A virtual resource recommendation method and device, electronic equipment and storage medium

Abstract

The application discloses a virtual resource recommendation method and device, electronic equipment and storage medium, the method comprises the following steps: according to the quality analysis index of multidimension, resource screening is carried out on resource theme, and target resource theme is obtained. At least two types of theme virtual resources associated with the target resource theme are determined from the virtual resources to be recommended. Based on the resource recommendation index corresponding to the at least two types of theme virtual resources, resource screening is carried out on the at least two types of theme virtual resources respectively, and the target virtual resources corresponding to the at least two types of theme virtual resources are obtained. The recommendation operation is performed on the target virtual resources. The method can improve the diversity of virtual resource screening by screening different types of theme virtual resources with different resource recommendation indexes, so that more comprehensive recommendation can be made when recommending virtual resources, the effectiveness of virtual resource recommendation is improved, and the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a method, apparatus, electronic device and storage medium for recommending virtual resources. Background Technology

[0002] With the increasing demand for wealth management and the growing popularity of funds, more and more users have been investing in the stock and mutual fund markets in recent years. The rapid changes in market themes in recent years have led to a surge in user attention to thematic investing. Therefore, thematic investing, as a highly efficient way to generate profits, is being accepted and used by an increasing number of investors.

[0003] In existing technologies, funds corresponding to a theme are usually screened manually or using a single indicator. Users cannot intuitively perceive the relationship between the fund and the theme, as well as the current status of the theme. This results in low diversity in fund screening and low effectiveness in fund recommendations. Summary of the Invention

[0004] This application provides a virtual resource recommendation method, apparatus, electronic device, and storage medium, which can improve the diversity of virtual resource screening and enhance the effectiveness of virtual resource recommendation.

[0005] On the one hand, this application provides a virtual resource recommendation method, the method comprising:

[0006] Obtain the quality analysis indicators of the resource topics corresponding to the virtual resources to be recommended under multiple topic analysis dimensions;

[0007] Based on the quality analysis indicators, the resource topics are screened to obtain target resource topics;

[0008] From the virtual resources to be recommended, determine at least two types of topic virtual resources that are associated with the target resource topic;

[0009] Obtain resource recommendation metrics for at least two types of themed virtual resources;

[0010] Based on the resource recommendation indicators, resource filtering is performed on the at least two types of theme virtual resources to obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources.

[0011] Perform recommended operations on the target virtual resource.

[0012] On the other hand, a virtual resource recommendation device is provided, the device comprising:

[0013] The quality analysis index acquisition module is used to acquire the quality analysis indexes of the resource topics corresponding to the virtual resources to be recommended under multiple topic analysis dimensions.

[0014] The target resource topic acquisition module is used to filter the resource topics according to the quality analysis indicators to obtain target resource topics.

[0015] The theme virtual resource determination module is used to determine at least two types of theme virtual resources associated with the target resource theme from the virtual resources to be recommended;

[0016] The resource recommendation metric acquisition module is used to acquire resource recommendation metrics corresponding to at least two types of theme virtual resources.

[0017] The resource filtering module is used to filter the at least two types of theme virtual resources based on the resource recommendation indicators, and obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources.

[0018] The resource recommendation module is used to perform recommendation operations on the target virtual resources.

[0019] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement a virtual resource recommendation method as described above.

[0020] On the other hand, a computer-readable storage medium is provided, the storage medium including a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement a virtual resource recommendation method as described above.

[0021] On the other hand, a computer program product is provided, including a computer program that, when executed by a processor, implements the virtual resource recommendation method as described above.

[0022] This application provides a virtual resource recommendation method, apparatus, electronic device, and storage medium. The method includes: acquiring quality analysis indicators of resource topics corresponding to virtual resources to be recommended under multiple topic analysis dimensions; filtering resource topics based on multi-dimensional quality analysis indicators to obtain target resource topics; identifying at least two types of topic virtual resources associated with the target resource topics from the virtual resources to be recommended; filtering the at least two types of topic virtual resources separately based on resource recommendation indicators corresponding to each of the at least two types of topic virtual resources to obtain target virtual resources corresponding to each of the at least two types of topic virtual resources; and performing a recommendation operation on the target virtual resources. This method improves the diversity of virtual resource filtering by filtering different types of topic virtual resources with different resource recommendation indicators, thereby enabling more comprehensive recommendations, improving the effectiveness of virtual resource recommendations, and enhancing user experience. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram illustrating an application scenario of a virtual resource recommendation method provided in an embodiment of this application.

[0025] Figure 2 A flowchart illustrating a virtual resource recommendation method provided in this application embodiment;

[0026] Figure 3 This application provides a flowchart illustrating resource filtering in a virtual resource recommendation method.

[0027] Figure 4 This is a flowchart illustrating the resource filtering of a first type of virtual resource in a virtual resource recommendation method provided in an embodiment of this application;

[0028] Figure 5 This is a flowchart illustrating the resource filtering of a first type of virtual resource in a virtual resource recommendation method provided in an embodiment of this application;

[0029] Figure 6 A flowchart illustrating the process of obtaining relevant display information on topic popularity in a virtual resource recommendation method provided in this application embodiment;

[0030] Figure 7A schematic diagram of a topic recommendation page in a virtual resource recommendation method provided in an embodiment of this application;

[0031] Figure 8 A schematic diagram of a resource recommendation page in a virtual resource recommendation method provided in an embodiment of this application;

[0032] Figure 9 A flowchart illustrating the acquisition of popularity fluctuation information and popularity prompt information in a virtual resource recommendation method provided in this application embodiment;

[0033] Figure 10 A schematic diagram of the curve corresponding to the popularity fluctuation information in a virtual resource recommendation method provided in this application embodiment;

[0034] Figure 11 This is a schematic diagram illustrating the execution logic of a virtual resource recommendation method provided in this application when applied to fund recommendation.

[0035] Figure 12 This is a schematic diagram of the structure of a virtual resource recommendation device provided in an embodiment of this application;

[0036] Figure 13 This is a schematic diagram of the hardware structure of a device for implementing the method provided in the embodiments of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0038] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Furthermore, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein.

[0039] Please see Figure 1This illustration shows an application scenario diagram of a virtual resource recommendation method provided in this application embodiment. The application scenario includes a client 110 and a server 120. The server 120 obtains the quality analysis indicators of the resource topic corresponding to the virtual resource to be recommended under multiple topic analysis dimensions, and performs resource filtering on the resource topic according to the quality analysis indicators to obtain the target resource topic. From the virtual resources to be recommended, the server 120 determines at least two types of topic virtual resources associated with the target resource topic. The server 120 obtains the resource recommendation indicators corresponding to each of the at least two types of topic virtual resources, and then performs resource filtering on the at least two types of topic virtual resources respectively based on the resource recommendation indicators to obtain the target virtual resources corresponding to each of the at least two types of topic virtual resources. The server 120 pushes the target virtual resources to the client 110 for display. The server 120 can also calculate the topic popularity information of the target resource topic and push the topic popularity information to the client 110 for display as well.

[0040] In this embodiment, client 110 includes physical devices such as smartphones, desktop computers, tablets, laptops, digital assistants, and smart wearable devices, and may also include software running on the physical device, such as applications. The operating system running on the physical device in this embodiment may include, but is not limited to, Android, iOS, Linux, Unix, and Windows. Client 110 includes a UI (User Interface) layer, through which it provides the display of topic popularity information and target virtual resources. Additionally, it sends user data required for data analysis to server 120 based on API (Application Programming Interface). It should be noted that all user information involved in this application (including but not limited to user device information and user personal information) is information authorized by the user or fully authorized by all parties.

[0041] In this embodiment, server 120 may include a standalone server, a distributed server, or a server cluster consisting of multiple servers. Server 120 may include a network communication unit, a processor, and memory, etc. Specifically, server 120 can be used to determine the target resource topic, the target virtual resource corresponding to the target resource topic, and the topic popularity information of the target resource topic.

[0042] Please see Figure 2 It demonstrates a virtual resource recommendation method applicable to the server side, the method comprising:

[0043] S210. Obtain the quality analysis indicators of the resource topics corresponding to the virtual resources to be recommended under multiple topic analysis dimensions;

[0044] In some embodiments, before obtaining quality analysis indicators, a preliminary screening step can be performed. In this preliminary screening step, initial resource topics suitable for topic recommendation are determined from the resource topics corresponding to the virtual resources to be recommended. Then, quality analysis indicators of the initial resource topics under multiple topic analysis dimensions are obtained. The quality analysis indicators are indicators determined based on topic quality information and user interest information. Topic quality information may include price fluctuations, net inflow of main funds, etc., while user interest information may include user search volume, news popularity, etc.

[0045] In some embodiments, during the initial screening, resource topics can be filtered according to preset initial screening conditions to obtain initial resource topics that meet the conditions. Initial screening conditions may include constituent stock quantity conditions, resource quantity screening conditions, topic content conditions, and topic similarity conditions, etc., and are used to measure the applicability of resource topics for topic recommendation. The constituent stock quantity condition can be a preset range of constituent stock quantity. Resource topics are sorted according to the number of constituent stocks, and resource topics matching the constituent stock quantity range are obtained. Resource topics with a number of constituent stocks less than the minimum value of the range are removed, as are those with a number of constituent stocks greater than the maximum value. For example, if the constituent stock quantity range is 100 to 500, and resource topic A has only 1 constituent stock while resource topic B has 1981 constituent stocks, then resource topic A and resource topic B can be removed. The resource quantity screening condition can be a preset topic market capitalization. Resource topics with a market capitalization less than or equal to the preset topic market capitalization are removed, as these resource topics pose a certain risk and therefore need to be removed. The theme content condition identifies resource themes with relatively clear content, meaning there needs to be a clear correspondence between the theme content and the resource theme. For example, biopharmaceuticals is a specific theme, while Shanghai-Hong Kong Stock Connect is a broader resource theme encompassing many different themes. The theme similarity condition assesses the similarity between the names, content, or corresponding constituent stocks of resource themes. During the initial screening, at least two resource themes with a similarity greater than or equal to the theme similarity condition are deduplicated. Therefore, each pair of initial resource themes is independent, there are no duplicate resource themes, and the initial resource themes correspond to the theme content, meaning the initial resource themes have definite thematic content.

[0046] S220. Based on the quality analysis indicators, resource topics are screened to obtain target resource topics;

[0047] In some embodiments, the quality analysis indicators can be reacquired every preset time period to update the original quality analysis indicators. Based on the updated quality analysis indicators, resource topics can be filtered to obtain updated target resource topics.

[0048] In some embodiments, the quality analysis indicators are indicators corresponding to multiple quality analysis dimensions. The rise and fall of each resource theme index in the quality analysis indicators can include the rise and fall of each resource theme index over a period of time, which may include the rise and fall of each resource theme index over a first preset period of time and the rise and fall of each resource theme index over a second preset period of time. The main capital inflow in the quality analysis indicators is the sum of the net main capital inflows of each resource theme index over a period of time, which may include the main capital inflows of each resource theme index over a first preset period of time and the main capital inflows of each resource theme index over a second preset period of time. The information popularity in the quality analysis indicators is the number of related news articles for each resource theme index over a period of time, which may include the information popularity of each resource theme index over a first preset period of time and the information popularity of each resource theme index over a second preset period of time. The first preset period of time may be one week and the second preset period of time may be one month.

[0049] For each resource topic, the quality analysis indicators corresponding to multiple quality analysis dimensions are weighted and summed to obtain the target quality analysis indicator for each resource topic. Based on the target quality analysis indicator, the resource topics are sorted from largest to smallest. Resource topics with target quality analysis indicators greater than or equal to preset quality conditions are selected as target resource topics, or the top preset number of resource topics are selected as target resource topics. The weight information for the weighted summation is the preset weight of the quality analysis indicators. For example, the weights for price fluctuation, net inflow of main funds, number of user searches, and news popularity are set to 30%, 30%, 30%, and 10%, respectively, with the weights of two specific indicators in price fluctuation, net inflow of main funds, number of user searches, and news popularity both at 50% and 50%. Based on these two weights, the quality analysis indicators for each resource topic are weighted and summed, then sorted and filtered to determine the target resource topics.

[0050] In some embodiments, resource topic buffer information can be set when obtaining target resource topics. During the first virtual resource recommendation, a first preset number of target resource topics can be obtained; during subsequent virtual resource recommendations, a second preset number of target resource topics can be obtained, and these second preset number of target resource topics are used as resource topic buffer information. The previous target resource topic from the previous virtual resource recommendation is obtained for each virtual resource recommendation. Based on the previous target resource topic and the resource topic buffer information, the target resource topic corresponding to each virtual resource recommendation is determined. That is, if the resource topic buffer information includes the previous target resource topic, then the first preset number of target resource topics and the previous target resource topic are obtained from the resource topic buffer information; if the previous target resource topic is included in the first preset number of target resource topics, then the first preset number of target resource topics can be directly obtained. If the resource topic buffer information does not include the previous target resource topic, then the first preset number of target resource topics are obtained from the resource topic buffer information.

[0051] For example, during the first virtual resource recommendation, the top 6 resource topics were selected as target resource topics from the ranking of resource topics, with topic C being ranked 5th. During the second virtual resource recommendation, the top 13 resource topics were selected as target resource topics from the ranking of resource topics, with topic C being ranked 7th. Therefore, the top 6 resource topics and topic C were selected from these top 13 resource topics, and the virtual resource recommendation was continued.

[0052] By using multiple dimensions of quality analysis indicators to filter resource topics, the accuracy and comprehensiveness of resource topic selection can be improved, resulting in high-quality target resource topics that match user interests.

[0053] S230. From the virtual resources to be recommended, identify at least two types of topic virtual resources that are associated with the topic of the target resource;

[0054] In some embodiments, when determining at least two types of virtual resources associated with a target resource topic, first fluctuation information corresponding to the target resource topic and second fluctuation information corresponding to the virtual resource to be recommended can be obtained. The first fluctuation information can be a change curve of the target resource topic within a preset historical time period, and the second fluctuation information can be a change curve of the virtual resource to be recommended within the preset historical time period. The first fluctuation information and the second fluctuation information are compared to determine the similarity between them.

[0055] Obtain the percentage information of sample virtual resources that correspond to the target resource theme in the virtual resources to be recommended. For example, if the recommended virtual resource is a fund, obtain the percentage of constituent stocks in the fund that correspond to the target resource theme.

[0056] If the similarity meets a preset similarity condition and the proportion information meets a preset ratio condition, then thematic virtual resources associated with the target resource theme are obtained. These thematic virtual resources are then categorized to obtain at least two types of thematic virtual resources. The preset similarity condition can be that the similarity between the first fluctuation information and the second fluctuation information is greater than or equal to a preset similarity; for example, the similarity between the first fluctuation information corresponding to the trend of the target resource theme and the second fluctuation information corresponding to the trend of the fund reaches 80% or more. The preset ratio condition can be that the proportion information is greater than or equal to a preset ratio; for example, the proportion of constituent stocks in the fund corresponding to the target resource theme is 10% or more.

[0057] In some embodiments, if the target resource topic is a newly added resource topic and there is no corresponding first fluctuation information, then the virtual resources whose proportion of sample virtual resources corresponding to the target resource topic is greater than a preset proportion threshold and the virtual resources whose proportion of holding virtual resources corresponding to the target resource topic is greater than a preset proportion threshold can be obtained. These two virtual resources are compared, and the smaller number of virtual resources is obtained to perform subsequent steps.

[0058] Different algorithms are used to filter newly added and non-new target resource topics, thus ensuring that newly added target resource topics are also included in the reference scope, thereby increasing the diversity and comprehensiveness of virtual resource screening.

[0059] S240. Obtain resource recommendation metrics for at least two types of themed virtual resources;

[0060] S250. Based on resource recommendation indicators, perform resource screening on at least two types of theme virtual resources respectively to obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources;

[0061] In some embodiments, see Figure 3 At least two types of themed virtual resources, including a first type of virtual resource and a second type of virtual resource, are selected based on resource recommendation metrics. The target virtual resources corresponding to each of the at least two types of themed virtual resources are then obtained, including:

[0062] S310. Based on the resource recommendation indicators corresponding to the first type of virtual resources, the first type of virtual resources are screened to obtain the first target virtual resources;

[0063] S320. Based on the resource recommendation indicators corresponding to the second type of virtual resources, the second type of virtual resources are screened to obtain the second target virtual resources;

[0064] S330. Use the first target virtual resource and the second target virtual resource as target virtual resources.

[0065] In some embodiments, the changes in the virtual resources of the first type are similar. The first type of virtual resource can be an index fund, which passively follows a certain index and changes with the index it follows. Therefore, the changing trends of index funds corresponding to the same index are similar. The changes in the virtual resources of the second type are different. The second type of virtual resource can be an actively managed fund, which adjusts according to market changes. Therefore, the changing trends of actively managed funds are different.

[0066] In some embodiments, the first type of virtual resource and the second type of virtual resource can correspond to different resource recommendation metrics. By filtering the first type of virtual resource according to its resource recommendation metrics, a first target virtual resource can be obtained. Similarly, by filtering the second type of virtual resource according to its resource recommendation metrics, a second target virtual resource can be obtained.

[0067] The first target virtual resource and the second target virtual resource are obtained from the first type of virtual resource and the second type of virtual resource, respectively, and used as target virtual resources. For example, if a certain target resource topic requires six target virtual resources associated with the topic, then two first target virtual resources corresponding to the first type of virtual resource and four second target virtual resources corresponding to the second type of virtual resource can be obtained.

[0068] Based on different types of virtual resources, the target virtual resources corresponding to each type of virtual resource are determined, so that each type of virtual resource can be filtered out to meet different user needs and improve the comprehensiveness and diversity of target virtual resource filtering.

[0069] In some embodiments, see Figure 4 The first type of virtual resources includes multiple virtual resources. Based on the resource recommendation indicators corresponding to the first type of virtual resources, the first type of virtual resources are filtered to obtain the first target virtual resources, which include:

[0070] S410. Determine the resource set type corresponding to each virtual resource in the first type of virtual resources and the resource recommendation index corresponding to the first type of virtual resources;

[0071] S420. Based on the resource recommendation indicators, perform resource filtering on virtual resources of the same resource set type in the first type of virtual resources to obtain the initial filtering results;

[0072] S430. Determine the first target virtual resource from the initial screening results.

[0073] In some embodiments, the resource set type is the market indication information corresponding to the first type of virtual resource. If the first type of virtual resource is an index fund, the resource set type can be the index tracked by the index fund. The resource recommendation indicator corresponding to the first type of virtual resource can be resource quantity information, which represents the size of the first type of virtual resource. Resource quantity information can be the fund size, i.e., the fund's net asset value. Under each resource set type, the initial screening results are obtained by sorting according to the size of the resource quantity information. Then, the initial screening results are sorted again according to the size of the resource quantity information to determine the first target virtual resource. When sorting according to the size of the resource quantity information under each resource set type, the first type of virtual resource can be deduplicated.

[0074] When screening the first type of virtual resources, since the changing trends of the first type of virtual resources are relatively consistent, a relatively small number of resource recommendation indicators can be selected for screening based on this characteristic of the first type of virtual resources, thereby improving screening efficiency and reducing time and computing costs.

[0075] In some embodiments, see Figure 5 Based on the resource recommendation indicators corresponding to the second type of virtual resources, the second type of virtual resources are filtered to obtain the second target virtual resources, which include:

[0076] S510. Obtain resource recommendation metrics under multiple resource recommendation dimensions corresponding to the second type of virtual resources;

[0077] S520. Weighted summation of multiple resource recommendation indicators to obtain the target resource recommendation indicator;

[0078] S530. Based on the target resource recommendation indicators, the second type of virtual resources are screened to obtain the second target virtual resources.

[0079] In some embodiments, the resource recommendation metric is an indicator derived from resource quality information and user interest information of virtual resources. Resource quality information includes resource quantity information, resource return information, and resource risk information, while user interest information may include award information and attention information.

[0080] Resource quantity information is information that characterizes the size of the second type of virtual resources. Resource quantity information can be the fund size, that is, the fund's net asset value.

[0081] Resource return information characterizes the return on the second type of virtual resources. This information can include the cumulative return rate over the first time period, the cumulative return rate over the second time period, and the cumulative return rate over the third time period. If the third time period is longer than the second time period, and the second time period is longer than the first time period, the cumulative return rates of the third time period, the second time period, and the first time period can be weighted and summed at 60%, 30%, and 10% respectively to calculate the resource return information. It is necessary to select the second type of virtual resources with the highest return rate. The first time period can be one year, the second time period can be three years, and the third time period can be five years.

[0082] Resource risk information characterizes the risk profile of the second type of virtual resource. This information can include the annualized volatility over the second time period, the volatility over the first time period, the maximum drawdown over the second time period, the maximum drawdown over the first time period, the ranking stability of the virtual resource over the second time period, the risk-adjusted return over the second time period, and the risk-adjusted return over the first time period. The risk-adjusted return can be represented by the Sharpe ratio, which comprehensively considers both risk and return. The annualized volatility over the second time period, the volatility over the first time period, the maximum drawdown over the second time period, the maximum drawdown over the first time period, the ranking stability of the virtual resource over the second time period, the risk-adjusted return over the second time period, and the risk-adjusted return over the first time period can be weighted and summed according to weights of 20%, 10%, 20%, 10%, 20%, 10%, and 10%, respectively, to calculate the resource risk information. The selected second-type virtual resource should exhibit low volatility, low drawdown, stable ranking, and a high Sharpe ratio. The first time period can be one year, and the second time period can be three years.

[0083] Award information can include the type of award and the number of awards received. The award type and the number of awards can be weighted and summed at 30% and 70% respectively to calculate the award information. Among them, the second type of virtual resource with the most award types and the most awards received should be selected.

[0084] Attention information represents the degree of attention users or investment institutions pay to the second type of virtual resources. Attention information can include changes in holders and changes in scale. Changes in holders can include the number of new holders in the most recent period, and the ratio between the number of new holders in the most recent period and the number of holders at the end of the previous period. The number of new holders in the most recent period and this ratio can be weighted and summed at 70% and 30% respectively to calculate the change in holders information. Changes in scale can include the scale of new resources in the most recent quarter, and the ratio between the scale of new resources in the most recent quarter and the scale of resources at the end of the previous quarter. The scale of new resources in the most recent quarter and this ratio can be weighted and summed at 70% and 30% respectively to calculate the change in scale information. Attention information can be calculated by weighting the changes in holders and the change in scale at 50% and 50% respectively. The focus should be on second-type virtual resources where both the number of holders and the scale have increased.

[0085] In some embodiments, resource quantity information, resource revenue information, resource risk information, award information, and attention information can be weighted and summed according to weights of 15%, 40%, 25%, 10%, and 10% to calculate the target resource recommendation index corresponding to the second type of virtual resource.

[0086] Based on the target resource recommendation index, the second type of virtual resources are sorted. From the sorted second type of virtual resources, the second type of virtual resources that meet the target resource recommendation index are selected as the second target virtual resources. Alternatively, if the smaller the index, the better, the first preset number of second type virtual resources are selected as the second target virtual resources.

[0087] When screening second-type virtual resources, since the changing trends of second-type virtual resources vary, more comprehensive quality information of second-type virtual resources can be obtained through multi-dimensional resource recommendation indicators, thereby improving the accuracy and comprehensiveness of screening second-type virtual resources.

[0088] S260. Perform the recommended operation on the target virtual resource.

[0089] In some embodiments, when performing a recommendation operation on a target virtual resource, the target resource topic corresponding to the target virtual resource can be displayed simultaneously, along with the topic popularity information corresponding to the target resource topic.

[0090] In some embodiments, after filtering resource topics based on quality analysis indicators to obtain target resource topics, the method further includes:

[0091] Obtain resource quantity popularity data and operation popularity data corresponding to the target resource topic. Resource quantity popularity data is used to measure the resource quantity of the virtual resources corresponding to the target resource topic, and operation popularity data is used to measure the operation frequency of the virtual resources corresponding to the target resource topic.

[0092] The resource volume popularity data and operation popularity data are weighted and summed to obtain the topic popularity information corresponding to the target resource topic.

[0093] In some embodiments, resource volume heat data can be used to measure the resource volume of virtual resources corresponding to a target resource theme. When the virtual resource is a fund and the target resource theme is the theme corresponding to the fund, the resource volume can represent the value of the fund. Therefore, resource volume heat data can be determined based on the value of the fund. Thus, resource volume heat data can be valuation heat data, which includes the historical percentile of the trailing twelve months price-earnings ratio (PE-TTM) and the historical percentile of the last file price-to-book ratio (PB-LF). PE-TTM is the data in the corresponding report file for the historical time period, and PB-LF is the real-time data in the last report file. PE-TTM is the ratio of the market capitalization of all constituent stocks under the target resource theme to the net profit of all constituent stocks over the past 12 months. PB-LF is the ratio of the market capitalization of all constituent stocks under the target resource theme to the net assets of all constituent stocks. The historical percentiles of PE-TTM and PB-LF can be weighted and summed with weights of 70% and 30% respectively to calculate the resource volume heat data.

[0094] In some embodiments, operation frequency data can be used to measure the operation frequency of virtual resources corresponding to a target resource theme. When the virtual resource is a fund and the target resource theme is the theme corresponding to the fund, the operation frequency can represent the trading frequency of the fund, thus operation frequency data can be determined based on the trading frequency of the fund. Therefore, operation frequency data can be considered trading frequency data. Trading frequency data includes turnover rate indicators, trading volume indicators, the percentage of stocks hitting new highs, and northbound capital inflow indicators.

[0095] The turnover rate metric is the historical percentile of the average turnover rate of the virtual resources corresponding to the target resource theme within a preset time period. The preset period can be 5 years, and the preset time period can be several months or several weeks.

[0096] The turnover rate metric is the historical percentile of the ratio between the industry's trading volume and the free-float market capitalization. The trading volume ratio is the ratio between the industry's trading volume for each target resource theme and the total market trading volume. The free-float market capitalization ratio is the ratio between the industry's free-float market capitalization for each target resource theme and the total market free-float market capitalization.

[0097] The percentage of stocks hitting new highs is the historical percentile of the number of stocks that reached new highs in the past year within a preset time period under the target resource theme. The preset time period can be 20 days. The highest price of the stocks that reached new highs in the past year within the preset time period is the ratio of the number of stocks with the highest price in the past year to the total number of constituent stocks. Based on this ratio, the stocks that reached new highs in the past year within the preset time period are determined, and the number of such stocks is calculated.

[0098] The Northbound Capital Index is the historical percentile of the total market value of stocks held by Northbound Capital within a preset time period, which can be up to 5 years. The Northbound Capital Index can also be calculated as the sum of the market value of all constituent stocks under the target resource theme held by Northbound Capital.

[0099] The turnover rate, trading volume, percentage of stocks hitting new highs, and northbound capital inflows can be weighted and summed at 25%, 25%, 25%, and 25% respectively to calculate the trading activity data.

[0100] The resource volume popularity data and operation popularity data can be weighted and summed with 50% and 50% weights respectively to obtain the topic popularity information corresponding to the target resource topic.

[0101] By calculating topic popularity information, users can be alerted to current risks and opportunities, thereby improving the accuracy and effectiveness of users' actions and enhancing the user experience.

[0102] In some embodiments, see Figure 6 The method also includes:

[0103] S610. Based on topic popularity information, generate the topic popularity value corresponding to the target resource topic;

[0104] S620. Based on the topic popularity value and the preset popularity range, generate the target popularity range corresponding to the target resource topic;

[0105] S630. Generate resource quantity heat value based on resource quantity heat data in topic heat information;

[0106] S640. Generate operation popularity values ​​based on operation popularity data in topic popularity information;

[0107] In some embodiments, based on topic popularity information, the topic popularity value corresponding to the target resource topic is calculated, and the resource quantity popularity value corresponding to resource quantity popularity data and the operation popularity value corresponding to operation popularity data can also be determined. The topic popularity value is obtained by weighted summation of the resource quantity popularity value and the operation popularity value. The resource quantity popularity value, operation popularity value, and topic popularity value can be values ​​between 0 and 100. For example, the resource quantity popularity value is 75, the operation popularity value is 55, and the topic popularity value is 65. If the popularity value is expressed in the form of a thermometer, the unit of the popularity value can be set to ℃. That is, the resource quantity popularity value is 75℃, the operation popularity value is 55℃, and the topic popularity value is 65℃.

[0108] The target popularity range is determined based on the topic popularity value and is used to measure the current popularity status of the target resource topic. The target popularity range can be the interval corresponding to the topic popularity value within a preset popularity range. The preset popularity range can be set to the intervals corresponding to four different popularity states, including the first temperature interval corresponding to the overheated state, the second temperature interval corresponding to the moderately hot state, the third temperature interval corresponding to the moderately cold state, and the fourth temperature interval corresponding to the overheated state.

[0109] The topic popularity value corresponding to the first temperature range is greater than or equal to the first preset popularity value. The topic popularity value corresponding to the second temperature range is less than the first preset popularity value but greater than the second preset popularity value. The topic popularity value corresponding to the third temperature range is less than or equal to the second preset popularity value but greater than the third preset popularity value. The topic popularity value corresponding to the fourth temperature range is less than or equal to the fourth preset popularity value. The first preset popularity value can be 90, the second preset popularity value can be 50, and the third preset popularity value can be 10. Both excessively high and low topic popularity values ​​indicate potential risk for the target resource topic. For example, a topic popularity value higher than the first preset popularity value indicates a risky target resource topic, while a topic popularity value lower than the third preset popularity value suggests a potential long-term investment opportunity, but also carries inherent risks.

[0110] In some embodiments, while calculating the three popularity values ​​corresponding to the target resource topic, the topic popularity value, resource quantity popularity value, and operation popularity value of other resource topics in the recommended resource topics other than the target resource topic can also be calculated, and the target popularity range corresponding to the topic popularity value can be determined.

[0111] By displaying topic popularity information through target popularity ranges and popularity values, the current popularity status of target resource topics can be shown intuitively and clearly, thereby improving the effectiveness of displaying the status of target resource topics.

[0112] In some embodiments, the method further includes:

[0113] In response to the page launch command, the theme recommendation page is displayed, which shows the theme display information corresponding to the target resource theme;

[0114] In response to the theme display instruction triggered by the theme display information, the user is redirected from the theme recommendation page to the resource recommendation page. The resource recommendation page displays the theme popularity value, resource quantity popularity value, operation popularity value, target popularity range, and target virtual resources corresponding to the target resource theme.

[0115] In some embodiments, in response to a user-triggered page launch command, a theme recommendation page is displayed, such as... Figure 7 As shown, the topic recommendation page displays topic information corresponding to the target resource topic. The topic recommendation page can display at least one topic, and users can view all topic information through scrolling down or other methods. Topic information may include the name of the target resource topic, topic popularity information, and a brief overview of the target resource topic. When a user clicks on topic information, in response to the topic display instruction triggered by the topic information, the user is redirected from the topic recommendation page to the resource recommendation page for the corresponding target resource topic. For example... Figure 8 As shown, the resource recommendation page displays topic popularity, resource quantity popularity, operation popularity, target popularity range, and target virtual resources corresponding to the target resource topic. The preset temperature range and target temperature range can be displayed on the resource recommendation page in the form of a thermometer. The preset temperature range can be a first preset color, and the target temperature range can be a second preset color.

[0116] By displaying the target popularity range, popularity value, and target virtual resources on the resource recommendation page, the popularity of the topic and the virtual resources associated with the topic can be displayed intuitively, thus providing a reference for users to take corresponding actions and improving the effectiveness of virtual resource recommendations.

[0117] In some embodiments, see Figure 9 The method also includes:

[0118] S910. Obtain the topic popularity information of the target resource topic within a preset historical time period;

[0119] S920. Based on the topic popularity information within a preset historical time period, generate popularity fluctuation information and corresponding popularity prompt information;

[0120] S930. Display popularity fluctuation information and popularity prompts on the resource recommendation page.

[0121] In some embodiments, the topic popularity information of a target resource topic within a preset historical time period is obtained. For example, the target resource topic is determined every week and the topic popularity information corresponding to the target resource topic for that week is calculated. This can obtain the topic popularity information of a target resource topic within one month, six months, or one year. Since the topic popularity information within the preset historical time period can include multiple topic popularity information, therefore, as... Figure 10 As shown, based on this multi-topic popularity information, the popularity change curve of the target resource topic can be determined, thus obtaining popularity fluctuation information. And as... Figure 9 As shown, corresponding heat index alerts can be generated based on heat index fluctuation information. For example, if the curve corresponding to the heat index fluctuation information shows an upward trend for x1 consecutive days, the heat index alert would be "heating up for x1 consecutive days." Similarly, if the curve corresponding to the heat index fluctuation information shows an upward trend for x2 consecutive months or x3 consecutive weeks, the heat index alert would be "heating up for x2 consecutive months" or "heating up for x3 consecutive weeks." If the heat index fluctuation curve shows a downward trend, the corresponding heat index alert would be "cooling down."

[0122] Furthermore, based on the curves corresponding to the popularity fluctuation information, the popularity difference over a period of time can be calculated, and corresponding popularity alerts can be generated. For example, in the popularity fluctuation information within a week, if the difference in popularity between the weekend and Monday is T1, the popularity alert could be a temperature increase of T℃ this week. In the popularity fluctuation information within a month, if the difference in popularity between the end and beginning of the month is T2, the popularity alert could be a temperature increase of T2℃ this month. If the popularity of the theme at the beginning of the month is greater than that at the end of the month, or if the popularity of the theme on Monday is greater than that on the weekend, the corresponding popularity fluctuation alert would be a temperature decrease.

[0123] When the topic popularity corresponding to the popularity fluctuation information exceeds a preset threshold, the popularity alert message will be "Current popularity is too high, please pay attention." For example, if the topic popularity value is greater than 90, the alert message will be "Current popularity is too high, please pay attention." Similarly, when the topic popularity corresponding to the popularity fluctuation information is lower than a preset threshold, the popularity alert message will be "Current popularity is too low, please pay attention." For example, if the topic popularity value is less than 10, the alert message will be "Current popularity is too low, please pay attention."

[0124] In addition to displaying the current popularity value, it can also display the historical popularity value change curve and corresponding popularity prompts, which can better assist users in performing corresponding operations and improve the user experience.

[0125] In some embodiments, see Figure 11 ,like Figure 11As shown, when the virtual resource is a fund, the topics to be recommended, i.e., the topics corresponding to the fund, are initially screened, and the topics after the initial screening are obtained. Then, in each preset period, the quality analysis indicators of the topics after the initial screening are obtained under multiple topic analysis dimensions. Based on these multi-dimensional quality analysis indicators, the topics after the initial screening are further screened to obtain the target resource topics. When the topic screening is carried out in the first preset period, the target resource topic can be directly determined. When the topic screening is carried out in other preset periods, the target resource topic corresponding to each preset period is determined based on the buffer pool and the previous target resource topic obtained in the previous preset period. The number of resource topics in the buffer pool is greater than the number of resource topics displayed on the page. The topic popularity information corresponding to the target resource topic is calculated, and the topic popularity information corresponding to other resource topics in the topics to be recommended besides the target resource topic can also be calculated. Thus, a topic thermometer can be generated based on the current topic popularity information, and a curve corresponding to the popularity fluctuation information can be generated based on the historical topic popularity information.

[0126] When filtering funds based on a theme, the selection can be made according to the target resource theme. From the virtual resources to be recommended, funds associated with the target resource theme can be identified, and these funds must include at least two types. Different resource recommendation indicators are obtained for different types of funds, and then the target fund for each type is determined based on the resource recommendation indicators corresponding to each type of fund. The target fund is then recommended to the user, and the theme popularity information of the target resource theme corresponding to the target fund is displayed on the target fund's display page.

[0127] This application proposes a virtual resource recommendation method. This method improves the diversity of virtual resource selection by filtering different types of themed virtual resources using different resource recommendation metrics. This allows for more comprehensive recommendations, enhancing the effectiveness of virtual resource recommendations and improving user experience.

[0128] This application also provides a virtual resource recommendation device; please refer to [link to relevant documentation]. Figure 12 ,like Figure 12 As shown, the device includes:

[0129] The quality analysis index acquisition module 1210 is used to acquire the quality analysis index of the resource topic corresponding to the virtual resource to be recommended under multiple topic analysis dimensions.

[0130] The target resource topic acquisition module 1220 is used to filter resource topics based on quality analysis indicators to obtain target resource topics.

[0131] The theme virtual resource determination module 1230 is used to determine at least two types of theme virtual resources associated with the target resource theme from the virtual resources to be recommended;

[0132] The resource recommendation index acquisition module 1240 is used to acquire resource recommendation indices corresponding to at least two types of theme virtual resources.

[0133] The resource filtering module 1250 is used to filter at least two types of theme virtual resources based on resource recommendation indicators, and obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources.

[0134] The resource recommendation module 1260 is used to perform recommendation operations on the target virtual resources.

[0135] In some embodiments, at least two types of virtual resources for a given topic include a first type of virtual resource and a second type of virtual resource, and the resource filtering module includes:

[0136] The first screening unit is used to screen the first type of virtual resources according to the resource recommendation indicators corresponding to the first type of virtual resources, and obtain the first target virtual resources.

[0137] The second filtering unit is used to filter the second type of virtual resources according to the resource recommendation indicators corresponding to the second type of virtual resources, so as to obtain the second target virtual resources.

[0138] The target virtual resource acquisition unit is used to acquire the first target virtual resource and the second target virtual resource as target virtual resources.

[0139] In some embodiments, the first type of virtual resource includes multiple virtual resources, and the first filtering unit includes:

[0140] The first recommendation index acquisition unit is used to determine the resource set type corresponding to each virtual resource in the first type of virtual resources and the resource recommendation index corresponding to the first type of virtual resources.

[0141] The initial screening unit is used to screen virtual resources of the same resource set type in the first type of virtual resources according to the resource recommendation index, and obtain the initial screening results;

[0142] The first target virtual resource acquisition unit is used to determine the first target virtual resource from the initial screening results.

[0143] In some embodiments, the second filtering unit includes:

[0144] The second recommendation indicator acquisition unit is used to acquire resource recommendation indicators under multiple resource recommendation dimensions corresponding to the second type of virtual resources;

[0145] The target recommendation index acquisition unit is used to perform a weighted summation of multiple resource recommendation indices to obtain the target resource recommendation index.

[0146] The second target virtual resource acquisition unit is used to filter the second type of virtual resources according to the target resource recommendation index to obtain the second target virtual resources.

[0147] In some embodiments, the apparatus further includes:

[0148] The popularity reference information acquisition module is used to acquire resource quantity popularity data and operation popularity data corresponding to the target resource topic. The resource quantity popularity data is used to measure the resource quantity of the virtual resources corresponding to the target resource topic, and the operation popularity data is used to measure the operation frequency of the virtual resources corresponding to the target resource topic.

[0149] The topic popularity determination module is used to perform a weighted summation of resource volume popularity data and operation popularity data to obtain the topic popularity information corresponding to the target resource topic.

[0150] In some embodiments, the device further includes:

[0151] The topic popularity value generation module is used to generate the topic popularity value corresponding to the target resource topic based on topic popularity information.

[0152] The target popularity range determination module is used to generate the target popularity range corresponding to the target resource topic based on the topic popularity value and the preset popularity range.

[0153] The resource quantity popularity value generation module is used to generate resource quantity popularity values ​​based on resource quantity popularity data in topic popularity information.

[0154] The operation popularity value generation module is used to generate operation popularity values ​​based on operation popularity data in topic popularity information;

[0155] In some embodiments, the apparatus further includes:

[0156] The first page display module is used to respond to the page launch command and display the theme recommendation page, which displays the theme display information corresponding to the target resource theme;

[0157] The second page display module is used to respond to the theme display command triggered by the theme display information, and jump from the theme recommendation page to the resource recommendation page. The resource recommendation page displays the theme popularity value, resource quantity popularity value, operation popularity value, target popularity range, and target virtual resources corresponding to the target resource theme.

[0158] In some embodiments, the apparatus further includes:

[0159] The historical popularity acquisition module is used to acquire the popularity information of the target resource topic within a preset historical time period;

[0160] The information generation module is used to generate popularity fluctuation information and corresponding popularity prompt information based on the popularity information of topics within a preset historical time period.

[0161] The display module is used to show information on popularity fluctuations and popularity alerts on the resource recommendation page.

[0162] The apparatus provided in the above embodiments can execute the method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in the above embodiments, please refer to a virtual resource recommendation method provided in any embodiment of this application.

[0163] This embodiment also provides a computer-readable storage medium storing computer-executable instructions, which are loaded by a processor and executed by the virtual resource recommendation method described above in this embodiment.

[0164] This embodiment also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the virtual resource recommendations described above.

[0165] This embodiment also provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program adapted to be loaded by the processor and executed by the virtual resource recommendation method described above in this embodiment.

[0166] The device can be a computer terminal, a mobile terminal, or a server, and it can also participate in constituting the apparatus or system provided in the embodiments of this application. For example... Figure 13 As shown, server 13 may include one or more processors 1302 (shown as 1302a, 1302b, ..., 1302n in the figure) (processor 1302 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 1304 for storing data, and a transmission device 1306 for communication functions. In addition, it may also include: input / output interfaces (I / O interfaces), network interfaces, and a power supply. Those skilled in the art will understand that... Figure 13 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 13 may also include... Figure 13The more or fewer components shown, or having the same Figure 13 The different configurations shown.

[0167] It should be noted that the aforementioned one or more processors 1302 and / or other data processing circuitry are generally referred to herein as “data processing circuitry.” This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the server 13.

[0168] The memory 1304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method in this embodiment. The processor 1302 executes various functional applications and data processing by running the software programs and modules stored in the memory 1304, thereby realizing the above-described method for generating temporal behavior capture boxes based on self-attention networks. The memory 1304 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1304 may further include memory remotely located relative to the processor 1302, and these remote memories can be connected to the server 13 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0169] The transmission device 1306 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 13. In one example, the transmission device 1306 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 1306 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0170] This specification provides method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operation steps may be included. The steps and order listed in the embodiments are merely one possible execution order among many steps and do not represent the only execution order. In actual system or interrupt product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0171] The structures shown in this embodiment are only partial structures related to the solution of this application and do not constitute a limitation on the device to which the solution of this application is applied. Specific devices may include more or fewer components than shown, or combinations of certain components, or arrangements of different components. It should be understood that the methods, apparatuses, etc., disclosed in this embodiment can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection between devices or unit modules through some interfaces.

[0172] Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0173] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0174] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recommending virtual resources, characterized in that, The method includes: The quality analysis indicators of the resource topic corresponding to the virtual resource to be recommended are obtained under multiple topic analysis dimensions; the resource to be recommended is a virtual resource in the financial field; the quality analysis indicators include indicators determined based on topic quality information. Based on the quality analysis indicators, the resource topics are screened to obtain target resource topics; Based on the first fluctuation information corresponding to the target resource theme and the second fluctuation information corresponding to the virtual resource to be recommended, at least two types of theme virtual resources associated with the target resource theme are determined from the virtual resources to be recommended. Obtain resource recommendation metrics for at least two types of themed virtual resources; Based on the resource recommendation indicators, resource filtering is performed on the at least two types of theme virtual resources to obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources. Perform recommended operations on the target virtual resource; The method further includes: Use the target resource topic as the resource topic buffer information for the current round; Based on the resource topic buffer information and the previous target resource topic determined during the last virtual resource recommendation, the target resource topic for the current round is updated.

2. The virtual resource recommendation method according to claim 1, characterized in that, The at least two types of themed virtual resources include a first type of virtual resources and a second type of virtual resources. Based on the resource recommendation metrics, resource filtering is performed on the at least two types of themed virtual resources to obtain the target virtual resources corresponding to each of the at least two types of themed virtual resources, including: Based on the resource recommendation indicators corresponding to the first type of virtual resources, the first type of virtual resources are filtered to obtain the first target virtual resources; Based on the resource recommendation indicators corresponding to the second type of virtual resources, the second type of virtual resources are filtered to obtain the second target virtual resources; The first target virtual resource and the second target virtual resource are used as the target virtual resource.

3. The virtual resource recommendation method according to claim 2, characterized in that, The first type of virtual resource includes multiple virtual resources. The step of filtering the first type of virtual resources according to the resource recommendation indicators corresponding to the first type of virtual resource to obtain the first target virtual resource includes: Determine the resource set type corresponding to each virtual resource in the first type of virtual resources and the resource recommendation index corresponding to the first type of virtual resources; Based on the resource recommendation indicators, virtual resources of the same resource set type in the first type of virtual resources are filtered to obtain initial filtering results; The first target virtual resource is determined from the initial screening results.

4. The virtual resource recommendation method according to claim 2, characterized in that, The step of filtering the second type of virtual resources according to the resource recommendation indicators corresponding to the second type of virtual resources to obtain the second target virtual resources includes: Obtain resource recommendation metrics under multiple resource recommendation dimensions corresponding to the second type of virtual resources; The target resource recommendation index is obtained by weighted summation of the multiple resource recommendation indicators; Based on the target resource recommendation index, the second type of virtual resources are filtered to obtain the second target virtual resource.

5. The virtual resource recommendation method according to claim 1, characterized in that, After filtering the resource topics according to the quality analysis indicators to obtain the target resource topics, the method further includes: Obtain resource quantity popularity data and operation popularity data corresponding to the target resource topic. The resource quantity popularity data is used to measure the resource quantity of the virtual resources corresponding to the target resource topic, and the operation popularity data is used to measure the operation frequency of the virtual resources corresponding to the target resource topic. The resource volume popularity data and the operation popularity data are weighted and summed to obtain the topic popularity information corresponding to the target resource topic.

6. The virtual resource recommendation method according to claim 5, characterized in that, The method further includes: Based on the topic popularity information, a topic popularity value corresponding to the target resource topic is generated; Based on the topic popularity value and the preset popularity range, a target popularity range corresponding to the target resource topic is generated; Based on the resource quantity popularity data in the topic popularity information, a resource quantity popularity value is generated; Based on the operation popularity data in the topic popularity information, an operation popularity value is generated.

7. The virtual resource recommendation method according to claim 5, characterized in that, The method further includes: In response to the page launch command, a theme recommendation page is displayed, which shows theme display information corresponding to the target resource theme; In response to the theme display instruction triggered by the theme display information, the user is redirected from the theme recommendation page to the resource recommendation page. The resource recommendation page displays the theme popularity value, the resource quantity popularity value, the operation popularity value, the target popularity range, and the target virtual resources corresponding to the target resource theme.

8. The virtual resource recommendation method according to claim 7, characterized in that, The method further includes: Obtain the topic popularity information of the target resource topic within a preset historical time period; Based on the topic popularity information within the preset historical time period, popularity fluctuation information and popularity prompt information corresponding to the popularity fluctuation information are generated; The popularity fluctuation information and popularity prompt information are displayed on the resource recommendation page.

9. A virtual resource recommendation device, characterized in that, The device includes: The quality analysis index acquisition module is used to acquire the quality analysis indexes of the resource topic corresponding to the virtual resource to be recommended under multiple topic analysis dimensions; the resource to be recommended is a virtual resource in the financial field; the quality analysis indexes include indicators determined based on topic quality information; The target resource topic acquisition module is used to filter the resource topics according to the quality analysis indicators to obtain target resource topics. The theme virtual resource determination module is used to determine at least two types of theme virtual resources associated with the target resource theme from the virtual resources to be recommended, based on the first fluctuation information corresponding to the target resource theme and the second fluctuation information corresponding to the virtual resources to be recommended; The resource recommendation metric acquisition module is used to acquire resource recommendation metrics corresponding to at least two types of theme virtual resources. The resource filtering module is used to filter the at least two types of theme virtual resources based on the resource recommendation indicators, and obtain the target virtual resources corresponding to each of the at least two types of theme virtual resources. The resource recommendation module is used to perform recommendation operations on the target virtual resources; The target resource topic acquisition module is also used to use the target resource topic as the resource topic buffer information for the current round; and to update the target resource topic for the current round based on the resource topic buffer information and the previous target resource topic determined during the last virtual resource recommendation.

10. The apparatus according to claim 9, characterized in that, The at least two types of virtual resources include a first type of virtual resource and a second type of virtual resource, and the resource filtering module includes: The first screening unit is used to screen the first type of virtual resources according to the resource recommendation indicators corresponding to the first type of virtual resources, and obtain the first target virtual resources. The second filtering unit is used to filter the second type of virtual resources according to the resource recommendation indicators corresponding to the second type of virtual resources, so as to obtain the second target virtual resources. The target virtual resource acquisition unit is used to acquire the first target virtual resource and the second target virtual resource as target virtual resources.

11. The apparatus according to claim 10, characterized in that, The first type of virtual resource includes multiple virtual resources, and the first filtering unit includes: The first recommendation index acquisition unit is used to determine the resource set type corresponding to each virtual resource in the first type of virtual resources and the resource recommendation index corresponding to the first type of virtual resources. The initial screening unit is used to screen virtual resources of the same resource set type in the first type of virtual resources according to the resource recommendation index, and obtain the initial screening results; The first target virtual resource acquisition unit is used to determine the first target virtual resource from the initial screening results.

12. The apparatus according to claim 10, characterized in that, The second filtering unit includes: The second recommendation indicator acquisition unit is used to acquire resource recommendation indicators under multiple resource recommendation dimensions corresponding to the second type of virtual resources; The target recommendation index acquisition unit is used to perform a weighted summation of multiple resource recommendation indices to obtain the target resource recommendation index. The second target virtual resource acquisition unit is used to filter the second type of virtual resources according to the target resource recommendation index to obtain the second target virtual resources.

13. The apparatus according to claim 9, characterized in that, The device further includes: The popularity reference information acquisition module is used to acquire resource quantity popularity data and operation popularity data corresponding to the target resource topic. The resource quantity popularity data is used to measure the resource quantity of the virtual resources corresponding to the target resource topic, and the operation popularity data is used to measure the operation frequency of the virtual resources corresponding to the target resource topic. The topic popularity determination module is used to perform a weighted summation of resource volume popularity data and operation popularity data to obtain the topic popularity information corresponding to the target resource topic.

14. The apparatus according to claim 13, characterized in that, The device further includes: The topic popularity value generation module is used to generate the topic popularity value corresponding to the target resource topic based on topic popularity information. The target popularity range determination module is used to generate the target popularity range corresponding to the target resource topic based on the topic popularity value and the preset popularity range. The resource quantity popularity value generation module is used to generate resource quantity popularity values ​​based on resource quantity popularity data in topic popularity information. The operation popularity value generation module is used to generate operation popularity values ​​based on operation popularity data in topic popularity information.

15. The apparatus according to claim 13, characterized in that, The device further includes: The first page display module is used to respond to the page launch command and display the theme recommendation page, which displays the theme display information corresponding to the target resource theme; The second page display module is used to respond to the theme display command triggered by the theme display information, and jump from the theme recommendation page to the resource recommendation page. The resource recommendation page displays the theme popularity value, resource quantity popularity value, operation popularity value, target popularity range, and target virtual resources corresponding to the target resource theme.

16. The apparatus according to claim 15, characterized in that, The device further includes: The historical popularity acquisition module is used to acquire the popularity information of the target resource topic within a preset historical time period; The information generation module is used to generate popularity fluctuation information and corresponding popularity prompt information based on the popularity information of topics within a preset historical time period. The display module is used to show information on popularity fluctuations and popularity alerts on the resource recommendation page.

17. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement a virtual resource recommendation method as described in any one of claims 1-8.

18. A computer-readable storage medium, characterized in that, The storage medium includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a virtual resource recommendation method as described in any one of claims 1-8.

19. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the virtual resource recommendation method according to any one of claims 1-8.

Images