Ranking method and apparatus

Abstract

The application discloses a ranking method and device, and relates to the technical field of electronic commerce. A specific embodiment of the method comprises the following steps: acquiring the weight of a new product feature, wherein the weight of the new product feature is based on the historical data of an old product and is determined by using a lightGBM algorithm; determining a new product score based on the weight of the new product feature and the score of the new product feature, wherein the score of the new product feature is obtained according to a preset scoring rule; and adjusting the ranking of the new product in an original commodity score sequence according to the new product score. The embodiment helps to realize the fair competition between the new product and the old product.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to the field of e-commerce technology, and in particular to a sorting method and apparatus. Background Technology

[0002] New product development is a key focus for major e-commerce companies and brands. Platforms see hundreds of millions of new products listed daily, a massive volume, but resources allocated are limited. Both platforms and merchants lack guidance on resource allocation, making it difficult to predict return on investment. This results in inefficient resource investment, with significant resources wasted without yielding effective returns. Furthermore, efficiency data for new products is sparse, putting them at a disadvantage in search rankings compared to established products.

[0003] The existing new product scoring model on the search side relies on manual parameter tuning based on human experience. This does not make good use of the large amount of historical data accumulated on the search side, resulting in poor products receiving high exposure, uneven traffic distribution and efficiency, and low efficiency feedback for new products. Summary of the Invention

[0004] This application provides a sorting method, apparatus, device, and storage medium.

[0005] According to the first aspect, embodiments of this application provide a sorting method, the method comprising: obtaining the weight of a new product feature, the weight of the new product feature being determined based on historical data of old products using the lightGBM algorithm; determining a new product score based on the weight of the new product feature and the score of the new product feature, the score of the new product feature being obtained according to a preset scoring rule; and adjusting the sorting of the new product in the original product score sequence according to the new product score, the products including: new products and old products.

[0006] According to a second aspect, embodiments of this application provide a sorting apparatus, comprising: an acquisition module configured to acquire weights of new product features, the weights of the new product features being determined based on historical data of existing products using the lightGBM algorithm; a scoring module configured to determine a new product score based on the weights and scores of the new product features, the scores of the new product features being obtained according to preset scoring rules; and a sorting module configured to adjust the sorting of the new product in the original product score sequence according to the new product score, the products including: new products and existing products.

[0007] According to a third aspect, embodiments of this application provide an electronic device including one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform an ordering as described in any embodiment of the first aspect.

[0008] According to a fourth aspect, embodiments of this application provide a computer-readable medium having a computer program stored thereon that, when executed by a processor, implements the sorting as described in any embodiment of the first aspect.

[0009] This application obtains the weights of new product features, which are determined using the lightGBM algorithm based on historical data of existing products. Based on the weights and scores of the new product features, a new product score is determined, with the score obtained according to a preset scoring rule. The ranking of the new product in the original product score sequence is adjusted according to the new product score. The products include both new and existing products, thus improving the new product's ranking in the product score sequence and facilitating fair competition between new and existing products.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0012] Figure 2 This is a flowchart of one embodiment of the sorting method according to this application;

[0013] Figure 3 This is a schematic diagram of an application scenario of the sorting method according to this application;

[0014] Figure 4 This is a flowchart of another embodiment of the sorting method according to this application;

[0015] Figure 5 This is a schematic diagram of one embodiment of the sorting apparatus according to this application;

[0016] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing the server embodiments of this application. Detailed Implementation

[0017] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Figure 1 An exemplary system architecture 100 is shown, in which the sorting method of this application can be applied.

[0020] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0021] Terminal devices 101, 102, and 103 interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications, such as shopping applications and communication applications, can be installed on terminal devices 101, 102, and 103.

[0022] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays, including but not limited to mobile phones and laptops. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., used to provide sorting services) or as a single software program or software module. No specific limitations are made here.

[0023] Server 105 can be a server that provides various services, such as: obtaining the weight of new product features, the weight of new product features being determined based on historical data of old products using the lightGBM algorithm; determining the new product score based on the weight and score of the new product features, the score of the new product features being obtained according to a preset scoring rule; and adjusting the order of new products in the original product score sequence according to the new product score, the products including: new products and old products.

[0024] It should be noted that server 105 can be either hardware or software. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules (e.g., used to provide sorting services), or as a single software program or software module. No specific limitations are made here.

[0025] It should be noted that the sorting provided in the embodiments of this disclosure can be performed by server 105, by terminal devices 101, 102, and 103, or by server 105 and terminal devices 101, 102, and 103 in cooperation with each other. Accordingly, the various parts (e.g., various units, sub-units, modules, and sub-modules) included in the UI style update device can all be set in server 105, all of them can be set in terminal devices 101, 102, and 103, or they can be set in server 105 and terminal devices 101, 102, and 103 respectively.

[0026] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0027] Figure 2 A flowchart 200 illustrates an embodiment of the sorting method applicable to this application. In this embodiment, the sorting method includes the following steps:

[0028] Step 201: Obtain the weights of the new product features.

[0029] In this embodiment, since the platform tags hundreds of millions of products daily, the executing entity (such as...) Figure 1 The server 105 or terminal devices 101, 102, 103 shown can first perform preliminary screening of new products and obtain the weights of the features of the screened new products.

[0030] Here, the way the implementing entity filters new products is to first filter out new products that have exposure and sales within a preset time period (e.g., the last 30 days) from the current time, and then calculate the store dimension scores such as store score, advertising score, and seller service rating of all new products according to preset rules, and filter out poor products with a preset percentage of low scores (e.g., 10%) to obtain the filtered new products.

[0031] Furthermore, the implementing entity can use the LightGBM algorithm to determine the weights of the features of the screened new products based on the historical data of the old products.

[0032] New product characteristics may include one or more of the following: new product operation, service and store quality, traffic conversion, and support level.

[0033] Here, the implementing entity can use the following important attributes in LightGBM to determine the weights of various features of the new product based on the historical data of the old product: 1) gain: the Gini index used when using features for splitting; 2) split: the evaluation based on the number of times the feature is used.

[0034] LightGBM, launched by Microsoft in 2017, is a scalable machine learning system. It's a distributed gradient boosting framework based on the GBDT (Gradient Boosting Decision Tree) algorithm. To reduce model computation time, LightGBM's design focuses on minimizing memory and computational resource usage, as well as reducing communication costs during multi-machine parallel computation. LightGBM offers advantages such as high efficiency and scalability, robustness, direct support for missing values ​​and categorical features, and no need for additional data processing.

[0035] Specifically, if the characteristics of a new product include new product operation, service and store quality, and traffic conversion, the weights of each characteristic determined by the lightGBM algorithm based on the historical data of the old product are 0.2, 0.15, and 0.65, respectively.

[0036] Among some optional approaches, new product features include at least one of the following: new product operation, service and store quality, and traffic conversion.

[0037] In this implementation, the implementing entity obtains the weight of at least one of the following: new product operation, service and store quality, and traffic conversion. Based on the weight and score of the new product features, the entity determines the new product score, which helps to improve the reliability of the new product score.

[0038] Step 202: Determine the new product score based on the weights and scores of the new product features.

[0039] In this embodiment, after obtaining the weights of each feature of the new product, the executing entity can determine the score of the new product based on the weights and scores of each feature. The scores of the new product features are obtained according to preset scoring rules.

[0040] The preset scoring rules are determined based on experience and actual needs, and this application does not impose any restrictions on them.

[0041] Specifically, new product characteristics include: new product operation, service and store quality, and traffic conversion. The new product operation score can be determined based on advertising spending, which in turn is determined by the spending ranking within the third-level category. The service and store quality score can be determined based on store support score, store quality score, DSR (Detailed Seller Rating) score, and brand score. The store support score can be determined based on store click-through rate, new product launch rate, and recommendation rate. The store quality score can be determined based on store followers, exposure, and conversion rates. The DSR score can be determined based on product quality, positive review rate, return rate, and service quality. The brand score can be determined based on the brand's overall score (e.g., exposure, conversion rates). The traffic conversion score can be determined based on search feedback score and overall site feedback score. The search feedback score is determined based on the score within the third-level category, while the overall site feedback score is determined based on the overall site sales ranking within the third-level category.

[0042] Specifically, given the weights of new product features (new product operation, service and store quality, traffic conversion) and their scores, the new product score can be expressed by the following formula:

[0043] score = a * ads score +b*shop score +c*feedback score

[0044] Among them, the parameter weights a, b, and c are determined by the lightGBM algorithm;

[0045] ads score shop score feedback score These are ratings for new product operation, service and store quality, and traffic conversion.

[0046] In some optional methods, the new product score is determined based on the weight and score of the new product features, including: in response to determining that the support period for the new product is greater than or equal to a preset first time period threshold and less than a preset second time period threshold, the new product score is determined based on the weight, score, and time decay factor of the new product features.

[0047] In this implementation, the implementing entity determines the support period for new products, that is, the promotion period for new products after their launch, and if the support period is greater than or equal to a preset first time period threshold but less than a preset second time period threshold, the new product score can be determined based on the weight of the new product features, the score of the new product features, and the time decay factor.

[0048] Here, the threshold for the second time period is greater than the threshold for the first time period. The thresholds for the first and second time periods can be determined based on experience, actual needs, and specific application scenarios, such as 7 days, 30 days, 40 days, etc. This application does not limit this.

[0049] Specifically, given the weights of new product features (new product operation, service and store quality, traffic conversion) and the feature scores of the new product, the new product score1 can be expressed by the following formula:

[0050] score1=(a*ads score +b*shop score +c*feedback score )*p t ,

[0051] 7≤support days <30

[0052] Among them, the parameter weights a, b, and c are determined by the lightGBM algorithm;

[0053] ads score shop score feedback score These are respectively the new product operation rating, service and store quality rating, and traffic conversion rating. days To support time

[0054] p t The time decay factor is expressed by the following formula:

[0055]

[0056] Where Δt represents the number of days the new product receives support on the search side. days ); α represents the time decay coefficient, with a default value of 1, and 0 for best-selling products;

[0057] This implementation method determines the score of a new product by responding to the condition that the support period for the new product is greater than or equal to a preset first time period threshold and less than a preset second time period threshold. Based on the weight of the new product features, the score of the new product features, and the time decay factor, it highlights the impact of the support period on the new product score and helps to improve the accuracy of the new product score.

[0058] In some optional methods, the new product score is determined based on the weight and score of the new product features, including: in response to determining that the support time for the new product is greater than or equal to a preset second time period threshold, the new product score is determined based on the weight, score, time decay factor and circuit breaker signal of the new product features.

[0059] In this implementation, after determining the support period for the new product—that is, the promotion period for the new product after its launch—and finding that it is greater than or equal to a preset second time period threshold, the implementing entity can determine the new product score based on the weight of the new product features, the score of the new product features, the time decay factor, and the circuit breaker signal. The circuit breaker signal is determined based on whether the new product's exposure exceeds a preset exposure threshold and whether the number of orders for the new product is zero.

[0060] Specifically, given the weights of new product features (new product operation, service and store quality, traffic conversion) and the feature scores of the new product, the new product score2 can be expressed by the following formula:

[0061] score2=(a*ads score +b*shop score +c*feedback score )*p t *γ,

[0062] support days ≥30

[0063] Among them, the parameter weights a, b, and c are determined by the lightGBM algorithm;

[0064] ads score shop score feedback score These are respectively the new product operation rating, service and store quality rating, and traffic conversion rating. days To support time

[0065] p t The time decay factor is expressed by the following formula:

[0066]

[0067] Where Δt represents the number of days the new product receives support on the search side. days ); α represents the time decay coefficient, with a default value of 1, and 0 for best-selling products;

[0068] γ represents the fuse trigger signal, specifically as follows:

[0069]

[0070] Among them, orderlines represent the number of orders for a product, and pv>pv_thres means that the exposure of a new product is greater than the exposure threshold of the category;

[0071] This implementation method determines the score of a new product by responding to the determination that the support period for the new product is greater than or equal to a preset second time period threshold, based on the weight of the new product features, the score of the new product features, the time decay factor, and the circuit breaker signal. This highlights the impact of the support period on the new product score and helps to improve the accuracy of the new product score.

[0072] In some optional methods, the new product score is determined based on the weight and score of the new product features, including: in response to determining that the support period for the new product is greater than or equal to a preset second time period threshold and the new product conversion rate (CVR) meets preset conditions, the new product score is determined based on the weight, score, and circuit breaker signal of the new product features.

[0073] In this implementation, after determining that the new product conversion rate (CVR) meets the preset conditions, the executing entity can determine the new product score based on the weight of the new product features, the score of the new product features, and the circuit breaker signal.

[0074] The preset conditions can be determined based on experience, actual needs and specific application scenarios. For example, CVR is greater than the average CVR of the last 3 days, CVR is greater than the average CVR of the last 7 days, etc. This application does not limit these conditions.

[0075] Specifically, given the weights of new product features (new product operation, service and store quality, traffic conversion) and their scores, the new product score (score3) can be expressed by the following formula:

[0076] score3=(a*ads score +b*shop score +c*feedback score )*γ

[0077] cvr>cvr 3days >cvr 7days

[0078] support days ≥30

[0079] Among them, the parameter weights a, b, and c are determined by the lightGBM algorithm;

[0080] ads score shop score feedback score These are respectively: new product operation score, service and store quality score, and traffic conversion score;

[0081] CVR represents the ratio of conversions to clicks, i.e., conversion rate. CVR > CVR 3days >cvr 7daysThis indicates that the current conversion rate is greater than the average conversion rate of the last 3 days, which is greater than the average conversion rate of the last 7 days.

[0082] It should be noted that, as can be seen from the above, for new products with a conversion rate greater than the preset conversion rate threshold, the new product score is not affected by the time decay factor and can always be displayed in a high position on the search homepage, thus becoming a best-selling product.

[0083] This implementation method determines the new product score based on the weight of the new product features, the score of the new product features, and the circuit breaker signal, in response to the determination that the support period for the new product is greater than or equal to a preset second time period threshold and the new product conversion rate (CVR) meets preset conditions. This highlights the impact of support period and new product conversion rate on the new product score and helps to improve the accuracy of the new product score.

[0084] Step 203: Adjust the order of the new products in the original product score sequence based on the new product score.

[0085] In this embodiment, after obtaining the new product score, the executing entity can modify the original score of the new product in the original product (including new and old products) score sequence according to preset rules to obtain the modified new product score. Based on the modified new product score, the ranking of the new product in the original product score sequence is adjusted. The product score sequence is used to indicate the weight of the product displayed on the main search page.

[0086] Here, the preset rules can include a variety of methods. For example, the new product score can be directly added to the original score of the new product to obtain the corrected new product score; the new product score of a preset ratio (such as 1 / 3) can be added to the original score of the new product to obtain the corrected new product score, etc. This application does not limit this.

[0087] Specifically, the score of each product (including new and old products) in the original product score sequence can be obtained by the following formula:

[0088]

[0089] Detailed grading score ∈[0,1], coarse sorting score ∈[0,1],commodity score ∈[0,1]

[0090] Where a, b, and c are sorting parameters determined by technicians based on experience.

[0091] Here, rough layout score This refers to the score used for initial screening and final ranking of products on the search side. score This refers to the score obtained by refining the products after the initial screening on the search side based on various factors.

[0092] The implementing entity adjusts the original scores of new products in the original product score sequence based on the scores of the new products, thus obtaining the adjusted scores for the new products. 修正score It can be obtained through the following formula:

[0093]

[0094] Detailed grading score ∈[0,1], coarse sorting score ∈[0,1],new product 修正score ∈[0,1]

[0095] Where a, b, and c are sorting parameters determined by technicians based on experience.

[0096] After the implementing entity adjusts the ranking of new products in the original product score sequence, a new product score sequence is obtained. The products are then displayed on the main search page according to the new product score sequence, so that new products and old products compete with each other under the same efficiency. The ranking of new products will be improved compared to before the correction, making up for the disadvantage of new products competing with old products without sufficient confidence efficiency data.

[0097] In some optional methods, the method also includes: in response to determining that the support time for the new product is greater than or equal to a preset second time period threshold, and the exposure of the new product is greater than a preset exposure threshold and the number of orders for the new product is zero, removing the new product from the product score sequence.

[0098] In this implementation, the executing entity removes the new product from the product score sequence when it determines that the support period for the new product is greater than or equal to the second time period threshold, for example, 30 days, and the exposure of the new product is greater than the preset exposure threshold and the number of orders for the new product is zero.

[0099] This method helps improve the effectiveness of the product score sequence and reduces traffic loss for new products with exposure exceeding the preset exposure threshold but no conversions by deleting new products that have no conversions.

[0100] In some alternative approaches, the method also includes recording information related to the new product score and displaying that information to the merchant.

[0101] In this implementation, the executing entity can synchronously record relevant information about the new product score, such as the new product score, the top 3 new products with rising scores, the top 3 new products with falling scores, etc., and display the above relevant information to the merchant in the form of a new product score dashboard. This allows the merchant to understand the overall level of the store's new products in search results based on the changes in the new product score, and then adjust resource investment strategies to reduce risks.

[0102] In some alternative approaches, the method may also include: classifying new products according to their scores and corresponding total sales to obtain classification results; and implementing corresponding exposure enhancement strategies for the new products based on the classification results.

[0103] In this implementation, after determining the score of a new product, the executing entity can further sort all new products according to their scores and classify them based on the total transaction value (GMV) of each new product within a certain time period (e.g., premium layer, potential layer, ordinary layer, sparse layer, elimination layer, etc.). Based on the classification results, corresponding exposure enhancement strategies are implemented for the new products, such as increasing the placement and exposure ratio of higher-level new products, while no adjustments are made to lower-level new products.

[0104] Specifically, after determining the scores of new products, the implementing entity sorts all new products in descending order of their scores. Based on this sorting, the GMV corresponding to each new product is accumulated. New products whose accumulated GMV reaches 65% of the total GMV of all new products are classified as "High-Quality" products; those reaching 65%–80% are classified as "Potential" products; and those reaching 80%–100% are classified as "Ordinary" products. For the remaining new products after removing those already classified as "High-Quality," "Potential," or "Ordinary" products, categories with relatively sparse new product volume, such as mobile phones and home appliances, are further classified into a "Sparse" category. The remaining new products, excluding those classified as "Sparse," are then classified into an "Eliminated" category.

[0105] For new products in the premium, potential, and ordinary tiers, an exposure boost of 30%, 20%, and 10% can be invested respectively to further develop the development potential of the new products. For new products in the sparse tier, an exposure boost of 20% can also be invested to further develop the development potential of new products in sparse categories. For new products in the obsolete tier, no exposure boost can be invested.

[0106] This approach categorizes new products based on their scores and corresponding total sales, and then applies appropriate exposure enhancement strategies based on these scores. This helps to further develop the new products' growth potential and improve their competitiveness.

[0107] See also Figure 3 , Figure 3 This is a schematic diagram of an application scenario of the sorting method according to this embodiment.

[0108] exist Figure 3In the application scenario, the executing entity 301 obtains the weights 302 of new product features (e.g., new product operation, service and store quality, traffic conversion), which are 0.2, 0.15, and 0.65 respectively. The weights of the new product features are determined using the lightGBM algorithm based on historical data of existing products. Based on the weights 302 and the scores 303 of the new product features, the new product score 304 is determined, and the scores are obtained according to preset scoring rules. For example, if the score for new product operation is 0.8, the score for service and store quality is 0.7, and the score for traffic conversion is 0.7, then the new product score 304 is 0.2*0.8 + 0.15*0.7 + 0.65*0.7 = 0.72. Based on the new product score 304, the order of the new product in the original product (including new and old products) score sequence 305 is adjusted. For example, if the original product score sequence is Old Product 1 - 0.8 points, Old Product 2 - 0.72 points, and New Product - 0.04 points, the new product score in the original product score sequence can be directly corrected according to the new product score and preset rules. For example, the corrected new product score is 0.76. This results in the adjusted product score sequence 306: Old Product 1 - 0.8 points, New Product - 0.76 points, and Old Product 2 - 0.52 points.

[0109] The sorting method disclosed herein obtains the weights of new product features, which are determined using the lightGBM algorithm based on historical data of old products; the new product score is determined based on the weights and scores of the new product features, which are obtained according to preset scoring rules; the new product score is used to adjust the sorting of the new product in the original product score sequence, which helps to achieve fair competition between new and old products.

[0110] Further reference Figure 4 This illustrates a flow 400 of another embodiment of the sorting method. The flow 400 of the sorting method in this embodiment may include the following steps:

[0111] Step 401: Obtain the weights of the new product features.

[0112] In this embodiment, the implementation details and technical effects of step 401 can be found in the description of step 201, and will not be repeated here.

[0113] Step 402: In response to determining that the support period for the new product is less than a preset first time period threshold, the new product score is determined based on the weight and score of the new product features.

[0114] In this embodiment, after determining that the support period for the new product, i.e. the promotion period for the new product after its launch, is less than a preset first time period threshold, the executing entity can determine the score of the new product based on the weight and score of the new product features.

[0115] The threshold for the first time period can be determined based on experience, actual needs, and specific application scenarios, such as 7 days, 10 days, etc. This application does not limit it.

[0116] Specifically, given the weights of new product features (new product operation, service and store quality, traffic conversion) and their scores, the new product score (score4) can be expressed by the following formula:

[0117] score4=a*ads score +b*shop score +c*feedback score support days <7

[0118] Among them, the parameter weights a, b, and c are determined by the lightGBM algorithm;

[0119] ads score shop score feedback score These are respectively the new product operation rating, service and store quality rating, and traffic conversion rating. days To support the time.

[0120] Step 403: Adjust the order of the new products in the original product score sequence according to the new product score.

[0121] In this embodiment, the implementation details and technical effects of step 403 can be found in the description of step 203, and will not be repeated here.

[0122] The above embodiments of this application, and Figure 2 Compared to the corresponding embodiments, the sorting method in this embodiment, in process 400, reflects the determination of the new product score based on the weight and score of the new product features in response to the determination that the support time for the new product is less than a preset first time period threshold. This implementation highlights the impact of the support time on the new product score and helps to improve the accuracy of the new product score.

[0123] Further reference Figure 5 As an implementation of the methods shown in the above figures, this application provides an embodiment of a sorting device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0124] like Figure 5 As shown, the sorting device 500 in this embodiment includes: an acquisition module 501, a scoring module 502, and a sorting module 503.

[0125] The acquisition module 501 can be configured to acquire the weights of new product features.

[0126] The scoring module 502 can be configured to determine the score of a new product based on the weights and scores of the new product features.

[0127] The sorting module 503 can be configured to adjust the sorting of new products in the original product score sequence based on the new product score.

[0128] In some optional embodiments of this example, the scoring module is further configured to: in response to determining that the support period for the new product is less than a preset first time period threshold, determine the score of the new product based on the weight of the new product features and the score of the new product features.

[0129] In some optional embodiments of this example, the scoring module is further configured to: in response to determining that the support time for the new product is greater than or equal to a preset first time period threshold and less than a preset second time period threshold, determine the new product score based on the weight of the new product features, the score of the new product features, and the time decay factor, wherein the second time period threshold is greater than the first time period threshold.

[0130] In some optional embodiments of this example, the scoring module is further configured to: in response to determining that the support time for the new product is greater than or equal to a preset second time period threshold, determine the score of the new product based on the weight of the new product features, the score of the new product features, the time decay factor, and the circuit breaker signal, wherein the circuit breaker signal is determined based on whether the exposure of the new product is greater than a preset exposure threshold and whether the order quantity of the new product is zero.

[0131] In some optional embodiments of this example, the scoring module is further configured to: in response to determining that the support period for the new product is greater than or equal to a preset second time period threshold, and that the new product conversion rate (CVR) meets a preset condition, determine a new product score based on the weight of the new product features, the score of the new product features, and a circuit breaker signal, wherein the circuit breaker signal is determined based on whether the new product exposure is greater than a preset exposure threshold and whether the number of orders for the new product is zero.

[0132] In some alternative embodiments of this embodiment, the device further includes a deletion module configured to delete the new product from the product score sequence in response to determining that the support time for the new product is greater than or equal to a preset second time period threshold, the exposure of the new product is greater than a preset exposure threshold, and the order quantity of the new product is zero.

[0133] In some alternative embodiments of this embodiment, the device further includes a recording module configured to record information related to the new product score and display the information to the merchant.

[0134] In some optional embodiments of this example, the device further includes a grading module, configured to grade new products according to their scores and the total transaction amount, and obtain grading results; and to implement corresponding exposure enhancement strategies for the new products based on the grading results.

[0135] In some optional ways of this embodiment, the new product features include at least one of the following: new product operation, service and store quality, and traffic conversion.

[0136] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0137] like Figure 6 The diagram shown is a block diagram of an electronic device according to an embodiment of the sorting method of this application.

[0138] 600 is a block diagram of an electronic device according to an embodiment of the sorting method of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0139] like Figure 6 As shown, the electronic device includes one or more processors 601, a memory 602, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take the 601 processor as an example.

[0140] The memory 602 is the non-transitory computer-readable storage medium provided in this application. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the sorting method provided in this application. The non-transitory computer-readable storage medium of this application stores computer instructions for causing a computer to perform the sorting method provided in this application.

[0141] Memory 602, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the sorting method in the embodiments of this application (e.g., appendix). Figure 5 The acquisition module 501, scoring module 502, and sorting module 503 are shown. The processor 601 executes various server functions and data processing by running non-transient software programs, instructions, and modules stored in the memory 602, thereby implementing the sorting method in the above method embodiments.

[0142] Memory 602 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the UI-style updated electronic device. Furthermore, memory 602 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 602 may optionally include memory remotely located relative to processor 601, and these remote memories can be connected to the UI-style updated electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0143] The electronic device for the sorting method may further include an input device 603 and an output device 604. The processor 601, memory 602, input device 603, and output device 604 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0144] Input device 603 can receive input numerical or character information, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 604 may include a display device, auxiliary lighting device (e.g., LED), and haptic feedback device (e.g., vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touchscreen.

[0145] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] These computational programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0149] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0150] The technical solutions according to the embodiments of this application help to achieve fair competition between new and old products.

[0151] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A sorting method, the method comprising: The weights of new product features are obtained, and these weights are determined using the lightGBM algorithm based on historical data of existing products. The new product score is determined based on the weights and scores of the new product features, including: in response to determining that the support period for the new product is greater than or equal to a preset first time period threshold and less than a preset second time period threshold, the new product score is determined based on the weights, scores, and time decay factors of the new product features, where the second time period threshold is greater than the first time period threshold. The support period for the new product is used to indicate the promotion period for the new product after its launch; in response to determining that the support period for the new product is greater than or equal to the preset second time period threshold, the new product score is determined based on the weights, scores, time decay factors, and circuit breaker signals of the new product features. The circuit breaker signal is determined based on whether the exposure of the new product is greater than a preset exposure threshold and whether the order quantity of the new product is zero. The scores of the new product features are obtained according to preset scoring rules. The order of new products in the original product score sequence is adjusted based on the new product score. The products include new products and old products, wherein the data used to determine the new product score in the original product score sequence is less than the data used to determine the old product score in the original product score sequence.

2. The method according to claim 1, wherein, The determination of the new product score based on the weights and scores of the new product features includes: In response to the determination that the support period for the new product is less than a preset first time period threshold, the new product score is determined based on the weight and score of the new product features.

3. The method according to claim 1, wherein, The determination of the new product score based on the weights and scores of the new product features includes: In response to the determination that the support period for the new product is greater than or equal to a preset second time period threshold, and the new product conversion rate (CVR) meets the preset conditions, the new product score is determined based on the weight of the new product features, the score of the new product features, and the circuit breaker signal. The circuit breaker signal is determined based on whether the exposure of the new product is greater than a preset exposure threshold and whether the number of orders for the new product is zero.

4. The method according to claim 1, further comprising: In response to the determination that the support period for a new product is greater than or equal to a preset second time period threshold, and the exposure of the new product is greater than a preset exposure threshold and the number of orders for the new product is zero, the new product will be removed from the product score sequence.

5. The method according to claim 1, further comprising: Record the relevant information of the new product score and display the relevant information to the merchant.

6. The method according to claim 1, further comprising: The new products are classified according to their scores and the total transaction amount, resulting in a classification result. Based on the classification results, implement corresponding exposure enhancement strategies for new products.

7. The method according to claim 1, wherein, The new product features include at least one of the following: new product operation, service and store quality, and traffic conversion.

8. A sorting apparatus, the apparatus comprising: The acquisition module is configured to acquire the weights of new product features, the weights of which are determined based on historical data of old products using the lightGBM algorithm. The scoring module is configured to determine a new product score based on the weights and scores of the new product features, including: in response to determining that the support period for the new product is greater than or equal to a preset first time period threshold and less than a preset second time period threshold, determining the new product score based on the weights, scores, and time decay factors of the new product features, wherein the second time period threshold is greater than the first time period threshold, and the support period for the new product is used to indicate the promotion period for the new product after its launch; in response to determining that the support period for the new product is greater than or equal to the preset second time period threshold, determining the new product score based on the weights, scores, time decay factors, and circuit breaker signals of the new product features, wherein the circuit breaker signal is determined based on whether the new product exposure is greater than a preset exposure threshold and whether the number of orders for the new product is zero, and the scores of the new product features are obtained according to preset scoring rules; The sorting module is configured to adjust the order of new products in the original product score sequence based on the new product score, the products including new products and old products, wherein the data used to determine the new product score in the original product score sequence is less than the data used to determine the old product score in the original product score sequence.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores information that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images