extraction is carried out on the personal information and the preference information to obtain the label characteristic information.
Meanwhile, under the condition that the user agrees, operation records generated by the user in the process of using the annuity service platform can be collected, and behavior feature preference of the user is determined based on the user operation records to obtain behavior feature information.
Then, a feature vector describing the user feature can be generated based on the behavior feature information and the label feature information of the user, so that the construction of the user portrait is completed,
specifically, after obtaining the feature vector of the user, a recommended annuity set plan list may be further determined based on the feature vector of the user and the product association table to determine an annuity set plan list including at least one ordered annuity set plan that may be of interest to the user.
The product association table may use the association between the annuity aggregation plans as a category, and records several annuity aggregation plans. So that a series of annuity aggregation plans that may be of interest to the user can be more easily determined based on the product association table.
In an embodiment of the present invention, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
and S11, inputting the feature vector of the user and the product association table into a preset recommendation model, and acquiring a recommendation annuity set plan list output by the recommendation model.
Specifically, a recommendation model may be trained in advance, and the recommendation model may output a recommended annuity aggregate plan list by using a feature vector of a user and a product association table as inputs, so that recommendation of the annuity aggregate plan is completed based on the preference of the user and the association between products. The recommendation model may be a collaborative filtering model, a factorization model, a gradient lifting decision tree model, a large-scale piecewise linear model, and the like, which is not limited in the present invention.
In an embodiment of the present invention, the recommendation model is obtained by training in the following way:
s21, acquiring historical selection information for recording the historical selection annuity set plan of the user;
in order to train the recommendation model, a training set needs to be constructed first, and history selection information recording a user history selection annuity set plan can be acquired as output of the model in the training process.
S22, generating a training set based on the feature vector of the user, the product association table and the historical selection information;
the historical selection information, the feature vector of the user corresponding to the historical selection information and the product association table can be combined into a training sample. Forming a plurality of training samples in the same way, thereby obtaining a training set;
and S23, training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
After the training set is obtained, the training set can be adopted to train the recommendation model to be trained until the training completion condition is met, and then the recommendation model is obtained.
The training completion condition may be that the loss function is optimal, the loss function is smaller than a preset threshold, and the like, which is not limited by the present invention.
In an embodiment of the present invention, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
s31, comparing the similarity between users based on the characteristic vectors of the users;
specifically, in addition to recommending an annuity aggregate plan list based on a recommendation model, recommending an annuity aggregate plan to a user can be realized based on the similarity between users.
Since similar users may have similar preferences, the similarity between users may be compared based on the feature vectors of the users, so as to search for other users with high similarity to the user who needs the recommended annuity aggregation plan.
S32, aiming at a user, determining an annuity collection plan associated with at least one user selected by other users similar to the user;
specifically, for a user who needs to recommend an annuity aggregate plan, after finding other users with high similarity to the user, it may be determined whether the other users have selected the annuity aggregate plan, and if the other users have selected the annuity aggregate plan, the annuity aggregate plan may be considered to be associated with the other users, and may be an annuity aggregate plan preferred by the user who needs to recommend the annuity aggregate plan.
S33, determining at least one annuity collection plan associated with a product similar to the user-associated annuity collection plan based on the product association table;
after determining the annuity aggregate plan associated with at least one user selected by other users similar to the user needing the recommended annuity aggregate plan, the annuity aggregate plan associated with the user may also be the annuity aggregate plan of interest to the user needing the recommended annuity aggregate plan. Thus, at least one annuity aggregate plan associated with a product similar to the user-associated annuity aggregate plan can be determined based on the product association table, so that other annuity plans interested by the user needing the recommended annuity aggregate plan can be found based on the product association table.
S34, selecting at least one annual fund collection plan not selected by the user from the annual fund collection plans associated with the users and the annual fund collection plan associated with the product, and generating a recommended annual fund collection plan list.
In the annuity aggregate plan in which the user-associated annuity aggregate plan is associated with the product, there may be a case where the annuity aggregate plan has been selected by the user who needs to recommend the annuity aggregate plan, and does not need to be recommended to the user again. Therefore, at least one annual fund collection plan which is not selected by the user can be selected from the annual fund collection plans associated with the users and the annual fund collection plans associated with the products, and a recommended annual fund collection plan list is generated, so that a recommended annual fund collection plan list which is possibly interested by the users can be obtained.
In a specific implementation, the recommended annuity aggregate plan list may be determined by simultaneously using a recommendation model and a recommendation mode based on the annuity aggregate plan selected by the similar user, or may be determined by using one of the recommendation model and the recommendation mode based on the annuity aggregate plan selected by the similar user.
in order to further improve the recommendation accuracy of the annuity aggregate plan, after the recommended annuity aggregate plan list is obtained, the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list can be further adjusted, so that a user can more easily check the interested annuity aggregate plans.
Thus, a similarity matrix between annuity collection plans can be established to further determine the similarity between annuity collection plans.
Specifically, a user-annuity aggregate plan inverted table may be first created, and information of the user and the annuity aggregate plan preferred by the user may be recorded in the user-annuity aggregate plan inverted table. Thereafter, a similarity matrix between the annuity aggregate plans may be created in which 1 is added to the number of co-occurrences of the two annuity aggregate plans if a user selects both annuity aggregate plans at the same time.
Meanwhile, the number of users for selecting the annuity aggregate plan can be determined aiming at each annuity aggregate plan;
thereafter, a similarity between annuity collection plans can be determined based on a similarity matrix between annuity collection plans. Specifically, the similarity between the articles can be calculated using the following formula:
the term, | N (i) | is the number of users who like the annuity aggregate plan i, | N (i) N (j) | is the number of users who like the annuity aggregate plan i and the annuity aggregate plan j simultaneously, and denominator is the weight of the punishment annuity aggregate plans i and j, so that the possibility that the popular annuity aggregate plan is similar to a plurality of annuity aggregate plans is reduced.
In one embodiment of the invention, the method further comprises:
and S41, establishing a similarity matrix between the annuity set plans and normalizing the similarity matrix.
Specifically, in order to further improve the recommendation accuracy of the annuity aggregate plans, a similarity matrix between the annuity aggregate plans may be established and normalized, so that the similarity matrix may better express the similarity between the annuity aggregate plans.
Specifically, the similarity matrix is normalized by the maximum value using the following formula:
in particular, after determining the similarity between the annuity collection plans, the annuity plan products that the user may prefer may be determined based on the similarity between the user-selected annuity collection plan and other annuity plans. If the similarity between the annuity aggregate plan selected by the user and other annuity plans is higher, the user can be considered to have higher interest degree in the annuity aggregate plan in the recommended annuity aggregate plan list.
Specifically, the ranking of the annuity aggregate plans may be adjusted based on the interest level of the user in the annuity aggregate plan in the recommended annuity aggregate plan list, so that the annuity aggregate plan may more easily put the product in which the user is interested in the front position to recommend to the user, and the user may more easily obtain the annuity aggregate plan in which the user is interested.
In one embodiment of the invention, the method further comprises:
s51, reducing the sequence of the annual fund collection plans with high popularity in the recommended annual fund collection plan list, and/or improving the sequence of the annual fund collection plans with low popularity in the recommended annual fund collection plan list.
Specifically, in general, since a case in which a list of annual fund collection plans that tend to be highly recommended is likely to occur in the process of recommending an annual fund collection plan, a long-tailed exposure effect will be produced. In order to avoid the long tail exposure effect, the ranking of the high-popularity annuity aggregate plans in the recommended annuity aggregate plan list can be reduced according to actual needs, and/or the ranking of the low-popularity annuity aggregate plans in the recommended annuity aggregate plan list can be improved, so that single popular annuity aggregate plans are avoided.
According to the annuity product recommendation method, the characteristic vector of the user is generated based on the behavior characteristic information and the label characteristic information of the user, and the recommended annuity set plan list is determined based on the characteristic vector of the user and the product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence; the ranking of the annuity aggregate plans in the recommended annuity aggregate plan list is adjusted based on the similarity and/or popularity among the annuity aggregate plans to obtain a target annuity aggregate plan list and send the target annuity aggregate plan list to the user, the recommended annuity aggregate plan list preferred by the user can be obtained, the user can easily find the annuity aggregate plan meeting the preference of the user in the target annuity aggregate plan list, and the recommendation accuracy is high.
It should be noted that for simplicity of description, the method embodiments are shown as a series of combinations of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 3, a block diagram of a structure of a recommendation apparatus for annuity products provided in the embodiment of the present invention is shown, and specifically, the structure may include the following modules:
a user feature generation module 301, configured to generate a feature vector of a user based on behavior feature information and tag feature information of the user;
a recommending module 302, configured to determine a recommended annuity aggregate plan list based on the feature vector of the user and a product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence;
an adjusting module 303, configured to adjust the ranking of the annuity aggregation plans in the recommended annuity aggregation plan list based on similarity and/or popularity between the annuity aggregation plans to obtain a target annuity aggregation plan list, and send the target annuity aggregation plan list to the user.
Optionally, the recommending module includes:
and the model recommendation submodule is used for inputting the feature vector of the user and the product association table into a preset recommendation model and acquiring a recommendation annuity set plan list output by the recommendation model.
Optionally, the recommendation model is trained in the following manner:
the history acquisition module is used for acquiring history selection information for recording a user history selection annuity set plan;
a training set generating module, configured to generate a training set based on the feature vector of the user, the product association table, and the history selection information;
and the model training module is used for training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
Optionally, the recommendation module includes:
the similarity comparison submodule is used for comparing the similarity between the users based on the characteristic vectors of the users;
the association determination submodule is used for determining an annuity set plan associated with at least one user selected by other users similar to the user;
an association recommendation sub-module to determine at least one annuity aggregation plan associated with a product similar to the user-associated annuity aggregation plan based on the product association table;
and the list generation submodule is used for selecting at least one annuity set plan which is not selected by the user from the user related annuity set plans and the product related annuity set plans to generate a recommended annuity set plan list.
Optionally, the adjusting module includes:
the similarity comparison submodule is used for determining the similarity between the annuity set plans according to a similarity matrix between the annuity set plans;
the interest determination sub-module is used for determining the interest degree of the user in the annuity set plans in the recommended annuity set plan list based on the similarity between the annuity set plans;
and the adjusting sub-module is used for adjusting the sequence of the annuity set plan based on the interest degree.
Optionally, the method comprises:
and the normalization module is used for establishing a similarity matrix between the annuity set plans and carrying out normalization processing on the similarity matrix.
Optionally, the adjusting module includes:
and the sorting adjustment sub-module is used for reducing the sorting of the annual fund collection plans with high popularity in the recommended annual fund collection plan list and/or improving the sorting of the annual fund collection plans with low popularity in the recommended annual fund collection plan list.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
In addition, an electronic device is further provided in the embodiments of the present invention, as shown in fig. 4, and includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, where the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404,
a memory 403 for storing a computer program;
the processor 401, when executing the program stored in the memory 403, implements the following steps:
generating a feature vector of a user based on behavior feature information and label feature information of the user;
determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence;
and adjusting the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list based on the similarity and/or popularity of the annuity aggregate plans to obtain a target annuity aggregate plan list and sending the target annuity aggregate plan list to the user.
Optionally, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
and inputting the characteristic vector of the user and the product association table into a preset recommendation model, and acquiring a recommendation annuity set plan list output by the recommendation model.
Optionally, the recommendation model is obtained by training in the following manner:
acquiring historical selection information for recording a historical annual fund collection plan selected by a user;
generating a training set based on the feature vector of the user, the product association table and the historical selection information;
and training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
Optionally, the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table includes:
comparing similarity between users based on the feature vectors of the users;
for a user, determining an annuity collection plan associated with at least one user selected by other users similar to the user;
determining, based on the product association table, at least one product-associated annuity collection program similar to the user-associated annuity collection program;
and selecting at least one annual fund set plan not selected by the user from the annual fund set plans associated with the users and the annual fund set plans associated with the products to generate a recommended annual fund set plan list.
Optionally, the step of adjusting the ranking of the annuity collection plans in the recommended annuity collection plan list based on the similarity and popularity between the annuity collection plans includes:
determining the similarity between the annuity set plans according to a similarity matrix between the annuity set plans;
determining a degree of user interest in an annuity collection plan in the recommended annuity collection plan list based on similarity between the annuity collection plans;
adjusting the ranking of the annuity aggregation plan based on the level of interest.
Optionally, the method comprises:
and establishing a similarity matrix among the annuity set plans and carrying out normalization processing on the similarity matrix.
Optionally, the step of adjusting the ranking of the annuity aggregation plans in the recommended annuity aggregation plan list based on the similarity and popularity between the annuity aggregation plans includes:
decreasing the ranking of the annuity aggregate plans with high popularity in the recommended annuity aggregate plan list, and/or increasing the ranking of the annuity aggregate plans with low popularity in the recommended annuity aggregate plan list.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.
In yet another embodiment provided by the present invention, as shown in fig. 5, there is further provided a computer-readable storage medium 501, which stores instructions that, when run on a computer, cause the computer to execute the method for recommending annuity products described in the above embodiments.
In yet another embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for recommending annuity products described in the above embodiment.
In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, relational terms such as first and second, and the like 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. Also, 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.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the system embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method for recommending annuity products, comprising:
generating a feature vector of a user based on behavior feature information and label feature information of the user;
determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence;
and adjusting the sequence of the annuity aggregate plans in the recommended annuity aggregate plan list based on the similarity and/or popularity of the annuity aggregate plans to obtain a target annuity aggregate plan list and sending the target annuity aggregate plan list to the user.
2. The method of claim 1, wherein the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table comprises:
and inputting the characteristic vector of the user and the product association table into a preset recommendation model, and acquiring a recommendation annuity set plan list output by the recommendation model.
3. The method of claim 2, wherein the recommendation model is trained by:
acquiring historical selection information for recording a historical selection annuity set plan of a user;
generating a training set based on the feature vector of the user, the product association table and the historical selection information;
and training the recommendation model to be trained by adopting the training set to obtain the recommendation model.
4. The method according to claim 1 or 2, wherein the step of determining a recommended annuity collection plan list based on the feature vector of the user and a product association table comprises:
comparing similarity between users based on the feature vectors of the users;
for a user, determining an annuity collection plan associated with at least one user selected by other users similar to the user;
determining, based on the product association table, at least one product-associated annuity collection program similar to the user-associated annuity collection program;
and selecting at least one annual fund collection plan which is not selected by the user from the annual fund collection plans associated with the users and the annual fund collection plan associated with the product to generate a recommended annual fund collection plan list.
5. The method of claim 1, wherein the step of adjusting the ordering of annuity collection plans in the recommended annuity collection plan list based on similarity and popularity among annuity collection plans comprises:
determining the similarity between the annuity set plans according to a similarity matrix between the annuity set plans;
determining the interest degree of a user in the annuity collection plans in the recommended annuity collection plan list based on the similarity between the annuity collection plans;
adjusting the ranking of the annuity aggregation plan based on the level of interest.
6. The method of claim 5, wherein the method comprises:
and establishing a similarity matrix between the annuity set plans and carrying out normalization processing on the similarity matrix.
7. The method of claim 1, wherein the step of adjusting the ordering of annuity collection plans in the recommended annuity collection plan list based on similarity and popularity among annuity collection plans comprises:
decreasing the ranking of the annuity aggregate plans with high popularity in the recommended annuity aggregate plan list, and/or increasing the ranking of the annuity aggregate plans with low popularity in the recommended annuity aggregate plan list.
8. An annuity product recommendation device, the device comprising:
the user characteristic generation module is used for generating a characteristic vector of the user based on the behavior characteristic information and the label characteristic information of the user;
the recommending module is used for determining a recommended annuity set plan list based on the feature vector of the user and a product association table; wherein the recommended annuity aggregate plan list comprises at least one annuity aggregate plan arranged in sequence;
and the adjusting module is used for adjusting the sequence of the annuity set plans in the recommended annuity set plan list based on the similarity and/or popularity among the annuity set plans to obtain a target annuity set plan list and sending the target annuity set plan list to the user.
9. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
the memory is used for storing a computer program;
the processor, when executing a program stored on the memory, implementing the method of any of claims 1-7.
10. One or more computer-readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210446820.8A CN114741605A (en) | 2022-04-26 | 2022-04-26 | Method and device for recommending annuity products, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210446820.8A CN114741605A (en) | 2022-04-26 | 2022-04-26 | Method and device for recommending annuity products, electronic equipment and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114741605A true CN114741605A (en) | 2022-07-12 |
Family
ID=82284563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210446820.8A Pending CN114741605A (en) | 2022-04-26 | 2022-04-26 | Method and device for recommending annuity products, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114741605A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523976A (en) * | 2020-04-23 | 2020-08-11 | 京东数字科技控股有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
| CN112632385A (en) * | 2020-12-29 | 2021-04-09 | 中国平安人寿保险股份有限公司 | Course recommendation method and device, computer equipment and medium |
| CN112991025A (en) * | 2021-05-08 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Intelligent insurance recommendation method, system and equipment and computer readable storage medium |
| CN113282832A (en) * | 2021-06-10 | 2021-08-20 | 北京爱奇艺科技有限公司 | Search information recommendation method and device, electronic equipment and storage medium |
| CN113643103A (en) * | 2021-08-31 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Product recommendation method, device, equipment and storage medium based on user similarity |
-
2022
- 2022-04-26 CN CN202210446820.8A patent/CN114741605A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523976A (en) * | 2020-04-23 | 2020-08-11 | 京东数字科技控股有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
| CN112632385A (en) * | 2020-12-29 | 2021-04-09 | 中国平安人寿保险股份有限公司 | Course recommendation method and device, computer equipment and medium |
| CN112991025A (en) * | 2021-05-08 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Intelligent insurance recommendation method, system and equipment and computer readable storage medium |
| CN113282832A (en) * | 2021-06-10 | 2021-08-20 | 北京爱奇艺科技有限公司 | Search information recommendation method and device, electronic equipment and storage medium |
| CN113643103A (en) * | 2021-08-31 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Product recommendation method, device, equipment and storage medium based on user similarity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111079022B (en) | Personalized recommendation method, device, equipment and medium based on federal learning | |
| CN109118336B (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN107862022B (en) | Culture resource recommendation system | |
| US8560513B2 (en) | Searching for information based on generic attributes of the query | |
| CN105787055B (en) | Information recommendation method and device | |
| CN108885624B (en) | Information recommendation system and method | |
| CN109189990B (en) | Search word generation method and device and electronic equipment | |
| US20200364506A1 (en) | Article Recommendation Method and Apparatus, Computer Device, and Storage Medium | |
| US8660901B2 (en) | Matching of advertising sources and keyword sets in online commerce platforms | |
| CN108228745B (en) | Recommendation algorithm and device based on collaborative filtering optimization | |
| US9767409B1 (en) | Latent feature based tag routing | |
| CN111931055B (en) | Object recommendation method, object recommendation device and electronic equipment | |
| CN112818218B (en) | Information recommendation method, device, terminal equipment and computer readable storage medium | |
| US20190087859A1 (en) | Systems and methods for facilitating deals | |
| CN113077317A (en) | Item recommendation method, device and equipment based on user data and storage medium | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN111078997B (en) | Information recommendation method and device | |
| KR101621735B1 (en) | Recommended search word providing method and system | |
| CN111400516B (en) | Label determining method, electronic device and storage medium | |
| CN113282831A (en) | Search information recommendation method and device, electronic equipment and storage medium | |
| CN112163415A (en) | User intention identification method and device for feedback content and electronic equipment | |
| CN115794898B (en) | Financial information recommendation method and device, electronic equipment and storage medium | |
| CN110633408B (en) | Intelligent business information recommendation method and system | |
| CN114741605A (en) | Method and device for recommending annuity products, electronic equipment and readable medium | |
| CN116610853A (en) | Search recommendation method, search recommendation system, computer device, and storage medium |
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 |