Recommended resource optimization configuration method, device, storage medium and product

Abstract

Embodiments of the present application relate to a recommended resource optimization configuration method and device, a storage medium and a product. The method comprises: first obtaining sales data, user browsing behavior and evaluation information of a communication product, taking the communication product, user behavior and evaluation as nodes, taking the number of behaviors as a first edge weight and the number of evaluations as a second edge weight, constructing a semantic network model, then based on the model, taking product popularity, profit and inventory as indicators, calculating the comprehensive evaluation score of each product, and accordingly formulating a multiplex resource allocation scheme.

Description

Technical Field

[0001] This application relates to the field of IT operation support technology, and in particular to a method, device, storage medium and product for recommending resource optimization configuration. Background Technology

[0002] In the mobile internet era, mobile product service platforms (such as app stores and e-commerce platforms) typically rely on recommendation systems to push mobile products (such as applications, data plans, and marketing campaigns) that users may be interested in. Currently, the mainstream recommendation methods include collaborative filtering and content-based recommendation.

[0003] Collaborative filtering methods construct a "user-product" interaction matrix by analyzing users' historical behaviors (such as downloads, purchases, and browsing), and use algorithms such as cosine similarity or Pearson correlation coefficient to find similar user groups and make recommendations accordingly. However, when faced with new users or new products, this method suffers from the "cold start" problem due to the lack of historical interaction data, leading to recommendation failure. Furthermore, when dealing with sparse data, it is prone to matrix sparsity issues, affecting recommendation accuracy.

[0004] Content-based recommendation methods focus on matching product features by extracting product attributes (such as functionality, price, and brand) and comparing them with user preferences. However, this method typically remains at the keyword matching level and struggles to deeply understand the underlying semantics of user needs. When user needs are vague or complex, recommendation accuracy is limited. Furthermore, when faced with frequent updates to product features, this method suffers from model iteration lag and cannot quickly adapt to new recommendation requirements.

[0005] Furthermore, during peak traffic periods (such as "Double Eleven" promotions or new product launches), existing recommendation systems often experience response delays due to insufficient computing resources, leading to a decline in user experience and loss of platform benefits. At the same time, existing technologies lack a dynamic allocation mechanism for recommendation resources, failing to allocate them rationally based on a product's real-time popularity, profit contribution, and inventory status, resulting in resource waste or uneven distribution. Summary of the Invention

[0006] To address the aforementioned issues, embodiments of this application provide a method, device, storage medium, and product for optimizing resource allocation.

[0007] According to a first aspect of the embodiments of this application, a method for recommending optimized resource allocation is provided, the method comprising: Obtain sales data, user browsing behavior, and evaluation information of the target telecommunications operator's communication products; Using communication products, user behavior, and user reviews as nodes, and with the number of user behavior nodes as the weight of the first side and the number of user reviews as the weight of the second side, a target semantic network model is generated. The first side is used to represent the relationship between the nodes of user behavior and the nodes of the corresponding communication products, and the second side is used to represent the relationship between the nodes of user reviews and the nodes of the corresponding communication products. Based on the target semantic network model, the popularity, profit and inventory of communication products are used as evaluation indicators to determine the comprehensive evaluation score of each communication product. The popularity is positively correlated with the number of user reviews, and the inventory is negatively correlated with the sales volume. The resource allocation scheme for multiplexing resources for each communication product is determined based on the comprehensive evaluation score of each communication product.

[0008] In one implementation, determining the resource allocation scheme for each communication product in multiplexing resources based on the comprehensive evaluation score of each communication product includes: Based on the comprehensive evaluation score, the recommended resource allocation ratio for each communication product is determined, and time-division multiplexing is used to allocate the recommended resources to each communication product in proportion. The time is divided into multiple time slots, so that each communication product has exclusive access to the transmission channel in the corresponding time slot, thereby realizing the multiplexing of recommended resources, including transmission bandwidth.

[0009] In one embodiment, the method further includes: Real-time monitoring of changes in the popularity, profit, and inventory of target communication products; Determine the first weight corresponding to the changed popularity and the second weight corresponding to the changed inventory; A third weight corresponding to the profit is determined based on the first weight and the second weight; The resource allocation scheme is adjusted based on the first weight, the second weight, and the third weight.

[0010] In one embodiment, the method further includes: Based on the resource allocation schemes of various communication products, a recommended communication product scheme that matches the user profile of the target user is selected and pushed to the target user.

[0011] In one implementation, the method, based on the resource allocation schemes of various communication products, selects a communication product recommendation scheme that matches the user profile of the target user and pushes it to the target user, including: The optimized recommendation resources are integrated into the recommendation system, and a personalized product recommendation list is generated based on the user profile. The personalized product recommendation list is pushed to the target user's terminal.

[0012] In one embodiment, the method further includes: Collect user interaction data on the personalized product recommendation list, including click-through rate and / or purchase conversion rate; Based on the interaction behavior data, the recommendation effect is evaluated, and feedback is provided to optimize the target semantic network model and resource allocation scheme.

[0013] In one implementation, determining the overall evaluation score for each communication product includes: Based on the number of reviews, page views, and purchases of the target communication product, obtain the quantitative value of the target communication product's popularity. Based on the profit value of the target communication product, and the maximum and minimum profit values ​​of each communication product, obtain the quantitative profit value of the target communication product. Based on the quantitative value corresponding to the inventory level of the target communication product, obtain the quantitative inventory value of the target communication product; Based on the quantitative values ​​of heat, profit, and inventory, and their corresponding weights, a comprehensive evaluation score for the target communication product is determined.

[0014] According to a second aspect of the embodiments of this application, an electronic device is provided, comprising: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspects.

[0015] According to a third aspect of the embodiments of this application, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0016] According to a fourth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0017] The embodiments of this application achieve the following beneficial effects: First, sales data, user browsing behavior, and evaluation information of communication products are obtained. Using communication products, user behavior, and evaluations as nodes, and with the number of behaviors as the first side weight and the number of evaluations as the second side weight, a semantic network model is constructed. Then, based on this model, using product popularity, profit, and inventory as indicators, a comprehensive evaluation score for each product is calculated, and a multi-path resource allocation scheme is formulated accordingly. By deeply mining the implicit relationships between user behavior and products through semantic networks, the problem of insufficient semantic understanding in traditional methods is solved, significantly improving the accuracy of subsequent recommendations and user satisfaction. Multi-dimensional dynamic evaluation replaces single-indicator decision-making, making resource allocation more aligned with the actual value of products and market conditions, avoiding resource waste. Combined with multi-path multiplexing technology, on-demand scheduling of bandwidth and other resources is achieved, ensuring system stability and efficient response during peak traffic periods, thereby improving conversion rates and reducing operating costs.

[0018] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0020] Figure 2 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0021] Figure 3 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0022] Figure 4 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0023] Figure 5 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0024] Figure 6 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0025] Figure 7 This is a flowchart of a recommended resource optimization allocation method provided in an embodiment of this application.

[0026] Figure 8 This is a block diagram of an electronic device provided in one embodiment of this application. Detailed Implementation

[0027] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0028] It should be understood that the term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description.

[0029] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. The modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless explicitly stated in the context, they should be understood as "one or more". In the description of this application, unless otherwise stated, "multiple" means two or more, and other quantifiers are similar; "at least one item", "one item or multiple items", or similar expressions refer to any combination of these items, including any combination of single or multiple items.

[0030] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of this application, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of this application, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of this application are for illustrative purposes only and are not intended to limit the scope of these messages or information. It is understood that before using the technical solutions disclosed in the embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0032] First, the application scenarios of this application will be explained. In existing technologies, mobile product recommendations mainly rely on collaborative filtering and content recommendation methods. Collaborative filtering predicts mobile products that users may be interested in by analyzing their historical behavior and preferences. Specifically, it uses a "user-product" interaction matrix based on the purchase history and browsing behavior of similar user groups, and employs similarity algorithms (such as cosine similarity or Pearson correlation coefficient) to identify user groups with similar preferences, and then recommends products liked by these similar users. For example, on an e-commerce platform, if user A frequently browses and purchases a certain category of mobile products, the system will recommend products similar to that category or from the same brand to A. However, when encountering new users or new products, and lacking sufficient historical data, this method often struggles to make accurate recommendations, resulting in the so-called "cold start" problem.

[0033] Content recommendation focuses on feature matching for mobile products, recommending products by comparing the similarity between product attributes (such as features, price, brand, etc.) and user preferences. It constructs a feature vector for the product and extracts key features from the text description based on text analysis or classification algorithms, matching product features with user preferences. For example, for a mobile product with a high-resolution camera and long battery life, the system would recommend it to users who prefer photography and long battery life. However, this method is usually based solely on keyword matching of product features and cannot deeply understand the underlying semantics of user needs, especially when user needs are complex or ambiguous, resulting in limited recommendation accuracy. Furthermore, during peak traffic periods, such as new product launches or large promotional events, user traffic surges, and the recommendation system needs to process a large number of requests in a short time. At this time, collaborative filtering and content recommendation methods may experience response delays due to insufficient computing resources, reducing recommendation efficiency and impacting user experience and platform efficiency. Collaborative filtering is prone to the sparse matrix problem when processing sparse data, leading to inaccurate recommendation results. Content recommendation, on the other hand, struggles to adapt to new recommendation needs when mobile product features are frequently updated or user needs change, as its model updates are not timely. These shortcomings limit the effectiveness and reliability of existing technologies in practical applications.

[0034] In view of this, there is an urgent need for a method, device, storage medium, and product for optimizing the allocation of recommendation resources. By constructing a semantic network model, the semantic information of products and user behavior can be deeply mined to achieve dynamic and accurate allocation of recommendation resources, improve recommendation accuracy and conversion rate, and optimize resource utilization efficiency during peak traffic periods. The following describes this application with specific embodiments.

[0035] Figure 1 This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 1 As shown in the figure, this application provides a method for recommending optimized resource allocation, which may include the following steps: In step S10, sales data, user browsing behavior, and evaluation information of the target telecommunications operator's communication products are obtained.

[0036] In step S20, a target semantic network model is generated by taking communication products, user behavior, and user evaluation as nodes, and using the number of user behavior as the weight of the first side and the number of user evaluation as the number of the second side. The first side is used to represent the relationship between the node of user behavior and the node of the corresponding communication product, and the second side is used to represent the relationship between the node of user evaluation and the node of the corresponding communication product.

[0037] In step S30, based on the target semantic network model, the comprehensive evaluation score of each communication product is determined using the popularity, profit and inventory of the communication product as evaluation indicators. The popularity is positively correlated with the number of user reviews, and the inventory is negatively correlated with the sales volume.

[0038] In step S40, the resource allocation scheme for each communication product in multiplexing resources is determined based on the comprehensive evaluation score of each communication product.

[0039] For example, one can first obtain sales data, user browsing behavior, and user reviews of the target telecommunications operator's communication products. This data covers various product types, including tariff packages, marketing activities, and value-added services. Based on this, a semantic network model can be constructed, using communication products, user behavior, and user reviews as nodes.

[0040] Specifically, the number of user behaviors (such as browsing and purchasing) is used as the weight of the first side to connect user behavior nodes with corresponding communication product nodes; the number of user reviews is used as the weight of the second side to connect user review nodes with corresponding communication product nodes, thereby generating the target semantic network model.

[0041] For example, to record user A browsing the details page of tariff package X, a browsing node A_browse_X is created and connected to the package X node, with the edge weight initially set to 1. If multiple users browse X, the weight accumulates. For user B's review "The product is very good, high cost-performance ratio," keywords are extracted through text analysis, and a review node B_review_Y is created and connected to the marketing campaign Y node, with the edge weight also increasing with the number of similar reviews. Next, based on this target semantic network model, the popularity, profit, and inventory of communication products are used as evaluation indicators to determine the comprehensive evaluation score of each communication product. Among them, popularity is positively correlated with the number of user reviews, and inventory is negatively correlated with sales volume; that is, the more reviews, the higher the popularity, and the higher the sales volume, the lower the inventory. Finally, based on the comprehensive evaluation scores of each communication product, a resource allocation scheme for each communication product in multiplexing resources is formulated.

[0042] This application embodiment achieves accurate allocation of recommendation resources by deeply mining the semantic relationship between user behavior and products through semantic networks and combining multi-dimensional indicators for comprehensive evaluation. This significantly improves resource utilization efficiency and recommendation accuracy, and avoids recommendation bias caused by data sparsity or insufficient semantic understanding in traditional methods.

[0043] Figure 2 This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 2 As shown, determining the resource allocation scheme for each communication product in multiplexing resources based on the comprehensive evaluation score of each communication product may include the following steps: In step S401, the recommended resource allocation ratio for each communication product is determined based on the comprehensive evaluation score, and time-division multiplexing is used to allocate the recommended resources to each communication product in proportion.

[0044] In step S402, the time is divided into multiple time slots, so that each communication product occupies the transmission channel exclusively in the corresponding time slot, thereby realizing the multiplexing of recommended resources, including transmission bandwidth.

[0045] For example, the allocation ratio of recommended resources can be further determined based on the comprehensive evaluation score of each communication product, and time-division multiplexing technology can be used to allocate the recommended resources to each communication product proportionally. Specifically, time is divided into multiple time slots, so that each communication product exclusively occupies the transmission channel within the allocated time slot, thereby realizing the multiplexing of recommended resources, which may include transmission bandwidth.

[0046] For example, assuming the total recommended resource transmission bandwidth is 10Mbps, and based on the comprehensive evaluation score, Package Z should be allocated 60% and Package X 40%, corresponding to 6Mbps and 4Mbps respectively. Following the time-division multiplexing principle, time is divided into 1ms time slots. In each time slot, Package Z occupies 600μs and Package X occupies 400μs. A high-speed switching device ensures that each product has exclusive channel access within its corresponding time slot. At the receiving end, the demultiplexer accurately identifies the recommended resources for each product based on the time slot synchronization signal, restores the original data stream, and completes the demultiplexing process.

[0047] The embodiments of this application effectively improve the utilization efficiency of recommendation resources, especially during peak traffic periods such as promotional activities. They can avoid system congestion and response delays, ensure the stability and smoothness of recommendation services, and thus improve user experience and conversion rates.

[0048] Figure 3 This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 3 As shown, the method may further include the following steps: In step S50, the popularity, profit and inventory of the target communication product are monitored in real time.

[0049] In step S60, the first weight corresponding to the changed heat and the second weight corresponding to the changed inventory are determined.

[0050] In step S70, a third weight corresponding to the profit is determined based on the first weight and the second weight.

[0051] In step S80, the resource allocation scheme is adjusted based on the first weight, the second weight, and the third weight.

[0052] For example, during resource allocation, changes in the popularity, profit, and inventory of target communication products can be monitored in real time, and the allocation scheme can be dynamically adjusted based on these changes. First, the first weight corresponding to the changed popularity and the second weight corresponding to the changed inventory are determined. Then, based on the first and second weights, the third weight corresponding to profit is determined, ensuring that the sum of the three weights is 1. Finally, the comprehensive evaluation score of each product is recalculated based on the adjusted first, second, and third weights, and the resource allocation scheme is adjusted accordingly.

[0053] For example, when the inventory status of Package X changes from "good" to "tight," its inventory quantification value drops from 0.6 to 0.3. At this time, the inventory weight is dynamically adjusted from 0.2 to 0.5, the popularity weight remains unchanged at 0.5, and the profit weight is adjusted from 0.3 to 0.1. After recalculation, the overall evaluation score of Package X changes from 0.491 to 0.464, and the overall evaluation score of Package Z changes from 0.634 to 0.671. The resource allocation ratio is adjusted accordingly to 70% for Package Z and 30% for Package X, and the time slot width of time-division multiplexing also changes accordingly.

[0054] The following table shows an example of the overall evaluation score and resource allocation ratio for product popularity, profit, and inventory status before adjustment: Table 1:

[0055] An example of the adjusted comprehensive evaluation score for product popularity, profit, and inventory status, along with the corresponding resource allocation ratio, is shown in the table below: Table 2:

[0056] This dynamic adjustment mechanism in the embodiments of this application enables recommended resources to respond to market changes in real time, prioritizing support for products with tight inventory or high demand, thereby improving operational flexibility and the accuracy of resource allocation, and maximizing overall benefits.

[0057] Figure 4This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 4 As shown, the method may further include the following steps: In step S90, based on the resource allocation scheme of each communication product, a communication product recommendation scheme that matches the user profile of the target user is selected and pushed to the target user.

[0058] For example, after determining the resource allocation scheme for each communication product, the system can further combine the user profile of the target user to select and push a matching communication product recommendation scheme to the target user. For instance, based on user A's historical preference for high-value packages, the system prioritizes recommending package Z, which has a higher overall evaluation score, while also combining it with some packages X to form a recommended combination that meets the user's personalized needs.

[0059] This application embodiment deeply integrates resource allocation schemes with user profiles to ensure that the pushed products not only comply with the platform's resource optimization strategy but also meet the user's real needs, thereby effectively improving the relevance of recommendations and user acceptance.

[0060] Figure 5 This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 5 As shown, the method, based on the resource allocation scheme of each communication product, selects a communication product recommendation scheme that matches the user profile of the target user and pushes it to the target user, which may include the following steps: In step S901, the optimized recommended resources are integrated into the recommendation system, and a personalized product recommendation list is generated based on the user profile.

[0061] In step S902, the personalized product recommendation list is pushed to the target user's terminal.

[0062] For example, when implementing personalized push notifications, optimized recommendation resources can be integrated into the recommendation system, and a personalized product recommendation list can be generated based on user profiles. This list is then pushed to the target user's device. For instance, in the recommendation system backend, display priorities and bandwidth resources have been set for each product based on dynamic resource allocation. The system calls upon preference features from the user profile (such as price sensitivity, feature preferences, etc.) to filter products with high matching degrees from candidate products, sorts them according to comprehensive evaluation scores to generate a list, and finally presents it to the user through the mobile terminal.

[0063] This embodiment of the application directly transforms resource optimization results into personalized services that users can perceive, thereby enhancing the attractiveness and conversion potential of the recommendation list.

[0064] Figure 6This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 6 As shown, the method may further include the following steps: In step S100, user interaction data on the personalized product recommendation list is collected, including click-through rate and / or purchase conversion rate.

[0065] In step S110, the recommendation effect is evaluated based on the interaction behavior data, and feedback is provided to optimize the target semantic network model and resource allocation scheme.

[0066] For example, to continuously improve recommendation performance, user interaction data on personalized product recommendation lists can be collected, including click-through rates and purchase conversion rates. The recommendation effectiveness can then be evaluated based on this data, and the evaluation results can be fed back to the target semantic network model and resource allocation scheme for optimization. For instance, if user A's click-through rate on the recommendation list is 20% and the purchase conversion rate is 5%, this represents a significant improvement compared to the previous 15% click-through rate and 3% conversion rate, indicating effective optimization. If the conversion rate of package Z is found to be lower than expected, the analysis suggests the reason might be an inappropriate recommendation order or an inaccurate target user group. This could lead to adjustments in the recommendation order, optimization of the user profile matching strategy, or optimization of the edge weights of the target semantic network model.

[0067] Through this closed-loop feedback mechanism, the recommendation system in this embodiment can continuously learn and improve itself, ensuring that the recommendation quality continues to improve and user satisfaction gradually increases.

[0068] Figure 7 This is a flowchart illustrating a recommended resource optimization allocation method provided in an embodiment of this application. For example... Figure 7 As shown, determining the comprehensive evaluation score for each communication product may include the following steps: In step S301, the quantitative value of the heat of the target communication product is obtained based on the number of reviews, views, and purchases of the target communication product.

[0069] In step S302, based on the profit value of the target communication product and the maximum and minimum profit values ​​of each communication product, the profit quantification value of the target communication product is obtained.

[0070] In step S303, the inventory quantification value of the target communication product is obtained based on the quantification value corresponding to the inventory level of the target communication product.

[0071] In step S304, the comprehensive evaluation score of the target communication product is determined based on the quantitative value of heat, the quantitative value of profit, the quantitative value of inventory, and the corresponding weights.

[0072] For example, when determining the comprehensive evaluation score of each communication product, a quantitative calculation method can be used: first, obtain the quantitative value of heat based on the number of evaluations, page views, and purchases of the target communication product. For example, the quantitative value of heat can be calculated using the formula (page views × 0.6 + purchases × 0.4) / (page views + purchases).

[0073] For example: Package X had 1000 views and 200 purchases in the past week. The heat value is calculated as (1000 × 0.6 + 200 × 0.4) / (1000 + 200) = (600 + 80) / 1200 ≈ 0.567, rounded to 0.57.

[0074] Secondly, based on the profit value of the target communication product and the maximum and minimum profit values ​​of all communication products, the profit quantification value is obtained, that is, the normalization process is adopted: (actual profit - minimum profit) / (maximum profit - minimum profit).

[0075] For example: Among all products, the minimum profit is 30 yuan and the maximum profit is 100 yuan. The profit of package X is 50 yuan, and the normalized profit = (50 - 30) / (100 - 30) = 20 / 70 ≈ 0.286; the profit of package Z is 80 yuan, and the normalized profit = (80 - 30) / 70 = 50 / 70 ≈ 0.714.

[0076] Then, based on the quantitative values ​​corresponding to the inventory levels, the inventory status is divided into three levels: tight, good, and sufficient, assigned quantitative values ​​of 0.3, 0.6, and 0.9 respectively. Finally, the popularity quantitative value, profit quantitative value, and inventory quantitative value are multiplied by their corresponding weights and summed to obtain the comprehensive evaluation score of the communication product. For example, if Package X has a popularity of 0.57, a normalized profit of 0.286, and an inventory quantitative value of 0.6, and the weights are set to popularity 0.5, profit 0.3, and inventory 0.2, then the comprehensive evaluation score is 0.57×0.5 + 0.286×0.3 + 0.6×0.2 = 0.491.

[0077] The quantitative method described in this application scientifically and objectively integrates multi-dimensional indicators, providing a reliable basis for resource allocation, avoiding subjective assumptions, and ensuring the rationality and fairness of decision-making.

[0078] Figure 8 This is a block diagram of an electronic device provided in one embodiment of this application. For example... Figure 8As shown, the electronic device 800 may include a processor 801 and a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805.

[0079] The processor 801 controls the overall operation of the electronic device 800 to complete all or part of the steps in the recommended resource optimization configuration method described above. The memory 802 stores various types of data to support the operation of the electronic device 800. This data may include, for example, instructions for any application or method operating on the electronic device 800, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0080] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the recommended resource optimization configuration method described above.

[0081] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the recommended resource optimization configuration method described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the electronic device 800 to complete the recommended resource optimization configuration method described above.

[0082] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described recommended resource optimization configuration method when executed by the programmable device.

[0083] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solution of this application, and these simple modifications all fall within the protection scope of this application.

[0084] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this application will not describe the various possible combinations separately.

[0085] Furthermore, various different implementations of this application can be combined in any way, as long as they do not violate the spirit of this application, they should also be regarded as the content disclosed in this application.

Claims

1. A method for recommending optimal resource allocation, characterized in that, The method includes: Obtain sales data, user browsing behavior, and evaluation information of the target telecommunications operator's communication products; Using communication products, user behavior, and user reviews as nodes, and with the number of user behavior nodes as the weight of the first side and the number of user reviews as the weight of the second side, a target semantic network model is generated. The first side is used to represent the relationship between the nodes of user behavior and the nodes of the corresponding communication products, and the second side is used to represent the relationship between the nodes of user reviews and the nodes of the corresponding communication products. Based on the target semantic network model, the popularity, profit and inventory of communication products are used as evaluation indicators to determine the comprehensive evaluation score of each communication product. The popularity is positively correlated with the number of user reviews, and the inventory is negatively correlated with the sales volume. The resource allocation scheme for multiplexing resources for each communication product is determined based on the comprehensive evaluation score of each communication product.

2. The method according to claim 1, characterized in that, The method for determining the resource allocation scheme for multiplexing resources for each communication product based on the comprehensive evaluation score of each communication product includes: Based on the comprehensive evaluation score, the recommended resource allocation ratio for each communication product is determined, and time-division multiplexing is used to allocate the recommended resources to each communication product in proportion. The time is divided into multiple time slots, so that each communication product has exclusive access to the transmission channel in the corresponding time slot, thereby realizing the multiplexing of recommended resources, including transmission bandwidth.

3. The method according to claim 1, characterized in that, The method further includes: Real-time monitoring of changes in the popularity, profit, and inventory of target communication products; Determine the first weight corresponding to the changed popularity and the second weight corresponding to the changed inventory; A third weight corresponding to the profit is determined based on the first weight and the second weight; The resource allocation scheme is adjusted based on the first weight, the second weight, and the third weight.

4. The method according to claim 1, characterized in that, The method further includes: Based on the resource allocation schemes of various communication products, a recommended communication product scheme that matches the user profile of the target user is selected and pushed to the target user.

5. The method according to claim 4, characterized in that, The method, based on the resource allocation schemes of various communication products, selects a communication product recommendation scheme that matches the user profile of the target user and pushes it to the target user, including: The optimized recommendation resources are integrated into the recommendation system, and a personalized product recommendation list is generated based on the user profile. The personalized product recommendation list is pushed to the target user's terminal.

6. The method according to claim 5, characterized in that, The method further includes: Collect user interaction data on the personalized product recommendation list, including click-through rate and / or purchase conversion rate; Based on the interaction behavior data, the recommendation effect is evaluated, and feedback is provided to optimize the target semantic network model and resource allocation scheme.

7. The method according to claim 1, characterized in that, The determination of the comprehensive evaluation score for each communication product includes: Based on the number of reviews, page views, and purchases of the target communication product, obtain the quantitative value of the target communication product's popularity. Based on the profit value of the target communication product, and the maximum and minimum profit values ​​of each communication product, obtain the quantitative profit value of the target communication product. Based on the quantitative value corresponding to the inventory level of the target communication product, obtain the quantitative inventory value of the target communication product; Based on the quantitative values ​​of heat, profit, and inventory, and their corresponding weights, a comprehensive evaluation score for the target communication product is determined.

8. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images