Object recommendation method, object recommendation apparatus, electronic device, and storage medium

Abstract

The present disclosure provides an object recommendation method, an object recommendation device, an electronic device and a storage medium, which can be applied to the technical field of big data. The object recommendation method comprises: determining M first objective indexes, N second objective indexes and a target variable relationship matched with an application scene, the target variable relationship being used to determine a to-be-recommended object, the first objective indexes being used to represent transaction characteristics of a user, the second objective indexes being used to represent social relationship characteristics of the user, M being greater than or equal to 1, and N being greater than or equal to 1; obtaining a recommendation data set of a target user, the recommendation data set comprising first objective data corresponding to the first objective indexes and second objective data corresponding to the second objective indexes; and determining the to-be-recommended object according to the M first objective data, the N second objective data and the target variable relationship.

Description

Technical Field

[0001] This disclosure relates to the field of big data, specifically to an object recommendation method, an object recommendation device, an electronic device, and a storage medium. Background Technology

[0002] In the financial industry, users can make investments or trades by choosing financial advisors, product managers, and other professionals. To cater to individual user needs, banks can recommend suitable financial advisors and product managers to meet those needs.

[0003] In related technologies, the object recommendation scenario described above typically relies on user satisfaction to perform the recommendation operation. User satisfaction is determined through subjective evaluation methods such as questionnaires and survey reports. However, differences in evaluation criteria and satisfaction standards among multiple users lead to technical problems in existing technologies, such as inaccurate object recommendations and poor user experience. Summary of the Invention

[0004] In view of the above problems, this disclosure provides an object recommendation method, an object recommendation device, an electronic device, and a storage medium.

[0005] According to a first aspect of this disclosure, an object recommendation method is provided, comprising:

[0006] Determine M primary objective indicators, N secondary objective indicators, and target variable relationships that match the application scenario. The target variable relationships are used to determine the objects to be recommended. The primary objective indicators are used to characterize the user's transaction characteristics, and the secondary objective indicators are used to characterize the user's social relationship characteristics. M≥1, N≥1.

[0007] Obtain the recommendation dataset for the target users. The recommendation dataset includes first objective data corresponding to a first objective metric and second objective data corresponding to a second objective metric; and

[0008] Based on the relationship between M primary objective data, N secondary objective data, and the target variable, the objects to be recommended are determined.

[0009] According to embodiments of this disclosure, determining the object to be recommended based on M first objective data, N second objective data, and the relationship between the target variable includes:

[0010] Based on M primary objective data points, N secondary objective data points, and the relationship with the target variable, a recommendation index value is calculated. This recommendation index value is used to characterize user objective satisfaction.

[0011] If the recommended indicator values ​​meet the preset conditions, the objects to be recommended are determined from the recommendation list, which includes multiple objects.

[0012] According to embodiments of this disclosure, the target variable relationship includes a first variable relationship, a second variable relationship, and a third variable relationship;

[0013] Based on the relationship between M primary objective data points, N secondary objective data points, and the target variable, the recommendation index value is calculated, including:

[0014] Based on the relationship between M primary objective data points and primary variables, generate trading indicator values;

[0015] Based on N secondary objective data and their relationships with secondary variables, generate social relationship index values; and

[0016] The recommendation index value is calculated based on the transaction index value, the social relationship index value, and the third variable relationship.

[0017] According to embodiments of this disclosure, determining the relationship between M first objective indicators, N second objective indicators, and the target variable that match the application scenario includes:

[0018] Based on the scenario identifier of the application scenario, obtain the relationship table that matches the application scenario. The relationship table includes M primary objective indicators, N secondary objective indicators, and the relationship of the target variable.

[0019] According to embodiments of this disclosure, before obtaining the relationship table matching the application scenario based on the scenario identifier, the process includes:

[0020] Based on the scenario identifier of the application scenario, determine P first initial objective indicators, Q second initial objective indicators and S subjective indicators. The subjective indicators are used to represent the user's subjective satisfaction, P≥M≥1, Q≥N≥1, S≥1.

[0021] Obtain the initial dataset, which includes the third objective data corresponding to the first initial objective indicator, the fourth objective data corresponding to the second initial objective indicator, and the subjective data corresponding to the subjective indicator;

[0022] Based on P third-party objective data, Q fourth-party objective data, and S subjective data, generate initial variable relationships; and

[0023] Based on the test results of the initial variable relationships, M first objective indicators are determined from P first initial objective indicators, N second objective indicators are determined from Q second initial objective indicators, and the target variable relationships are determined from the initial variable relationships, and a relationship table is generated.

[0024] According to embodiments of this disclosure, generating initial variable relationships based on P third objective data, Q fourth objective data, and S subjective data includes:

[0025] Determine the first covariance matrix among P third objective data points, Q fourth objective data points, and S subjective data points; and

[0026] Input the first covariance matrix into the first structural equation model and output the initial variable relationship. The first structural equation model is constructed according to the first assumption relationship, which is determined according to the application scenario.

[0027] According to embodiments of this disclosure, the process of determining M first objective indicators from P first initial objective indicators, determining N second objective indicators from Q second initial objective indicators, and determining target variable relationships from the initial variable relationships, based on the test results of the initial variable relationships, and generating a relationship table, includes:

[0028] If the test results do not meet the significance test criteria, based on the test results, M first objective indicators are determined from P first initial objective indicators, and N second objective indicators are determined from Q second initial objective indicators.

[0029] Determine the second covariance matrix among M primary objective indicators, N secondary objective indicators, and S subjective data; and

[0030] The second covariance matrix is ​​input into the second structural equation model, and the target variable relationship is output. The second structural equation model is constructed according to the second hypothesis relationship, which is determined based on the test results.

[0031] According to embodiments of this disclosure, the first objective indicator includes at least one of the following: monthly asset returns and asset returns under the application scenario; the second objective indicator includes at least one of the following: the number of associated users and the recommendation frequency.

[0032] A second aspect of this disclosure provides an object recommendation apparatus, comprising:

[0033] The determination module is used to determine M first objective indicators, N second objective indicators, and target variable relationships that match the application scenario. The target variable relationships are used to determine the objects to be recommended. The first objective indicators are used to characterize the user's transaction characteristics, and the second objective indicators are used to characterize the user's social relationship characteristics. M≥1, N≥1.

[0034] The acquisition module is used to acquire the recommendation dataset of the target user. The recommendation dataset includes first objective data corresponding to a first objective metric and second objective data corresponding to a second objective metric; and

[0035] The recommendation module is used to determine the objects to be recommended based on M primary objective data, N secondary objective data, and the relationship between the target variable and the target variable.

[0036] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the object-recommended method described above.

[0037] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the object-recommended method described above.

[0038] The fifth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described object recommendation method.

[0039] The embodiments of this disclosure determine the relationship between M first objective indicators, N second objective indicators, and a target variable that match the application scenario; obtain a recommendation dataset for the target user, the recommendation dataset including first objective data corresponding to the first objective indicators and second objective data corresponding to the second objective indicators; and determine the objects to be recommended based on the relationship between the M first objective data, N second objective data, and the target variable. Since the first and second objective indicators and the relationship between the target variable do not depend on the user's subjective evaluation, the recommendation operation is not affected by user subjective differences, thus improving recommendation accuracy and user experience. Furthermore, the embodiments of this disclosure use first objective indicators representing the user's transaction characteristics and second objective indicators representing the user's social relationship characteristics to determine the objects to be recommended, which expands the data dimensions, determining the objects to be recommended from both the user's transaction behavior and social relationship dimensions, further improving recommendation accuracy. Attached Figure Description

[0040] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0041] Figure 1 This illustration schematically depicts an application scenario of the object recommendation method according to embodiments of the present disclosure;

[0042] Figure 2 A flowchart illustrating an object recommendation method according to an embodiment of the present disclosure is shown schematically;

[0043] Figure 3 A flowchart illustrating a method for determining a recommended object according to an embodiment of the present disclosure is shown schematically;

[0044] Figure 4 A flowchart illustrating a method for calculating recommended index values ​​according to embodiments of the present disclosure is shown schematically.

[0045] Figure 5A schematic diagram of a first structural equation model according to an embodiment of the present disclosure is shown;

[0046] Figure 6 A schematic diagram of a second structural equation model according to an embodiment of the present disclosure is shown;

[0047] Figure 7 A schematic block diagram of an object recommendation device according to an embodiment of the present disclosure is shown; and

[0048] Figure 8 A block diagram schematically illustrates an electronic device suitable for an object recommendation method according to an embodiment of the present disclosure. Detailed Implementation

[0049] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0051] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0052] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0053] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of data (including but not limited to user personal information) comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0054] In related technologies, banks and other businesses can obtain user satisfaction data on features, applications, and financial advisors through questionnaires, surveys, or telephone follow-ups. They can then use this feedback to recommend suitable features, applications, or financial advisors to users.

[0055] However, when using satisfaction feedback from questionnaires, survey reports, or telephone follow-ups to perform object recommendation operations, the recommendation accuracy is low.

[0056] On the one hand, the influencing factors identified in questionnaires, survey reports, or telephone follow-ups are generally determined through company personnel research or subjective reasoning. There is no quantitative data analysis of these factors, making it impossible to determine their reliability. Furthermore, because these influencing factors involve social science fields, it is difficult to accurately and directly measure their impact on user satisfaction.

[0057] On the other hand, due to differences in users' rating habits and service evaluation standards, the satisfaction level determined by users based on questionnaires, survey reports, or telephone follow-ups relies on users' subjective evaluations, which further leads to low recommendation accuracy and affects the user experience.

[0058] Therefore, in scenarios where object recommendations are based on user subjective satisfaction, there are technical problems such as inaccurate object recommendations and poor user experience.

[0059] Embodiments of this disclosure provide an object recommendation method, comprising: determining M first objective indicators, N second objective indicators, and a target variable relationship that match an application scenario, wherein the target variable relationship is used to determine the object to be recommended, the first objective indicators are used to characterize the user's transaction characteristics, the second objective indicators are used to characterize the user's social relationship characteristics, M≥1, N≥1; obtaining a recommendation dataset of the target user, wherein the recommendation dataset includes first objective data corresponding to the first objective indicators and second objective data corresponding to the second objective indicators; and determining the object to be recommended based on the M first objective data, N second objective data, and the target variable relationship.

[0060] Figure 1 The illustration depicts an application scenario of the object recommendation method according to an embodiment of the present disclosure.

[0061] like Figure 1As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0062] Users can interact with server 105 via network 104 using at least one of the first terminal device 101, second terminal device 102, and third terminal device 103 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, second terminal device 102, and third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0063] For example, the first terminal device 101, the second terminal device 102, and the third terminal device 103 may have a bank client installed, and send the first objective data and the second objective data to the server 105.

[0064] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0065] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0066] It should be noted that the object recommendation method provided in this embodiment can generally be executed by server 105. Correspondingly, the object recommendation device provided in this embodiment can generally be located in server 105. The object recommendation method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the object recommendation device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0067] The object recommendation method provided in this embodiment can also be executed by one of the first terminal device 101, the second terminal device 102, and the third terminal device 103. Correspondingly, the object recommendation device provided in this embodiment can generally be located in the first terminal device 101, the second terminal device 102, or the third terminal device 103. The object recommendation method provided in this embodiment can also be executed by other terminal devices or cloud platforms that are different from the first terminal device 101, the second terminal device 102, or the third terminal device 103 and are capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the object recommendation device provided in this embodiment can also be located in other terminal devices or cloud platforms that are different from the first terminal device 101, the second terminal device 102, or the third terminal device 103 and are capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0068] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0069] The following will be based on Figure 1 The described scene, through Figures 2-6 The object recommendation method of the disclosed embodiments is described in detail.

[0070] Figure 2 A flowchart illustrating an object recommendation method according to an embodiment of this disclosure is shown schematically.

[0071] like Figure 2 As shown, the method 200 includes operations S210 to S230.

[0072] In operation S210, determine the relationship between M primary objective indicators, N secondary objective indicators, and target variables that match the application scenario, where M≥1 and N≥1.

[0073] According to embodiments of this disclosure, a first objective indicator is used to characterize a user's transaction characteristics, and a second objective indicator is used to characterize a user's social relationship characteristics.

[0074] According to embodiments of this disclosure, target variable relationships are used to determine objects to be recommended. The target variable relationships include multiple variable relationships used to determine objects to be recommended based on M first objective indicators and N second objective indicators.

[0075] According to embodiments of this disclosure, application scenarios include multiple recommendation scenarios, such as financial advisor recommendation scenarios, product manager recommendation scenarios, and financial product recommendation scenarios. The application scenario can be determined based on the operations performed by business personnel on the front-end page.

[0076] According to embodiments of this disclosure, multiple application scenarios can be matched with multiple types and multiple numbers of first objective indicators and multiple second objective indicators.

[0077] For example, application scenario A is matched with one first objective indicator and one second objective indicator, while application scenario B is matched with one first objective indicator and two second objective indicators. The first objective indicator matched with application scenario A is different from the first objective indicator matched with application scenario B; the two second objective indicators matched with application scenario B include the second objective indicator matched with application scenario A.

[0078] According to embodiments of this disclosure, the database contains fields corresponding to application scenarios, such as scenario identifiers. Determining the relationship between M first objective indicators, N second objective indicators, and the target variable that match the application scenario includes: determining the relationship between the M first objective indicators, N second objective indicators, and the target variable based on the scenario identifier of the current application scenario.

[0079] In operation S220, the recommendation dataset of the target user is obtained. The recommendation dataset includes first objective data corresponding to the first objective indicator and second objective data corresponding to the second objective indicator.

[0080] According to embodiments of this disclosure, the target user can be understood as a user with recommendation needs. For example, a user can select a recommendation function in the function recommendation module of a bank's client. Thus, the client can recommend one or more application scenarios to the user.

[0081] According to embodiments of this disclosure, after determining the relationship between the first objective indicator, the second objective indicator, and the target variable that matches the application scenario, a recommendation dataset of the target user can be obtained so as to accurately recommend the required object to the target user based on the recommendation dataset of the target user.

[0082] According to embodiments of this disclosure, obtaining a recommendation dataset for a target user includes: obtaining the target user's recommendation dataset from a database based on the target user's identification information.

[0083] In operation S230, based on M primary objective data, N secondary objective data, and the relationship between the target variable, the objects to be recommended are determined.

[0084] According to embodiments of this disclosure, after determining the first objective data corresponding to the first objective indicator and the second objective data corresponding to the second objective indicator, the objects to be recommended can be determined based on M first objective data and N second objective data according to the target variable relationship.

[0085] According to embodiments of this disclosure, the type of the object to be recommended is related to the application scenario. For a financial advisor recommendation scenario, the object to be recommended is a financial advisor; for a product manager recommendation scenario, the object to be recommended is a product manager; for a wealth management product recommendation scenario, the object to be recommended is a wealth management product, etc.

[0086] The embodiments of this disclosure determine the relationship between M first objective indicators, N second objective indicators, and a target variable that match the application scenario; obtain a recommendation dataset for the target user, the recommendation dataset including first objective data corresponding to the first objective indicators and second objective data corresponding to the second objective indicators; and determine the objects to be recommended based on the relationship between the M first objective data, N second objective data, and the target variable. Since the first and second objective indicators and the relationship between the target variable do not depend on the user's subjective evaluation, the recommendation operation is not affected by user subjective differences, thus improving recommendation accuracy and user experience. Furthermore, the embodiments of this disclosure use first objective indicators representing the user's transaction characteristics and second objective indicators representing the user's social relationship characteristics to determine the objects to be recommended, which expands the data dimensions, determining the objects to be recommended from both the user's transaction behavior and social relationship dimensions, further improving recommendation accuracy.

[0087] According to embodiments of this disclosure, the first objective indicator includes at least one of the following: monthly asset returns and asset returns under the application scenario; the second objective indicator includes at least one of the following: the number of associated users and the recommendation frequency.

[0088] According to embodiments of this disclosure, for recommendation scenarios, the target user's own transaction behavior can reflect information such as the user's preferences and satisfaction level.

[0089] According to embodiments of this disclosure, user transaction behavior varies across different application scenarios. Therefore, while considering user transaction behavior, both overall user transaction behavior and specific user transaction behavior in a particular application scenario are considered to determine a first objective indicator. For example, the first objective indicator includes monthly asset returns representing overall transaction behavior, as well as asset returns specific to the application scenario.

[0090] According to the embodiments disclosed herein, the social relationships of the target user can also influence the user's preferences and satisfaction levels. For example, the target user's satisfaction level may change due to the evaluations or recommendations of friends or relatives; it may also be affected by factors such as the frequency of recommendations. For instance, a high recommendation frequency indicates that the user is more satisfied with the recommendation process.

[0091] According to embodiments of this disclosure, a second objective indicator is determined by considering the target user's transaction behavior and social relationships, so as to combine the first and second objective indicators to determine the target to be recommended.

[0092] Figure 3 A flowchart illustrating a method for determining a recommended object according to an embodiment of the present disclosure is shown schematically.

[0093] like Figure 3 As shown, the method 300 for determining the recommended object in this embodiment includes operations S331 to S332, which can be used as a specific embodiment of operation S230.

[0094] In operation S331, the recommended index value is calculated based on M primary objective data, N secondary objective data, and the relationship between the target variable and the data.

[0095] In operation S332, if the recommended indicator value meets the preset conditions, the object to be recommended is determined from the recommendation list.

[0096] According to embodiments of this disclosure, the recommended index value is used to characterize the user's objective satisfaction.

[0097] According to embodiments of this disclosure, a first objective indicator is used to characterize a user's transaction characteristics, and a second objective indicator is used to characterize a user's social relationship characteristics.

[0098] In calculating the recommendation index value based on the first objective data, the second objective data, and the relationship between the target variables, the transaction recommendation data can be determined first based on the first objective data and the variable relationships related to the first objective index. Then, the social relationship recommendation data can be determined based on the second objective data and the variable relationships related to the second objective index. Finally, the recommendation index value is determined based on the transaction recommendation data, the social relationship recommendation data, and the relevant variable relationships.

[0099] According to embodiments of this disclosure, whether the recommended indicator value meets the preset conditions includes: whether the recommended indicator value is greater than or equal to the recommended threshold.

[0100] According to embodiments of this disclosure, a recommendation index value greater than or equal to a recommendation threshold indicates that the user accepts the recommendation operation. Therefore, when it is determined that the recommendation index value meets the preset conditions, the object to be recommended is determined and the object to be recommended is pushed to the user.

[0101] According to embodiments of this disclosure, a recommendation index value less than a recommendation threshold indicates that the user does not accept the recommendation operation. Therefore, if it is determined that the recommendation index value does not meet the preset conditions, the recommendation operation is terminated without determining the recommendation object, thereby improving the user experience and reducing the consumption of computing resources.

[0102] According to embodiments of this disclosure, the recommendation list includes multiple objects. The process of determining the object to be recommended from the recommendation list can be understood as the process of filtering out the most suitable recommended object from multiple objects.

[0103] According to embodiments of this disclosure, multiple objects in the recommendation list can be arranged according to recommendation priority, and determining the object to be recommended from the recommendation list includes: determining the object with the highest recommendation priority as the object to be recommended.

[0104] According to embodiments of this disclosure, the recommendation priority can be determined based on the object's asset returns in the application scenario, monthly asset returns in other application scenarios, and the frequency and number of recommendations.

[0105] For example, in a scenario where financial advisors are recommended, the recommendation list includes three advisors: Advisor A, Advisor B, and Advisor C. For Advisor A, the recommendation priority can be determined based on Advisor A's asset returns in the financial recommendation scenario, its monthly asset returns in other recommendation scenarios such as funds, and the frequency and number of times Advisor A is recommended.

[0106] According to the embodiments of this disclosure, the process of determining the object to be recommended from the recommendation list includes, but is not limited to, the above embodiments. As long as the recommended index value can be determined from the recommendation list, the object to be recommended can be determined.

[0107] The embodiments of this disclosure calculate recommendation index values ​​of objective attributes based on transaction characteristics and social relationship characteristics, and compare the recommendation index values ​​with preset conditions to determine the objects to be recommended, which can improve the accuracy of recommendations.

[0108] According to embodiments of this disclosure, the target variable relationship includes a first variable relationship, a second variable relationship, and a third variable relationship.

[0109] Based on M primary objective data points, N secondary objective data points, and the relationship between the target variable, the recommended indicator value is calculated, including: generating a transaction indicator value based on the M primary objective data points and the relationship between the primary variable; generating a social relationship indicator value based on the N secondary objective data points and the relationship between the secondary variable; and calculating the recommended indicator value based on the transaction indicator value, the social relationship indicator value, and the relationship between the secondary variable.

[0110] According to embodiments of this disclosure, the first variable relationship corresponds to the first objective indicator and is used to determine transaction recommendation information, that is, transaction indicator values.

[0111] According to embodiments of this disclosure, the first variable relationship may include M first sub-variable relationships, each first sub-variable relationship corresponding to a first objective data point. The trading indicator value is calculated by linear summation based on the M first sub-variable relationships and the M first objective data points.

[0112] According to embodiments of this disclosure, the second variable relationship corresponds to the second objective indicator and is used to determine social relationship recommendation information, that is, social relationship indicator values.

[0113] According to embodiments of this disclosure, the second variable relationship may include N second sub-variable relationships, each second sub-variable relationship corresponding to a second objective data point. The social relationship index value is calculated by linear summation based on the N second sub-variable relationships and the N second objective data points.

[0114] According to embodiments of this disclosure, the third variable relationship is used to determine the recommended indicator value based on the transaction indicator value and the social relationship indicator value.

[0115] According to embodiments of this disclosure, the third variable relationship includes two or three third sub-variable relationships. When the third variable relationship includes two third independent variable relationships, such as a first third sub-variable relationship and a second third sub-variable relationship, the first third sub-variable relationship characterizes the correlation between the trading indicator value and the social relationship indicator value, and the second third sub-variable relationship characterizes the correlation between the social relationship indicator value and the recommendation indicator value. The recommendation indicator value can be determined based on the trading indicator value, the social relationship indicator value, the first third sub-variable relationship, and the second third sub-variable relationship.

[0116] According to embodiments of this disclosure, when the third variable relationship includes three third sub-variable relationships, such as a first third sub-variable relationship, a second third sub-variable relationship, and a third third sub-variable relationship, the third third sub-variable relationship characterizes the correlation between the trading indicator value and the recommendation indicator value. The recommendation indicator value can be determined based on the trading indicator value, the social relationship indicator value, the first third sub-variable relationship, the second third sub-variable relationship, and the third third sub-variable relationship.

[0117] Figure 4 A flowchart illustrating a method for calculating recommended index values ​​according to an embodiment of the present disclosure is shown.

[0118] like Figure 4 As shown, the flowchart 400 of the method for calculating the recommended index value includes M first objective data, such as the first first objective data 401_1...the Mth first objective data 401_M, and N second objective data, such as the first second objective data 402_1...the Nth second objective data 402_N.

[0119] like Figure 4As shown, based on M primary objective data points, such as the first primary objective data point 401_1…the Mth primary objective data point 401_M and the primary variable relationships, the transaction indicator value 403 is calculated. Based on N secondary objective data points, such as the first secondary objective data point 402_1…the Nth secondary objective data point 402_N and the secondary variable relationships, the social relationship indicator value 404 is calculated.

[0120] The social relationship indicator value is determined based on the transaction indicator value 403 and the relationship between the transaction indicator value 403 and the third variable corresponding to it.

[0121] According to embodiments of this disclosure, determining the relationship between M first objective indicators, N second objective indicators, and target variables that match an application scenario includes: obtaining a relationship table that matches the application scenario based on the scenario identifier of the application scenario, wherein the relationship table includes the relationship between M first objective indicators, N second objective indicators, and target variables.

[0122] According to embodiments of this disclosure, the relationships between the first objective indicator, the second objective indicator, and the target variable are related to the application scenario. In a recommendation scenario, a relationship table matching the application scenario can be directly determined to identify the relationships between M first objective indicators, N second objective indicators, and the target variable under that application scenario. This eliminates the need to determine the relationships between the first objective indicators, second objective indicators, and target variables one by one according to the scenario identifier of the application scenario, thereby improving recommendation efficiency.

[0123] According to embodiments of this disclosure, before obtaining a relationship table matching the application scenario based on the scenario identifier, the following steps are included:

[0124] Based on the scenario identifier of the application scenario, P first initial objective indicators, Q second initial objective indicators, and S subjective indicators are determined. The subjective indicators are used to represent the user's subjective satisfaction, where P≥M≥1, Q≥N≥1, and S≥1.

[0125] Obtain the initial dataset, which includes the third objective data corresponding to the first initial objective indicator, the fourth objective data corresponding to the second initial objective indicator, and the subjective data corresponding to the subjective indicator.

[0126] Generate initial variable relationships based on P third-party objective data, Q fourth-party objective data, and S subjective data.

[0127] Based on the test results of the initial variable relationships, M first objective indicators are determined from P first initial objective indicators, N second objective indicators are determined from Q second initial objective indicators, and the target variable relationships are determined from the initial variable relationships, and a relationship table is generated.

[0128] According to embodiments of this disclosure, before executing the object recommendation method, multiple relationship tables related to multiple application scenarios can be generated in advance, and matching relationships can be established.

[0129] According to embodiments of this disclosure, during the generation of the relationship table, the target variable relationship is determined by filtering multiple first initial objective indicators and multiple second initial objective indicators.

[0130] According to embodiments of this disclosure, in the process of determining the target variable relationship and generating a relationship table, the final relationship between the first objective indicator, the second objective indicator, and the target variable can be determined by determining the relationship between the subjective indicator and the first initial objective indicator and the second initial objective indicator.

[0131] According to embodiments of this disclosure, subjective indicators are used to characterize users' subjective evaluations, and users' subjective satisfaction can be determined based on subjective indicators.

[0132] Specifically, using the subjective data corresponding to the subjective indicators as a benchmark, structural equation modeling is used to process the third and fourth objective data to obtain the initial variable relationships, so as to explore the relationship between objective data and recommended indicator values ​​starting from the subjective data.

[0133] According to embodiments of this disclosure, after obtaining user-defined satisfaction levels through questionnaires, survey reports, or telephone follow-ups, evaluation indicators can be determined based on evaluation ranges. Subjective indicators include evaluation metrics, such as satisfaction levels; they also include user types, such as ordinary users, advanced users, and special users.

[0134] According to embodiments of this disclosure, since user satisfaction is difficult to measure accurately and directly, a structural equation model is used to link subjective and objective indicators through variable relationships. This allows for the direct determination of user satisfaction and the identification of recommended objects based on objective indicators, thereby improving recommendation accuracy.

[0135] According to embodiments of this disclosure, an initial variable relationship is generated based on P third objective data, Q fourth objective data, and S subjective data, including:

[0136] Determine the first covariance matrix among P third objective data points, Q fourth objective data points, and S subjective data points.

[0137] Input the first covariance matrix into the first structural equation model and output the initial variable relationship. The first structural equation model is constructed according to the first assumption relationship, which is determined according to the application scenario.

[0138] According to embodiments of this disclosure, the first covariance matrix represents the covariance among P third objective data, Q fourth objective data, and S subjective data.

[0139] For example, the first initial objective indicators include asset returns x1 and monthly asset returns x2 in the application scenario; the second initial objective indicators include recommendation frequency x3 and number of associated users x4; and the subjective indicators include user level y1 and evaluation indicator y2. The first covariance matrix is ​​shown in Table 1.

[0140] Table 1 First Covariance Matrix

[0141] x1 x2 x3 x4 y1 y2 x1 10.5 x2 5.5 8.7 x3 5.4 4.1 11.6 x4 4.2 4.8 6.4 8.8 y1 -4.1 -2.7 -2.6 -2.4 8.5 y2 -17.6 -16.4 -27.5 -16.6 30.3 399.3

[0142] According to embodiments of this disclosure, after determining the first covariance matrix, the first covariance matrix can be input into the first structural equation model to output the initial variable relationships.

[0143] Figure 5 A schematic diagram of a first structural equation model according to an embodiment of the present disclosure is shown.

[0144] like Figure 5 As shown, the schematic diagram 500 of the first structural equation model can represent the first hypothesis relationship. Here, e1, e2, e3, e4, e5, and e6 correspond to x1, x2, x3, x4, y1, and y2 respectively, representing the data corresponding to x1, x2, x3, x4, y1, and y2. For example, e2 represents the third objective data corresponding to the monthly asset return x2. A represents the transaction indicator value, B represents the social relationship indicator value, and C represents the recommendation indicator value.

[0145] The first set of assumed relationships includes A being related to x1 and x2, B being related to x3 and x4, and C being related to y1 and y2. C is also related to A and B, and B is related to A. For example, A = x1 + x2. The coefficients of x1 and x2 can be determined using the first structural equation model to serve as the initial variable relationship between A and x1 and x2. Other assumed relationships can be: B = A, C = A + B, B = x3 + x4, C = y1 + y2. The process of determining other assumed relationships is similar to that of A and x1 and x2, and will not be elaborated here.

[0146] According to embodiments of this disclosure, after determining the initial variable relationships, a significance test is performed on the initial variable relationships to obtain the test results. Based on the test results of the initial variable relationships, M first objective indicators, N second objective indicators, and the target variable relationships can be determined, and a relationship table can be generated.

[0147] According to embodiments of this disclosure, the method for significance testing includes: calculating a significance coefficient P, and determining the test result based on whether the significance coefficient P reaches a standard threshold. For example, the standard threshold can be 0.001.

[0148] The embodiments of this disclosure, by utilizing a first structural equation model, can objectively determine objective indicators that affect the accuracy of recommendations.

[0149] According to embodiments of this disclosure, based on the test results of the initial variable relationships, M first objective indicators are determined from P first initial objective indicators, N second objective indicators are determined from Q second initial objective indicators, and target variable relationships are determined from the initial variable relationships, and a relationship table is generated, including:

[0150] If the test results do not meet the significance test criteria, based on the test results, M first objective indicators are determined from P first initial objective indicators, and N second objective indicators are determined from Q second initial objective indicators.

[0151] Determine the second covariance matrix among M primary objective indicators, N secondary objective indicators, and S subjective data; and

[0152] The second covariance matrix is ​​input into the second structural equation model, and the target variable relationship is output. The second structural equation model is constructed according to the second hypothesis relationship, which is determined based on the test results.

[0153] According to embodiments of this disclosure, the initial variable relationship includes variable relationships across multiple paths. For example... Figure 5 As shown, the initial variable relationship includes the coefficients of x1 and x2.

[0154] For example, still using Figure 5 For example, when the initial variable relationship is the target variable relationship, the initial variable relationship includes the first variable relationship, the second variable relationship, and the third variable relationship. The first variable relationship includes the coefficients of x1 and x2, the second variable relationship includes the coefficients of x3 and x4, and the third variable relationship includes the coefficients of the assumed relationship between A, B, and C.

[0155] According to embodiments of this disclosure, determining that the test result meets the significance test criteria includes: all variable relationships in the initial variable relationships are less than a standard threshold. Determining that the test result does not meet the significance test criteria includes: there is a variable relationship in the initial variable relationships that is greater than or equal to the standard threshold.

[0156] According to embodiments of this disclosure, if the test results do not meet the significance test criteria, one or more variable relationships in the initial variable relationships that are greater than or equal to the standard threshold are determined based on the test results, and the first initial objective index and / or the second initial objective index related to the above one or more variable relationships are deleted, resulting in M ​​first objective indices and Q second objective indices.

[0157] According to embodiments of this disclosure, a second hypothesis relation is obtained by removing one or more variable relations greater than or equal to a standard threshold from the initial variable relations. The second structural equation model is optimized based on the first structural equation model to obtain an accurate and stable model using fewer objective indicators or variable relations.

[0158] According to embodiments of this disclosure, after determining M first objective indicators and Q second objective indicators, a second covariance matrix is ​​determined among the M first objective indicators, N second objective indicators, and S subjective data; and the second covariance matrix is ​​input into a second structural equation model to output the target variable relationship.

[0159] According to embodiments of this disclosure, if the test results meet the significance test criteria, the current first structural model is deemed to meet the requirements, and no adjustment to the objective indicators and variable relationships is necessary. Therefore, given that the test results meet the significance test criteria, the first initial objective factor indicator is determined as the first objective factor indicator, the second initial objective factor indicator is determined as the second objective factor indicator, and the initial variable relationship is determined as the target variable relationship.

[0160] Figure 6 A schematic diagram of a second structural equation model according to an embodiment of the present disclosure is shown.

[0161] like Figure 6 As shown in the diagram 600, the second structural equation model can represent the second hypothesis relationship. Here, e1, e2, e3, e4, e5, and e6 are data corresponding to x1, x2, x3, x4, y1, and y2, respectively. For example, e2 could be a third objective data point corresponding to the monthly asset return x2. A represents the transaction indicator value, B represents the social relationship indicator value, and C represents the recommendation indicator value.

[0162] like Figure 6 As shown, the second hypothesis modifies the relationship between A and C. In the first structural equation model, there is a relationship between A and C, but in the second structural equation model, there is no relationship between A and C. The other hypotheses are the same as the first hypothesis.

[0163] Table 2 Results of structural equation modeling analysis

[0164] index Target variable relationship coefficient Significance test x1 x1->A 1 pass x2 x2->A 5.597 pass x3 x3->B 1 pass x4 x4->B 0.742 pass y1 y1->C 1 pass y2 y2->C 0.755 pass C B->C 0.770 pass B A->B -0.715 pass

[0165] According to embodiments of this disclosure, after outputting the target variable relationship using the second structural equation model, significance testing and structural equation analysis can be performed on the target variable relationship. Table 2 shows the asset return x1 and monthly asset return x2 in the application scenario, the second initial objective indicators including recommendation frequency x3 and number of associated users x4, the subjective indicators including user level y1, satisfaction evaluation index y2, and the structural equation analysis results of the target variable analysis. The coefficients represent the numerical values ​​of the target variable relationship.

[0166] According to embodiments of this disclosure, after obtaining the target variable relationship, transaction indicator values, social relationship indicator values, and recommendation indicator values ​​can be randomly generated based on the target variable relationship, and the target variable relationship can be verified.

[0167] Figure 7 A schematic block diagram of an object recommendation device according to an embodiment of the present disclosure is shown.

[0168] like Figure 7 As shown, the object recommendation device 700 of this embodiment includes a determination module 710, an acquisition module 720, and a recommendation module 730.

[0169] The determination module 710 is used to determine M first objective indicators, N second objective indicators, and target variable relationships that match the application scenario. The target variable relationships are used to determine the objects to be recommended. The first objective indicators are used to characterize the user's transaction characteristics, and the second objective indicators are used to characterize the user's social relationship characteristics. M≥1, N≥1. In one embodiment, the determination module 710 can be used to perform the operation S210 described above, which will not be repeated here.

[0170] The acquisition module 720 is used to acquire a recommendation dataset for the target user. The recommendation dataset includes first objective data corresponding to a first objective indicator and second objective data corresponding to a second objective indicator. In one embodiment, the acquisition module 720 can be used to perform the operation S220 described above, which will not be repeated here.

[0171] The recommendation module 730 is used to determine the objects to be recommended based on M first objective data, N second objective data, and the relationship between the target variable. In one embodiment, the recommendation module 730 can be used to perform the operation S230 described above, which will not be repeated here.

[0172] According to embodiments of this disclosure, the recommendation module 730 includes a calculation submodule and a recommendation submodule.

[0173] The calculation submodule is used to calculate the recommendation index value based on M first objective data, N second objective data, and the relationship with the target variable. The recommendation index value is used to characterize the user's objective satisfaction. In one embodiment, the calculation submodule can be used to perform the operation S331 described above, which will not be repeated here.

[0174] The recommendation submodule is used to determine objects to be recommended from the recommendation list when the recommendation index value meets preset conditions. The recommendation list includes multiple objects. In one embodiment, the recommendation submodule can be used to perform the operation S332 described above, which will not be repeated here.

[0175] According to embodiments of this disclosure, the target variable relationship includes a first variable relationship, a second variable relationship, and a third variable relationship. The calculation submodule includes a first generation unit, a second generation unit, and a calculation unit.

[0176] The first generation unit is used to generate trading indicator values ​​based on M first objective data and the relationship between first variables.

[0177] The second generation unit is used to generate social relationship index values ​​based on N second objective data and the relationship between the second variables.

[0178] The calculation unit is used to calculate the recommendation indicator value based on the transaction indicator value, the social relationship indicator value, and the third variable relationship.

[0179] According to an embodiment of this disclosure, the determining module 710 includes an acquisition submodule, which is used to acquire a relationship table matching the application scenario based on the scenario identifier of the application scenario. The relationship table includes M first objective indicators, N second objective indicators, and target variable relationships.

[0180] According to embodiments of this disclosure, the object recommendation device 700 further includes a relation table generation submodule. The relation table generation submodule includes: a first determining unit, an acquiring unit, a third generating unit, and a fourth generating unit.

[0181] The first determining unit is used to determine P first initial objective indicators, Q second initial objective indicators and S subjective indicators based on the scenario identifier of the application scenario. The subjective indicators are used to characterize the user's subjective satisfaction, where P≥M≥1, Q≥N≥1, and S≥1.

[0182] The acquisition unit is used to acquire the initial dataset, which includes the third objective data corresponding to the first initial objective indicator, the fourth objective data corresponding to the second initial objective indicator, and the subjective data corresponding to the subjective indicator.

[0183] The third generation unit is used to generate initial variable relationships based on P third objective data, Q fourth objective data, and S subjective data.

[0184] The fourth generation unit is used to determine M first objective indicators from P first initial objective indicators, N second objective indicators from Q second initial objective indicators, and target variable relationships from the initial variable relationships based on the test results of the initial variable relationships, and generate a relationship table.

[0185] According to embodiments of this disclosure, the third generation unit includes a first determining subunit and a first output subunit.

[0186] The first determining subunit is used to determine the first covariance matrix among P third objective data, Q fourth objective data, and S subjective data.

[0187] The first output sub-unit is used to input the first covariance matrix into the first structural equation model and output the initial variable relationship. The first structural equation model is constructed according to the first assumption relationship, which is determined according to the application scenario.

[0188] According to embodiments of this disclosure, the fourth generation unit includes a second determining subunit, a third determining subunit, and a second output subunit.

[0189] The second determining subunit is used to determine M first objective indicators from P first initial objective indicators and N second objective indicators from Q second initial objective indicators when the determination test result does not meet the significance test criteria.

[0190] The third determining subunit is used to determine the second covariance matrix among M first objective indicators, N second objective indicators, and S subjective data.

[0191] The second output sub-unit is used to input the second covariance matrix into the second structural equation model and output the target variable relationship. The second structural equation model is constructed according to the second hypothesis relationship, which is determined based on the test results.

[0192] According to embodiments of this disclosure, the first objective indicator includes at least one of the following: monthly asset returns and asset returns under the application scenario; the second objective indicator includes at least one of the following: the number of associated users and the recommendation frequency.

[0193] According to embodiments of this disclosure, any and multiple modules among the determining module 710, obtaining module 720, and recommending module 730 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functionality of one or more of these modules can be combined with at least some of the functionality of other modules and implemented in one module.

[0194] According to embodiments of this disclosure, at least one of the determining module 710, obtaining module 720, and recommending module 730 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, at least one of the determining module 710, obtaining module 720, and recommending module 730 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0195] Figure 8 A block diagram schematically illustrates an electronic device suitable for an object recommendation method according to an embodiment of the present disclosure.

[0196] like Figure 8 As shown, an electronic device 800 according to an embodiment of this disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0197] RAM 803 stores various programs and data required for the operation of electronic device 800. Processor 801, ROM 802, and RAM 803 are interconnected via bus 804. Processor 801 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 802 and / or RAM 803. It should be noted that the programs may also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0198] According to embodiments of this disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the input / output I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0199] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0200] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 802 and / or RAM 803 and / or one or more memories other than ROM 802 and RAM 803 described above.

[0201] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0202] When the computer program is executed by the processor 801, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0203] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 809, and / or installed from a removable medium 811. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0204] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by processor 801, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0205] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0206] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0207] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0208] The specific embodiments described above further illustrate the purpose, technical solutions, and beneficial effects of this disclosure. It should be understood that the above descriptions are merely specific embodiments of this disclosure and are not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. An object recommendation method, comprising: M first objective indicators, N second objective indicators, and target variable relationships are determined to match the application scenario. The target variable relationships are used to determine the objects to be recommended. The first objective indicators are used to characterize the user's transaction characteristics, and the second objective indicators are used to characterize the user's social relationship characteristics. M≥1, N≥1; the target variable relationships include first variable relationships, second variable relationships, and third variable relationships. Obtain a recommendation dataset for the target user, the recommendation dataset including first objective data corresponding to the first objective indicator and second objective data corresponding to the second objective indicator; Based on the relationship between the M first objective data and the first variable, generate trading indicator values; The first variable relationship corresponds to the first objective indicator; Based on the relationship between N second objective data points and the second variable, generate social relationship index values; The second variable relationship corresponds to the second objective indicator; Based on the transaction indicator value, social relationship indicator value, and the third variable relationship, a recommendation indicator value is calculated. The recommendation indicator value is used to characterize the user's objective satisfaction. The third variable relationship includes at least: a first third sub-variable relationship, used to characterize the correlation between the transaction indicator value and the social relationship indicator value, and a second third sub-variable relationship, used to characterize the correlation between the social relationship indicator value and the recommendation indicator value. as well as If the recommended index value meets the preset conditions, the recommended object is determined from the recommendation list, which includes multiple objects.

2. The method according to claim 1, wherein, The determination of the relationship between M first objective indicators, N second objective indicators, and target variables that match the application scenario includes: Based on the scenario identifier of the application scenario, obtain a relationship table that matches the application scenario. The relationship table includes M first objective indicators, N second objective indicators, and the target variable relationship.

3. The method according to claim 2, wherein, Before obtaining the relationship table matching the application scenario based on the scenario identifier, the process includes: Based on the scenario identifier of the application scenario, P first initial objective indicators, Q second initial objective indicators and S subjective indicators are determined. The subjective indicators are used to characterize the user's subjective satisfaction, where P≥M≥1, Q≥N≥1, and S≥1. Obtain an initial dataset, which includes third objective data corresponding to the first initial objective indicator, fourth objective data corresponding to the second initial objective indicator, and subjective data corresponding to the subjective indicator; Based on P third objective data points, Q fourth objective data points, and S subjective data points, generate initial variable relationships; and Based on the test results of the initial variable relationship, M first objective indicators are determined from P first initial objective indicators, N second objective indicators are determined from Q second initial objective indicators, and the target variable relationship is determined from the initial variable relationship, and the relationship table is generated.

4. The method according to claim 3, wherein, The step of generating initial variable relationships based on P third objective data points, Q fourth objective data points, and S subjective data points includes: Determine the first covariance matrix among P third objective data points, Q fourth objective data points, and S subjective data points; and The first covariance matrix is ​​input into the first structural equation model, and the initial variable relationship is output. The first structural equation model is constructed according to the first assumption relationship, which is determined according to the application scenario.

5. The method according to claim 3, wherein, Based on the test results of the initial variable relationships, M first objective indicators are determined from P first initial objective indicators, N second objective indicators are determined from Q second initial objective indicators, and the target variable relationship is determined from the initial variable relationships, and the relationship table is generated, including: If the test result does not meet the significance test criteria, based on the test result, M first objective indicators are determined from P first initial objective indicators, and N second objective indicators are determined from Q second initial objective indicators; Determine the second covariance matrix among M first objective indicators, N second objective indicators, and S subjective data; and The second covariance matrix is ​​input into the second structural equation model, and the target variable relationship is output. The second structural equation model is constructed according to the second hypothesis relationship, which is determined based on the test results.

6. The method according to claim 1, wherein, The first objective indicator includes at least one of the following: monthly asset returns and asset returns under the application scenario; the second objective indicator includes at least one of the following: the number of associated users and the recommendation frequency.

7. An object recommendation device, comprising: The determination module is used to determine M first objective indicators, N second objective indicators, and target variable relationships that match the application scenario. The target variable relationships are used to determine the objects to be recommended. The first objective indicators are used to characterize the user's transaction characteristics, and the second objective indicators are used to characterize the user's social relationship characteristics. M≥1, N≥1; the target variable relationships include first variable relationships, second variable relationships, and third variable relationships. The acquisition module is used to acquire the recommendation dataset of the target user, wherein the recommendation dataset includes first objective data corresponding to the first objective indicator and second objective data corresponding to the second objective indicator; as well as The first generation unit is used to generate trading indicator values ​​based on M pieces of the first objective data and the first variable relationship; The first variable relationship corresponds to the first objective indicator; The second generation unit is used to generate social relationship index values ​​based on N second objective data and the relationship between the second variables; The second variable relationship corresponds to the second objective indicator; The calculation unit is used to calculate the recommendation index value based on the transaction index value, the social relationship index value, and the third variable relationship. The recommendation index value is used to characterize the user's objective satisfaction. The third variable relationship includes at least: a first third sub-variable relationship, used to characterize the correlation between the transaction index value and the social relationship index value, and a second third sub-variable relationship, used to characterize the correlation between the social relationship index value and the recommendation index value. as well as The recommendation submodule is used to determine the objects to be recommended from the recommendation list when the recommendation index value meets the preset conditions. The recommendation list includes multiple objects.

8. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program that, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 6.

Images