Method, device, equipment and medium for generating and sending virtual item recommendation information

Abstract

The embodiments of the present disclosure disclose a method, apparatus, device, and medium for generating and transmitting virtual item recommendation information. A specific implementation of the method includes: obtaining a virtual item circulation history data table corresponding to each preset virtual item trustee identifier; updating the virtual item circulation history data table; performing the following recommendation steps for each preset virtual item trustee identifier: generating an available virtual item circulation information set corresponding to the preset virtual item trustee identifier; constructing an alternative virtual item circulation information set; sorting the alternative virtual item circulation information set; generating virtual item recommendation information; performing a network quality detection process on the client's network; and, in response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, compressing the virtual item recommendation information and transmitting it to the client. This implementation shortens transmission time.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to methods, devices, equipment, and media for generating and sending virtual item recommendation information. Background Art

[0002] Generating and sending virtual item recommendation information is a technology used to recommend virtual items to users. Delivering this recommendation information, including virtual items, to users as quickly as possible is crucial for their decision-making regarding virtual items. Currently, when recommending virtual items to users, only those with high credit ratings are recommended, and the corresponding virtual item recommendation information is directly sent to the client.

[0003] However, when using the above method to send virtual item recommendation information to the client, the following technical problems often occur:

[0004] Currently, there are a huge number of virtual items in circulation, and different virtual item trustees have different standards for accepting virtual items. When a user conducts a transfer transaction with a virtual item trustee, if only virtual items with higher credit ratings among the virtual items owned by the user are recommended, the recommended virtual items with higher credit ratings may not meet the acceptance standards of the virtual item trustee to be transferred, resulting in an increase in the number of failed transfer transactions, which in turn leads to a poor user experience. At the same time, the generated virtual item recommendation information is directly sent to the client without testing the client's network quality. When the client's network transmission delay interval is large, it usually means that the network bandwidth is limited or the network is congested. When the network bandwidth is limited or the network is congested, the data transmission channel becomes narrower, the amount of data that can be transmitted per unit time is reduced, and the transmission efficiency is low, resulting in a longer transmission time for large amounts of virtual item recommendation information.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure provide methods, devices, electronic devices, and computer-readable media for generating and sending virtual item recommendation information to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for generating and sending virtual item recommendation information, the method comprising: obtaining a virtual item circulation history data table corresponding to each preset virtual item trustee identifier; updating the above virtual item circulation history data table to obtain an updated virtual item circulation history data table; for each preset virtual item trustee identifier among the above preset virtual item trustee identifiers, performing the following recommendation steps: based on the above updated virtual item circulation history data table, generating an available virtual item circulation information set corresponding to the above preset virtual item trustee identifier; based on the above updated virtual item circulation history data table, constructing an alternative virtual item circulation information set; performing reception rate prediction processing on the above updated virtual item circulation history data table and the above alternative virtual item circulation information set to obtain a virtual item circulation information set corresponding to the above alternative virtual item circulation information set. a virtual item acceptance rate information set; based on the virtual item acceptance rate information set, sorting the alternative virtual item circulation information set to obtain an alternative virtual item circulation information sequence; in response to receiving the virtual item selection recommendation request information corresponding to the preset virtual item trustee identifier sent by the client, generating virtual item recommendation information based on the virtual item selection recommendation request information, the available virtual item circulation information set, the alternative virtual item circulation information sequence and a pre-trained virtual item circulation recommendation model; in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, performing network quality detection processing on the network of the client to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than the preset interval, compressing the virtual item recommendation information and sending it to the client.

[0009] In a second aspect, some embodiments of the present disclosure provide a device for generating and sending virtual item recommendation information, the device comprising: an acquisition unit configured to acquire a virtual item circulation history data table corresponding to each preset virtual item trustee identifier; an updating unit configured to update the above-mentioned virtual item circulation history data table to obtain an updated virtual item circulation history data table; a recommendation unit configured to perform the following recommendation steps for each preset virtual item trustee identifier among the above-mentioned preset virtual item trustee identifiers: based on the above-mentioned updated virtual item circulation history data table, generate an available virtual item circulation information set corresponding to the above-mentioned preset virtual item trustee identifier; based on the above-mentioned updated virtual item circulation history data table, construct an alternative virtual item circulation information set; perform reception rate prediction processing on the above-mentioned updated virtual item circulation history data table and the above-mentioned alternative virtual item circulation information set to obtain an information set corresponding to the above-mentioned alternative virtual item circulation information set. Select a virtual item receipt rate information set corresponding to the virtual item circulation information set; based on the above virtual item receipt rate information set, sort the above alternative virtual item circulation information set to obtain an alternative virtual item circulation information sequence; in response to receiving the virtual item selection recommendation request information corresponding to the above preset virtual item trustee identifier sent by the client, generate virtual item recommendation information based on the above virtual item selection recommendation request information, the above available virtual item circulation information set, the above alternative virtual item circulation information sequence and a pre-trained virtual item circulation recommendation model; in response to determining that the data volume of the above virtual item recommendation information is greater than or equal to a preset threshold, perform network quality detection processing on the network of the above client to obtain network quality detection information; and in response to determining that the above network quality detection information indicates that the transmission delay interval is greater than the preset interval, compress the above virtual item recommendation information and send it to the above client.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: Through the virtual item recommendation information generation and transmission methods of some embodiments of the present disclosure, the user experience is improved and the transmission time of virtual item recommendation information is shortened. Specifically, the reasons for the poor user experience and the long transmission time of virtual item recommendation information are: the number of virtual items currently issued is huge, and the standards for accepting virtual items by different virtual item trustees vary. When a user transfers virtual items to a virtual item trustee, if only virtual items with higher credit ratings among the virtual items owned by the user are recommended, the recommended virtual items with higher credit ratings may not meet the acceptance standards of the virtual item trustee to be transferred, resulting in an increase in the number of transfer transaction failures, thereby resulting in a poor user experience. At the same time, the generated virtual item recommendation information is directly sent to the client without checking the client's network quality. When the client's network transmission delay interval is large, it usually means that the network bandwidth is limited or the network is congested. When the network bandwidth is limited or the network is congested, the data transmission channel becomes narrower, the amount of data that can be transmitted per unit time is reduced, and the transmission efficiency is low, resulting in a long transmission time for large amounts of virtual item recommendation information. Based on this, some embodiments of the present disclosure provide a method for generating and sending virtual item recommendation information. First, a virtual item circulation history data table corresponding to each preset virtual item trustee identifier is obtained. The above-mentioned virtual item circulation history data table is updated to obtain an updated virtual item circulation history data table. In this way, it can be ensured that the information in the circulation history data table is up to date. Then, for each preset virtual item trustee identifier among the above-mentioned preset virtual item trustee identifiers, the following recommendation steps are performed: a first sub-step, based on the above-mentioned updated virtual item circulation history data table, an available virtual item circulation information set corresponding to the above-mentioned preset virtual item trustee identifier is generated. In this way, an available virtual item circulation information set that clearly meets the acceptance criteria of the virtual item trustee can be generated. A second sub-step, based on the above-mentioned updated virtual item circulation history data table, an alternative virtual item circulation information set is constructed. In this way, an alternative virtual item circulation information set that may meet the acceptance criteria of the virtual item trustee can be generated. The third sub-step involves performing a reception rate prediction process on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set. This process can predict the reception rates of the virtual item trustee for each virtual object represented by the candidate virtual item circulation information set, i.e., the virtual item reception rate information set. The fourth sub-step involves sorting the candidate virtual item circulation information set based on the virtual item reception rate information set to obtain a candidate virtual item circulation information sequence.The fifth sub-step, in response to receiving a virtual item selection and recommendation request message from the client corresponding to the preset virtual item trustee identifier, generates virtual item recommendation information based on the virtual item selection and recommendation request message, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model. Thus, virtual item recommendation information can be generated upon receiving a virtual item selection and recommendation request message representing user needs. Due to the adoption of the above-mentioned recommendation step, based on the clear available virtual item circulation information set that meets the virtual item trustee's acceptance criteria and the candidate virtual item circulation information sequence that may meet the virtual item trustee's acceptance criteria, the pre-trained virtual item circulation recommendation model comprehensively considers multiple factors, no longer limiting recommendations to virtual items with high credit ratings. Instead, recommendations are provided based on the trustee's actual situation and the user's actual needs, providing virtual item recommendations that are most likely to be accepted by the trustee and meet the user's needs, thereby improving the user experience. Finally, in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, a network quality detection process is performed on the client's network to obtain network quality detection information. In response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, the virtual item recommendation information is compressed and transmitted to the client. Thus, when the data volume of the virtual item recommendation information is large, the network quality detection process is performed on the client's network, and if the client's network transmission delay interval is large, the virtual item recommendation information is compressed and transmitted to the client, thereby reducing the amount of data transmitted per unit time, improving transmission efficiency, and shortening transmission time. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the method for generating and sending virtual item recommendation information according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of some embodiments of the apparatus for generating and sending virtual item recommendation information according to the present disclosure;

[0016] Figure 3 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1 A process 100 of some embodiments of the method for generating and sending virtual item recommendation information according to the present disclosure is shown. The method for generating and sending virtual item recommendation information includes the following steps:

[0024] Step 101: Obtain a virtual item transfer history data table corresponding to each preset virtual item trustee identifier.

[0025] In some embodiments, the execution entity (e.g., a computing device) of the method for generating and sending virtual item recommendation information may obtain a virtual item transaction history data table corresponding to each preset virtual item trustee identifier. In practice, the execution entity may obtain the virtual item transaction history data table corresponding to each preset virtual item trustee identifier from a preset system (e.g., a preset database system, a preset log system, etc.). Each of the preset virtual item trustee identifiers may be an identifier of an institution (e.g., a game developer identifier such as 012345 or a bank identifier) ​​that transacts with a user (e.g., a trader). The virtual item transaction history data table may include each virtual item transaction history data item, each of which includes the virtual item trustee identifier, virtual item identifier, valid identifier information, discount rate information, update time, virtual item value, and virtual item attribute information. The virtual item attribute information includes item transaction platform characteristics, virtual item characteristics, and basic attribute information. The above-mentioned virtual item identifier can be the identifier of the virtual item (for example, it can be virtual equipment C in non-financial scenarios, and it can be bond A in financial scenarios). The above-mentioned valid identification information can be an identifier representing the preset validity or invalidity (for example, the preset valid identifier is represented by "1", and the preset invalid identifier is represented by "0"). The above-mentioned item circulation platform characteristic information can represent the level of the item circulation platform (for example, the platform item throughput, platform rating, such as AAA, AA, A, etc.). The above-mentioned virtual item characteristic information can represent the characteristic level of the virtual item (for example, quality, trustworthiness, such as AA, etc.). The above-mentioned basic attribute information can represent the basic attributes of the virtual item (for example, the category of the virtual item (such as equipment category, bond category), the circulation period of the virtual item, etc.). The above-mentioned virtual item can be an item with circulation performance (for example, virtual equipment, bonds, etc.) and can be used for circulation transactions.

[0026] Step 102: update the virtual item circulation history data table to obtain an updated virtual item circulation history data table.

[0027] In some embodiments, the execution entity may update the virtual item circulation history data table to obtain an updated virtual item circulation history data table.

[0028] In some optional implementations of some embodiments, the execution entity may update the virtual item circulation history data table through the following steps to obtain an updated virtual item circulation history data table:

[0029] The first step is to set the system time to the current time.

[0030] The second step is to update the above virtual item circulation history data table by performing the following steps:

[0031] In a first sub-step, for each virtual item circulation history data included in the virtual item circulation history data table, in response to determining that the valid identification information included in the virtual item circulation history data is a preset valid identification, the update time included in the virtual item circulation history data is determined as the historical update time.

[0032] The second sub-step is, in response to determining that the time interval between the above-mentioned historical update time and the above-mentioned current time is greater than the preset interval, updating the valid identification information included in the above-mentioned virtual item circulation history data to a preset invalid identification, and updating the update time included in the above-mentioned virtual item circulation history data to the above-mentioned current time, so as to update the above-mentioned virtual item circulation history data.

[0033] In the third step, the virtual item circulation history data table after the updating step is executed is determined as the updated virtual item circulation history data table.

[0034] Step 103: For each preset virtual item trustee identifier in each preset virtual item trustee identifier, perform the following recommended steps:

[0035] Step 1031 : Based on the updated virtual item circulation history data table, an available virtual item circulation information set corresponding to the preset virtual item trustee identifier is generated.

[0036] In some embodiments, the execution entity may generate an available virtual item circulation information set corresponding to the preset virtual item trustee identifier based on the updated virtual item circulation history data table.

[0037] In some optional implementations of some embodiments, the execution entity may generate an available virtual item transfer information set corresponding to the preset virtual item trustee identifier based on the updated virtual item transfer history data table through the following steps:

[0038] In the first step, each virtual item circulation history data including the virtual item trustee identifier being the preset virtual item trustee identifier in the updated virtual item circulation history data table is determined as the initial virtual item circulation history data set.

[0039] In the second step, each initial virtual item circulation history data set having valid identification information as a preset valid identification in the initial virtual item circulation history data set is determined as each available virtual item circulation information.

[0040] In the third step, the determined pieces of available virtual item circulation information are determined as an available virtual item circulation information set.

[0041] Step 1032: construct an alternative virtual item circulation information set based on the updated virtual item circulation history data table.

[0042] In some embodiments, the execution entity may construct an alternative virtual item circulation information set based on the updated virtual item circulation history data table.

[0043] In the process of adopting technical solutions to solve the problems mentioned in the background technology, the following problems often arise:

[0044] Before virtual item recommendation information is pushed to a client, a candidate virtual item circulation information set must be constructed for generating the virtual item recommendation information. Currently, when constructing this set, the typical approach is to select all virtual item circulation history data in the virtual item circulation history data table, excluding the available virtual item circulation information set, whose issuer rating is greater than a preset issuer rating and whose credit rating is greater than a preset credit rating. However, this selected candidate virtual item circulation information fails to consider the basic attributes of the virtual item (such as type and function). This may result in the candidate set containing information that does not match the basic attributes of the available set, resulting in lower accuracy and usability of the candidate virtual item circulation information set, and consequently, lower accuracy of the generated virtual item recommendation information, wasting network transmission resources for pushing virtual item recommendation information.

[0045] Faced with the above technical problems, the inventors decided to adopt the following solutions:

[0046] In some optional implementations of some embodiments, the execution entity may construct a candidate virtual item circulation information set based on the updated virtual item circulation history data table through the following steps:

[0047] In the first step, each virtual item circulation history data included in the updated virtual item circulation history data table is determined as a target virtual item circulation history data set.

[0048] In the second step, a difference set between the target virtual item circulation history data set and the available virtual item circulation information set is determined as an initial candidate virtual item circulation information set.

[0049] In the third step, for each available virtual item circulation information in the available virtual item circulation information set, the virtual item attribute information included in the available virtual item circulation information is determined as the initial virtual item attribute information.

[0050] The fourth step is to perform deduplication processing on each of the determined initial virtual item attribute information to obtain deduplicated virtual item attribute information. Each of the deduplicated virtual item attribute information includes item circulation platform feature information, virtual item feature information, and basic attribute information. In practice, the execution entity may employ a hash-based deduplication algorithm to perform deduplication processing on each of the determined initial virtual item attribute information to obtain deduplicated virtual item attribute information.

[0051] Step 5: For each piece of deduplicated virtual item attribute information, perform the following processing:

[0052] The first sub-step is to determine the basic attribute information included in the deduplicated virtual item attribute information as the target attribute information.

[0053] In the second sub-step, each piece of initial candidate virtual item circulation information containing the target attribute information in the initial candidate virtual item circulation information set is determined as each piece of candidate virtual item circulation information to be determined.

[0054] In the third sub-step, the to-be-determined virtual item circulation information among the above-mentioned candidate virtual item circulation information that satisfies the rating represented by the item circulation platform characteristic information is greater than or equal to the rating represented by the item circulation platform characteristic information included in the above-mentioned deduplicated virtual item attribute information and the rating represented by the virtual item characteristic information is greater than or equal to the rating represented by the virtual item characteristic information included in the above-mentioned deduplicated virtual item attribute information is determined as the candidate virtual item circulation information. As an example, the above-mentioned various candidate virtual item circulation information to be determined can be {virtual item trustee identification: 012345, virtual item identification: virtual equipment C, valid identification information: 1, deduction rate information: 0.9, update time: 2024-12-12:12 and virtual item attribute information: item circulation platform characteristic information: AA, virtual item characteristic information: A and basic attribute information A}, {virtual item trustee identification: 012346, virtual item identification: virtual equipment A, valid identification information: 0, deduction rate information: 0.75, update time: 2025-01-12:12 and virtual item attribute information: item circulation platform characteristic information: AB, virtual item characteristic information: A and basic attribute information A}. The available virtual item circulation information set may be "{virtual item trustee identifier: 012348, virtual item identifier: virtual equipment C, valid identifier information: 0, discount rate information: 0.75, update time: 2025-01-12:12 and virtual item attribute information: item circulation platform feature information: A, virtual item feature information: B and basic attribute information A}". The alternative virtual item circulation information may be "{virtual item trustee identifier: 012345, virtual item identifier: virtual equipment C, valid identifier information: 1, discount rate information: 0.9, update time: 2024-12-12:12 and virtual item attribute information: item circulation platform feature information: AA, virtual item feature information: A and basic attribute information A}".

[0055] In the sixth step, the determined virtual item circulation information is determined as a virtual item circulation information set.

[0056] The above technical solution, combined with steps 1033 to 1036 and their related content, serves as an inventive feature of an embodiment of the present disclosure, addressing the technical issue of "wasting network transmission resources." Factors contributing to this waste of network resources are often as follows: Before virtual item recommendation information is pushed to a client, a candidate virtual item circulation information set must be constructed for generating the virtual item recommendation information. Currently, when constructing this candidate virtual item circulation information set, the candidate virtual item circulation information set is typically determined by selecting all virtual item circulation history data in the virtual item circulation history data table, excluding the available virtual item circulation information set, whose issuer rating is greater than a preset issuer rating and credit rating is greater than a preset credit rating. However, this selection of candidate virtual item circulation information fails to consider the basic attributes of the virtual item (such as type and function). This may result in the candidate set containing information that does not match the basic attributes of the available set, resulting in lower accuracy and usability of the candidate virtual item circulation information set, and consequently, lower accuracy of the generated virtual item recommendation information, wasting network transmission resources for pushing the virtual item recommendation information. Resolving these factors can reduce network resource waste. To achieve this effect, first, each virtual item circulation history data item included in the updated virtual item circulation history data table is determined as a target virtual item circulation history data set. Then, the difference between the target virtual item circulation history data set and the available virtual item circulation information set is determined as an initial candidate virtual item circulation information set. Next, for each available virtual item circulation information item in the available virtual item circulation information set, the virtual item attribute information included in the available virtual item circulation information set is determined as the initial virtual item attribute information. Thus, the virtual item attribute information of the available virtual item circulation information item is determined to be the initial virtual item attribute information. Next, deduplication processing is performed on each determined initial virtual item attribute information item to obtain deduplicated virtual item attribute information item. Each deduplicated virtual item attribute information item in each deduplicated virtual item attribute information item includes item circulation platform feature information, virtual item feature information, and basic attribute information. Thus, through the above steps, the virtual item attribute information of each available virtual item circulation information item in the available virtual item circulation information set is extracted, and the extracted virtual item attribute information item is deduplicated. For each deduplicated virtual item attribute information, the following processing is performed: a first sub-step of determining the basic attribute information included in the deduplicated virtual item attribute information as target attribute information. A second sub-step of determining each piece of initial candidate virtual item circulation information that includes the target attribute information in the initial candidate virtual item circulation information set as each piece of candidate virtual item circulation information to be determined.In a third sub-step, the pending virtual item circulation information, among the aforementioned candidate virtual item circulation information, is determined as candidate virtual item circulation information, provided that the rating represented by the item circulation platform characteristic information is greater than or equal to the rating represented by the item circulation platform characteristic information included in the deduplicated virtual item attribute information, and the rating represented by the virtual item characteristic information is greater than or equal to the rating represented by the virtual item characteristic information included in the deduplicated virtual item attribute information. Finally, the determined candidate virtual item circulation information is determined as a candidate virtual item circulation information set. Thus, through the above steps, only candidate virtual item circulation information is retained that has the same virtual item attribute information as that included in the available virtual item circulation information set, and whose issuer rating and credit rating are both greater than or equal to the issuer rating and credit rating corresponding to at least one available virtual item circulation information. This ensures that the basic attribute information (e.g., type, function, etc.) of the selected candidate virtual item circulation information is aligned with the available virtual item circulation information in terms of virtual item attributes, thereby improving the accuracy and usability of the candidate virtual item circulation information set. Through steps 1033 to 1036, more accurate virtual item recommendation information can be generated and pushed based on an alternative virtual item circulation information set that has higher accuracy and availability and is more consistent with the virtual item attributes of the available virtual item circulation information set, thereby reducing the number of times virtual item recommendation information is regenerated and pushed when the accuracy of the virtual item recommendation information is low, and reducing the waste of network transmission resources.

[0057] Step 1033 : Perform reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set.

[0058] In some embodiments, the execution entity may perform reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set.

[0059] In some optional implementations of some embodiments, the execution entity may perform reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set through the following steps to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set:

[0060] The first step is to perform collaborative filtering on the above-mentioned virtual item circulation history data table to obtain the respective preference prediction information corresponding to the above-mentioned preset virtual item trustee identifiers. Each of the above-mentioned preset virtual item trustee identifiers corresponds to one of the above-mentioned preference prediction information, and the above-mentioned preference prediction information includes various preference prediction sub-information, and each of the above-mentioned preference prediction sub-information includes a virtual item identifier and an interest value. In practice, the above-mentioned execution entity may use a collaborative filtering algorithm to perform collaborative filtering on the above-mentioned virtual item circulation history data table to obtain the respective preference prediction information corresponding to the above-mentioned preset virtual item trustee identifiers. The above-mentioned interest value may represent the intensity of the trustee's preference for the virtual item corresponding to the preset virtual item trustee identifier, and the above-mentioned interest value may be represented by a preference probability (e.g., a value between 0 and 1).

[0061] In the second step, each virtual item circulation history data containing the preset virtual item trustee identifier in the virtual item circulation history data table is determined as each reference virtual item circulation history data.

[0062] In the third step, each virtual item attribute information included in the aforementioned reference virtual item circulation history data is determined as each reference virtual item attribute information.

[0063] Step 4: For each candidate virtual item circulation information in the candidate virtual item circulation information set, perform the following steps:

[0064] In a first sub-step, the virtual item attribute information included in the candidate virtual item circulation information is determined as the attribute information to be compared.

[0065] The second sub-step is to determine the virtual item identifiers included in the above-mentioned preference level prediction sub-information as the identifiers of the items to be compared.

[0066] The third sub-step is to query the virtual item attribute information corresponding to the aforementioned item identifiers to be compared from the aforementioned virtual item circulation history data table, and determine the queryed virtual item attribute information as the attribute information of the respective compared virtual items.

[0067] The fourth sub-step is to generate attribute information similarities based on the attribute information to be compared and the attribute information of each compared virtual item. Each attribute information similarity in the attribute information similarities corresponds to one of the preference prediction sub-information in each of the preference prediction sub-information. In practice, for each of the compared virtual item attribute information in each of the compared virtual item attribute information, the execution entity may determine the cosine similarity between the compared virtual item attribute information and the attribute information to be compared as the attribute information similarity. Each of the attribute information similarities in the attribute information similarities may represent the similarity between the attribute information to be compared and one of the compared virtual item attribute information in each of the compared virtual item attribute information. The similarities may be represented by cosine similarity.

[0068] Step 5: Based on the aforementioned attribute information similarities and the aforementioned preference prediction sub-information, virtual item acceptance rate information corresponding to the candidate virtual item circulation information is generated. In practice, the execution entity may determine the attribute information similarity with the greatest similarity among the aforementioned attribute information similarities as the target similarity. Subsequently, the execution entity may determine the interest value included in the preference prediction sub-information corresponding to the target similarity within each preference prediction sub-information as the target interest value. Finally, the execution entity may determine the virtual item acceptance rate as the product of the target similarity and the target interest value, which serves as the virtual item acceptance rate information.

[0069] Step 1034 : Based on the virtual item receiving rate information set, the candidate virtual item circulation information set is sorted to obtain a candidate virtual item circulation information sequence.

[0070] In some embodiments, the execution entity may sort the alternative virtual item circulation information set based on the virtual item acceptance rate information set to obtain an alternative virtual item circulation information sequence. In practice, the execution entity may sort the corresponding alternative virtual item circulation information in the alternative virtual item circulation information set from large to small according to the size of the virtual item acceptance rate included in the virtual item acceptance rate information set to obtain an alternative virtual item circulation information sequence. As an example, the alternative virtual item circulation information set may be "alternative virtual item circulation information A, alternative virtual item circulation information B, alternative virtual item circulation information C". The virtual item acceptance rate information set may be "0.85, 0.6, 0.5". Among them, alternative virtual item circulation information A corresponds to 0.85. Alternative virtual item circulation information B corresponds to 0.6. The alternative virtual item circulation information C corresponds to 0.5". Then the alternative virtual item circulation information sequence can be "{alternative virtual item circulation information A, alternative virtual item circulation information B, alternative virtual item circulation information C}".

[0071] Step 1035, in response to receiving the virtual item selection recommendation request information corresponding to the preset virtual item trustee identifier sent by the client, virtual item recommendation information is generated based on the virtual item selection recommendation request information, the available virtual item circulation information set, the alternative virtual item circulation information sequence and the pre-trained virtual item circulation recommendation model.

[0072] In some embodiments, the execution entity may, in response to receiving a virtual item selection recommendation request message from a client corresponding to the preset virtual item trustee identifier, generate virtual item recommendation information based on the virtual item selection recommendation request message, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model. The virtual item selection recommendation request message may be text representing selection criteria entered by a user in an input box when interacting with the virtual item circulation recommendation model. For example, the virtual item selection recommendation request message may be "Prefer virtual items in category A." The virtual item circulation recommendation model may be a large language model (e.g., a DeepSeek large language model) that takes the virtual item selection recommendation request message and the available virtual item circulation information set as input and outputs at least one recommended virtual item circulation information and at least one recommendation rating information. Each of the at least one recommended virtual item circulation information may be available virtual item circulation information selected by the large language model from the available virtual item circulation information set based on the virtual item selection recommendation request message. Each recommendation rating information in the at least one recommendation rating information may be a rating for the corresponding virtual item circulation information. Optionally, in practice, the execution entity may combine the virtual item selection recommendation request information, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation instruction generation model to obtain virtual item circulation recommendation instruction information. The virtual item circulation recommendation instruction information may be an instruction for filtering and sorting the available virtual item circulation information set and the candidate virtual item circulation information sequence based on the virtual item selection recommendation request information. The instruction corresponding to the virtual item circulation recommendation instruction information is executed, and based on the virtual item selection recommendation request information, at least one available virtual item circulation information is selected from the available virtual item circulation information set and the selected at least one available virtual item circulation information is sorted to obtain virtual item recommendation information. The virtual item circulation recommendation instruction information and the virtual item selection recommendation request information are stored. The virtual item circulation recommendation instruction generation model may further, upon receiving virtual item selection recommendation request information sent by the user client, determine the received virtual item selection recommendation request information as the virtual item selection recommendation request information to be compared. The virtual item circulation recommendation instruction generation model may then compare the virtual item selection recommendation request information to be compared with at least one pre-stored virtual item selection recommendation request information and determine the virtual item selection recommendation request information that is most similar to the virtual item selection recommendation request information to be compared as the reference virtual item selection recommendation request information.The execution entity may then determine the pre-stored virtual item transfer recommendation instruction information corresponding to the reference virtual item selection recommendation request information as the reference item transfer recommendation instruction information. The execution entity may then determine the reference item transfer recommendation instruction information as the virtual item recommendation information. The virtual item transfer recommendation instruction generation model may be a large language model (e.g., a DeepSeek large language model).

[0073] In some optional implementations of some embodiments, the execution entity may generate virtual item recommendation information based on the virtual item selection recommendation request information, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model through the following steps:

[0074] In the first step, the virtual item selection recommendation request and the available virtual item circulation information set are input into the virtual item circulation recommendation model to obtain at least one piece of recommended virtual item circulation information and at least one piece of recommendation rating information. Each piece of recommended virtual item circulation information in the at least one piece of recommended virtual item circulation information corresponds to one piece of recommended rating information in the at least one piece of recommended rating information.

[0075] In a second step, virtual item recommendation information is generated based on the at least one recommended virtual item circulation information, the at least one recommendation rating information, and the candidate virtual item circulation information sequence.

[0076] In some optional implementations of some embodiments, the execution entity may generate virtual item recommendation information based on the at least one recommended virtual item circulation information, the at least one recommendation rating information, and the candidate virtual item circulation information sequence through the following steps:

[0077] The first step is to sort the at least one recommended virtual item circulation information based on the at least one recommendation rating information to obtain a recommended virtual item circulation information sequence. In practice, the execution entity may sort the at least one recommended virtual item circulation information corresponding to the at least one recommendation rating information from largest to smallest according to the ratings corresponding to the at least one recommendation rating information to obtain the recommended virtual item circulation information sequence. The recommended ratings corresponding to the recommended virtual item circulation information distributed from front to back in the recommended virtual item circulation information sequence decrease in order.

[0078] The second step is to perform consensus value verification on the above-mentioned recommended virtual item circulation information sequence to obtain consensus value verification information. In practice, for each recommended virtual item circulation information in the recommended virtual item circulation information sequence, the above-mentioned execution entity may determine the product of the virtual item value included in the above-mentioned recommended virtual item circulation information and the discount rate corresponding to the discount rate information included in the above-mentioned recommended virtual item circulation information as the discount value. Then, the above-mentioned execution entity may obtain the demand value input by the user. Afterwards, the above-mentioned execution entity may compare the discount value with the demand value. In response to determining that the discount value is less than or equal to the demand value, the above-mentioned execution entity may determine that the recommended virtual item circulation information meets the preset consensus value verification condition. In response to determining that the discount value is greater than the demand value, the above-mentioned execution entity may determine that the recommended virtual item circulation information does not meet the preset consensus value verification condition. Among them, the above-mentioned preset consensus value verification condition may be that the product of the virtual item value and the discount rate is less than or equal to the demand value. In response to determining that at least one piece of recommended virtual item circulation information in the recommended virtual item circulation information sequence satisfies a preset consensus value verification condition, information indicating that at least one piece of recommended virtual item circulation information in the recommended virtual item circulation information sequence exists is determined as consensus value verification information. In response to determining that no piece of recommended virtual item circulation information in the recommended virtual item circulation information sequence satisfies the preset consensus value verification condition, information indicating that no piece of recommended virtual item circulation information in the recommended virtual item circulation information sequence satisfies the preset consensus value verification condition is determined as consensus value verification information.

[0079] In a third step, in response to determining that the consensus value verification information indicates that at least one recommended virtual item circulation information in the recommended virtual item circulation information sequence satisfies a preset consensus value verification condition, the at least one recommended virtual item circulation information satisfying the preset consensus value verification condition is sorted from largest to smallest according to the score corresponding to the at least one recommendation score information corresponding to the at least one recommended virtual item circulation information, thereby obtaining a target recommended virtual item circulation information sequence. The target recommended virtual item circulation information sequence is determined as the virtual item recommendation information.

[0080] In a fourth step, in response to determining that the consensus value verification information indicates that the recommended virtual item circulation information sequence does not contain any recommended virtual item circulation information that meets the preset consensus value verification conditions, virtual item recommendation information is generated based on the candidate virtual item circulation information sequence. In practice, the execution entity may determine as the virtual item recommendation information at least one candidate virtual item circulation information that meets the consensus value verification conditions in the candidate virtual item circulation information sequence and at least one virtual item acceptance rate information corresponding to the at least one candidate virtual item circulation information.

[0081] Step 1036: In response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, a network quality detection process is performed on the client's network to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, the virtual item recommendation information is compressed and sent to the client.

[0082] In some embodiments, in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, the execution entity may perform a network quality check on the client's network to obtain network quality information. Furthermore, in response to determining that the network quality information indicates a transmission delay interval greater than a preset interval, the execution entity may compress the virtual item recommendation information and transmit it to the client. In practice, the execution entity may employ UDP probing technology to perform network quality testing on the client network. For example, the execution entity may send a UDP probe packet to the client and record the time of receipt of a response packet to the UDP probe packet. In response to determining that the time interval between the transmission of the probe packet and the reception of the response packet is greater than a preset time interval, the execution entity may determine the information indicating that the transmission delay interval is greater than the preset interval as the network quality information. In practice, the execution entity may employ a lossless compression technique (e.g., the LZW compression algorithm) to compress the virtual item recommendation information to obtain compressed virtual item recommendation information. Afterwards, the above-mentioned execution entity can generate and send compressed virtual item recommendation information to the above-mentioned client, so that the client can perform circulation operations on each virtual item corresponding to the compressed virtual item recommendation information (for example, mortgaging each bond corresponding to the compressed virtual item recommendation information to an online bank selected by the client through online operations).

[0083] In the process of adopting technical solutions to solve the problems mentioned in the background technology, the following problems often arise:

[0084] To enhance the user experience, when a user manually selects virtual items for circulation without interacting with the virtual item circulation recommendation model to input virtual item selection recommendation request information, personalized recommendations can be made based on the user's historical selection behavior data, namely the virtual item circulation history data table. However, because the sequence of available virtual item circulation information generated for the user contains private data (e.g., the user's previous circulation transactions), directly transmitting this sequence of available virtual item circulation information to the client may result in the leakage of private data. If the sequence of available virtual item circulation information is encrypted and then transmitted, the amount of data transmitted after encryption increases, and a single transmission may occupy a large amount of bandwidth resources. Especially in bandwidth-constrained network environments, this may cause instantaneous transmission bottlenecks, resulting in reduced data transmission efficiency.

[0085] Optionally, the above execution entity may further perform the following steps:

[0086] In the first step, in response to determining that no virtual item selection recommendation request information from the client has been received within a preset time period and the number of virtual item transaction history data included in the virtual item transaction history data table is greater than a preset value, the available virtual item transaction information set is cold-start sorted based on the virtual item transaction history data table to obtain a sequence of available virtual item transaction information. In practice, the execution entity may employ a RankNet method to cold-start sort the available virtual item transaction information set based on the virtual item transaction history data table to obtain a sequence of available virtual item transaction information. In practice, the execution entity may employ a learning-to-rank method to sort the available virtual item information set. Specifically, the RankNet method may be employed, with the following steps: Dataset Preparation: Using the historical data corresponding to the trustee from the virtual item transaction history data table, a dataset is constructed using the Pari-Wise method. A RankNet model is trained based on the constructed dataset to obtain a trained RankNet model. Subsequently, the available virtual item transaction information set is input into the RankNet model to obtain a sequence of available virtual item transaction information. (As an example (specifically, for a certain piece of historical circulation data, any two positions in its overall holdings constitute a piece of training data. If the pair of positions both appear or do not appear in the circulation information, the model is expected to output the same output, that is, the expected output is 0 after difference; if one appears and the other does not appear, the model is expected to output a high output for the one that appears, that is, the expected output is greater than or less than 0 after difference, and the larger the absolute value, the better. The absolute value of the model output is meaningless, we only need the relative size of the model output), the model input is the overall holding status of the virtual item when the circulation occurs, and the feature information of the target virtual item. Model construction: The model uses a fully connected model, contains 2 hidden layers (512 neurons), and is activated by the Relu function. Training: The two virtual items in a piece of training data are forwarded on the model respectively, and the outputs are differentiated. Then the loss function is applied to optimize the parameters. Usage: Each position is applied to the model and sorted by model output.).

[0087] The second step is to perform a reachability check on the client network to obtain reachability network detection information. In practice, the execution entity may send an ICMP Echo Request packet (i.e., a Ping request) to the client. Upon receiving an ICMP Echo Reply packet from the client within a preset response time, the execution entity determines the information indicating network reachability as the reachability network detection information.

[0088] In a third step, in response to determining that the reachability network detection information indicates network reachability, the available virtual item flow information sequence is encrypted to obtain encrypted data corresponding to the available virtual item flow information sequence. In practice, the execution entity may employ an AES CBC encryption algorithm to encrypt the available virtual item flow information sequence to obtain encrypted data corresponding to the available virtual item flow information sequence.

[0089] The fourth step is to generate data fingerprint information related to the encrypted data. In practice, the execution entity can determine the hash value of the encrypted data as the data fingerprint information.

[0090] In the fifth step, the number of bytes of the encrypted data is determined as the transmission volume information corresponding to the encrypted data.

[0091] In step 6, in response to determining that the value represented by the transmission volume information is greater than a preset transmission volume value, the encrypted data is fragmented to obtain individual encrypted fragmented data. Each of the encrypted fragmented data is associated with a sequence number and a verification tag. In practice, the execution entity may employ data fragmentation technology to fragment the encrypted data to obtain individual encrypted fragmented data. Each of the encrypted fragmented data may be a sub-data block obtained by fragmenting the encrypted data. The sequence number may be a unique, incremental identifier assigned to each encrypted fragmented data, used to mark the position of the fragmented data within the original data (i.e., the encrypted data). The verification tag may be a VRF tag.

[0092] In the seventh step, for each of the encrypted fragmented data, the encrypted fragmented data is sent to the client.

[0093] In step 8, in response to receiving the feedback information sent by the client indicating that the encrypted fragmented data has been received, the data fingerprint information is sent to the client for the client to verify the integrity of the combined encrypted data. The feedback information indicating that the encrypted fragmented data has been received can be text information.

[0094] The above-described technical solution and its related contents, as an inventive feature of an embodiment of the present disclosure, address the technical problem of "reduced data transmission efficiency." Factors contributing to reduced data transmission efficiency are often as follows: When a user manually selects virtual items for transfer, rather than interacting with the virtual item transfer recommendation model to input virtual item selection recommendation request information, personalized recommendations can be made based on the user's historical selection behavior data, i.e., the virtual item transfer history data table, to enhance the user experience. However, because the generated sequence of available virtual item transfer information for a user contains private data (e.g., the user's previous transfer transactions), directly transmitting this sequence to the client may result in the leakage of private data. Encrypting the sequence of available virtual item transfer information and then transmitting it after obtaining the encrypted data increases the amount of data transmitted, potentially consuming significant bandwidth resources per transmission. This can, particularly in bandwidth-constrained network environments, lead to transient transmission bottlenecks, resulting in reduced data transmission efficiency. Addressing these factors can improve data transmission efficiency. To achieve this effect, first, in response to determining that no virtual item selection and recommendation request information has been received from the client within a preset time period and the number of virtual item transaction history data items included in the virtual item transaction history data table is greater than a preset value, a cold start sorting process is performed on the available virtual item transaction information set based on the virtual item transaction history data table to obtain an available virtual item transaction information sequence. This allows the user to receive a personalized recommendation of the available virtual item transaction information sequence without interacting with the virtual item transaction recommendation model to improve the user experience. Next, a reachability check is performed on the client network to obtain reachability network detection information. This allows the client network to be detected as reachable. Next, in response to determining that the reachability network detection information indicates network reachability, the available virtual item transaction information sequence is encrypted to obtain encrypted data corresponding to the available virtual item transaction information sequence. Thus, before transmitting the virtual item circulation information sequence, the transmitted virtual item circulation information sequence can be encrypted to reduce the risk of the transmitted virtual item circulation information sequence being leaked during the transmission process, thereby improving the security of the data during the transmission process. Afterwards, data fingerprint information corresponding to the above-mentioned encrypted data is generated. Thus, data fingerprint information can be generated for the above-mentioned client to verify the integrity of the combined encrypted data. Afterwards, the number of bytes of the above-mentioned encrypted data is determined as the transmission volume information corresponding to the above-mentioned encrypted data. Then, in response to determining that the value represented by the above-mentioned transmission volume information is greater than the preset transmission volume value, the above-mentioned encrypted data is fragmented to obtain individual encrypted fragmented data, wherein each of the above-mentioned encrypted fragmented data corresponds to a sequence number and a verification tag.Then, for each of the above-mentioned encrypted shard data, the above-mentioned encrypted shard data is sent to the above-mentioned client. In this way, the encrypted data can be processed and transmitted in shards, reducing the bandwidth resources occupied by a single transmission and improving the efficiency of data transmission. Finally, in response to the feedback information sent by the client indicating that the reception of the encrypted shard data has been completed, the above-mentioned data fingerprint information is sent to the above-mentioned client for the above-mentioned client to verify the integrity of the combined encrypted data. Also, when transmitting the available virtual item flow information sequence containing privacy data, in order to improve the security of data transmission, the virtual item flow information sequence is encrypted. And when the amount of encrypted data transmitted after encryption is large, shard transmission is adopted to reduce the bandwidth resources occupied by a single transmission and improve the efficiency of data transmission.

[0095] The above-mentioned embodiments of the present disclosure have the following beneficial effects: Through the virtual item recommendation information generation and transmission methods of some embodiments of the present disclosure, the user experience is improved and the transmission time of virtual item recommendation information is shortened. Specifically, the reasons for the poor user experience and the long transmission time of virtual item recommendation information are: the number of virtual items currently issued is huge, and the standards for accepting virtual items by different virtual item trustees vary. When a user transfers virtual items to a virtual item trustee, if only virtual items with higher credit ratings among the virtual items owned by the user are recommended, the recommended virtual items with higher credit ratings may not meet the acceptance standards of the virtual item trustee to be transferred, resulting in an increase in the number of transfer transaction failures, thereby resulting in a poor user experience. At the same time, the generated virtual item recommendation information is directly sent to the client without checking the client's network quality. When the client's network transmission delay interval is large, it usually means that the network bandwidth is limited or the network is congested. When the network bandwidth is limited or the network is congested, the data transmission channel becomes narrower, the amount of data that can be transmitted per unit time is reduced, and the transmission efficiency is low, resulting in a long transmission time for large amounts of virtual item recommendation information. Based on this, some embodiments of the present disclosure provide a method for generating and sending virtual item recommendation information. First, a virtual item circulation history data table corresponding to each preset virtual item trustee identifier is obtained. The above-mentioned virtual item circulation history data table is updated to obtain an updated virtual item circulation history data table. In this way, it can be ensured that the information in the circulation history data table is up to date. Then, for each preset virtual item trustee identifier among the above-mentioned preset virtual item trustee identifiers, the following recommendation steps are performed: a first sub-step, based on the above-mentioned updated virtual item circulation history data table, an available virtual item circulation information set corresponding to the above-mentioned preset virtual item trustee identifier is generated. In this way, an available virtual item circulation information set that clearly meets the acceptance criteria of the virtual item trustee can be generated. A second sub-step, based on the above-mentioned updated virtual item circulation history data table, an alternative virtual item circulation information set is constructed. In this way, an alternative virtual item circulation information set that may meet the acceptance criteria of the virtual item trustee can be generated. The third sub-step involves performing a reception rate prediction process on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set. This process can predict the reception rates of the virtual item trustee for each virtual object represented by the candidate virtual item circulation information set, i.e., the virtual item reception rate information set. The fourth sub-step involves sorting the candidate virtual item circulation information set based on the virtual item reception rate information set to obtain a candidate virtual item circulation information sequence.The fifth sub-step, in response to receiving a virtual item selection and recommendation request message from the client corresponding to the preset virtual item trustee identifier, generates virtual item recommendation information based on the virtual item selection and recommendation request message, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model. Thus, virtual item recommendation information can be generated upon receiving a virtual item selection and recommendation request message representing user needs. Due to the adoption of the above-mentioned recommendation step, based on the clear available virtual item circulation information set that meets the virtual item trustee's acceptance criteria and the candidate virtual item circulation information sequence that may meet the virtual item trustee's acceptance criteria, the pre-trained virtual item circulation recommendation model comprehensively considers multiple factors, no longer limiting recommendations to virtual items with high credit ratings. Instead, recommendations are provided based on the trustee's actual situation and the user's actual needs, providing virtual item recommendations that are most likely to be accepted by the trustee and meet the user's needs, thereby improving the user experience. Finally, in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, a network quality detection process is performed on the client's network to obtain network quality detection information. In response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, the virtual item recommendation information is compressed and transmitted to the client. Thus, when the data volume of the virtual item recommendation information is large, the network quality detection process is performed on the client's network, and if the client's network transmission delay interval is large, the virtual item recommendation information is compressed and transmitted to the client, thereby reducing the amount of data transmitted per unit time, improving transmission efficiency, and shortening transmission time.

[0096] Further references Figure 2 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a device for generating and sending virtual item recommendation information. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0097] like Figure 2As shown, some embodiments of the virtual item recommendation information generation and sending device 200 include: an acquisition unit 201, an updating unit 202 and a recommendation unit 203. The acquisition unit is configured to acquire a virtual item circulation history data table corresponding to each preset virtual item trustee identifier; the updating unit is configured to update the above virtual item circulation history data table to obtain an updated virtual item circulation history data table; the recommendation unit is configured to perform the following recommendation steps for each preset virtual item trustee identifier in the above preset virtual item trustee identifiers: based on the above updated virtual item circulation history data table, generate an available virtual item circulation information set corresponding to the above preset virtual item trustee identifier; based on the above updated virtual item circulation history data table, construct an alternative virtual item circulation information set; perform reception rate prediction processing on the above updated virtual item circulation history data table and the above alternative virtual item circulation information set to obtain a virtual item reception rate corresponding to the above alternative virtual item circulation information set. rate information set; based on the virtual item reception rate information set, sorting the alternative virtual item circulation information set to obtain an alternative virtual item circulation information sequence; in response to receiving the virtual item selection recommendation request information corresponding to the preset virtual item trustee identifier sent by the client, generating virtual item recommendation information based on the virtual item selection recommendation request information, the available virtual item circulation information set, the alternative virtual item circulation information sequence and a pre-trained virtual item circulation recommendation model; in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, performing network quality detection processing on the network of the client to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than the preset interval, compressing the virtual item recommendation information and sending it to the client.

[0098] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be repeated here.

[0099] Reference below Figure 3 , which shows a structural diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0100] like Figure 3As shown, electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage device 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for the operation of electronic device 300. Processing device 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0101] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0102] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the methods of some embodiments of the present disclosure are performed.

[0103] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0104] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0105] The computer-readable medium may be contained in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When one or more programs are executed by the electronic device, the electronic device: obtains a virtual item circulation history data table corresponding to each preset virtual item trustee identifier; updates the above virtual item circulation history data table to obtain an updated virtual item circulation history data table; for each preset virtual item trustee identifier among the above preset virtual item trustee identifiers, performs the following recommended steps: based on the above updated virtual item circulation history data table, generates an available virtual item circulation information set corresponding to the above preset virtual item trustee identifier; based on the above updated virtual item circulation history data table, constructs an alternative virtual item circulation information set; performs reception rate prediction processing on the above updated virtual item circulation history data table and the above alternative virtual item circulation information set to obtain an available virtual item circulation information set corresponding to the above alternative virtual item circulation information set. the virtual item receipt rate information set corresponding to the virtual item receipt rate information set; based on the virtual item receipt rate information set, the alternative virtual item circulation information set is sorted to obtain an alternative virtual item circulation information sequence; in response to receiving the virtual item selection recommendation request information corresponding to the preset virtual item trustee identifier sent by the client, virtual item recommendation information is generated based on the virtual item selection recommendation request information, the available virtual item circulation information set, the alternative virtual item circulation information sequence and a pre-trained virtual item circulation recommendation model; in response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, network quality detection processing is performed on the network of the client to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than the preset interval, the virtual item recommendation information is compressed and sent to the client.

[0106] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The units described in some embodiments of the present disclosure may be implemented in software or hardware. The units described may also be provided in a processor. For example, they may be described as: a processor including an acquisition unit, an update unit, and a recommendation unit. The names of these units do not, in some cases, limit the units themselves. For example, the acquisition unit may also be described as "a unit for acquiring a virtual item flow history data table corresponding to each preset virtual item trustee identifier."

[0109] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0110] The above descriptions are merely some preferred embodiments of the present disclosure and illustrate the underlying technical principles. Those skilled in the art should understand that the scope of the invention encompassed by the embodiments of the present disclosure is not limited to technical solutions formed by specific combinations of technical features, but also encompasses other technical solutions formed by any combination of technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing a feature with (but not limited to) a technical feature having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for generating and sending virtual item recommendation information, comprising: Obtaining a virtual item transfer history data table corresponding to each preset virtual item trustee identifier; performing an updating process on the virtual item circulation history data table to obtain an updated virtual item circulation history data table; For each of the preset virtual item trustee identifiers, perform the following recommended steps: generating an available virtual item circulation information set corresponding to the preset virtual item trustee identifier based on the updated virtual item circulation history data table; Constructing an alternative virtual item circulation information set based on the updated virtual item circulation history data table; performing reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set; sorting the candidate virtual item circulation information set based on the virtual item reception rate information set to obtain a candidate virtual item circulation information sequence; In response to receiving a virtual item selection recommendation request message corresponding to the preset virtual item trustee identifier sent by the client, generating virtual item recommendation information based on the virtual item selection recommendation request message, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model; In response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, performing network quality detection processing on the network of the client to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, compressing the virtual item recommendation information and sending it to the client.

2. The method according to claim 1, wherein The virtual item circulation history data table includes various virtual item circulation history data, each virtual item circulation history data in the various virtual item circulation history data includes a virtual item trustee identifier, a virtual item identifier, valid identifier information, discount rate information, update time, and virtual item attribute information, and generating an available virtual item circulation information set corresponding to the preset virtual item trustee identifier based on the updated virtual item circulation history data table, including: determining each virtual item circulation history data in the updated virtual item circulation history data table, which includes the virtual item trustee identifier as the preset virtual item trustee identifier, as an initial virtual item circulation history data set; Determining each initial virtual item circulation history data set having valid identification information as a preset valid identification in the initial virtual item circulation history data set as each available virtual item circulation information; The determined pieces of available virtual item circulation information are determined as an available virtual item circulation information set.

3. The method according to claim 2, wherein: The updating of the virtual item circulation history data table to obtain an updated virtual item circulation history data table includes: Set the system time to the current time; For the virtual item circulation history data table, perform the following update steps: For each virtual item circulation history data in each virtual item circulation history data included in the virtual item circulation history data table, in response to determining that the valid identification information included in the virtual item circulation history data is a preset valid identification, determining the update time included in the virtual item circulation history data as the historical update time; In response to determining that the time interval between the historical update time and the current time is greater than a preset interval, updating the valid identification information included in the virtual item circulation history data to a preset invalid identification, and updating the update time included in the virtual item circulation history data to the current time, so as to update the virtual item circulation history data; The virtual item circulation history data table after executing the updating step is determined as the updated virtual item circulation history data table.

4. The method according to claim 1, wherein The performing reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set includes: performing collaborative filtering processing on the updated virtual item circulation history data table to obtain respective preference prediction information corresponding to the respective preset virtual item trustee identifiers, wherein each preset virtual item trustee identifier among the respective preset virtual item trustee identifiers corresponds to one preference prediction information among the respective preference prediction information, the preference prediction information including respective preference prediction sub-information, each preference prediction sub-information among the respective preference prediction sub-information including a virtual item identifier and an interest value; determining each virtual item circulation history data containing the preset virtual item trustee identifier in the virtual item circulation history data table as each reference virtual item circulation history data; Determining each virtual item attribute information included in each reference virtual item circulation history data as each reference virtual item attribute information; For each candidate virtual item circulation information in the candidate virtual item circulation information set, the following steps are performed: determining the virtual item attribute information included in the candidate virtual item circulation information as the attribute information to be compared; determining each virtual item identifier included in each preference level prediction sub-information as each to-be-compared item identifier; querying each virtual item attribute information corresponding to each to-be-compared item identifier from the virtual item circulation history data table, and determining each virtual item attribute information obtained from the query as each virtual item attribute information for comparison; generating attribute information similarities based on the attribute information to be compared and the attribute information of each virtual item to be compared, wherein each attribute information similarity in the attribute information similarities corresponds to one preference prediction sub-information in the preference prediction sub-information; Based on the similarities of the respective attribute information and the respective preference prediction sub-information, virtual item receiving rate information corresponding to the candidate virtual item circulation information is generated.

5. The method according to claim 1, wherein The generating of virtual item recommendation information based on the virtual item selection recommendation request information, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model includes: Inputting the virtual item selection recommendation request information and the available virtual item circulation information set into the virtual item circulation recommendation model to obtain at least one piece of recommended virtual item circulation information and at least one piece of recommendation rating information, wherein each piece of recommended virtual item circulation information in the at least one piece of recommended virtual item circulation information corresponds to one piece of recommendation rating information in the at least one piece of recommended rating information; Generate virtual item recommendation information based on the at least one recommended virtual item circulation information, the at least one recommendation rating information, and the candidate virtual item circulation information sequence.

6. The method according to claim 5, wherein: The generating virtual item recommendation information based on the at least one recommended virtual item circulation information, the at least one recommendation rating information, and the candidate virtual item circulation information sequence includes: sorting the at least one recommended virtual item circulation information based on the at least one recommendation rating information to obtain a recommended virtual item circulation information sequence; Performing consensus value verification processing on the recommended virtual item circulation information sequence to obtain consensus value verification information; In response to determining that the consensus value verification information indicates that at least one recommended virtual item circulation information in the recommended virtual item circulation information sequence satisfies a preset consensus value verification condition, determining the at least one recommended virtual item circulation information satisfying the preset consensus value verification condition and at least one recommendation rating information corresponding to the at least one recommended virtual item circulation information as virtual item recommendation information; In response to determining that the consensus value verification information indicates that there is no recommended virtual item circulation information that meets the preset consensus value verification condition in the recommended virtual item circulation information sequence, virtual item recommendation information is generated based on the candidate virtual item circulation information sequence.

7. A device for generating and sending virtual item recommendation information, comprising: an acquiring unit configured to acquire a virtual item transfer history data table corresponding to each preset virtual item trustee identifier; an updating unit configured to update the virtual item circulation history data table to obtain an updated virtual item circulation history data table; a recommendation unit configured to perform the following recommendation steps for each preset virtual item trustee identifier among the preset virtual item trustee identifiers: generating an available virtual item circulation information set corresponding to the preset virtual item trustee identifier based on the updated virtual item circulation history data table; Constructing an alternative virtual item circulation information set based on the updated virtual item circulation history data table; performing reception rate prediction processing on the updated virtual item circulation history data table and the candidate virtual item circulation information set to obtain a virtual item reception rate information set corresponding to the candidate virtual item circulation information set; sorting the candidate virtual item circulation information set based on the virtual item acceptance rate information set to obtain a candidate virtual item circulation information sequence; and generating virtual item recommendation information based on the virtual item selection recommendation request information, the available virtual item circulation information set, the candidate virtual item circulation information sequence, and a pre-trained virtual item circulation recommendation model in response to receiving a virtual item selection recommendation request corresponding to the preset virtual item trustee identifier sent by the client; In response to determining that the data volume of the virtual item recommendation information is greater than or equal to a preset threshold, performing network quality detection processing on the network of the client to obtain network quality detection information; and in response to determining that the network quality detection information indicates that the transmission delay interval is greater than a preset interval, compressing the virtual item recommendation information and sending it to the client.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images