Article ordering method, apparatus, device, medium, and program product

Abstract

The present disclosure provides an article sorting method, device, equipment, medium and program product, relating to the technical field of article sorting and recommendation. An embodiment of the method comprises: obtaining click rates of a plurality of articles; sorting the plurality of articles according to the click rates and correlation coefficients of the plurality of articles to obtain a final sorting result, wherein the correlation coefficients are determined based on the following steps: obtaining a target conversion rate and a target click rate of each sorting position of a target article in a historical time period; and determining the correlation coefficients according to the target conversion rate and the target click rate.

Description

Technical Field

[0001] This disclosure relates to the field of computers, specifically to item sorting and recommendation, and more particularly to an item sorting method, apparatus, device, medium, and program product. Background Technology

[0002] The traditional methods for reordering are: (1) Rule-based methods. This method directly adjusts the position of the results after CTR (Click Through Rate) based on a single business objective. Generally, this method directly places the target items required by a single business into the first few positions. Although this method has a significant improvement on items in terms of a single business objective. (2) CTR-based methods. This method improves the weight of the training samples of items by adding more features that are conducive to improving the weight of items. This method makes the overall ranking of items relatively higher. Summary of the Invention

[0003] This disclosure provides an article sorting method, apparatus, device, medium, and program product.

[0004] In a first aspect, embodiments of this disclosure propose an item sorting method, including: obtaining the click-through rate of multiple items; sorting the multiple items according to the click-through rate and a correlation coefficient to obtain a final sorting result, wherein the correlation coefficient is determined based on the following steps: obtaining the target conversion rate and the target click-through rate of each sorting position of the target item within a historical time period; and determining the correlation coefficient based on the target conversion rate and the target click-through rate.

[0005] Secondly, embodiments of this disclosure propose an item sorting device, comprising: a first acquisition module configured to acquire the click-through rate of multiple items; and an item sorting module configured to sort the multiple items according to the click-through rate and a correlation coefficient to obtain a final sorting result, wherein the correlation coefficient is determined based on the following steps: acquiring the target conversion rate and the target click-through rate of each sorting position of the target item within a historical time period; and determining the correlation coefficient based on the target conversion rate and the target click-through rate.

[0006] Thirdly, embodiments of this disclosure provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.

[0007] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described in the first aspect.

[0008] Fifthly, embodiments of this disclosure provide a computer program product including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0009] The item sorting method, apparatus, device, medium, and program product provided in this disclosure can sort multiple items based on the click-through rate of the items and the correlation coefficient determined based on the target conversion rate and target click-through rate of each sorting position of the target items within a preset time period, so as to eliminate the influence of sorting position deviation on the sorting of multiple items.

[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] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. Wherein:

[0012] Figure 1 This is an exemplary system architecture diagram to which this disclosure can be applied;

[0013] Figure 2 This is a flowchart of an embodiment of the item sorting method according to the present disclosure;

[0014] Figure 3 This is a flowchart of an embodiment of the item sorting method according to the present disclosure;

[0015] Figure 4 This is a flowchart of an embodiment of the item sorting method according to the present disclosure;

[0016] Figure 5 This is a flowchart of an embodiment of the item sorting method according to the present disclosure;

[0017] Figure 6 This is a schematic diagram of an application scenario of the item sorting method disclosed herein;

[0018] Figure 7 This is a schematic diagram of the structure of an embodiment of the item sorting device according to the present disclosure;

[0019] Figure 8 This is a block diagram of an electronic device used to implement embodiments of the present disclosure. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and 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 disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Figure 1 An exemplary system architecture 100 is shown, to which embodiments of the item sorting method or item sorting apparatus of this disclosure may be applied.

[0023] 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.

[0024] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104, for example, by monitoring the click rates of multiple items. Various client applications and intelligent interactive applications, such as shopping apps, news apps, and music apps, can be installed on terminal devices 101, 102, and 103.

[0025] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be electronic products that allow human-computer interaction with users through one or more methods such as a keyboard, touchpad, touchscreen, remote control, voice interaction, or handwriting devices. Examples include PCs (Personal Computers), mobile phones, smartphones, PDAs (Personal Digital Assistants), wearable devices, PPCs (Pocket PCs), tablets, smart car systems, smart TVs, smart speakers, laptops, and desktop computers, etc.; terminal devices can also be non-motorized vehicles with communication capabilities. When terminal devices 101, 102, and 103 are software, they can be implemented as multiple software programs or software modules, or as a single software program or software module. No specific limitations are made here.

[0026] Server 105 can provide various services. For example, server 105 can obtain the click-through rate of multiple items; based on the click-through rate and correlation coefficient of multiple items, it can sort the multiple items to obtain the final sorting result, wherein the correlation coefficient is determined based on the following steps: obtaining the target conversion rate and target click-through rate of each sorting position of the target item within a historical time period; and determining the correlation coefficient based on the target conversion rate and target click-through rate.

[0027] 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 distributed services), or as a single software program or software module. No specific limitations are made here.

[0028] It should be noted that the item sorting method provided in this embodiment is generally executed by server 105, and correspondingly, the item sorting device is generally set in server 105.

[0029] It should be understood that Figure 1 The number of terminal devices, networks, and computing devices shown is merely illustrative. Depending on implementation needs, there can be any number of terminal devices, networks, and servers.

[0030] Continue to refer to Figure 2 The diagram illustrates a flow 200 of an embodiment of an item sorting method according to the present disclosure. The item sorting method may include the following steps:

[0031] Step 201: Obtain the click-through rate of multiple items.

[0032] In this embodiment, the execution body of the item sorting method (e.g.) Figure 1 The server 105 shown can be accessed via a network (e.g., Figure 1 The network 104 shown above starts from the terminal device (e.g., Figure 1 The click-through rate (CTR) of multiple items retrieved from the terminal devices 101, 102, and 103 shown, or from local storage. The CTR can refer to the ratio of the number of times an item on a website page is clicked to the number of times it is displayed, i.e., clicks / views, which is a percentage. It reflects the level of attention a particular item receives on the webpage and can be used to measure the item's attractiveness. The aforementioned items include, but are not limited to, any type of goods that can be offered to the market for consumption or use. For example, items can include physical items such as clothing, coffee, and cars; they can also include intangible items such as services, education, games, and virtual resources.

[0033] Here, the click-through rate of the above items can be determined based on the following method:

[0034] Method 1: Use features extracted from the data accumulated in the scene and data from the scene in which the item whose click rate is to be predicted is located to train a click rate prediction model, and then use the trained click rate prediction model to predict the click rate.

[0035] Method 2: Use data samples extracted from the data accumulated from the scene and data samples extracted from the scene of the item whose click rate is to be predicted to train a click rate prediction model, and then use the trained click rate prediction model to predict the click rate.

[0036] The click-through rate prediction model mentioned above can employ a binary classification model. This binary classification model can be a logistic regression model, a gradient boosting decision tree model, or a deep neural network model.

[0037] It should be noted that the target scenarios mentioned above can be social scenarios, such as adding friends or reading copy; or shopping scenarios, such as promotions or flash sales.

[0038] The collection, storage, use, processing, transmission, provision, and disclosure of click rates for multiple items involved in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0039] Step 202: Sort the multiple items according to their click-through rates and relevance coefficients to obtain the final sorting result. The relevance coefficient is determined based on the following steps: obtaining the target conversion rate and target click-through rate of each sorting position of the target item within the historical time period; and determining the relevance coefficient based on the target conversion rate and target click-through rate.

[0040] In this embodiment, the executing entity can use the click-through rate and relevance coefficient of multiple items to sort them and obtain a final sorting result. The initial sorting result can be used to characterize the sorting order in which multiple items are recalled and displayed.

[0041] Here, the aforementioned correlation coefficient can be determined based on the following steps: obtaining the target conversion rate and target click-through rate for each sorting position of the target item within a historical time period; then, determining the correlation coefficient based on the target conversion rate and target click-through rate. The sorting position can be the position corresponding to the order in which the item is displayed, for example, the computer item in the second position. The target click-through rate and target conversion rate can be the actual click-through rate and conversion rate of the target item. The target item can be any one of the multiple items mentioned in step 201.

[0042] In one example, the correlation coefficient can be either r-squared or adjusted R-squared.

[0043] Generally, items ranked higher in the search bar tend to generate more conversions. However, due to other factors, the correlation between position and conversion cannot be guaranteed. Therefore, a conversion correlation analysis is first performed on the position, and the conversion ranking is then re-sorted for clicks at different positions to maximize conversions.

[0044] In one example, the conversion rate of each location at each moment in the past 30 days (within a preset time period) can be extracted. Since click-through rate (CTR) may be manipulated, the conversion rate is selected for performance analysis. First, the conversion rate of each location is aggregated and statistically analyzed. Then, the correlation between the aggregated conversion rate and the CTR is analyzed to obtain the r-squared coefficient between the CTR and the conversion rate.

[0045] If the r-squared coefficient is greater than a preset threshold, such as 0.8, it indicates a strong correlation between the two. For example, the conversion rates for 5 positions are: 1 (0.4), 2 (0.5), 3 (0.2), 4 (0.6), 5 (0.3), which, after reordering, become: 3, 5, 1, 2, 4. The preset threshold can be set according to the recall precision or by the user.

[0046] It should be noted that during the sorting process, the position of each item in the sorting order will be different at different times. The target click-through rate mentioned above can be the click-through rate of the target item at different sorting positions. The target conversion rate mentioned above can be the conversion rate of the target item at each sorting position within a preset time period. This conversion rate can be used to characterize the likelihood of a user performing a predetermined action on the item, which may include, but is not limited to, browsing, clicking, and purchasing.

[0047] The item sorting method provided in this disclosure first obtains the click-through rate (CTR) of multiple items; then, it sorts the multiple items based on their CTR and a correlation coefficient to obtain a final sorting result. The correlation coefficient is determined based on the following steps: obtaining the target conversion rate and target CTR of each sorting position of the target item within a historical time period; and determining the correlation coefficient based on the target conversion rate and target CTR. This method can sort multiple items based on their CTR and the correlation coefficient determined by the target conversion rate and target CTR of each sorting position of the target item within a preset time period, thereby eliminating the influence of sorting position deviations on the sorting of multiple items.

[0048] Further reference Figure 3 , Figure 3A flow 300 is shown as an embodiment of an item sorting method according to the present disclosure. The item sorting method may include the following steps:

[0049] Step 301: Obtain the click-through rate of multiple items.

[0050] In this embodiment, the execution body of the item sorting method (e.g.) Figure 1 The server 105 shown can be accessed via a network (e.g., Figure 1 The network 104 shown above starts from the terminal device (e.g., Figure 1 The click-through rate (CTR) of multiple items obtained from the terminal devices 101, 102, and 103 shown, or from local storage. The CTR can refer to the ratio of the number of times an item on a website page is clicked to the number of times it is displayed, i.e., clicks / views. It is a percentage that reflects the level of attention an item receives on a webpage and can be used to measure the item's attractiveness. The aforementioned items include, but are not limited to, any type of goods that can be offered to the market for consumption or use. For example, items can include physical items such as clothing, coffee, and cars; they can also include intangible items such as services, education, games, and virtual resources.

[0051] The collection, storage, use, processing, transmission, provision, and disclosure of click rates for multiple items involved in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0052] Step 302: Sort the multiple items according to their click-through rates to obtain an initial sorting result.

[0053] In this embodiment, the execution entity can sort multiple items based on their click-through rates to obtain an initial sorting result. This initial sorting result can be used to characterize the sorting order of the multiple items.

[0054] Step 303: Use the correlation coefficient to re-sort the initial sorting results to obtain the final sorting results. The correlation coefficient is determined based on the following steps: obtain the target conversion rate and target click-through rate of each sorting position of the target item within the historical time period; determine the correlation coefficient based on the target conversion rate and target click-through rate.

[0055] In this embodiment, the aforementioned executing entity can use the correlation coefficient to re-sort the initial sorting results to obtain the final sorting results.

[0056] Here, the aforementioned correlation coefficient can be determined based on the following steps: obtaining the target conversion rate and target click-through rate for each sorting position of the target item within a historical time period; then, determining the correlation coefficient based on the target conversion rate and target click-through rate.

[0057] In this embodiment, the specific operation of step 301 has been described. Figure 2 Step 201 in the illustrated embodiment is described in detail and will not be repeated here.

[0058] It should be noted that multiple items can be sorted separately based on correlation coefficient and click-through rate; then, the multiple items sorted by correlation coefficient and click-through rate can be matched to determine the final sorting result.

[0059] In one example, the correlation coefficient is first determined, and multiple items are sorted according to the correlation coefficient to obtain an initial sorting result; then, the initial sorting result is sorted again according to the obtained click rate to obtain the final sorting result.

[0060] from Figure 3 It can be seen from this that, with Figure 2 Compared to the corresponding embodiments, the item sorting method in this embodiment emphasizes the step of sorting multiple items based on their click-through rates and relevance coefficients. Therefore, the scheme described in this embodiment can first sort multiple items by click-through rate to obtain an initial sorting result; then, it uses the relevance coefficient to sort the initial sorting result again to obtain the final sorting result. It can sort multiple items based on their click-through rate and the relevance coefficient determined by the target conversion rate and target click-through rate of each sorting position of the target item within a preset time period, thereby eliminating the influence of sorting position deviations on the sorting of multiple items.

[0061] Further reference Figure 4 , Figure 4 A flow 400 is shown as an embodiment of an item sorting method according to the present disclosure. The item sorting method may include the following steps:

[0062] Step 401: Obtain the click-through rate of multiple items.

[0063] In this embodiment, the execution body of the item sorting method (e.g.) Figure 1 The server 105 shown can be accessed via a network (e.g., Figure 1 The network 104 shown above starts from the terminal device (e.g., Figure 1The click-through rate (CTR) of multiple items retrieved from the terminal devices 101, 102, and 103 shown, or from local storage. The CTR can refer to the ratio of the number of times an item on a website page is clicked to the number of times it is displayed, i.e., clicks / views, which is a percentage. It reflects the level of attention a particular item receives on the webpage and can be used to measure the item's attractiveness. The aforementioned items include, but are not limited to, any type of goods that can be offered to the market for consumption or use. For example, items can include physical items such as clothing, coffee, and cars; they can also include intangible items such as services, education, games, and virtual resources.

[0064] The collection, storage, use, processing, transmission, provision, and disclosure of click rates for multiple items involved in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0065] Step 402: Sort the multiple items according to their click-through rates and corresponding first adjustment coefficients to obtain an initial sorting result.

[0066] In this embodiment, the aforementioned execution entity can sort multiple items based on their click-through rates and corresponding first adjustment coefficients to obtain an initial sorting result. The first adjustment coefficient can be set based on the precision of the recalled items or by the user. This first adjustment coefficient is used to adjust the click-through rate so that the items sorted based on the click-through rate and the first adjustment coefficient better match the user's preferences.

[0067] Step 403: Use the correlation coefficient to re-sort the initial sorting results to obtain the final sorting results. The correlation coefficient is determined based on the following steps: obtain the target conversion rate and target click-through rate of each sorting position of the target item within the historical time period; determine the correlation coefficient based on the target conversion rate and target click-through rate.

[0068] In this embodiment, the aforementioned executing entity can use the correlation coefficient to re-sort the initial sorting results to obtain the final sorting results.

[0069] Here, the aforementioned correlation coefficient can be determined based on the following steps: obtaining the target conversion rate and target click-through rate for each sorting position of the target item within a historical time period; then, determining the correlation coefficient based on the target conversion rate and target click-through rate.

[0070] In this embodiment, the specific operations of steps 401 and 403 have been described. Figure 3 Steps 301 and 303 in the illustrated embodiments are described in detail and will not be repeated here.

[0071] from Figure 4 It can be seen from this that, with Figure 3Compared to the corresponding embodiments, the item sorting method in this embodiment emphasizes the step of sorting multiple items based on their click-through rates and corresponding first adjustment coefficients to obtain an initial sorting result. Therefore, the scheme described in this embodiment can first sort multiple items based on their click-through rates and corresponding first adjustment coefficients to obtain an initial sorting result; then, it can re-sort the initial sorting result using a correlation coefficient to obtain a final sorting result. This approach first uses the first adjustment coefficient to make the initial sorting result obtained based on the first adjustment coefficient and click-through rate more accurate; then, it re-sorts the initial sorting result based on the correlation coefficient determined by the target conversion rate and target click-through rate of each sorting position of the target item within a preset time period, thereby eliminating the impact of sorting position deviations on the sorting of multiple items.

[0072] In some optional implementations of this embodiment, the first adjustment coefficient is determined based on the following steps: obtaining the click volume and conversion volume of multiple items; and determining the first adjustment coefficient based on the click volume and conversion volume of multiple items.

[0073] In this implementation, the first adjustment coefficient can be determined based on the following steps: obtaining the click-through rate and conversion rate of multiple items; then, determining the first adjustment coefficient based on the click-through rate and conversion rate of the multiple items. The click-through rate can be the actual number of actions performed on an item, such as the number of times an item is clicked or viewed. The conversion rate can be the actual number of conversions, such as the number of times an item is purchased.

[0074] In some optional implementations of this embodiment, determining the first adjustment coefficient based on the click volume and conversion volume of multiple items includes: determining the first adjustment coefficient based on the click volume, conversion volume and second adjustment coefficient corresponding to the click volume of multiple items.

[0075] In this implementation, the aforementioned executing entity can determine the first adjustment coefficient based on the click-through rate, conversion rate, and the second adjustment coefficient corresponding to the click-through rate for multiple items. The second adjustment coefficient can be set based on the recall precision or by the user, and this second adjustment precision is used to adjust the click-through rate to obtain the first adjustment coefficient.

[0076] In one example, the click-through rate can be adjusted using a first adjustment factor, which can be as follows:

[0077]

[0078] Where x is the number of clicks, y is the number of conversions, a is the second adjustment coefficient, and ctr is the click-through rate.

[0079] In this implementation, the rate of decay can be adjusted by the conversion rate; the more conversions, the faster the decay rate. This further optimizes the overall traffic allocation. Simultaneously, to satisfy prior user preferences (i.e., ranking based on relevance coefficients), click-through rates (e.g., those in step 201) are used to model users and items, obtaining each user's preference value for an item. Finally, the two values ​​are summed to obtain the final ranking value. Through this re-ranking, both traffic allocation and user experience are optimized.

[0080] In some optional implementations of this embodiment, obtaining the target conversion rate for each sorting position within a historical time period includes: obtaining the conversion rate of the target item for each sorting position at each time within a historical time period; and determining the target conversion rate for each position of the target item based on the conversion rate of the target item for each sorting position at each time.

[0081] In this implementation, the aforementioned executing entity can first integrate the conversion rates of the target item at each time and each sorting position within the historical time period to determine the target conversion rate for each position of the target item. This integration can be either summation or weighted summation.

[0082] It should be noted that the weighted summation can be a weighted summation between the weight and conversion rate corresponding to each position.

[0083] In one example, the item sorting method may also include: selecting items from the final sorting results as recommended items according to preset conditions.

[0084] In this implementation, the aforementioned execution entity can filter recommended items from the final sorting results according to preset conditions, and then recommend them to the user. These recommended items can be any items to be recommended to the user.

[0085] Here, the aforementioned preset conditions can be items selected by the user from the final sorting results or items ranked among the top few.

[0086] In this implementation, recommended items can be selected from the final sorting results based on preset conditions.

[0087] Further reference Figure 5 , Figure 5 A flow 500 is shown as an embodiment of an item sorting method according to the present disclosure. The item sorting method may include the following steps:

[0088] Step 501: Sort multiple items using correlation coefficients to obtain an initial sorting result.

[0089] In this embodiment, the execution body of the item sorting method (e.g.) Figure 1 The server 105 shown can use correlation coefficients to sort multiple items and obtain an initial sorting result. The initial sorting result can be used to characterize the sorting order of multiple items.

[0090] Here, the aforementioned correlation coefficient can be determined based on the following steps: obtaining the target conversion rate and target click-through rate for each sorting position of the target item within a historical time period; then, determining the correlation coefficient based on the target conversion rate and target click-through rate.

[0091] Step 502: Obtain the click-through rate of multiple items.

[0092] In this embodiment, the execution body of the item sorting method (e.g.) Figure 1 The server 105 shown can be accessed via a network (e.g., Figure 1 The network 104 shown above starts from the terminal device (e.g., Figure 1 The click-through rate (CTR) of multiple items obtained from the terminal devices 101, 102, and 103 shown, or from local storage. The CTR can refer to the ratio of the number of times an item on a website page is clicked to the number of times it is displayed, i.e., clicks / views. It is a percentage that reflects the level of attention an item receives on a webpage and can be used to measure the item's attractiveness. The aforementioned items include, but are not limited to, any type of goods that can be offered to the market for consumption or use. For example, items can include physical items such as clothing, coffee, and cars; they can also include intangible items such as services, education, games, and virtual resources.

[0093] The collection, storage, use, processing, transmission, provision, and disclosure of click rates for multiple items involved in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0094] Step 503: Based on the click-through rates of multiple items, re-sort the initial sorting results to obtain the final sorting results.

[0095] In this embodiment, the execution entity can re-sort the initial sorting results in step 501 based on the click-through rates of multiple items to obtain the final sorting results.

[0096] In this embodiment, the specific operation of step 502 has been described. Figure 2 Step 201 in the illustrated embodiment is described in detail and will not be repeated here.

[0097] It should be noted that step 501 can be executed first, followed by step 502; or steps 502 and 501 can be executed simultaneously.

[0098] from Figure 5 It can be seen from this that, with Figure 2 Compared to the corresponding embodiments, the item sorting method in this embodiment emphasizes the step of sorting multiple items based on their click-through rates and relevance coefficients. Therefore, the scheme described in this embodiment can first sort multiple items using the relevance coefficients to obtain an initial sorting result; then, it can re-sort the initial sorting result using the click-through rate to obtain the final sorting result. This method can sort multiple items based on their click-through rates and the relevance coefficients determined by the target conversion rate and target click-through rate of each sorting position of the target items within a preset time period, thereby eliminating the impact of sorting position deviations on the sorting of multiple items.

[0099] Further reference Figure 6 , Figure 6 A schematic diagram illustrating an application scenario of the item sorting method according to this disclosure is shown. In this application scenario, the item sorting method may include the following steps:

[0100] The first step is to obtain the target conversion rate and target click-through rate for each sorting position of the target item within the historical time period.

[0101] The second step is to determine the correlation coefficient (i.e., positional deviation analysis) based on the target conversion rate and target click-through rate.

[0102] The third step is to sort the multiple items using correlation coefficients to obtain the initial sorting results.

[0103] The fourth step is to obtain the click-through rate of multiple items.

[0104] The fifth step is to sort the multiple items based on their click-through rates and corresponding first adjustment coefficients to obtain the initial sorting results.

[0105] The sixth step is to match the initial sorting results obtained in the third and fifth steps to obtain the final initial sorting result.

[0106] In this implementation, to make the allocation more accurate, the initial sorting result in the third step is matched with the initial sorting result in the fifth step to obtain the final sorting order (i.e., the final sorting result).

[0107] It should be noted that steps one and two can be performed simultaneously with step four, or step four can be performed first, followed by steps one and two.

[0108] Further reference Figure 7 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of an item sorting device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0109] like Figure 7 As shown, the item sorting device 700 of this embodiment may include a first acquisition module 701 and an item sorting module 702. The first acquisition module 701 is configured to acquire the click-through rates of multiple items; the item sorting module 702 is configured to sort the multiple items based on their click-through rates and a correlation coefficient, wherein the correlation coefficient is determined based on the following steps: acquiring the target conversion rate and target click-through rate of each sorting position of the target item within a historical time period; and determining the correlation coefficient based on the target conversion rate and target click-through rate.

[0110] In this embodiment, the specific processing of the first acquisition module 701 and the item sorting module 702 in the item sorting device 700 and the resulting technical effects can be referred to respectively. Figure 2 The relevant descriptions of steps 201-202 in the corresponding embodiments will not be repeated here.

[0111] In some optional implementations of this embodiment, the item sorting module 702 includes: a first sorting unit configured to sort multiple items according to their click rates to obtain an initial sorting result; and a second sorting unit configured to sort the initial sorting result using a correlation coefficient to obtain a final sorting result.

[0112] In some optional implementations of this embodiment, the first sorting unit is further configured to: sort multiple items according to their click-through rates and corresponding first adjustment coefficients to obtain an initial sorting result.

[0113] In some optional implementations of this embodiment, the item sorting device further includes: a second acquisition module, further configured to acquire the click volume and conversion volume of multiple items; and a coefficient determination module, configured to determine a first adjustment coefficient based on the click volume and conversion volume of multiple items.

[0114] In some optional implementations of this embodiment, the coefficient determination module is further configured to: determine the first adjustment coefficient based on the click volume, conversion volume and second adjustment coefficient corresponding to the click volume of multiple items.

[0115] In some optional implementations of this embodiment, the first acquisition module 701 is further configured to: acquire the conversion rate of the target item at each sorting position at each time within a historical time period; and determine the target conversion rate of each position of the target item based on the conversion rate of the target item at each sorting position at each time.

[0116] In some optional implementations of this embodiment, the item sorting device further includes: an item as a module, configured to select items from the final sorting result as recommended items according to preset conditions.

[0117] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0118] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. 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 illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0119] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0120] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0121] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the item sorting method. For example, in some embodiments, the item sorting method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the item sorting method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the item sorting method by any other suitable means (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments 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 transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] 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).

[0126] 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.

[0127] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0128] Artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0129] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution mentioned in this disclosure can be achieved, and this is not limited herein.

[0130] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. An article ranking method, obtaining click rates of a plurality of items, wherein, the click rate is a ratio of a number of times of being clicked to a number of times of being displayed; ranking the plurality of articles according to the click rate and the correlation coefficient to obtain a final ranking result, including: ranking the plurality of articles according to the click rate to obtain an initial ranking result; and ranking the initial ranking result according to the correlation coefficient to obtain the final ranking result, wherein the correlation coefficient is determined based on the following steps: obtaining a target conversion rate and a target click rate of each ranking position of a target article in a historical time period; and determining the correlation coefficient according to the target conversion rate and the target click rate.

2. The method of claim 1, wherein, the ranking the plurality of articles according to the click rate to obtain an initial ranking result, including: ranking the plurality of articles according to the click rate and a corresponding first adjustment coefficient to obtain an initial ranking result.

3. The method of claim 2, wherein, the first adjustment coefficient is determined based on the following steps: obtaining a click volume and a conversion volume of the plurality of articles; determining the first adjustment coefficient according to the click volume and the conversion volume of the plurality of articles.

4. The method of claim 3, wherein, the determining the first adjustment coefficient according to the click volume and the conversion volume of the plurality of articles, including: determining the first adjustment coefficient according to the click volume, the conversion volume and a second adjustment coefficient corresponding to the click volume of the plurality of articles.

5. The method according to any one of claims 1 to 4, wherein, the obtaining the target conversion rate of each ranking position in the historical time period, including: obtaining a conversion rate of each ranking position corresponding to each time of the target article in the historical time period; determining the target conversion rate of each position of the target article according to the conversion rate of each ranking position corresponding to each time of the target article.

6. The method of claim 1, further comprising: selecting an article in the final ranking result as a recommended article according to a preset condition.

7. An article ranking device, a first obtaining module configured to obtain click rates of a plurality of items, wherein the click rate is a ratio of a number of times of being clicked to a number of times of being displayed; an article ranking module configured to rank the plurality of articles according to the click rate and the correlation coefficient to obtain a final ranking result, including: a first ranking unit configured to rank the plurality of articles according to the click rate to obtain an initial ranking result; and a second ranking unit configured to rank the initial ranking result according to the correlation coefficient to obtain the final ranking result, wherein the correlation coefficient is determined based on the following steps: obtaining a target conversion rate and a target click rate of each ranking position of a target article in a historical time period; and determining the correlation coefficient according to the target conversion rate and the target click rate.

8. The apparatus of claim 7, wherein, the first ranking unit is further configured to: rank the plurality of articles according to the click rate and a corresponding first adjustment coefficient to obtain an initial ranking result.

9. The device of claim 8, further comprising: a second obtaining module further configured to obtain a click volume and a conversion volume of the plurality of articles; a coefficient determining module configured to determine the first adjustment coefficient according to the click volume and the conversion volume of the plurality of articles.

10. The apparatus of claim 9, wherein, the coefficient determining module is further configured to: According to the click amount, the conversion amount and the second adjustment coefficient corresponding to the click amount of the plurality of items, the first adjustment coefficient is determined.

11. The apparatus of any of claims 7-10, wherein, The first obtaining module is further configured to: obtain a conversion rate of the target item at each ranking position corresponding to each time in a historical time period; determine a target conversion rate of each position of the target item according to the conversion rate of the target item at each ranking position corresponding to each time.

12. The apparatus of claim 7, further comprising: an item as a module configured to select an item in the final ranking result as a recommended item according to a preset condition.

13. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.

Images