Virtual resource object recommendation method and device, computer equipment and storage medium

Abstract

The invention relates to a virtual resource object recommendation method and device, computer equipment and a storage medium, which can be used in the financial field or other fields. The method comprises the following steps: in response to a virtual resource object recommendation request for a to-be-recommended user, detecting whether the to-be-recommended user is associated with a historical virtual resource interaction behavior; under the condition that the to-be-recommended user is not associated with the historical virtual resource interaction behavior, asymmetry evaluation values, corresponding to other virtual resource objects, of the current virtual resource object in a preset virtual resource object set are obtained; and performing summation processing on the asymmetry evaluation values of the current virtual resource object corresponding to the other virtual resource objects, and recommending the current virtual resource object to the to-be-recommended user under the condition that a summation result meets a preset condition. By adopting the method, the accuracy degree of virtual resource object recommendation can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of information recommendation, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for recommending virtual resource objects. Background Art

[0002] With the development of information recommendation technology, a recommendation technology for virtual resource objects has emerged. The virtual resource object can be a financial product. By obtaining the correlation between the user and the virtual resource object, the virtual resource object with the greatest relevance to the user can be recommended to the user from a variety of virtual resource objects.

[0003] In the conventional technology, the above recommendation process relies on the user's historical behavior towards virtual resource objects to determine the user's user preference, thereby screening out the most relevant virtual resource objects based on the user preference. However, in the case where virtual resource objects need to be recommended to new users, due to the lack of the new user's historical behavior, it is impossible to determine the user preference based on the user's historical behavior, and then implement the recommendation of virtual resource objects. The current virtual resource object recommendation method for new users usually randomly screens out a part of the virtual resource objects for recommendation, so the accuracy of the recommended virtual resource objects is low. Summary of the invention

[0004] Based on this, it is necessary to provide a virtual resource object recommendation method, apparatus, computer device, computer-readable storage medium and computer program product that can improve the accuracy of recommended virtual resource objects in response to the above technical problems.

[0005] In a first aspect, the present application provides a virtual resource object recommendation method, the method comprising:

[0006] In response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0007] In the case where the user to be recommended is not associated with any historical virtual resource interaction behavior, obtaining asymmetric evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0008] The asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed up, and when the summation result meets a preset condition, the current virtual resource object is recommended to the user to be recommended.

[0009] In one of the embodiments, the method of obtaining an asymmetry evaluation value of a current virtual resource object corresponding to each other virtual resource object in a preset set of virtual resource objects includes: obtaining a preset virtual resource object attribute, and a first attribute quantization value of the current virtual resource object for each of the virtual resource object attributes; obtaining a second attribute quantization value of a target other virtual resource object for each of the virtual resource object attributes; the target other virtual resource object is any other virtual resource object; comparing the first attribute quantization value and the second attribute quantization value of each of the virtual resource object attributes, and obtaining sub-asymmetry evaluation values ​​corresponding to each of the virtual resource object attributes according to the comparison result; and obtaining an asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object according to each of the sub-asymmetry evaluation values.

[0010] In one of the embodiments, the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource objects is obtained based on each of the sub-asymmetry evaluation values, including: obtaining the importance weight corresponding to each of the virtual resource object attributes that matches the user to be recommended; using the importance weight corresponding to each of the virtual resource object attributes, performing weighted summation processing on the sub-asymmetry evaluation values ​​corresponding to each of the virtual resource object attributes, to obtain the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource objects.

[0011] In one of the embodiments, the obtaining of importance weights corresponding to the attributes of each virtual resource object that matches the user to be recommended includes: obtaining user attribute information of the user to be recommended, and obtaining a recommended user type of the user to be recommended based on the user attribute information; obtaining a target importance weight set corresponding to the recommended user type based on a predetermined correspondence between the user type and the importance weight set; and using the importance weights corresponding to the attributes of each virtual resource object in the target importance weight set as the importance weights corresponding to the attributes of each virtual resource object that matches the user to be recommended.

[0012] In one embodiment, the sub-asymmetry evaluation value includes: a first sub-asymmetry evaluation value, a second sub-asymmetry evaluation value and a third sub-asymmetry evaluation value; wherein, the first sub-asymmetry evaluation value is greater than the second sub-asymmetry evaluation value, and the second sub-asymmetry evaluation value is greater than the third sub-asymmetry evaluation value; the sub-asymmetry evaluation value corresponding to each of the virtual resource object attributes is obtained according to the comparison result, including: obtaining the current virtual resource object attribute; the current virtual resource object attribute is any one of the virtual resource object attributes; the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is better than the In the case of the target other virtual resource object, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the first sub-asymmetry evaluation value; in the case of the comparison result corresponding to the current virtual resource object attribute, indicating that the current virtual resource object is the same as the target other virtual resource object, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the second sub-asymmetry evaluation value; in the case of the comparison result corresponding to the current virtual resource object attribute, indicating that the current virtual resource object is inferior to the target other virtual resource object, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the third sub-asymmetry evaluation value.

[0013] In one of the embodiments, when the sum result satisfies a preset condition, recommending the current virtual resource object to the user to be recommended includes: obtaining a preset asymmetry evaluation threshold; and when the sum result is greater than the preset asymmetry evaluation threshold, recommending the current virtual resource object to the user to be recommended.

[0014] In a second aspect, the present application further provides a virtual resource object recommendation device, the device comprising:

[0015] A recommendation request response module, configured to respond to a virtual resource object recommendation request for a user to be recommended, and detect whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0016] an asymmetry evaluation module, for obtaining, when the user to be recommended is not associated with any historical virtual resource interaction behavior, an asymmetry evaluation value of a current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0017] The resource object recommendation module is used to sum the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object, and recommend the current virtual resource object to the user to be recommended when the summation result meets a preset condition.

[0018] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0019] In response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0020] In the case where the user to be recommended is not associated with any historical virtual resource interaction behavior, obtaining asymmetric evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0021] The asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed up, and when the summation result meets a preset condition, the current virtual resource object is recommended to the user to be recommended.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0023] In response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0024] In the case where the user to be recommended is not associated with any historical virtual resource interaction behavior, obtaining asymmetric evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0025] The asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed up, and when the summation result meets a preset condition, the current virtual resource object is recommended to the user to be recommended.

[0026] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0027] In response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0028] In the case where the user to be recommended is not associated with any historical virtual resource interaction behavior, obtaining asymmetric evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0029] The asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed up, and when the summation result meets a preset condition, the current virtual resource object is recommended to the user to be recommended.

[0030] The above-mentioned virtual resource object recommendation method, device, computer equipment, storage medium and computer program product detect whether the user to be recommended is associated with historical virtual resource interaction behavior by responding to a virtual resource object recommendation request for the user to be recommended; when the user to be recommended is not associated with historical virtual resource interaction behavior, obtain the asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object; the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed, and when the summation result meets the preset conditions, the current virtual resource object is recommended to the user to be recommended. When recommending a virtual resource object to a user to be recommended, the present application can first detect whether the user to be recommended has any associated historical virtual resource interaction behavior. If not, the asymmetry evaluation value between any current virtual resource object contained in the virtual resource object set and other virtual resource objects in the set except the current virtual resource object is determined, and the asymmetry evaluation values ​​of each other virtual resource object are summed up, and when the summation result meets the preset conditions, the current virtual resource object is recommended to the user to be recommended. Compared with the prior art in which a part of virtual resource objects is randomly selected for recommendation, the present application can recommend virtual resource objects based on the asymmetry evaluation values ​​between the current virtual resource object and other virtual resource objects, thereby improving the accuracy of virtual resource object recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a flow chart of a virtual resource object recommendation method in one embodiment;

[0032] Figure 2 A schematic diagram of a process for obtaining an asymmetry evaluation value in one embodiment;

[0033] Figure 3 A schematic diagram of a process for obtaining importance weights in one embodiment;

[0034] Figure 4 It is a structural block diagram of a virtual resource object recommendation device in one embodiment;

[0035] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] In one embodiment, Figure 1 As shown, a virtual resource object recommendation method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0038] Step S101 : in response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with any historical virtual resource interaction behavior.

[0039] Among them, the user to be recommended refers to the user who needs to perform virtual resource objects, and the virtual resource object recommendation request is a recommendation request for recommending virtual resource objects to the user to be recommended, and the historical virtual resource interaction behavior refers to the virtual resource object interaction behavior that the user to be recommended has performed.

[0040] Specifically, when it is necessary to recommend a virtual resource object to the user to be recommended, a virtual resource object recommendation request for the user to be recommended can be triggered to the server, and the server can respond to the request and detect whether the user to be recommended has ever performed any virtual resource object interaction behavior, that is, detect whether the user to be recommended is associated with any historical virtual resource interaction behavior.

[0041] Step S102, when the user to be recommended is not associated with any historical virtual resource interaction behavior, obtain the asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object in the preset virtual resource object set; the current virtual resource object is any virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object.

[0042] The asymmetry evaluation value is an evaluation value used to evaluate the asymmetry between the current virtual resource object and each other virtual resource object, and the current virtual resource object can be any virtual resource object in the virtual resource object set, and other virtual resource objects are virtual resource objects in the virtual resource object set other than the current virtual resource object. In this embodiment, the virtual resource object set can be a set composed of multiple virtual resource objects, for example, it can be a financial product set, and the set can include multiple virtual resource objects, that is, multiple financial products, namely financial product A, financial product B and financial product C. If financial product A is used as the current virtual resource object, then financial product B and financial product C can be used as other virtual resource objects. Similarly, if financial product B is used as the current virtual resource object, then financial product A and financial product C can be used as other virtual resource objects.

[0043] Specifically, if the detected user to be recommended is not associated with a historical virtual resource interaction behavior, that is, the user to be recommended has never performed virtual resource object interaction, then the asymmetry evaluation value of each current virtual resource object corresponding to each other virtual resource object can be calculated from the preset virtual resource object set. For example, the virtual resource object set may include virtual resource object A, virtual resource object B, and virtual resource object C, and the server can respectively calculate the asymmetry evaluation value of virtual resource object A and virtual resource object B, the asymmetry evaluation value of virtual resource object A and virtual resource object C, the asymmetry evaluation value of virtual resource object B and virtual resource object A, the asymmetry evaluation value of virtual resource object B and virtual resource object C, the asymmetry evaluation value of virtual resource object C and virtual resource object A, and the asymmetry evaluation value of virtual resource object C and virtual resource object B.

[0044] Step S103, summing up the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object, and recommending the current virtual resource object to the user to be recommended when the summation result meets a preset condition.

[0045] After obtaining the asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object, the server can also sum the above asymmetry evaluation values. Taking virtual resource object A as the current virtual resource object as an example, the server can sum the asymmetry evaluation values ​​of other virtual resource objects corresponding to virtual resource object A, that is, sum the asymmetry evaluation values ​​of virtual resource object A and virtual resource object B, and the asymmetry evaluation values ​​of virtual resource object A and virtual resource object C. After obtaining the summed result, it can also be determined whether the summed result meets the pre-set conditions. If so, the server can recommend the current virtual resource object, that is, virtual resource object A, to the user to be recommended. If not, virtual resource object A will not be recommended to the user to be recommended.

[0046] In the above-mentioned virtual resource object recommendation method, by responding to a virtual resource object recommendation request for the user to be recommended, it is detected whether the user to be recommended is associated with a historical virtual resource interaction behavior; in the case that the user to be recommended is not associated with a historical virtual resource interaction behavior, an asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set is obtained; the current virtual resource object is any virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object; the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed, and when the summation result meets the preset conditions, the current virtual resource object is recommended to the user to be recommended. When recommending a virtual resource object to a user to be recommended, the present application can first detect whether the user to be recommended has any associated historical virtual resource interaction behavior. If not, the asymmetry evaluation value between any current virtual resource object contained in the virtual resource object set and other virtual resource objects in the set except the current virtual resource object is determined, and the asymmetry evaluation values ​​of each other virtual resource object are summed up, and when the summation result meets the preset conditions, the current virtual resource object is recommended to the user to be recommended. Compared with the prior art in which a part of virtual resource objects is randomly selected for recommendation, the present application can recommend virtual resource objects based on the asymmetry evaluation values ​​between the current virtual resource object and other virtual resource objects, thereby improving the accuracy of virtual resource object recommendations.

[0047] In one embodiment, Figure 2 As shown, step S102 may further include:

[0048] Step S201 : obtaining preset virtual resource object attributes and a first attribute quantized value of each virtual resource object attribute of the current virtual resource object.

[0049] The virtual resource object attribute refers to a pre-set attribute that can be used to evaluate the quality of the virtual resource object, and the first attribute quantization value is used to quantify the quantitative value of the current virtual resource object for each virtual resource object attribute. For example, a certain virtual resource object attribute can be a risk degree attribute, then the attribute quantization value corresponding to the attribute can be a quantitative value used to quantify the risk degree, which can be a risk value of 1-5, wherein the larger the risk value, the greater the risk degree. If the risk degree of the current virtual resource object is medium risk, then the attribute quantization value corresponding to the risk degree attribute, that is, the first attribute quantization value, can be set to 3. Similarly, corresponding to other virtual resource object attributes, quantification can also be performed in the above manner. In this way, the server can obtain the quantitative value of the current virtual resource object corresponding to each virtual resource object attribute as the first attribute quantization value of the current virtual resource object for each virtual resource object attribute.

[0050] Step S202, obtaining a second attribute quantized value of a target other virtual resource object for an attribute of each virtual resource object; the target other virtual resource object is any other virtual resource object.

[0051] The target other virtual resource object refers to any one of the other virtual resource objects, and the second attribute quantization value is used to quantify the quantization value of each virtual resource object attribute of the target other virtual resource object. Similar to the current virtual resource object, the server can also obtain the quantization value of each virtual resource object attribute of the target other virtual resource object as the second attribute quantization value of each virtual resource object attribute of the target other virtual resource object.

[0052] Step S203 : comparing the first attribute quantization value and the second attribute quantization value of each virtual resource object attribute, and obtaining the sub-asymmetry evaluation value corresponding to each virtual resource object attribute according to the comparison result.

[0053] The sub-asymmetric evaluation value refers to the asymmetry evaluation value corresponding to each virtual resource object attribute. In this embodiment, after obtaining the first attribute quantization value and the second attribute quantization value of each virtual resource object attribute, the server can mechanically compare the first attribute quantization value and the second attribute quantization value corresponding to the same virtual resource object attribute, thereby obtaining the sub-asymmetry evaluation value corresponding to the virtual resource object attribute according to the comparison result. Taking the virtual resource object attribute as the risk degree attribute as an example, after obtaining the risk degree attribute quantization value corresponding to the current virtual resource object and the risk degree attribute quantization value of other target virtual resource objects, the server can also compare the risk degree attribute quantization value corresponding to the current virtual resource object with the risk degree attribute quantization value of other target virtual resource objects, thereby obtaining the comparison result and then obtaining the sub-asymmetry evaluation value corresponding to the risk degree attribute.

[0054] Step S204: obtaining the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object according to each sub-asymmetry evaluation value.

[0055] Finally, after obtaining the sub-asymmetry evaluation values ​​corresponding to each virtual resource object attribute, the server can use the above sub-asymmetry evaluation values ​​to obtain the final asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object.

[0056] In this embodiment, the method for obtaining the asymmetry evaluation value can be to first quantize each virtual resource object attribute of the virtual resource object, and after obtaining the quantized value of each attribute, the sub-asymmetry evaluation value of the attribute can be obtained by comparing the quantized value of the corresponding attribute, and then the sub-asymmetry evaluation value of each attribute is used to determine the final asymmetry evaluation value. In this way, the asymmetry evaluation between different virtual resource object attributes is taken into account, thereby further improving the accuracy of the obtained asymmetry evaluation value.

[0057] Furthermore, step S204 may further include: obtaining the importance weights corresponding to the attributes of each virtual resource object that matches the user to be recommended; using the importance weights corresponding to the attributes of each virtual resource object, performing weighted summation processing on the sub-asymmetry evaluation values ​​corresponding to each virtual resource object attribute, to obtain the asymmetry evaluation value of the current virtual resource object corresponding to other target virtual resource objects.

[0058] Importance weight refers to the weight value used to characterize the importance between different virtual resource object attributes, and the weight value can be matched with the user to be recommended. Generally speaking, different users to be recommended attach different importance to different virtual resource object attributes, so different importance weights can be set for virtual resource object attributes for different users to be recommended. For example, virtual resource object attributes can include risk level attributes and yield rate attributes. Some users may attach more importance to the yield rate attribute, so a larger importance weight can be set for the yield rate attribute for this user. Similarly, if a user attaches more importance to the risk level attribute, a larger importance weight can be set for the risk level attribute for this user.

[0059] Specifically, the server may first obtain the importance weight corresponding to each virtual resource object attribute of the recommended user, and then use the above importance weight to perform weighted summation processing on the sub-asymmetry evaluation values ​​corresponding to each virtual resource object attribute, so as to obtain the final asymmetry evaluation value.

[0060] For example, the asymmetry evaluation value can be calculated by the following formula:

[0061]

[0062] Wherein, f represents the asymmetry evaluation value between virtual resource object a and virtual resource object b, represents the sub-asymmetry evaluation value of virtual resource object a and virtual resource object b for virtual resource object attribute i, and It represents the importance weight corresponding to the virtual resource object attribute i.

[0063] In this embodiment, importance weights may be introduced to perform weighted processing on the sub-asymmetry evaluation values ​​corresponding to the attributes of each virtual resource object, and the weights may be set to match the users to be recommended, thereby further improving the accuracy of the determined asymmetry evaluation values.

[0064] In addition, if Figure 3 As shown, obtaining the importance weight corresponding to each virtual resource object attribute matching the user to be recommended may further include:

[0065] Step S301, obtaining user attribute information of the user to be recommended, and obtaining the recommended user type of the user to be recommended according to the user attribute information.

[0066] The user attribute information refers to the user attributes of the user to be recommended, such as the age or gender of the user to be recommended, and the recommended user type refers to the user type of the user to be recommended, which can be determined based on the user attributes.

[0067] Specifically, when the server recommends virtual resource objects to the recommended user, it can first summarize the user account information of the recommended user to determine the user attribute information of the recommended user, and then obtain the user type of the recommended user, that is, the recommended user type, based on the above attribute information.

[0068] Step S302: based on the preset correspondence between the user type and the importance weight set, a target importance weight set corresponding to the recommended user type is obtained.

[0069] The importance weight set is a set used to store the importance weights of various virtual resource object attributes. In this embodiment, the correspondence between different user types and different importance weight sets can be pre-constructed. For example, corresponding to user type A, its corresponding importance weight set is set A, and set A includes importance weight A1 of virtual resource object attribute 1, and importance weight A2 of virtual resource object attribute 2. At the same time, for user type B, its corresponding importance weight set is set B, and set B includes importance weight B1 of virtual resource object attribute 1, and importance weight B2 of virtual resource object attribute 2. The target importance weight set refers to the importance weight set corresponding to the recommended user type. After obtaining the user type of the user to be recommended, the server can obtain the importance weight set corresponding to the user type of the user to be recommended based on the pre-constructed correspondence between the user type and the importance weight set, as the target importance weight set.

[0070] Step S303: taking the importance weight corresponding to each virtual resource object attribute in the target importance weight set as the importance weight corresponding to each virtual resource object attribute matching the user to be recommended.

[0071] Finally, the server may use the importance weight of each virtual resource object attribute in the target importance weight set as the importance weight corresponding to each virtual resource object attribute for matching the to-be-recommended user.

[0072] In this embodiment, the recommended user type of the user to be recommended can also be obtained through the user attributes to be recommended, so as to determine the importance weights corresponding to each virtual resource object attribute based on the recommended user type, thereby further improving the accuracy of setting the importance weights corresponding to each virtual resource object attribute.

[0073] In one embodiment, the sub-asymmetry evaluation value includes: a first sub-asymmetry evaluation value, a second sub-asymmetry evaluation value and a third sub-asymmetry evaluation value; wherein the first sub-asymmetry evaluation value is greater than the second sub-asymmetry evaluation value, and the second sub-asymmetry evaluation value is greater than the third sub-asymmetry evaluation value; step S203 may further include: obtaining the current virtual resource object attribute; the current virtual resource object attribute is any one of the virtual resource object attributes; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is better than other target virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the first sub-asymmetry evaluation value; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is the same as other target virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the second sub-asymmetry evaluation value; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is inferior to other target virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the third sub-asymmetry evaluation value.

[0074] In this embodiment, the sub-asymmetry evaluation value can be composed of three types, namely, a first sub-asymmetry evaluation value, a second sub-asymmetry evaluation value and a third sub-asymmetry evaluation value, and the value of the first sub-asymmetry evaluation value is greater than the second sub-asymmetry evaluation value, and the value of the second sub-asymmetry evaluation value is greater than the third sub-asymmetry evaluation value. For example, the value of the first sub-asymmetry evaluation value can be 1, the value of the second sub-asymmetry evaluation value can be 0, and the value of the third sub-asymmetry evaluation value can be -1. The sub-asymmetry evaluation value can represent the pros and cons of a virtual resource object attribute between virtual resource objects. The current virtual resource object attribute refers to any one of multiple virtual resource object attributes.

[0075] Specifically, the server can first determine one of the multiple virtual resource object attributes as the current virtual resource object attribute, and then obtain the comparison result of the first attribute quantization value and the second attribute quantization value corresponding to the current virtual resource object attribute, and the comparison result can be used to characterize the current virtual resource object and the advantages and disadvantages of the target other virtual resource objects for the current virtual resource object attribute, so as to use the advantages and disadvantages to obtain the sub-asymmetry evaluation value of the current virtual resource object attribute. That is, for the current virtual resource object attribute, if the current virtual resource object is better than the target other virtual resource objects, then the sub-asymmetry evaluation value corresponding to the corresponding current virtual resource object attribute can be set to 1, that is, the first sub-asymmetry evaluation value. If the current virtual resource object is the same as the target other virtual resource object, then the sub-asymmetry evaluation value corresponding to the corresponding current virtual resource object attribute can be set to 0, that is, the second sub-asymmetry evaluation value. Similarly, if the current virtual resource object is inferior to the target other virtual resource objects, then the sub-asymmetry evaluation value corresponding to the corresponding current virtual resource object attribute can be set to -1, that is, the third sub-asymmetry evaluation value.

[0076] Taking the risk attribute as an example, if the first attribute quantization value of the current virtual resource object for the risk attribute is 1, and the second attribute quantization value of the target other virtual resource object for the risk attribute is 3, it means that the current virtual resource object is better than the target other virtual resource object in terms of the risk attribute, and the sub-asymmetry evaluation value corresponding to the risk attribute can be set to 1. If the first attribute quantization value of the current virtual resource object for the risk attribute is 3, which is the same as the second attribute quantization value, then the sub-asymmetry evaluation value corresponding to the risk attribute can be set to 0. Similarly, if the first attribute quantization value of the current virtual resource object for the risk attribute is 5, that is, the current virtual resource object is inferior to the target other virtual resource objects, then the sub-asymmetry evaluation value corresponding to the risk attribute can be set to -1.

[0077] In this embodiment, the comparison results corresponding to the current virtual resource object attributes can also be used to determine the advantages and disadvantages between the current virtual resource object and other target virtual resource objects with respect to the current virtual resource object attributes. The sub-asymmetry evaluation value can be used to simply characterize the advantages and disadvantages between virtual resource objects with respect to the current virtual resource object attributes, thereby improving the accuracy and efficiency of obtaining the sub-asymmetry evaluation value.

[0078] In one embodiment, step S103 may further include: obtaining a preset asymmetry evaluation threshold; and recommending the current virtual resource object to the user to be recommended when the sum result is greater than the preset asymmetry evaluation threshold.

[0079] The asymmetry evaluation threshold is a pre-set conditional threshold used to determine whether to recommend the current virtual resource object to the user to be recommended. Since each sub-asymmetry evaluation value can represent the quality of two virtual resource objects in different virtual resource object attributes, if the sub-asymmetry evaluation value is larger, the asymmetry evaluation value will also be larger, and the sum result obtained by the summation processing will also be larger. Therefore, the size of the sum result can actually be used to represent the quality of each virtual resource object in the virtual resource object set. The larger the sum result, the higher the quality of the corresponding current virtual resource object. Therefore, the server can set an asymmetry evaluation threshold. Only when the sum result corresponding to the current virtual resource object is greater than the above-mentioned asymmetry evaluation threshold, the server will recommend the current virtual resource object to the user to be recommended, to ensure that the virtual resource objects recommended to the user to be recommended are relatively high-quality virtual resource objects.

[0080] In this embodiment, an asymmetry evaluation threshold can also be set, and the current virtual resource object will be recommended to the user to be recommended only when the sum of the asymmetry evaluation values ​​of the current virtual resource object corresponding to other virtual resource objects is greater than the asymmetry evaluation threshold. In this way, the quality of virtual resource object recommendations can be improved.

[0081] In one embodiment, a method for determining the recommendation order of virtual resource objects based on statistical analysis is also provided, because the advantages and disadvantages between the attributes of virtual resource object products are asymmetric. For example, for products A and B. For different attributes, there may be different advantages between the two products. For example, for the risk level attribute of the virtual resource object product, the risk value of product A is greater than that of product B, so product B should be recommended based on this attribute alone. However, considering the yield attribute, the yield of product A is greater than that of product B, so product A should be recommended based on the yield. It can be seen that the advantages and disadvantages of different products and different attributes are inconsistent. When most of the attributes of product A are better than product B, and a small part of the attributes of product A are worse than product B, there is asymmetry between products A and B, and the asymmetry direction is that product A is better than product B. Based on this asymmetric characteristic, all the attributes of the products are comprehensively considered to determine the asymmetric direction between the products, and then the recommendation order between the products is obtained. This can be specifically achieved through the following process:

[0082] Step 1: Quantify the various attributes of the virtual resource object product. For example, the risk level attribute of the product is quantified into risk values ​​1-5. The larger the risk value, the higher the risk.

[0083] Step 2: Compare and evaluate the same attributes of each financial product, and compare each attribute to get 0 (same), 1 (product A attribute is better than product B attribute), -1 (product A attribute is worse than product B attribute).

[0084] Step 3: Assign importance weights to each attribute of the product.

[0085] Step 4: Calculate the asymmetry between products based on the comparison results between product attributes in step 2. The asymmetry value is calculated as follows:

[0086] in, Indicates the result of comparing the i attributes of product A and product B (the result of step 2, is the importance weight of attribute i of product.

[0087] Step 5: Determine the relationship between virtual resource object products based on the asymmetry threshold.

[0088] Through the above process, all aspects of the virtual resource object product attributes can be comprehensively considered for recommendation, which is simple and efficient and can be applied to recommend virtual resource object products for new users in the absence of user preference information.

[0089] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0090] Based on the same inventive concept, the embodiment of the present application also provides a virtual resource object recommendation device for implementing the virtual resource object recommendation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more virtual resource object recommendation device embodiments provided below can refer to the limitations of the virtual resource object recommendation method above, and will not be repeated here.

[0091] In one embodiment, Figure 4As shown, a virtual resource object recommendation device is provided, comprising: a recommendation request response module 401, an asymmetry evaluation module 402 and a resource object recommendation module 403, wherein:

[0092] The recommendation request response module 401 is used to respond to the virtual resource object recommendation request for the user to be recommended, and detect whether the user to be recommended is associated with a historical virtual resource interaction behavior;

[0093] The asymmetry evaluation module 402 is used to obtain, when the user to be recommended is not associated with any historical virtual resource interaction behavior, an asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object;

[0094] The resource object recommendation module 403 is used to sum the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object, and recommend the current virtual resource object to the user to be recommended if the summation result meets a preset condition.

[0095] In one embodiment, the asymmetry evaluation module 402 is further used to obtain pre-set virtual resource object attributes, and the first attribute quantization value of the current virtual resource object for each virtual resource object attribute; obtain the second attribute quantization value of the target other virtual resource object for each virtual resource object attribute; the target other virtual resource object is any other virtual resource object; compare the first attribute quantization value and the second attribute quantization value of each virtual resource object attribute, and obtain the sub-asymmetry evaluation value corresponding to each virtual resource object attribute according to the comparison result; according to each sub-asymmetry evaluation value, obtain the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object.

[0096] In one embodiment, the asymmetry evaluation module 402 is further used to obtain the importance weights corresponding to the attributes of each virtual resource object that matches the user to be recommended; using the importance weights corresponding to the attributes of each virtual resource object, weighted summation is performed on the sub-asymmetry evaluation values ​​corresponding to each virtual resource object attribute to obtain the asymmetry evaluation value of the current virtual resource object corresponding to other target virtual resource objects.

[0097] In one embodiment, the asymmetry evaluation module 402 is further used to obtain user attribute information of the user to be recommended, and obtain the recommended user type of the user to be recommended based on the user attribute information; based on the predetermined correspondence between the user type and the importance weight set, obtain the target importance weight set corresponding to the recommended user type; and use the importance weight corresponding to each virtual resource object attribute in the target importance weight set as the importance weight corresponding to each virtual resource object attribute that matches the user to be recommended.

[0098] In one embodiment, the sub-asymmetry evaluation value includes: a first sub-asymmetry evaluation value, a second sub-asymmetry evaluation value and a third sub-asymmetry evaluation value; wherein the first sub-asymmetry evaluation value is greater than the second sub-asymmetry evaluation value, and the second sub-asymmetry evaluation value is greater than the third sub-asymmetry evaluation value; the asymmetry evaluation module 402 is further used to obtain the current virtual resource object attribute; the current virtual resource object attribute is any one of the virtual resource object attributes; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is better than the target other virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the first sub-asymmetry evaluation value; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is the same as the target other virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the second sub-asymmetry evaluation value; when the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is inferior to the target other virtual resource objects, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set to the third sub-asymmetry evaluation value.

[0099] In one embodiment, the resource object recommendation module is further used to obtain a preset asymmetry evaluation threshold; when the sum result is greater than the preset asymmetry evaluation threshold, recommend the current virtual resource object to the user to be recommended.

[0100] Each module in the above virtual resource object recommendation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0101] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store virtual resource object data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a virtual resource object recommendation method is implemented.

[0102] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0103] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0104] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0105] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0106] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0107] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0108] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A virtual resource object recommendation method, characterized in that: The method comprises: In response to a virtual resource object recommendation request for a user to be recommended, detecting whether the user to be recommended is associated with a historical virtual resource interaction behavior; In the case where the user to be recommended is not associated with any historical virtual resource interaction behavior, obtaining asymmetric evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object; The asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object are summed up, and when the summation result meets a preset condition, the current virtual resource object is recommended to the user to be recommended.

2. The method according to claim 1, characterized in that The step of obtaining the asymmetry evaluation value of the current virtual resource object corresponding to each other virtual resource object in the preset virtual resource object set includes: Acquire preset virtual resource object attributes, and first attribute quantized values ​​of the current virtual resource object for each of the virtual resource object attributes; Obtaining a second attribute quantized value of a target other virtual resource object for an attribute of each of the virtual resource objects; the target other virtual resource object is any other virtual resource object; Comparing the first attribute quantization value and the second attribute quantization value of each of the virtual resource object attributes, and obtaining the sub-asymmetry evaluation values ​​corresponding to each of the virtual resource object attributes according to the comparison result; According to each of the sub-asymmetry evaluation values, an asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object is obtained.

3. The method according to claim 2, characterized in that The step of obtaining the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object according to each of the sub-asymmetry evaluation values ​​includes: Obtaining importance weights corresponding to attributes of each of the virtual resource objects that match the user to be recommended; By using the importance weights corresponding to the attributes of each virtual resource object, weighted summation is performed on the sub-asymmetry evaluation values ​​corresponding to the attributes of each virtual resource object to obtain the asymmetry evaluation value of the current virtual resource object corresponding to the target other virtual resource object.

4. The method according to claim 3, characterized in that The obtaining of the importance weight corresponding to each attribute of the virtual resource object matching the user to be recommended includes: Acquire user attribute information of the user to be recommended, and obtain a recommended user type of the user to be recommended according to the user attribute information; Based on a preset correspondence between user types and importance weight sets, obtaining a target importance weight set corresponding to the recommended user type; The importance weights corresponding to the attributes of each virtual resource object in the target importance weight set are used as the importance weights corresponding to the attributes of each virtual resource object that match the user to be recommended.

5. The method according to claim 2, characterized in that: The sub-asymmetry evaluation values ​​include: a first sub-asymmetry evaluation value, a second sub-asymmetry evaluation value and a third sub-asymmetry evaluation value; wherein the first sub-asymmetry evaluation value is greater than the second sub-asymmetry evaluation value, and the second sub-asymmetry evaluation value is greater than the third sub-asymmetry evaluation value; The obtaining, according to the comparison result, the sub-asymmetry evaluation values ​​corresponding to the attributes of each virtual resource object respectively comprises: Acquire a current virtual resource object attribute; the current virtual resource object attribute is any one of the virtual resource object attributes; If the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is superior to the target other virtual resource object, setting the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute as the first sub-asymmetry evaluation value; When the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is the same as the target other virtual resource object, setting the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute as the second sub-asymmetry evaluation value; When the comparison result corresponding to the current virtual resource object attribute indicates that the current virtual resource object is inferior to the target other virtual resource object, the sub-asymmetry evaluation value corresponding to the current virtual resource object attribute is set as the third sub-asymmetry evaluation value.

6. The method according to claim 5, characterized in that When the summation result satisfies a preset condition, recommending the current virtual resource object to the to-be-recommended user includes: Obtaining a pre-set asymmetry evaluation threshold; When the sum result is greater than a preset asymmetry evaluation threshold, the current virtual resource object is recommended to the user to be recommended.

7. A virtual resource object recommendation device, characterized in that: The device comprises: A recommendation request response module, configured to respond to a virtual resource object recommendation request for a user to be recommended, and detect whether the user to be recommended is associated with a historical virtual resource interaction behavior; an asymmetry evaluation module, for obtaining, when the user to be recommended is not associated with any historical virtual resource interaction behavior, an asymmetry evaluation value of a current virtual resource object corresponding to each other virtual resource object in a preset virtual resource object set; the current virtual resource object is any one virtual resource object in the virtual resource object set, and the other virtual resource objects are virtual resource objects in the virtual resource object set except the current virtual resource object; The resource object recommendation module is used to sum the asymmetry evaluation values ​​of the current virtual resource object corresponding to each other virtual resource object, and recommend the current virtual resource object to the user to be recommended when the summation result meets a preset condition.

8. A computer 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 6 are implemented.

9. A computer-readable 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images