Article information processing method and device
By analyzing historical traffic log data, calculating target traffic and adjusting placement, the problem of optimizing items' placement position on the search result page is solved, and the traffic investment income is maximized and the traffic is continuously improved.
Patent Information
- Application Number
- CN202310612217.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-26
- Publication Date
- 2024-11-26
Smart Images

Figure CN119027207A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of Internet technology, specifically to the field of search, page display, Internet, and promotion technology, and especially to a method and device for processing item information. Background Art
[0002] With the development of Internet technology, various Internet platforms have gradually emerged, such as merchant platforms. Search is a medium for users, merchants and platforms to participate and interact. After searching, the platform can display various search results in the display position.
[0003] High-quality display positions are more conducive to obtaining positive feedback from users, such as higher click-through rates and purchase frequencies. Summary of the invention
[0004] Provided are a method, device, electronic device and storage medium for processing item information.
[0005] According to a first aspect, a method for processing item information is provided, comprising: obtaining data on the flow input and flow of items displayed on a page, wherein the data on the flow association is determined based on a historical flow log of the page displaying the items; based on the data on the flow association, generating the flow of the items on the page when the correlation between the flow input and flow of the items is maximum; based on the generated flow, determining a target flow that the items will use on the page; based on the target flow, determining flow adjustment information for the items in a preset time period in the future; and based on the flow adjustment information, updating the display position of the items on the page.
[0006] According to a second aspect, a device for processing item information is provided, comprising: an acquisition unit configured to acquire data on the flow input and flow correlation of an item displayed on a page, wherein the correlation data is determined based on a historical flow log of the page displaying the item; a generation unit configured to generate, based on the correlation data, the flow of the item on the page when the correlation between the flow input and flow of the item is maximum; a flow determination unit configured to determine, based on the generated flow, a target flow that the item will adopt on the page; an adjustment unit configured to determine, based on the target flow, flow adjustment information of the item in a preset time period in the future; and a booth update unit configured to update the display position of the item on the page based on the flow adjustment information.
[0007] According to a third aspect, an electronic device is provided, comprising: 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, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of any embodiment of the method for processing item information.
[0008] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute a method according to any embodiment of the method for processing item information.
[0009] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any embodiment of the method for processing item information.
[0010] According to the scheme disclosed in the present invention, a parameter indicating the correlation between traffic investment and traffic can be obtained. By maximizing the correlation between the two, the benefits of traffic investment can be maximized, which helps to increase the traffic of items when the traffic investment is increased. This helps users who invest in traffic to have a greater willingness to invest in traffic because of the increase in traffic. In addition, the present application also uses the target traffic to generate traffic adjustment information for the item, thereby updating the display position of the item on the page. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0012] Figure 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure may be applied;
[0013] Figure 2 is a flowchart of an embodiment of a method for processing item information according to the present disclosure;
[0014] Figure 3 is a schematic diagram of an application scenario of the method for processing item information according to the present disclosure;
[0015] Figure 4 is a flow chart for determining a traffic prediction value according to the method for processing item information disclosed herein;
[0016] Figure 5 is a structural schematic diagram of an embodiment of a device for processing item information according to the present disclosure;
[0017] Figure 6 The block diagram is a block diagram of an electronic device used to implement the method for processing item information according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0019] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved all comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.
[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0021] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of a method for processing item information or an apparatus for processing item information of the present disclosure can be applied.
[0022] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0023] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as video applications, live broadcast applications, instant messaging tools, email clients, social platform software, etc.
[0024] The terminal devices 101, 102, 103 here can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers and desktop computers, etc. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, multiple software or software modules for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.
[0025] The server 105 may be a server providing various services, such as a backend server providing support to the terminal devices 101, 102, and 103. The backend server may analyze and process data such as item flow input and flow, and feed back the processing results (such as the target flow of items) to the terminal device.
[0026] It should be noted that the method for processing item information provided in the embodiment of the present disclosure may be executed by the server 105 or the terminal devices 101 , 102 , 103 , and accordingly, the device for processing item information may be disposed in the server 105 or the terminal devices 101 , 102 , 103 .
[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0028] Continue to refer Figure 2 , shows a process 200 of an embodiment of a method for processing item information according to the present disclosure. The method for processing item information includes the following steps:
[0029] Step 201, obtaining the traffic input and traffic correlation data of the items displayed on the page, wherein the correlation data is determined based on the historical traffic log of the page displaying the items.
[0030] In this embodiment, the method for processing item information runs on an execution subject (eg Figure 1 The server or terminal device shown in the figure can obtain the associated data, where the associated data is data associated with the traffic input and traffic of the items displayed on the page. For example, the associated data includes historical traffic. The page refers to a web page or an application page.
[0031] Traffic refers to the number of exposures on a page. For example, displaying on a page, displaying on a page with item information, or displaying at the location of the item information on a page can achieve exposure and get traffic. In addition, exposure can also include displaying in a fixed display position (such as a display position on a web page).
[0032] Traffic investment refers to the resources invested to achieve the exposure of an item. Specifically, resources may include funds. In addition, resources may also include human resources, etc. Items may be commodities, etc., and may be expressed as various item information.
[0033] The historical traffic log records the traffic log of the page, specifically recording the traffic of items displayed on the page in the historical time. The above-mentioned execution subject or other electronic device can determine the associated data based on the historical traffic log of the page displaying the item. Taking the execution subject as an example, the above-mentioned execution subject can directly obtain the traffic of the item display in the preset historical time period in the historical traffic log, such as the exposure of the item on the page in the past week. Alternatively, the above-mentioned execution subject can accumulate the traffic of the item display in multiple preset historical time periods, such as the exposure of the item on the page in the past three weeks.
[0034] Step 202, based on the associated data, generates the traffic input of the item and the traffic of the item on the page when the correlation between the traffic is the largest.
[0035] In this embodiment, the execution subject can generate the specific flow of the item on the page based on the associated data. The specific flow here refers to the flow when the flow input of the item and the correlation of the flow are the largest.
[0036] The traffic generated in this application is the traffic of the item on the page when the traffic input and the correlation of the traffic are maximized. The correlation here is expressed by the correlation coefficient.
[0037] Step 203, based on the generated traffic, determine the target traffic that the item will adopt on the page.
[0038] In this embodiment, the execution entity may adopt various methods to predict the target traffic that the item will use on the page based on the traffic generated above. For example, the execution entity may directly determine the generated traffic as the target traffic. Alternatively, the execution entity may input the generated traffic into a preset formula or model and obtain the target traffic output from the formula or model. The target traffic is the traffic that the item is expected to reach, such as the target search volume. The target traffic is for a preset duration, that is, a preset time period, such as 1 day, 6 days or 1 week.
[0039] Step 204: Based on the target flow rate, determine the flow rate adjustment information of the item in a preset time period in the future.
[0040] In this embodiment, the execution subject may determine the flow adjustment information of the item in a future preset time period based on the target flow. The flow adjustment information is information indicating the adjustment of the target flow. Specifically, the flow adjustment information may indicate at least one of the following: adjustment amplitude, adjustment direction. The adjustment method here may be to increase or decrease.
[0041] The execution subject may determine the flow adjustment information of the item in a future preset time period based on the target flow in various ways. For example, the execution subject may obtain a formula or model for determining the flow adjustment information, and input the target flow into the formula or model, thereby obtaining the flow adjustment information output from the formula or model.
[0042] Step 205: based on the traffic adjustment information, update the display position of the item on the page.
[0043] In this embodiment, the execution subject can update the display position of the item on the page based on the traffic adjustment information. The traffic adjustment information can directly indicate the adjustment of the traffic, such as the decrease in traffic, or the traffic adjustment information can also indicate the adjustment of the display position, so as to achieve the purpose of adjusting the traffic.
[0044] For example, if the traffic adjustment information directly indicates the adjustment of traffic, the execution subject may update the display position of the item according to the correspondence between the traffic adjustment information and the display position. Alternatively, if the traffic adjustment information indicates the adjustment of the display position, the execution subject may directly update the display position of the item on the page according to the indicated display position adjustment information, such as moving forward one position.
[0045] The method provided by the above-mentioned embodiment of the present disclosure can obtain a parameter indicating the correlation between traffic investment and traffic, and maximize the benefits of traffic investment by maximizing the correlation between the two, thereby helping to increase the traffic of items when the traffic investment is increased. This in turn helps users who invest in traffic to have a greater willingness to invest in traffic because of the increase in traffic. In addition, the present application also uses the target traffic to generate traffic adjustment information for items, thereby updating the display position of the items on the page.
[0046] In some optional implementations of any embodiment of the present disclosure, the flow adjustment information includes a target increase ratio; determining the flow adjustment information of the item in a future preset time period based on the target flow includes: determining the flow deviation based on the target flow and the actual flow; and determining the target increase ratio of the flow in a future preset time period based on the flow deviation.
[0047] In these optional implementations, the flow deviation is used to indicate the difference between the actual flow and the target flow.
[0048] The execution subject may determine the flow deviation based on the target flow and the actual flow in various ways. For example, the execution subject may determine the difference between the actual flow and the target flow, and use the difference as the flow deviation. Alternatively, the execution subject may input the target flow and the actual flow into a specified formula or model, and obtain the result output by the specified formula or model, and determine the result as the flow deviation.
[0049] The target prompt ratio refers to the ratio of the expected traffic increase in the future preset time period relative to the historical traffic (such as today's traffic and / or the traffic in the past 6 days). For example, the historical traffic in the past preset time period, such as the past 7 days, is 1000 times. If the target prompt ratio is 0.5, the traffic in the future preset time period, i.e. the traffic in the next 7 days, will be 1500.
[0050] The above-mentioned execution subject can directly determine the target prompt ratio of the flow rate based on the flow deviation, or obtain the target prompt ratio determined by other electronic devices. In practice, the above-mentioned execution subject or other electronic devices can adopt various methods to determine the target prompt ratio of the flow rate based on the flow deviation. For example, the flow deviation can be input into a preset formula or model to obtain the target prompt ratio output from the formula or model. The preset formula or model can be used to determine the target prompt ratio of the flow rate based on the flow deviation.
[0051] The greater the deviation between the actual flow and the ideal target flow, the greater the target prompt ratio. Therefore, the target prompt ratio can be determined by the flow deviation.
[0052] The target flow and actual flow can be for a preset time period, i.e., a preset duration. The target prompt ratio of flow is for a subsequent preset time period (e.g., the next preset time period). Specifically, the length of the preset time period of each of the target flow and actual flow (the length is taken as the former), and the length of the preset time period of the target prompt ratio of flow (the length is taken as the latter) can be consistent, such as 1 day or 7 days, etc., or they can be different, for example, the former can be one day, and the latter can be 7 days. For another example, the former can be one week, and the latter can be one month.
[0053] These implementations can determine the difference between actual flow and expected flow through flow deviation, thereby accurately determining the magnitude of flow adjustment.
[0054] Optionally, the above-mentioned determination of the target increase ratio of the traffic in a future preset time period based on the traffic deviation may include: determining the traffic deviation of the item in the most recent historical preset time period as the traffic history deviation, wherein the most recent historical preset time period takes the most recent ranking change moment as the end moment; determining the target prompt ratio of the traffic in the next preset time period based on the traffic history deviation, the traffic deviation and the target traffic.
[0055] In these optional implementations, for each preset time period, the flow deviation cur_diff is represented by the target flow cur_target and the actual flow cur_comp_ratio, which can be expressed as:
[0056] cur_diff=cur_comp_ratio-cur_target
[0057] or:
[0058] cur_diff=cur_target-cur_comp_ratio
[0059] The traffic history deviation of the most recent preset time period (historical preset time period) can be expressed as last_diff. The target prompt ratio of traffic in the next preset time period, promote_ratio, can be expressed as:
[0060] promote_ratio=f(cur_comp_ratio,cur_diff,last_diff),
[0061] Wherein, f represents the functional relationship between the above-mentioned target prompt ratio and the flow history deviation, the flow deviation, and the target flow. The functional relationship can be a formula or a model, etc.
[0062] Alternatively, the execution entity may also send the flow history deviation, the flow deviation and the target flow to other electronic devices, and determine the target prompt ratio fed back by other electronic devices as the target prompt ratio of the flow in the next preset time period.
[0063] These implementation methods can use the traffic deviations in various time periods, the target traffic that needs to be achieved, and a target prompt ratio of the traffic in the next preset time period based on a comprehensive forecast.
[0064] Optionally, updating the display position of the item on the page based on the traffic adjustment information includes: updating the ranking change parameters of the item based on the target improvement ratio to obtain new ranking change parameters of the item; and changing the display position of the item according to the ranking change direction and ranking change amount indicated by the new ranking change parameters.
[0065] In these optional implementations, the ranking change parameter may indicate the ranking change direction and the ranking change amount. Specifically, the ranking change direction may indicate forward movement, that is, moving the ranking forward, or the ranking change direction may indicate backward movement, that is, moving the ranking backward. In some cases, the ranking change direction may also indicate no movement.
[0066] For example, the ranking change parameter may be -2, indicating a ranking change amount of 2. If the parameter is less than 0, it may indicate a backward shift, and the search result ranking of the search engine may be shifted back two places.
[0067] These optional implementations can change the ranking change parameters by the expected improvement ratio, because the ranking of the display position will directly affect the exposure, that is, the higher the position, the greater the exposure. Therefore, these implementations can adjust the display ranking to accurately indicate the ranking change method through the direction and amount of ranking change, thereby achieving traffic incentives.
[0068] In some optional implementations of any embodiment of the present disclosure, the correlation is characterized by a correlation coefficient; when the correlation coefficient is a positive number, the larger the correlation coefficient is, the greater the positive correlation between the traffic input and the traffic; when the correlation coefficient is a negative number, the smaller the correlation coefficient is, the greater the negative correlation between the traffic input and the traffic.
[0069] The larger the absolute value of the correlation coefficient is, the greater the correlation between the flow input and the flow. Specifically, if the correlation coefficient is a positive value, the larger the absolute value is, the greater the positive correlation between the flow input and the flow.
[0070] In practice, the smaller the negative value of the correlation coefficient is, the greater the negative correlation between the flow input and the flow indicated by the correlation coefficient is. In other words, if the correlation coefficient is a negative value, the larger the absolute value is, the greater the negative correlation between the flow input and the flow is. The closer the correlation coefficient is to zero, the smaller the correlation between the flow input and the flow is.
[0071] Maximizing the correlation coefficient refers to the situation where the correlation coefficient is maximized when various parameters that determine the correlation coefficient are reasonably set within the preset range.
[0072] In practice, the correlation coefficient is used to evaluate the correlation between the flow input and flow of an item, that is, the linkage. The correlation coefficient that can reflect the correlation relationship can be expressed by ρ, which is specifically expressed as:
[0073]
[0074] Where x is the flow input and y is the flow. t is the traffic investment for tomorrow's plan, i represents n days, for example, historical n days is -n days, x t-6 ,……,x t-1 They are the traffic inputs for the past six days, where x t-1 Invest in today's traffic. t-6 ,……,y t-1 They are the traffic for the past six days, which correspond one to one with the traffic input for the past six days. It is the average value of the traffic input for each day. It is the average value of the traffic counted on each day.
[0075] These implementations can accurately characterize the positive and negative correlations between traffic input and traffic.
[0076] In some optional implementations of any embodiment of the present disclosure, the associated data includes historical traffic input and historical traffic of the item in at least two historical time units; the generating, based on the associated data, the traffic of the item on the page when the correlation between the traffic input and the traffic of the item is the largest includes: determining an expression of the correlation coefficient between the traffic input and the traffic of the item based on the historical traffic input and the historical traffic; determining a linear relationship expression of the derivative function of the correlation coefficient with the target traffic as a variable using the expression of the correlation coefficient; and determining the traffic of the item when the correlation coefficient between the traffic input and the traffic is maximized based on the linear relationship expression.
[0077] In these implementations, the execution subject may adopt various methods to establish the correlation between the flow input and flow of the item based on the historical flow input and the historical flow, that is, determine the correlation coefficient between the flow input and flow of the item. For example, the execution subject may input the historical flow input and the historical flow into a specified formula or relationship determination model, and obtain the correlation output from the formula or model, that is, the correlation coefficient.
[0078] In practice, the time unit and the preset time period may be the same in length or different in length.
[0079] In these implementations, the execution subject may use the expression of the correlation coefficient to determine the derivative function of the correlation coefficient. Specifically, the derivative function takes the target flow rate as a variable.
[0080] The execution subject may adopt various methods to determine the flow of the item when the flow input of the item and the correlation coefficient of the flow are maximized based on the correlation relationship. For example, the execution subject may obtain a model, which may determine the flow of the item when the flow input of the item and the correlation coefficient of the flow are maximized based on the correlation relationship. The execution subject inputs the correlation relationship into the model, and may obtain a result output from the model, which indicates the flow of the item when the flow input of the item and the correlation coefficient of the flow are maximized.
[0081]
[0082]
[0083]
[0084]
[0085] Substituting the above correlation formulas of A, B, C, and D into the correlation relationship of the correlation coefficient ρ, we can obtain the derivative function ρ′ of the correlation coefficient:
[0086]
[0087] Among them, y t is the variable, i.e., the target flow rate, and n is the number of time units in the preset time period, where the time unit can be, for example, a predetermined time length such as one day or one hour. For example, if the preset time period is one week and the time unit is one day, then n is 7.
[0088]
[0089] Among them, k is the slope and b is the intercept.
[0090] These implementations can establish the correlation between flow input and flow through the historical data of flow input and flow. In addition, the present disclosure can fit the derivative function of the correlation coefficient, taking the target flow as a variable, so as to quantify the flow and improve the accuracy of determining the flow.
[0091] In some optional application scenarios of these implementations, the above-mentioned determination of the flow of the item when the correlation coefficient of flow input and flow is maximized based on the linear relationship expression may include: obtaining a predicted flow value of the item in a future preset time period; based on the predicted flow value, determining the flow range of the item in the future preset time period; within the flow range, determining the flow of the item when the correlation coefficient of the item is maximized.
[0092] In these application scenarios, the execution subject may determine the traffic prediction value by a predetermined model or formula. In addition, the determined traffic prediction value may be obtained from the device or other electronic devices. The duration of the preset time period in the future preset time period may be the same as or different from the duration of the aforementioned preset time period.
[0093] The execution subject may determine the flow range of the item in the future preset time period based on the flow prediction value in various ways. For example, the execution subject may input the flow prediction value into a formula or model for determining the flow range, and obtain the flow range output from the formula or model.
[0094] Afterwards, the execution subject may determine the flow rate of the item when the correlation coefficient of the item is maximized within the flow rate range based on the linear relationship expression in various ways. For example, the execution subject may obtain a model for determining the flow rate, and input the flow rate range and the linear relationship expression of the item into the model to obtain the flow rate of the item.
[0095] These application scenarios can help accurately determine the maximum correlation coefficient within the flow range by determining the flow range.
[0096] In some cases of these application scenarios, the above-mentioned determination of the flow range of the item in the future preset time period based on the flow prediction value may include: determining the minimum value of the flow range according to the flow prediction value; obtaining the maximum increase ratio of the flow, and determining the increased flow of the flow prediction value according to the maximum increase ratio; determining the maximum value of the flow range according to the increased flow.
[0097] In these cases, the execution entity may determine the minimum value of the flow range according to the exposure prediction value in various ways. For example, the execution entity may directly determine the flow prediction value as the minimum value of the flow range. Alternatively, the execution entity may input the flow prediction value into a formula or model for determining the flow range, thereby obtaining the minimum value of the flow range determined by the formula or model.
[0098] The maximum increase ratio refers to the maximum value of the increase ratio obtained or determined in advance for the flow. The maximum increase ratio corresponding to the flow may be different when the flow is in different value intervals.
[0099] The execution subject may increase the maximum increase ratio for the predicted flow value. Furthermore, the execution subject may determine the maximum value of the flow range according to the increased flow in various ways. For example, the execution subject may directly determine the increased flow as the maximum value of the flow range. That is, the maximum value pv of the flow range max The flow prediction value pv can be used forcast And the maximum improvement ratio prop max It is expressed as:
[0100] pv max =(1+prop max )*pv forcast
[0101] Alternatively, the execution subject may input the boosted flow rate into a formula or function to obtain the maximum value of the flow rate range output from the formula or function. The formula is used to determine the maximum value of the flow rate range using the boosted flow rate. Here, pv is equivalent to the aforementioned y.
[0102] These implementations can accurately determine the upper and lower limits of the flow range based on the flow prediction value and the maximum increase ratio.
[0103] Optionally, the step of generating the maximum increase ratio of the traffic includes: obtaining historical traffic information of the item, wherein the historical traffic information includes at least one of the following: historical traffic that has been increased, historical traffic that has not been increased, and the historical traffic includes the historical search times of the search term of the item and the historical search ranking of the item; performing statistics on the historical traffic information to obtain a historical increase ratio of the traffic; and generating different maximum increase ratios for traffic in different numerical ranges based on the historical increase ratios.
[0104] In these cases, the above execution entity can obtain the historical traffic that has not been improved and the historical traffic that has been improved, so as to obtain the historical improvement ratio. The historical traffic that has not been improved refers to the basic traffic, and there is no additional or more traffic investment in order to increase the traffic. The historical traffic that has been improved refers to the traffic obtained by making additional and more traffic investment in order to increase the traffic.
[0105] The above execution subject can obtain different maximum improvement ratios for traffic in different numerical intervals through historical improvement ratios. For example, the maximum value of the historical improvement ratios in different numerical intervals is directly used as the maximum improvement ratio. Alternatively, the historical improvement ratios in different numerical intervals are input into the formula using the improvement ratio formula to obtain the maximum improvement ratio corresponding to each numerical interval.
[0106] In practice, the maximum improvement ratio prop max Can be achieved through weekly traffic pv week To express it as:
[0107]
[0108] Specifically, a week can be used as a preset time period, and when the weekly flow of an item is in different value intervals, the maximum promotion ratio of the item is different. In practice, the larger the weekly flow of an item, the lower the maximum promotion ratio.
[0109] These implementations can utilize historical traffic increase data to generate accurate maximum increase ratios on a case-by-case basis. Furthermore, the execution subject can also accurately generate different maximum increase ratios for different value intervals.
[0110] In these optional implementations, the variable is the ratio of the intercept and the slope; within the flow range, based on the linear relationship expression, determining the flow of the item when the correlation coefficient of the item is maximized, including: when the slope and the intercept of the derivative function in the linear relationship expression both have at least two size relationships with zero, according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression with the increase of the variable, within the flow range, determining the flow input of the item and the flow correlation coefficient when the correlation coefficient is maximized, wherein, for the variable in each numerical interval, there is a corresponding changing trend of the derivative function.
[0111] When the numerical ranges of the slope and intercept are different, as the variable increases, the derivative of the correlation coefficient may increase first and then decrease, or decrease first and then increase. There can be more than one relationship between the slope of the derivative and zero, and there can also be more than one relationship between the intercept of the derivative and zero. Therefore, to summarize, the above slope and intercept can have more than one relationship with zero, that is, at least two.
[0112] The variation trend of the derivative function of the correlation coefficient in the linear relationship expression as the variable increases may be an increase or decrease. The execution subject may determine the flow of the item when the flow input and the correlation coefficient of the flow are maximized based on the variation trend. For example, the execution subject may input the variation trend and the flow range into the model and obtain the flow output from the model. Specifically, the model may utilize the variation trend of the derivative function of the correlation coefficient in the linear relationship expression as the variable increases and the flow range to determine the flow of the item when the correlation coefficient of the item is maximized.
[0113] These implementations can accurately determine the flow of items when the correlation coefficient is maximized based on the changing trend of the derivative function when there are multiple relationships between the slope and the intercept and zero.
[0114] Optionally, when the slope and intercept of the derivative function in the linear relationship expression have at least two size relationships with zero, determining the flow rate of the item when the flow input of the item and the correlation coefficient of the flow are maximized within the flow range according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression as the variable increases, can include: when the slope and intercept of the derivative function are both greater than or equal to zero, performing the following steps: in response to the first numerical interval where the variable is located, making the changing trend of the derivative function decrease as the variable increases, and determining the flow rate of the item according to the minimum value of the flow range, wherein the value of the first numerical interval is less than the minimum value of the flow range; in response to the second numerical interval where the variable is located, making the changing trend of the derivative function increase as the variable increases, and determining the flow rate of the item when the correlation coefficient is maximized according to the maximum value of the flow range, wherein the value of the second numerical interval is greater than or equal to the maximum value of the flow range.
[0115] In these implementations, when b≥0 and k≥0, the flow pv starts from 0, and the correlation coefficient increases first and then decreases. t (that is, the ratio of the intercept to the slope) and the minimum value of the flow range pv min , maximum value of flow range pv max The size relationship.
[0116] Specifically, when y t <pv minWhen the derivative function of the correlation coefficient decreases as the flow rate increases, the flow rate of the item when the correlation coefficient is maximized may be the minimum value of the flow rate range. Alternatively, the minimum value of the flow rate range may be processed by a preset method, such as multiplying it by a preset coefficient or inputting a preset formula, and the result of the preset processing may be determined as the flow rate of the item when the correlation coefficient is maximized.
[0117] Specifically, when y t ≥pv max When the derivative function of the correlation coefficient increases with the increase of the flow rate, at this time, the flow rate of the item when the correlation coefficient is maximized can be the maximum value of the flow rate range. Alternatively, the maximum value of the flow rate range can be processed by a preset process, such as multiplying it by a preset coefficient or inputting a preset formula, and the result of the preset process is determined as the flow rate of the item when the correlation coefficient is maximized.
[0118] These optional implementations can accurately determine the flow rate of the item when the correlation coefficient is maximized through the changing trend of the derivative function when the slope and the intercept are both greater than zero.
[0119] Optionally, when the slope and intercept of the derivative function in the linear relationship expression have at least two magnitude relationships with zero, according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression with the increase of the variable, within the flow range, determining the flow of the item when the flow input of the item and the correlation coefficient of the flow are maximized, comprising: when the slope and intercept of the derivative function are both greater than or equal to zero, performing the following steps: in response to the third numerical interval in which the variable is located, making the changing trend of the derivative function first increase and then decrease with the increase of the variable, then determining according to the linear relationship expression The value of the derivative function of the variable with the ratio of the intercept and the slope as the correlation coefficient is determined as the correlation coefficient, wherein the value of the third numerical interval is greater than or equal to the minimum value of the flow range and less than the maximum value of the flow range; in response to the correlation coefficient reaching the correlation threshold of the flow input and the flow, a convex optimization algorithm is adopted to determine the flow of the item when the correlation coefficient is maximized according to the value of the variable when the derivative function is equal to the correlation threshold; in response to the correlation coefficient not reaching the correlation threshold of the flow input and the flow, the flow of the item when the correlation coefficient is maximized is determined according to the ratio of the intercept and the slope.
[0120] Specifically, when pv min ≤y t <pv max When , the correlation coefficient increases first and then decreases as the flow increases. An acceptable correlation threshold ρ can be determined in advance targetIf the value of the correlation coefficient reaches the correlation threshold, that is, for the correlation coefficient ρ t , when ρ t ≥ρ target When the traffic increases, we can set a smaller traffic target to ensure that merchants can perceive the traffic growth along with traffic investment. At this time, we can save part of the traffic increment to achieve the target traffic, that is, the target traffic. For the above derivative function which is a convex function, the above execution subject can use various convex optimization algorithms such as Newton iteration algorithm to solve the value of the above variable, so that the derivative function of the correlation coefficient is equal to the correlation threshold.
[0121] When the correlation coefficient does not reach the flow input and flow, that is, ρ t < target When the execution subject can directly convert y t That is, the ratio of the intercept and the slope is determined as the flow rate of the item when the correlation coefficient is maximized.
[0122] The execution subject may determine the ratio of the intercept and the slope as the flow rate of the item when the correlation coefficient is maximized. Alternatively, the execution subject may input the ratio of the intercept and the slope into a formula for determining the flow rate, and use the flow rate output from the specified formula as the flow rate of the item when the correlation coefficient is maximized.
[0123] In practice, the correlation threshold can be used as a boundary to distinguish whether there is a certain correlation between traffic input and traffic. When this threshold is reached, it indicates that there is a certain correlation.
[0124] These optional implementations can accurately determine the flow of the item when the correlation coefficient is maximized by using the variation trend of the derivative function when the slope and intercept are both greater than or equal to zero. In addition, by setting a correlation threshold, the speed of determining the flow can be increased.
[0125] Optionally, when the slope and intercept of the derivative function in the linear relationship expression have at least two magnitude relationships with zero, the flow of the item when the correlation coefficient between the flow input and the flow of the item is maximized is determined within the flow range according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression as the variable increases, including: when the intercept of the derivative function is greater than or equal to zero and the slope is less than zero, in response to the fourth numerical interval in which the variable is located, the changing trend of the derivative function is made to increase with the increase of the variable, and the following steps are performed: in response to the correlation coefficient reaching the correlation threshold between the flow input and the flow, a convex optimization algorithm is used to determine the flow of the item when the correlation coefficient is maximized according to the value of the variable when the derivative function is equal to the correlation threshold, wherein the fourth numerical interval is greater than or equal to zero; in response to the correlation coefficient not reaching the correlation threshold between the flow input and the flow, the flow of the item when the correlation coefficient is maximized is determined according to the maximum value of the flow range.
[0126] Specifically, the variables start at zero and the correlation coefficients increase.
[0127] When pv max The corresponding correlation coefficient is higher than ρ target When , the above execution body can use the convex optimization algorithm to solve the correlation coefficient equal to ρ target And take this flow rate as the flow rate of the item when the correlation coefficient is maximized.
[0128] The execution subject may determine the flow of the item when the correlation coefficient is maximized according to the value of the variable when the derivative function is equal to the correlation threshold in various ways. For example, the execution subject may directly determine the value of the variable when the value of the derivative function is equal to the correlation threshold as the flow of the item when the correlation coefficient is maximized. Alternatively, the execution subject may input the value of the variable when the value of the derivative function is equal to the correlation threshold into a formula or model, and the formula or model is used to determine the flow of the item. The execution subject may use the output of the formula or model as the flow of the item when the correlation coefficient is maximized.
[0129] The execution subject may determine the flow rate of the item when the correlation coefficient is maximized according to the maximum value of the flow rate range in various ways. For example, the execution subject may directly determine the maximum value of the flow rate range as the flow rate of the item when the correlation coefficient is maximized. Alternatively, the execution subject may input the maximum value of the flow rate range into a predetermined formula or model, which is used to determine the flow rate of the item according to the maximum value of the flow rate range. The execution subject may use the output of the formula or model as the flow rate of the item when the correlation coefficient is maximized.
[0130] These implementations can accurately determine the flow of the items when the correlation coefficient is maximized by the variation trend of the derivative function. Furthermore, by setting a correlation threshold, the speed of determining the flow can be increased.
[0131] Optionally, when both the slope and the intercept of the derivative function in the linear relationship expression have at least two magnitude relationships with zero, the flow rate of the item when the flow input of the item and the correlation coefficient of the flow are maximized is determined within the flow range according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression with the increase of the variable, including: when the intercept of the derivative function is less than zero and the slope is greater than or equal to zero, performing the following steps: in response to the fifth numerical interval where the variable is located, making the changing trend of the derivative function decrease with the increase of the variable, and determining the flow rate of the item when the correlation coefficient is maximized according to the minimum value of the flow range, wherein the fifth numerical interval is greater than or equal to zero.
[0132] Specifically, when the intercept of the derivative function is less than zero and the slope is greater than or equal to zero, the flow starts from 0, and the larger the flow, the smaller the correlation coefficient. The above-mentioned execution subject can adopt various methods to determine the flow of the item when the correlation coefficient is maximized according to the minimum value of the flow range. For example, when the flow is equal to the minimum value of the flow range, the correlation coefficient is maximized. The above-mentioned execution subject can directly determine the minimum value of the flow range as the flow of the item when the correlation coefficient is maximized. Alternatively, the above-mentioned execution subject can input the minimum value of the flow range into a formula or model and obtain the flow output from the formula or model. The formula or model is used to determine the flow of the item when the correlation coefficient is maximized using the minimum value of the flow range.
[0133] These implementations can accurately determine the flow of the items when the correlation coefficient is maximized by the variation trend of the derivative function. Furthermore, by setting a correlation threshold, the speed of determining the flow can be increased.
[0134] Optionally, when the intercept of the derivative function is less than zero and the slope is less than zero, the following steps are performed: determine the correlation coefficients corresponding to the minimum and maximum values of the flow range, respectively, as the first correlation coefficient and the second correlation coefficient, respectively; in response to the sixth numerical interval in which the variable is located, make the changing trend of the derivative function first decrease and then increase with the increase of the variable, determine the correlation coefficients corresponding to the minimum and maximum values of the flow range, respectively, as the first correlation coefficient and the second correlation coefficient, respectively; determine the larger one of the first correlation coefficient and the second correlation coefficient, and determine the flow of the item when the correlation coefficient is maximized according to the flow corresponding to the larger one, wherein the sixth numerical interval is greater than or equal to zero.
[0135] In these optional implementations, when the intercept of the derivative function is less than zero and the slope is less than zero, if the variable is greater than or equal to zero, the variation trend of the derivative function is that it first decreases and then increases as the variable increases. min or pv max When the correlation coefficient is maximized, the flow of the item can be directly taken as pv min or pv max The flow that maximizes the correlation coefficient.
[0136] Alternatively, the execution entity may further process the obtained flow rate and use the processing result as the flow rate of the item when the correlation coefficient is maximized. For example, the further processing may include multiplying by a coefficient or inputting a formula.
[0137] These implementations can accurately determine the flow of the item when the correlation coefficient is maximized by the changing trend of the derivative function. In addition, by setting the correlation threshold, the speed of determining the flow can be increased.
[0138] Continue to see Figure 3 , Figure 3 FIG. 1 is a schematic diagram of an application scenario of the method for processing item information according to this embodiment. Figure 3In the application scenario, the execution body 301 obtains the associated data 304 of the traffic input 302 and the traffic 303 of the items displayed on the page, wherein the associated data is determined based on the historical traffic log of the page displaying the items. Based on the associated data 304, the execution body 301 generates the traffic 305 of the item on the page when the correlation between the traffic input and the traffic of the item is the largest. Based on the generated traffic 305, the execution body 301 determines the target traffic 306 that the item will adopt on the page. Based on the target traffic 306, the execution body 301 determines the traffic adjustment information 307 target decrease ratio of the item in the future preset time period. Based on the traffic adjustment information 307 target decrease ratio, the execution body 301 updates the display position 308 of the item on the page.
[0139] Further references Figure 4 , which shows the steps for determining the flow prediction value in the method for processing item information, which may include: step 401, obtaining information related to the historical flow of the item; step 402, using a preset method, based on the historical flow related information, predicting the flow of the item to obtain a flow prediction value, wherein, if the preset method is model prediction, the historical flow related information includes basic item information and historical flow, and if the preset method is statistics, the historical flow related information includes historical flow.
[0140] In this embodiment, the execution subject or other electronic device may use a model prediction method or a statistical method to predict the flow of items and obtain a flow prediction value. Specifically, the flow prediction value may be determined by a statistical method, that is, based on the historical flow, the future value of the flow is determined.
[0141] If model prediction is used, it is necessary to use a variety of historical traffic related information to input the model for prediction. The basic information of the item may include at least one of the following: item (ie, commodity) name, store name, category information. Historical traffic may include the number of trigger words, average display position (ie, display ranking). In addition to basic item information and historical traffic, historical traffic related information may also include time information, which may include whether there are promotional activities, whether there are large-scale promotional activities, whether new products are on the shelves, how long it takes to be put on the shelves, etc. The above-mentioned execution entity or other electronic device can input historical traffic related information into a model for predicting traffic and obtain the traffic prediction value output from the model.
[0142] This embodiment can use various information related to historical traffic to accurately determine the traffic prediction value.
[0143] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for processing item information. Figure 2 Corresponding to the method embodiment shown in FIG. 1 , in addition to the features described below, the device embodiment may also include Figure 2 The device can be applied to various electronic devices.
[0144] like Figure 5 As shown, the device 500 for processing item information of this embodiment includes: an acquisition unit 501, configured to acquire data on the flow input and flow correlation of items displayed on a page, wherein the correlation data is determined based on a historical flow log of the page displaying the items; a generation unit 502, configured to generate, based on the correlation data, the flow of the item on the page when the correlation between the flow input and flow of the item is maximum; a flow determination unit 503, configured to determine, based on the generated flow, the target flow that the item will adopt on the page; an adjustment unit 504, configured to determine, based on the target flow, flow adjustment information of the item in a preset time period in the future; and a booth update unit 505, configured to update the display position of the item on the page based on the flow adjustment information.
[0145] In this embodiment, the specific processing of the acquisition unit 501, the generation unit 502, the flow determination unit 503, the adjustment unit 504 and the booth updating unit 505 of the item information processing device 500 and the technical effects thereof can be referred to respectively. Figure 2 The relevant descriptions of steps 201 to 205 in the corresponding embodiment are not repeated here.
[0146] In some optional implementations of this embodiment, the method includes: an acquisition unit, configured to acquire data on the traffic input and traffic correlation of an item displayed on a page, wherein the correlation data is determined based on a historical traffic log of the page displaying the item; a generation unit, configured to generate, based on the correlation data, the traffic of the item on the page when the correlation between the traffic input and traffic of the item is maximum; a traffic determination unit, configured to determine, based on the generated traffic, the target traffic that the item will adopt on the page; an adjustment unit, configured to determine, based on the target traffic, traffic adjustment information of the item in a preset time period in the future; and a booth update unit, configured to update the display position of the item on the page based on the traffic adjustment information.
[0147] In some optional implementations of this embodiment, the flow adjustment information includes a target increase ratio; the adjustment unit is further configured to execute the flow adjustment information of the item in a future preset time period based on the target flow in the following manner: determine the flow deviation based on the target flow and the actual flow; determine the target increase ratio of the flow in a future preset time period based on the flow deviation.
[0148] In some optional implementations of the present embodiment, the adjustment unit is further configured to perform the determination of the target increase ratio of the flow in a future preset time period based on the flow deviation in the following manner: determine the flow deviation of the item in the most recent historical preset time period as the flow history deviation, wherein the most recent historical preset time period takes the most recent ranking change moment as the end moment; determine the target increase ratio of the flow in the next preset time period based on the flow history deviation, the flow deviation and the target flow.
[0149] In some optional implementations of this embodiment, the booth update unit is further configured to execute the updating of the display position of the item on the page based on the traffic adjustment information in the following manner: updating the ranking change parameters of the item based on the target improvement ratio to obtain new ranking change parameters of the item; and changing the display position of the item according to the ranking change direction and ranking change amount indicated by the new ranking change parameters.
[0150] In some optional implementations of this embodiment, the correlation is characterized by a correlation coefficient; when the correlation coefficient is a positive number, the larger the correlation coefficient is, the greater the positive correlation between the traffic input and the traffic; when the correlation coefficient is a negative number, the smaller the correlation coefficient is, the greater the negative correlation between the traffic input and the traffic.
[0151] In some optional implementations of this embodiment, the associated data includes historical traffic input and historical traffic of the item in at least two historical time units; the generating unit is further configured to execute the generation of the traffic of the item on the page when the correlation between the traffic input and traffic of the item is maximum based on the associated data in the following manner: based on the historical traffic input and the historical traffic, determine an expression for the correlation coefficient between the traffic input and traffic of the item; using the expression for the correlation coefficient, determine a linear relationship expression of the derivative function of the correlation coefficient with the target traffic as a variable; based on the linear relationship expression, determine the traffic of the item when the correlation coefficient between the traffic input and traffic is maximized.
[0152] In some optional implementations of the present embodiment, the generating unit is further configured to execute the determination of the flow of the item when the correlation coefficient between flow input and flow is maximized based on the linear relationship expression in the following manner: obtaining a predicted flow value of the item in a future preset time period; determining a flow range of the item in the future preset time period based on the predicted flow value; and determining the flow of the item when the correlation coefficient of the item is maximized based on the linear relationship expression within the flow range.
[0153] In some optional implementations of the present embodiment, the generating unit is further configured to perform the determination of the flow range of the item in the future preset time period based on the flow prediction value in the following manner: determining the minimum value of the flow range according to the flow prediction value; obtaining the maximum increase ratio of the flow, and determining the increased flow of the flow prediction value according to the maximum increase ratio; and determining the maximum value of the flow range according to the increased flow.
[0154] In some optional implementations of the present embodiment, the step of generating the maximum increase ratio of the traffic includes: obtaining historical traffic information of the item, wherein the historical traffic information includes at least one of the following: historical traffic that has been increased, historical traffic that has not been increased, and the historical traffic includes the historical search times of the search term of the item and the historical search ranking of the item; performing statistics on the historical traffic information to obtain a historical increase ratio of the traffic; and generating different maximum increase ratios for traffic in different numerical ranges based on the historical increase ratios.
[0155] In some optional implementations of the present embodiment, the variable is the ratio of the intercept and the slope; the generating unit is further configured to execute the determination of the flow of the item when the correlation coefficient of the item is maximized within the flow range based on the linear relationship expression in the following manner: when both the slope and the intercept of the derivative function in the linear relationship expression have at least two size relationships with zero, the flow input of the item and the flow of the item when the correlation coefficient of the flow is maximized are determined within the flow range according to the changing trend of the derivative function of the correlation coefficient in the linear relationship expression with the increase of the variable, wherein, for the variable in each numerical interval, there is a corresponding changing trend of the derivative function.
[0156] In some optional implementations of this embodiment, the step of determining the flow prediction value includes: obtaining historical flow-related information of the item; using a preset method to predict the flow of the item based on the historical flow-related information to obtain a flow prediction value, wherein if the preset method is model prediction, the historical flow-related information includes basic information of the item and historical flow; if the preset method is statistics, the historical flow-related information includes historical flow.
[0157] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0158] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment 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 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, 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 disclosure described and / or required herein.
[0159] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0160] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0161] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the processing method of item information. For example, in some embodiments, the processing method of item information may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the processing method of item information described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the processing method of item information in any other appropriate manner (e.g., by means of firmware).
[0162] Various implementations 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 chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0163] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0164] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0165] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).
[0166] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0167] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0168] 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 recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0169] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for processing item information, the method include: Obtaining traffic input and traffic correlation data of items displayed on the page, wherein the correlation data is determined based on a historical traffic log of the page displaying the items; Based on the association data, generate the traffic input of the item and the traffic of the item on the page when the correlation of the traffic is the largest; Based on the generated traffic, determining a target traffic that the item will take on the page; Based on the target flow rate, determining flow rate adjustment information of the item in a future preset time period; Based on the traffic adjustment information, the display position of the item on the page is updated.
2. The method according to claim 1, in, The flow adjustment information includes a target increase ratio; The determining, based on the target flow rate, flow adjustment information of the item in a future preset time period includes: Determining a flow deviation based on the target flow and the actual flow; Based on the flow deviation, a target increase ratio of flow in a future preset time period is determined.
3. The method according to claim 2, in, Determining a target increase ratio of flow in a future preset time period based on the flow deviation includes: Determine the flow deviation of the item in the most recent historical preset time period as the flow historical deviation, wherein the most recent historical preset time period takes the most recent ranking change time as the end time; Based on the traffic history deviation, the traffic deviation and the target traffic, a target increase ratio of the traffic in the next preset time period is determined.
4. The method according to claim 2, in, The updating of the display position of the item on the page based on the traffic adjustment information includes: Updating the ranking change parameter of the item based on the target improvement ratio to obtain a new ranking change parameter of the item; The display position of the item is changed according to the ranking change direction and ranking change amount indicated by the new ranking change parameters.
5. The method according to any one of claims 1 to 4, in, The associated data includes the historical flow input and historical flow of the item in at least two historical time units; The generating, based on the association data, the traffic input of the item and the traffic of the item on the page when the correlation of the traffic is the greatest includes: Determine an expression for a correlation coefficient between the flow input and flow of the item based on the historical flow input and the historical flow; Using the expression of the correlation coefficient, determine a linear relationship expression of a derivative function of the correlation coefficient with the target flow rate as a variable; Based on the linear relationship expression, the flow rate of the item is determined when the correlation coefficient between flow input and flow rate is maximized.
6. The method according to claim 5, in, The determining, based on the linear relationship expression, the flow rate of the item when the correlation coefficient between flow input and flow rate is maximized includes: Obtaining a traffic forecast value of the item in a future preset time period; Based on the traffic prediction value, determining the traffic range of the item in the future preset time period; Within the flow range, based on the linear relationship expression, the flow of the item when the correlation coefficient of the item is maximized is determined.
7. The method according to claim 6, in, The determining, based on the flow prediction value, the flow range of the item in the future preset time period includes: Determining a minimum value of the flow range according to the flow prediction value; Obtaining a maximum increase ratio of flow, and determining an increased flow of the flow prediction value according to the maximum increase ratio; The maximum value of the flow range is determined according to the increased flow rate.
8. The method according to claim 7, in, The step of generating the maximum increase ratio of the flow includes: Acquire historical traffic information of the item, wherein the historical traffic information includes at least one of the following: historical traffic that has been promoted and historical traffic that has not been promoted, and the historical traffic includes the historical search times of the search term of the item and the historical search ranking of the item; The historical traffic information is counted to obtain a historical increase ratio of traffic; According to the historical improvement ratio, different maximum improvement ratios are generated for traffic in different value intervals.
9. The method according to claim 7, in, The step of determining the flow prediction value comprises: Get historical traffic information of items; A preset method is adopted to predict the flow of the item based on the historical flow-related information to obtain a flow prediction value, wherein if the preset method is model prediction, the historical flow-related information includes basic item information and historical flow; if the preset method is statistics, the historical flow-related information includes historical flow.
10. A device for processing item information, the device include: An acquisition unit is configured to acquire traffic input and traffic correlation data of items displayed on a page, wherein the correlation data is determined based on a historical traffic log of the page displaying the items; A generating unit configured to generate, based on the association data, the traffic input of the item and the traffic of the item on the page when the correlation of the traffic is the largest; A flow determination unit, configured to determine a target flow that the article will adopt on the page based on the generated flow; an adjustment unit, configured to determine flow adjustment information of the article in a future preset time period based on the target flow; The booth updating unit is configured to update the display position of the item on the page based on the traffic adjustment information.
11. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed 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 according to any one of claims 1 to 9.
12. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.
