Resource management product recommendation method and device, electronic device, and storage medium

Abstract

The present invention provides a resource management product recommendation method and device, electronic device, and storage medium, the method comprising: obtaining a resource data set including multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; generating an information recommendation list according to the resource data set and similarity calculation principle; wherein the information recommendation list indicates the probability that each object is not associated with a target resource management product in one or more resource management products and is associated with the target resource management product; and recommending resource management products to the target object using the information recommendation list. The solution provided by the present invention solves the technical problem in the related art that resource management products cannot be recommended to users in a personalized manner.

Description

Technical Field

[0001] The present invention relates to the field of big data processing, and in particular to a resource management product recommendation method and device, electronic equipment, and storage medium. Background Art

[0002] At present, credit card recommendations of some financial institutions are mainly made by business experts who combine business knowledge and understanding of the overall user group to give a recommendation to all users, resulting in the same recommendation results for everyone; at the same time, due to the limited number of recommended results, some credit cards that are less used may not appear in the recommendation results, resulting in these credit cards not being promoted and thus being buried. Summary of the invention

[0003] In view of the above problems, the present invention proposes a resource management product recommendation method and device, electronic device, and storage medium to at least solve the technical problem in the related art that resource management products cannot be recommended to users in a personalized manner.

[0004] According to a first aspect of the present invention, there is provided a method for recommending resource management products, comprising: obtaining a resource data set comprising a plurality of objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; generating an information recommendation list according to the resource data set and a similarity calculation principle; wherein the information recommendation list indicates that each object is not associated with a target resource management product among the one or more resource management products and has a probability of being associated with the target resource management product; and using the information recommendation list to recommend the resource management product to the target object.

[0005] Optionally, generating an information recommendation list based on the resource data set and similarity calculation principle includes: using the resource data set to calculate a first similarity between any object among the multiple objects and other objects; selecting any object among the multiple objects as a first object, and identifying a first resource management product that is not associated with the first object; selecting at least one second object from the multiple objects whose first similarity with the first object is greater than or equal to a first preset value and is associated with the first resource management product, and generating a first information recommendation list for the first object in a list form based on the resource management product associated with the second object and the corresponding first similarity as the information recommendation list.

[0006] Optionally, calculating the first similarity between any object among the multiple objects and other objects based on the resource data set includes: converting at least one user feature and at least one product feature corresponding to each object into corresponding feature values; and calculating the first similarity between any object among the multiple objects and other objects using the Jaccard similarity calculation principle and the feature values ​​corresponding to each object.

[0007] Optionally, using the information recommendation list to recommend the resource management product to the target object includes: when it is identified that the target object has not paid attention to any resource management product or enters the associated page corresponding to the resource management product for the first time, recommending the first information recommendation list to the target object.

[0008] Optionally, generating an information recommendation list according to the resource data set and similarity calculation principle includes: calculating the second similarity between any one of the one or more resource management products and other resource management products according to product characteristics corresponding to each resource management product in the resource data set; selecting any one of the multiple objects as a third object and any one of the one or more resource management products as a second resource management product, and if it is identified that the third object has most recently paid attention to the second resource management product, selecting the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; generating a second information recommendation list for the third object in list form based on the third resource management product and the second similarity corresponding to the third resource management product; generating a third information recommendation list as the information recommendation list by performing weighted calculation on the first information recommendation list and the second information recommendation list.

[0009] Optionally, the using the information recommendation list to recommend the resource management product to the target object includes: when it is identified that the target object has most recently paid attention to the second resource management product in history, recommending the third information recommendation list to the target object.

[0010] Optionally, the use of the information recommendation list to recommend the resource management product to the target object includes: when it is identified that the target object has entered the associated page corresponding to a fourth resource management product among the one or more resource management products for multiple times, selecting a preset fifth resource management product that has similarity with the fourth resource management product from the one or more resource management products; updating the information recommendation list using the fifth resource management product; and recommending the updated information recommendation list to the target object.

[0011] According to the second aspect of the present invention, there is also provided a resource management product recommendation device, comprising: an acquisition module, used to acquire a resource data set containing multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; a generation module, used to generate an information recommendation list based on the resource data set and a similarity calculation principle; wherein the information recommendation list indicates that each object is not associated with a target resource management product among the one or more resource management products and there is a probability that it is associated with the target resource management product; and a recommendation module, used to use the information recommendation list to recommend the resource management product to the target object.

[0012] Optionally, the generation module includes: a first calculation unit, used to calculate the first similarity between any object among the multiple objects and other objects using the resource data set; an identification unit, used to select any object among the multiple objects as a first object, and identify a first resource management product not associated with the first object; a first generation unit, used to select at least one second object from the multiple objects, whose first similarity with the first object is greater than or equal to a first preset value and is associated with the first resource management product, and generate a first information recommendation list for the first object in a list form based on the resource management product associated with the second object and the corresponding first similarity, as the information recommendation list.

[0013] Optionally, the first calculation unit includes: a conversion subunit, used to convert at least one user feature and at least one product feature corresponding to each object into corresponding feature values; a calculation subunit, used to calculate the first similarity between any object among the multiple objects and other objects using the Jaccard similarity calculation principle and the feature values ​​corresponding to each object.

[0014] Optionally, the recommendation module includes: a first recommendation unit, configured to recommend the first information recommendation list to the target object when it is identified that the target object has not paid attention to any resource management product or enters the associated page corresponding to the resource management product for the first time.

[0015] Optionally, the generation module includes: a second calculation unit, used to calculate the second similarity between any one of the one or more resource management products and other resource management products based on the product characteristics corresponding to each resource management product in the resource data set; a first selection unit, used to select any one of the multiple objects as a third object and any one of the one or more resource management products as a second resource management product, and if it is identified that the third object has most recently paid attention to the second resource management product in history, select the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; a second generation unit, used to generate a second information recommendation list for the third object in a list form based on the third resource management product and the second similarity corresponding to the third resource management product; a third generation unit, used to generate a third information recommendation list as the information recommendation list by performing weighted calculation on the first information recommendation list and the second information recommendation list.

[0016] Optionally, the recommendation module includes: a second recommendation unit, configured to recommend the third information recommendation list to the target object when it is identified that the target object has most recently paid attention to the second resource management product in history.

[0017] Optionally, the recommendation module includes: a second selection unit, used to select a preset fifth resource management product that has similarity with the fourth resource management product from the one or more resource management products when it is identified that the target object has entered the associated page corresponding to the fourth resource management product among the one or more resource management products for multiple times; an updating unit, used to update the information recommendation list using the fifth resource management product; and a third recommendation unit, used to recommend the updated information recommendation list to the target object.

[0018] According to a third aspect of the present invention, there is further provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0019] According to a fourth aspect of the present invention, there is further provided a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above-mentioned device embodiments when running.

[0020] The technical solution provided by the present invention mines the preferences and needs of each object by collecting multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; then, the similarity calculation principle is adopted to use user features and product features to calculate the probability of each object being associated with any resource management product that has not been associated with the object in the past, thereby generating a personalized resource management product recommendation list for each object; and the resource management product recommendation list is used to recommend resource management products to the target object, so as to achieve a thousand faces for a thousand people, and to recommend resource management products that the target object is interested in or has a need for. The solution provided by the present invention solves the technical problem in the related art that it is impossible to recommend resource management products to users in a personalized manner, such as recommending credit cards.

[0021] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below.

[0022] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0024] Figure 1 is a flow chart of a resource management product recommendation method provided according to an embodiment of the present invention;

[0025] Figure 2 is a flow chart of a credit card recommendation method provided according to an embodiment of the present invention;

[0026] Figure 3 is a structural block diagram of a resource management product recommendation device provided according to an embodiment of the present invention;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such use is interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0030] In order to solve the technical problems existing in the related art, a resource management product recommendation method is provided in this embodiment. The technical scheme of the present invention and how the technical scheme of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0031] Figure 1 is a flow chart of a resource management product recommendation method provided according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0032] Step S102, obtaining a resource data set including a plurality of objects, a user feature corresponding to each object, one or more resource management products historically associated with each object, and a product feature corresponding to each resource management product;

[0033] In an optional example of this embodiment, the user characteristics corresponding to each object may include the user's interest preferences, attributes, etc. The interest preferences may include petting cats and dogs, food, cars, watching TV series and movies, credit card appearance, shopping, celebrities, travel, games, etc., and attributes may include age, gender, education, marital status, RV, occupation, annual income, life stage (such as employed, student, unemployed, retired), etc.; the resource management product is a credit card, and the product characteristics may include the attributes, functions, classification, and affiliated institutions of the credit card, such as the number of credit cards, the bank to which it belongs, functions (such as online shopping discounts, travel discounts, overseas consumption, gas discounts, food discounts, video membership gifts, shopping discounts, airline mileage redemption), types (such as standard cards, ordinary cards, gold cards, platinum cards, co-branded cards), etc.

[0034] By collecting the above-mentioned user characteristics and product characteristics, we can accurately analyze the user's preferences and needs, and proactively recommend credit cards that the user is interested in or has needs for, so that the recommendation results are tailored to each individual.

[0035] Step S104, generating an information recommendation list according to the resource data set and the similarity calculation principle; wherein the information recommendation list indicates the probability that each object is not associated with a target resource management product in one or more resource management products and is associated with the target resource management product;

[0036] In this embodiment, the Jaccard similarity calculation principle is preferably used to compare the similarities and differences between finite sample sets. The larger the Jaccard value, the higher the similarity, and the smaller the Jaccard value, the lower the similarity. Through this embodiment, it is possible to accurately identify resource management products associated with similar users of any object but not associated with the object, as well as the probability that the object will be associated with these resource management products, and finally form a corresponding resource management product recommendation list (and the above-mentioned information recommendation list).

[0037] Step S106: recommend resource management products to the target object using the information recommendation list.

[0038] In this embodiment, by performing collaborative filtering on the user features of the target object and the related products, personalized recommendations of resource management products are made to the target object.

[0039] The resource management product recommendation method provided in the embodiment of the present invention mines the preferences and needs of each object by collecting multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; then, the similarity calculation principle is adopted to use user features and product features to calculate the probability of each object being associated with any resource management product that has not been associated with the object in the past, thereby generating a personalized resource management product recommendation list for each object; and the resource management product recommendation list is used to recommend resource management products to the target object, so as to achieve a personalized recommendation for each target object. The solution provided by the present invention solves the technical problem in the related art that resource management products cannot be recommended to users in a personalized manner, such as recommending credit cards.

[0040] In a possible implementation of the present case, the above-mentioned step S104 includes: using the resource data set to calculate the first similarity between any object among multiple objects and other objects; selecting any object among the multiple objects as the first object, and identifying the first resource management product that is not associated with the first object; selecting at least one second object from the multiple objects whose first similarity with the first object is greater than or equal to a first preset value and is associated with the first resource management product, and generating a first information recommendation list for the first object in a list form based on the resource management product associated with the second object and the corresponding first similarity, as an information recommendation list.

[0041] Among them, calculating the first similarity between any object among multiple objects and other objects based on the resource data set specifically includes: converting at least one user feature and at least one product feature corresponding to each object into corresponding feature values; using the Jaccard similarity calculation principle and the feature values ​​corresponding to each object to calculate the first similarity between any object among multiple objects and other objects.

[0042] In an example of this embodiment, by calculating the Jaccard similarity (ie, the first similarity mentioned above) between various objects, a first information recommendation list is formed as a resource management product recommendation list.

[0043] For example, user attributes, preferences, and historical card application information are converted into numerical values, such as gender - male: 1, female: 0, education - primary school: 0, junior high school: 1, high school: 2, university: 3, master's: 4, doctorate: 5, and so on. Other information is processed in the same way. The feature value processing results corresponding to user characteristics and product characteristics are shown in Table 1:

[0044] Table 1:

[0045]

[0046] In another example, if the resource data set corresponding to user A is S1 = {1, 3, 4, 5, 7, 8, 9}, and the resource data set corresponding to user B is S2 = {1, 2, 3, 5, 6, 8}, then S1∩S2 = {1, 3, 5, 8}, S1∪S2 = {1, 2, 3, 4, 5, 6, 7, 8, 9}, using Jaccard similarity calculation formula (1):

[0047]

[0048] The similarity between S1 and S2 is then obtained to be 4 / 9 (ie, the first similarity mentioned above), ie, the Jaccard similarity between user A and user B.

[0049] Further, resource management products associated with similar users but not associated with the target user are formed into a first information recommendation list for the target user; optionally, a preset number of resource management products are selected according to the similarity sorting to form a resource management product recommendation list.

[0050] For example, taking credit cards as an example, assuming that the user sample set (i.e., the above resource data set) has 5 users, the similarity between user A and user B is 0.9 (i.e., the above first similarity), and the credit cards that A has not applied for but B has applied for are Card 1, Card 2, and Card 3; among them, the similarity between A and C is 0.85, and the credit cards that A has not applied for but C has applied for are Card 3, Card 4, Card 5, and Card 6; the similarity between A and D is 0.8, and the credit cards that A has not applied for but D has applied for are Card 7, Card 8, Card 9, and Card 10; the similarity between A and E is 0.7, and the credit cards that A has not applied for but E has applied for are Card 5, Card 11, and Card 12; then the recommendation list 1 (i.e., the above first information recommendation list) of user A (the above first object) is [Card 1, Card 2, Card 3, Card 4, Card 5, Card 6, Card 7, Card 8, Card 9, Card 10];

[0051] The same is true for other users, and finally a collection table of resource management product recommendation lists for all users is formed, as shown in Table 2:

[0052] Table 2:

[0053]

[0054] The numbers in Table 2 are Jaccard similarities. If the similarities are the same, the cards are randomly selected.

[0055] According to the above embodiment, when it is identified that the target object has not followed any resource management product or has entered the associated page corresponding to the resource management product for the first time, the first information recommendation list is recommended to the target object. For example, the target object is a user who currently enters the card application page (i.e., the associated page), that is, when a user enters the card application page, the above first information recommendation list is recommended to the target object, and the user's recommendation list is extracted from the above first information recommendation list set.

[0056] In another possible implementation of the present case, the above-mentioned step S104 includes: calculating the second similarity between any resource management product in one or more resource management products and other resource management products based on the product characteristics corresponding to each resource management product in the resource data set; selecting any object among multiple objects as a third object and any resource management product among one or more resource management products as a second resource management product, if it is identified that the third object has most recently paid attention to the second resource management product in history, selecting the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; generating a second information recommendation list for the third object in a list form based on the third resource management product and the second similarity corresponding to the third resource management product; generating a third information recommendation list as an information recommendation list by performing weighted calculation on the first information recommendation list and the second information recommendation list.

[0057] Taking credit cards as an example, we collect data on the functions, banks and types of each credit card. Among them, the functions of credit cards include online shopping discounts, travel discounts, overseas consumption, gas discounts, food discounts, video membership gifts, shopping discounts, airline mileage redemption, etc. The types of credit cards include standard cards, ordinary cards, gold cards, platinum cards, co-branded cards, etc. The affiliated institutions include China Construction Bank, China Merchants Bank, etc.

[0058] Furthermore, the product features are converted into corresponding feature values, and then the Jaccard similarity between credit cards is calculated using the Jaccard similarity calculation principle (i.e., the second similarity mentioned above).

[0059] Taking credit cards as an example, the feature value processing method of the product features corresponding to credit cards is the same as the method for calculating the similarity between users. The feature value processing results corresponding to product features are shown in Table 3:

[0060] Table 3:

[0061] Card Name Function type Bank Card 1 1 2 1 Card 2 2 3 3 …… …… …… ……

[0062] Preferably, the credit cards with high similarity to the credit card most recently clicked in the history of any object are selected as the recommendation list. For example, if the similarity between card 1 and card 2 is 0.9, the similarity between card 1 and card 3 is 0.85, the similarity between card 1 and card 4 is 0.8, etc., then the similar card list is as shown in Table 4:

[0063] Table 4:

[0064]

[0065] Preferably, the order of the cards in the similar card list is sorted by similarity.

[0066] Furthermore, if user A clicked card 1 (ie, the second resource management product) last time, user A's recommendation list 2 (ie, the second information recommendation list) is as shown in Table 5:

[0067] Table 5:

[0068]

[0069]

[0070] Preferably, the order of the cards is sorted by similarity; for example, take 10 credit cards to form a list.

[0071] Furthermore, the above step S106 specifically includes: when it is identified that the target object has paid attention to the second resource management product most recently in history, recommending a third information recommendation list to the target object.

[0072] In one example, if the user has a previous click record, a weighted calculation is performed on the above Table 2 and Table 5 to obtain a recommendation list 3 (ie, the above third information recommendation list) as the final recommendation result.

[0073] In an optional example, the results of recommendation list 3 = recommendation list 1*0.4 + recommendation list 2*0.6 are taken as the top 10); in this example, the weights in recommendation list 3 = recommendation list 1*0.4 + recommendation list 2*0.6 are determined based on business experience.

[0074] For example, if user A has a last click record, recommendation list 1 is {card 1: 0.9, card 2: 0.9, card 3: 0.9, card 4: 0.8, card 5: 0.85, card 6: 0.85, card 7: 0.8, card 8: 0.8, card 9: 0.8, card 10: 0.8};

[0075] Recommended list 2 is {card 2: 0.9, card 3: 0.85, card 4: 0.8, card 5: 0.8, card 9: 0.79, card 6: 0.77, card 7: 0:73, card 8, 0.71, card 9: 0.7, card 10: 0.69};

[0076] The calculation process of recommendation list 3 is: card 1: 0.9*0.4, card 2: 0.9*0.4+0.9*0.6, card 3: 0.9*0.4+0.85*0.6; and so on, calculate the values ​​of other cards, and finally sort the values ​​of each card, and take the first 10 cards as recommendation list 3.

[0077] Through the above embodiment, the above first information recommendation list, second information recommendation list and third information recommendation list can be generated offline, and the resource management products can be recommended to the target object using the offline constructed first information recommendation list, second information recommendation list or third information recommendation list.

[0078] In another optional embodiment of the present case, when it is identified that the target object has entered the associated page corresponding to a fourth resource management product in one or more resource management products for multiple times, a preset fifth resource management product having similarity with the fourth resource management product is selected from the one or more resource management products; the fifth resource management product is used to update the information recommendation list; and the updated information recommendation list is recommended to the target object.

[0079] In this embodiment, the offline constructed recommendation list is adjusted in real time to meet the needs of users in a timely manner. In one example, based on the real-time clicks of users after entering the card application page, if the same credit card is clicked three times, the three most similar credit cards to the credit card are used to replace the last three in the original recommendation list, and the updated information recommendation list is recommended to the target user, thereby achieving real-time update of the recommendation list and improving the accuracy of the recommendation.

[0080] The embodiment of the present invention starts from the two directions of real-time recommendation and offline recommendation, combines business rules (i.e., whether the user enters the associated page of the resource management product for the first time or has never paid attention to the resource management product) and collaborative filtering algorithm, and provides a personalized credit card list for each user who intends to apply for a credit card, thereby improving the user experience and increasing the number of credit card applications.

[0081] The following is a further description of the embodiment of the present invention in conjunction with the process of a specific embodiment:

[0082] Figure 2 is a flow chart of a credit card recommendation method provided according to an embodiment of the present invention. Figure 2 As shown, the following steps are included:

[0083] Step S201, obtaining user attributes, preferences, and historical card application data;

[0084] Step S202, using Jaccard similarity to calculate the similarity between users, and then forming a recommendation list 1;

[0085] Step S203, determining whether the target user is entering the card application page for the first time; if so, recommending recommendation list 1 to the target user; otherwise, executing step S204, recommending recommendation list 3;

[0086] Step S204, based on the attributes, types and other features of the credit cards that the user has historically followed, the similarity between the credit cards is calculated using Jaccard similarity to form recommendation list 2; then recommendation list 1*0.4+recommendation list 2*0.6 is used to obtain recommendation list 3.

[0087] Through the above implementation steps, different credit card recommendation lists are provided for different users based on the user's interest preferences and attributes, the credit card's attributes, functions, classifications and historical clicks, whether it is the first time for the user to enter the card application page and the collaborative filtering algorithm, so as to meet the preferences and needs of different users, enhance the user's sense of inspection, increase the overall credit card application volume, and promote unpopular credit cards.

[0088] Based on the resource management product recommendation method provided in each of the above embodiments, based on the same inventive concept, a resource management product recommendation device is also provided in this embodiment, which is used to implement the above embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0089] Figure 3 is a structural block diagram of a resource management product recommendation device provided according to an embodiment of the present invention, such as Figure 3 As shown, the device includes: an acquisition module 30, used to acquire a resource data set including multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; a generation module 32, connected to the above-mentioned acquisition module 30, used to generate an information recommendation list based on the resource data set and the similarity calculation principle; wherein the information recommendation list indicates the probability that each object is not associated with a target resource management product in one or more resource management products and has an associated target resource management product; a recommendation module 34, connected to the above-mentioned generation module 32, used to use the information recommendation list to recommend resource management products to the target object.

[0090] Optionally, the generation module 32 includes: a first calculation unit, used to calculate the first similarity between any object among multiple objects and other objects using the resource data set; an identification unit, used to select any object among multiple objects as the first object, and identify a first resource management product that is not associated with the first object; a first generation unit, used to select at least one second object from the multiple objects whose first similarity with the first object is greater than or equal to a first preset value and is associated with the first resource management product, and generate a first information recommendation list for the first object in a list form based on the resource management product associated with the second object and the corresponding first similarity, as an information recommendation list.

[0091] Optionally, the first calculation unit includes: a conversion subunit, used to convert at least one user feature and at least one product feature corresponding to each object into corresponding feature values; and a calculation subunit, used to calculate the first similarity between any object among multiple objects and other objects using the Jaccard similarity calculation principle and the feature values ​​corresponding to each object.

[0092] Optionally, the recommendation module 34 includes: a first recommendation unit, which is used to recommend a first information recommendation list to the target object when it is identified that the target object has not paid attention to any resource management product or enters the associated page corresponding to the resource management product for the first time.

[0093] Optionally, the generation module 32 includes: a second calculation unit, used to calculate the second similarity between any resource management product in one or more resource management products and other resource management products based on the product characteristics corresponding to each resource management product in the resource data set; a first selection unit, used to select any object in multiple objects as a third object and any resource management product in one or more resource management products as a second resource management product, if it is identified that the third object has most recently paid attention to the second resource management product in history, select the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; a second generation unit, used to generate a second information recommendation list for the third object in a list form based on the third resource management product and the second similarity corresponding to the third resource management product; a third generation unit, used to generate a third information recommendation list as an information recommendation list by performing weighted calculation on the first information recommendation list and the second information recommendation list.

[0094] Optionally, the recommendation module 34 includes: a second recommendation unit, configured to recommend a third information recommendation list to the target object when it is identified that the target object has most recently paid attention to the second resource management product in history.

[0095] Optionally, the recommendation module 34 includes: a second selection unit, used to select a preset fifth resource management product that has similarity with the fourth resource management product from one or more resource management products when it is identified that the target object has entered the associated page corresponding to the fourth resource management product in one or more resource management products for multiple times; an updating unit, used to update the information recommendation list using the fifth resource management product; and a third recommendation unit, used to recommend the updated information recommendation list to the target object.

[0096] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0097] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0098] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0099] S1, obtaining a resource data set including multiple objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product;

[0100] S2, generating an information recommendation list based on the resource data set and similarity calculation principle;

[0101] The information recommendation list indicates the probability that each object is not associated with a target resource management product in one or more resource management products and is associated with a target resource management product;

[0102] S3, using the information recommendation list to recommend resource management products to the target object.

[0103] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0104] Based on the above Figure 1 The method shown and Figure 3 In order to achieve the above-mentioned purpose, the embodiment of the present invention also provides an electronic device, such as Figure 4As shown, the system includes a memory 42 and a processor 41, wherein the memory 42 and the processor 41 are both arranged on a bus 43. The memory 42 stores a computer program, and the processor 41 executes the computer program to realize Figure 1 The recommended approach for resource management products shown.

[0105] Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a memory (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of the present invention.

[0106] Optionally, the device may also be connected to a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0107] Those skilled in the art will appreciate that the structure of an electronic device provided in this embodiment does not limit the physical device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0108] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0109] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0110] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A resource management product recommendation method, characterized in that: include: Obtaining a resource data set including a plurality of objects, a user feature corresponding to each object, one or more resource management products historically associated with each object, and a product feature corresponding to each resource management product; Generate an information recommendation list according to the resource data set and the similarity calculation principle; wherein the information recommendation list indicates that each object is not associated with a target resource management product among the one or more resource management products and has a probability of being associated with the target resource management product; Recommending the resource management product to the target object using the information recommendation list; Generating the information recommendation list according to the resource data set and the similarity calculation principle includes: Calculating a first similarity between any object in the plurality of objects and other objects using the resource data set; selecting any one of the plurality of objects as a first object, and identifying a first resource management product that is not associated with the first object; Selecting at least one second object from the multiple objects, the first similarity between which and the first object is greater than or equal to a first preset value and which is associated with the first resource management product, and generating a first information recommendation list of the first object in a list form based on the resource management products associated with the second object and the corresponding first similarity, as the information recommendation list; Generating the information recommendation list according to the resource data set and the similarity calculation principle includes: Calculate a second similarity between any resource management product in the one or more resource management products and other resource management products according to product features corresponding to each resource management product in the resource data set; Selecting any one of the multiple objects as a third object and any one of the one or more resource management products as a second resource management product, and if it is identified that the third object has most recently paid attention to the second resource management product, selecting the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; generating a second information recommendation list of the third object in a list form based on the third resource management product and the second similarity corresponding to the third resource management product; A third information recommendation list is generated by performing weighted calculation on the first information recommendation list and the second information recommendation list as the information recommendation list.

2. The method according to claim 1, characterized in that Calculating the first similarity between any object in the plurality of objects and other objects according to the resource data set includes: Converting at least one user feature and at least one product feature corresponding to each object into corresponding feature values; The first similarity between any object in the multiple objects and other objects is calculated by using the Jaccard similarity calculation principle and the feature values ​​corresponding to each object.

3. The method according to claim 1, characterized in that The recommending the resource management product to the target object by using the information recommendation list includes: When it is identified that the target object has not paid attention to any resource management product or enters the associated page corresponding to the resource management product for the first time, the first information recommendation list is recommended to the target object.

4. The method according to claim 1, characterized in that: The recommending the resource management product to the target object by using the information recommendation list includes: When it is identified that the target object has paid attention to the second resource management product most recently in history, the third information recommendation list is recommended to the target object.

5. The method according to claim 1, characterized in that The recommending the resource management product to the target object by using the information recommendation list includes: When it is identified that the target object has entered the associated page corresponding to the fourth resource management product among the one or more resource management products for multiple times, a preset fifth resource management product having a similarity to the fourth resource management product is selected from the one or more resource management products; Updating the information recommendation list using the fifth resource management product; Recommend the updated information recommendation list to the target object.

6. A resource management product recommendation device, characterized in that: include: An acquisition module, used to acquire a resource data set including a plurality of objects, user features corresponding to each object, one or more resource management products historically associated with each object, and product features corresponding to each resource management product; A generation module, used to generate an information recommendation list according to the resource data set and the similarity calculation principle; wherein the information recommendation list indicates that each object is not associated with a target resource management product among the one or more resource management products and has a probability of being associated with the target resource management product; A recommendation module, used to recommend the resource management product to the target object using the information recommendation list; A generation module is specifically used to calculate a first similarity between any object among the multiple objects and other objects using the resource data set; select any object among the multiple objects as a first object, and identify a first resource management product that is not associated with the first object; select at least one second object from the multiple objects whose first similarity with the first object is greater than or equal to a first preset value and is associated with the first resource management product, and generate a first information recommendation list of the first object in a list form based on the resource management product associated with the second object and the corresponding first similarity as the information recommendation list; A generation module is specifically used to calculate the second similarity between any resource management product among the one or more resource management products and other resource management products according to the product characteristics corresponding to each resource management product in the resource data set; select any object among the multiple objects as a third object and any resource management product among the one or more resource management products as a second resource management product, and if it is recognized that the third object has paid attention to the second resource management product for the most recent time in history, select the third resource management product when the second similarity between the third object and the second resource management product is greater than or equal to a second preset value; generate a second information recommendation list for the third object in a list form based on the third resource management product and the second similarity corresponding to the third resource management product; and generate a third information recommendation list as the information recommendation list by performing weighted calculation on the first information recommendation list and the second information recommendation list.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images