A data processing method and related device

Abstract

The present application discloses a method for data processing and a related device, the method comprising: calculating the recent average heat of an entity through historical relevant data of the entity in a first historical period, and calculating the historical average heat of the entity through historical relevant data of the entity in a second historical period; wherein the start time of the second historical period is before the start time of the first historical period. Combining the recent average heat and the historical average heat, a preset function with a limited upper limit value is used to calculate a target gain coefficient. Combining the recent average heat and the historical average heat, and combining the target gain coefficient, the heat optimization value of the entity is calculated. In an embodiment of the present application, the target gain coefficient is used to combine the recent average heat and the historical average heat to calculate the heat optimization value of the entity, which can truly and effectively reflect the user's attention to the data, so as to accurately recommend entities based on the heat optimization value of the entity.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method and related devices. Background Art

[0002] The popularity of an entity can reflect the user's attention to the entity. In the entity recommendation scenario, the popularity of an entity is an important parameter. For example, the entity recommendation scenario depends on the query popularity, co-occurrence popularity, etc. Whether the popularity of an entity can truly and effectively reflect the user's attention to the entity affects the accuracy of entity recommendation in the entity recommendation scenario. Generally, in the entity recommendation scenario, entity recommendations are made based on the entity's recent average popularity, historical average popularity, or the weighted average popularity of the former two.

[0003] After research, the inventors found that, based on the fact that the popularity of an entity changes over time, the above historical average popularity cannot well reflect the popularity of the entity in the recent period; the above recent average popularity only considers the popularity of the entity in the recent period, resulting in large volatility; the above weighted average popularity also introduces large volatility. In other words, the existing conventional entity popularity determination methods cannot truly and effectively reflect the user's attention to the entity, and thus cannot accurately recommend entities in entity recommendation scenarios. Summary of the invention

[0004] In view of this, the present application provides a data processing method and related devices, which can comprehensively reflect the user's attention to entities more realistically and effectively, thereby accurately recommending entities in entity recommendation scenarios.

[0005] In a first aspect, an embodiment of the present application provides a method for data processing, the method comprising:

[0006] According to the historical relevant data of the entity in the first historical period, the recent average popularity of the entity is obtained; according to the historical relevant data of the entity in the second historical period, the historical average popularity of the entity is obtained; the start time of the second historical period is before the start time of the first historical period;

[0007] According to the preset function of the recent average heat, the historical average heat and the limited upper limit value, a target gain coefficient is obtained; the target gain coefficient is the incremental change coefficient of the recent average heat relative to the historical average heat;

[0008] The heat optimization value of the entity is obtained according to the recent average heat, the historical average heat and the target gain coefficient.

[0009] Optionally, obtaining a target gain coefficient according to a preset function of the recent average heat, the historical average heat, and a limited upper limit value includes:

[0010] Obtaining a gain amplification factor and a normalization constant corresponding to the preset function; the gain amplification factor is determined based on an upper limit value of the preset function, and the normalization constant is determined based on the gain amplification factor;

[0011] Obtaining the target gain coefficient according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant;

[0012] The normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1.

[0013] Optionally, obtaining the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient includes:

[0014] Determine the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat;

[0015] According to the weight of the recent average heat and the weight of the historical average heat, weighted average processing is performed on the recent average heat and the historical average heat to obtain the weighted average heat of the entity;

[0016] The weighted average heat and the target gain coefficient are multiplied to obtain the heat optimization value of the entity.

[0017] Optionally, obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period includes:

[0018] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0019] Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0020] Optionally, obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period includes:

[0021] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0022] Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M;

[0023] A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0024] Optionally, obtaining the historical average popularity of the entity according to the historical related data of the entity in the second historical period includes:

[0025] According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period;

[0026] Perform arithmetic averaging on the heat of the entity at the jth time unit from the second end time to obtain the historical average heat of the entity.

[0027] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0028] A first obtaining unit is used to obtain the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period; and obtain the historical average popularity of the entity according to the historical relevant data of the entity in the second historical period; the start time of the second historical period is before the start time of the first historical period;

[0029] A second obtaining unit is used to obtain a target gain coefficient according to a preset function of the recent average heat, the historical average heat and a limited upper limit value; the target gain coefficient is an incremental change coefficient of the recent average heat relative to the historical average heat;

[0030] The third obtaining unit is used to obtain the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient.

[0031] Optionally, the second obtaining unit is used to:

[0032] Obtaining a gain amplification factor and a normalization constant corresponding to the preset function; the gain amplification factor is determined based on an upper limit value of the preset function, and the normalization constant is determined based on the gain amplification factor;

[0033] Obtaining the target gain coefficient according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant;

[0034] The normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1.

[0035] Optionally, the third obtaining unit is used to:

[0036] Determine the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat;

[0037] According to the weight of the recent average heat and the weight of the historical average heat, weighted average processing is performed on the recent average heat and the historical average heat to obtain the weighted average heat of the entity;

[0038] The weighted average heat and the target gain coefficient are multiplied to obtain the heat optimization value of the entity.

[0039] Optionally, the first obtaining unit is used to:

[0040] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0041] Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0042] Optionally, the first obtaining unit is further used to:

[0043] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0044] Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M;

[0045] A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0046] Optionally, the first obtaining unit is further used to:

[0047] According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period;

[0048] Perform arithmetic averaging on the heat of the entity at the jth time unit from the second end time to obtain the recent average heat of the entity.

[0049] In a third aspect, an embodiment of the present application provides a device for data processing, which includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to perform the data processing method described in any one of the first aspects above.

[0050] In a fourth aspect, an embodiment of the present application provides a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to perform a data processing method as described in any one of the above-mentioned first aspects.

[0051] Compared with the prior art, this application has at least the following advantages:

[0052] Adopting the technical solution of the embodiment of the present application, first, the recent average heat of the entity is calculated through the historical relevant data of the entity in the first historical period, and the historical average heat of the entity is calculated through the historical relevant data of the entity in the second historical period; wherein, the start time of the second historical period is before the start time of the first historical period. Then, combining the recent average heat and the historical average heat, the target gain coefficient is calculated using a preset function with a limited upper limit value. Finally, the heat optimization value of the entity is calculated by combining the recent average heat and the historical average heat, and combining the target gain coefficient. It can be seen that on the basis of obtaining the recent average heat and the historical average heat of the entity, the incremental change coefficient of the recent average heat relative to the historical average heat is expressed by calculating the target gain coefficient; the heat optimization value of the entity is calculated by combining the recent average heat, the historical average heat and the target gain coefficient, which can comprehensively reflect the user's attention to the entity in a more real and effective way, thereby accurately recommending the entity according to the heat optimization value of the entity in the entity recommendation scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A schematic diagram of a system framework involved in an application scenario in an embodiment of the present application;

[0055] Figure 2 A flowchart of a data processing method provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the structure of a device for data processing provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] At present, entity recommendation scenarios rely on the popularity data of entities, such as the recent average popularity of entities, the historical average popularity, or the weighted average popularity of the former two. However, the popularity of entities changes over time, and the historical average popularity cannot well reflect the recent popularity of entities; the recent average popularity only considers the recent popularity of entities, resulting in large volatility; the weighted average popularity also introduces large volatility. In other words, the existing conventional methods of determining the popularity of entities cannot truly and effectively reflect the user's attention to the entity, and thus cannot accurately recommend entities in entity recommendation scenarios.

[0061] In order to solve this problem, in an embodiment of the present application, the recent average heat of the entity is calculated through the historical relevant data of the entity in the first historical period, and the historical average heat of the entity is calculated through the historical relevant data of the entity in the second historical period; wherein, the start time of the second historical period is before the start time of the first historical period. Combining the recent average heat and the historical average heat, the target gain coefficient is calculated using a preset function with a limited upper limit value. Combining the recent average heat and the historical average heat, and combining the target gain coefficient, the heat optimization value of the entity is calculated. It can be seen that on the basis of obtaining the recent average heat and the historical average heat of the entity, by calculating the target gain coefficient, the incremental change coefficient of the recent average heat relative to the historical average heat is expressed; combining the recent average heat, the historical average heat and the target gain coefficient, the heat optimization value of the entity is calculated, which can comprehensively reflect the user's attention to the entity in a more real and effective way, thereby accurately recommending the entity according to the heat optimization value of the entity in the entity recommendation scenario.

[0062] For example, one of the scenarios of the embodiments of the present application may be applied to Figure 1 In the illustrated scenario, the scenario includes a terminal device 101 and a server 102. For example, a user performs an entity query operation through the terminal device 101, and the server 102 responds to the entity query operation and obtains the heat optimization value of the entity by using the implementation method provided in the embodiment of the present application to perform entity recommendation.

[0063] It is understandable that in the above application scenario, although the action description of the implementation mode of the present application is executed by the server 102; however, the present application is not limited in terms of the execution subject, as long as the actions disclosed in the implementation mode of the present application are executed.

[0064] It can be understood that the above scenario is only an example scenario provided by the embodiment of the present application, and the embodiment of the present application is not limited to this scenario.

[0065] The specific implementation of the data processing method and related devices in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0066] Exemplary Methods

[0067] See also Figure 2 , which shows a flow chart of a data processing method in an embodiment of the present application.

[0068] In this embodiment, the method may include the following steps:

[0069] Step 201: Based on the historical relevant data of the entity in the first historical period, obtain the recent average popularity of the entity; based on the historical relevant data of the entity in the second historical period, obtain the historical average popularity of the entity; the start time of the second historical period is before the start time of the first historical period.

[0070] In an embodiment of the present application, first, the recent average popularity of the entity in the first historical period and the historical average popularity of the entity in the second historical period are obtained respectively through the historical relevant data of the entity. Among them, the first historical period corresponds to the recent average popularity, and the second historical period corresponds to the historical average popularity. The first historical period and the second historical period are different. The start time of the second historical period needs to be before the start time of the first historical period; and the end time of the second historical period can be before the end time of the first historical period, or it can be the same as the end time of the first historical period. Generally, the start time of the second historical period is much earlier than the start time of the first historical period, and the end time of the second historical period is the same as the start time or end time of the first historical period.

[0071] The historical related data may be historical query data, historical click data, etc. Correspondingly, the popularity of an entity may refer to the query popularity of the entity, that is, the frequency with which a single entity is queried within a period of time (such as a day), which may be the number of searches, the number of clicks, or a weighted combination of the two. Specifically, that is, through historical query data, historical click data, etc., the number of queries for the single entity within a period of time (such as a day) is counted as the popularity of the single entity.

[0072] The heat of an entity can also refer to the co-occurrence heat of two entities, that is, the frequency of co-occurrence of two entities within a period of time (such as a day), which can be the number of times they are continuously queried, the number of times they are co-mentioned in articles, or a weighted combination of the two. Specifically, through historical query data, historical click data, etc., the number of times the two entities co-occur within a preset time range (such as 10 minutes) within a period of time (such as a day) is counted as the co-occurrence heat of the two entities.

[0073] Of course, the heat of the entity may also be other heats, which are set according to specific circumstances and are not specifically limited in the embodiments of the present application.

[0074] In the first specific implementation of step 201, in order to make the recent average popularity of the entity comprehensively represent the average popularity of the entity in the recent period and reduce the fluctuation of the popularity of the entity in the recent period, the weight corresponding to the popularity of the entity in the first historical period and the i-th time unit from the first end time can be set to be consistent, for example, but not limited to 1; i = 1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units. Among them, the first end time is the end time of the first historical period. If the first historical period is a period of time before the current time, the first end time is the current time.

[0075] If the popularity of entities in each time unit from the first end time in the first historical period is known, and the weights corresponding to the popularity of entities in each time unit from the first end time are consistent, an arithmetic average operation can be performed to calculate the recent average popularity of the entity.

[0076] Therefore, in an optional implementation of the embodiment of the present application, the step 201 of obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period may include steps A1-A2:

[0077] Step A1: According to the historical relevant data of the entity in the first historical period, determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2,..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period.

[0078] Step A2: performing arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0079] As an example, the calculation formula for the recent average popularity of an entity can be as follows:

[0080]

[0081] Among them, h(i) represents the popularity of the entity in the i-th time unit from the first end time of the first historical period; recent(M) represents the recent average popularity of the entity. Assuming that the first end time is the current time, the time unit is day, and M=7, then the first historical period is 7 days from the current time; then the recent average popularity of the entity represents the average daily popularity of the entity in the 7 days from the current time.

[0082] In the second specific implementation of step 201, different from the first specific implementation, further, in order to make the recent average popularity of the entity not only show the popularity of the entity in the recent period, but also more finely show the fluctuation of the popularity of the entity in the recent period, focusing on reflecting the volatility of the user's attention to the entity in the recent period; in the second specific implementation, for the first historical period, the weight corresponding to the popularity of the i-th time unit entity from the first end time is set to become smaller as the value of i increases; that is, the closer to the first end time, the greater the weight corresponding to the popularity of each time unit entity. For example, the weight corresponding to the popularity of the i-th time unit entity from the first end time can be calculated based on M and i.

[0083] Given the heat of each time unit entity in the first historical period from the first end time and the weights corresponding to the heat of each time unit entity from the first end time, we can perform a weighted average operation to calculate the recent average heat of the entity.

[0084] Therefore, in an optional implementation of the embodiment of the present application, the step 201 of obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period may include steps A3 to A5:

[0085] Step A3: According to the historical relevant data of the entity in the first historical period, determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2,..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period.

[0086] Step A4: Determine, based on i and M, the weights corresponding to the heat of the entity at the i-th time unit from the first end time.

[0087] The weights corresponding to the heat of the i-th time unit entity from the first end time may be, for example, M / i.

[0088] Step A5: Perform weighted averaging based on the weights corresponding to the heat of the entity at the i-th time unit from the first end time and the heat of the entity at the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0089] As an example, the calculation formula for the recent average popularity of an entity can be as follows:

[0090]

[0091]

[0092] Wherein, h(i) represents the entity heat of the i-th time unit from the first end time; Indicates the weight of the entity heat of the i-th time unit from the first end time. The smaller the value of i, the The larger the weight, the higher the value; sum(M) represents the sum of M weights; recent(M) represents the recent average popularity of the entity.

[0093] During the specific implementation of step 201, in order to make the historical average heat of the entity comprehensively represent the average heat of the entity in the second historical period earlier than the first historical period, and to reduce the heat fluctuation of the entity in the historical period as much as possible, the weight corresponding to the heat of the entity in the jth time unit from the second end time in the second historical period can be set to be consistent, for example, but not limited to 1; j = 1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units. Among them, the second end time is the end time of the second historical period. If the second historical period is a period of time before the current time, the second end time is the current time. The second end time can be earlier than the first end time, or it can be the same as the first end time.

[0094] If the heat of entities in each time unit from the second end time in the second historical period is known, and the weights corresponding to the heat of entities in each time unit from the second end time are consistent, an arithmetic average operation can be performed to calculate the historical average heat of the entity.

[0095] Therefore, in an optional implementation of the embodiment of the present application, the step 201 of obtaining the historical average popularity of the entity according to the historical relevant data of the entity in the second historical period may include, for example, steps B1 and B2:

[0096] Step B1: According to the historical relevant data of the entity in the second historical period, determine the popularity of the entity at the jth time unit from the second end time; j=1, 2,..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period.

[0097] Step B2: performing arithmetic averaging on the heat of the entity in the j-th time unit from the second end time to obtain the historical average heat of the entity.

[0098] As an example, the calculation formula for the historical average heat of an entity can be as follows:

[0099]

[0100] Among them, h(j) represents the unit entity heat at the jth time from the second end time of the second historical period; history(N) represents the historical average heat of the entity.

[0101] Assuming that the second end time is the current time, the time unit is day, and N=30, the second historical period is 30 days from the current time; the historical average heat of the entity represents the average daily heat of the entity 30 days from the current time.

[0102] Assuming that the current time is June, the second end time is May 31, the time unit is day, and N=31, then the second historical period is the whole month of May; the historical average heat of the entity represents the average heat of the entity every day in May.

[0103] Step 202: Obtain a target gain coefficient based on a preset function of the recent average heat, the historical average heat, and a limited upper limit value; the target gain coefficient is an incremental change coefficient of the recent average heat relative to the historical average heat.

[0104] In the embodiment of the present application, in order to solve the problem that the historical average heat of the entity cannot well reflect the recent heat of the entity, the recent average heat of the entity only considers the recent heat of the entity, resulting in large volatility. Even the weighted average heat of the first two introduces a large volatility problem. After obtaining the recent average heat and the historical average heat of the entity in step 201, it is necessary to calculate the incremental change coefficient of the recent average heat of the entity relative to the historical average heat based on the recent average heat and the historical average heat of the entity, using a preset function with a limited upper limit value, as the target gain coefficient.

[0105] When step 202 is specifically implemented, since the above-mentioned target gain coefficient represents the incremental change coefficient of the recent average heat of the entity relative to the historical average heat of the entity, the incremental change coefficient has an upper limit. On the basis that the preset function has an upper limit value, in order to make the upper limit of the calculated target gain coefficient more intuitive and obvious, it is necessary to amplify the upper limit value of the preset function. For example, in actual applications, in response to the demand for the target gain coefficient, the gain amplification coefficient corresponding to the preset function is pre-set according to the upper limit value of the preset function, and the gain amplification coefficient corresponding to the preset function is used to amplify the upper limit value of the preset function, so as to calculate a more reasonable target gain coefficient.

[0106] At the same time, when calculating the target gain coefficient, if the above-mentioned preset function has a corresponding gain amplification coefficient, it is also necessary to pre-set the normalization constant corresponding to the preset function according to the gain amplification coefficient so as to satisfy the target gain coefficient to be 1 when the recent average heat of the entity is the same as the historical average heat of the entity.

[0107] Based on the known recent average heat of the entity, the historical average heat of the entity, the preset function, the gain amplification factor corresponding to the preset function, and the normalization constant corresponding to the preset function, the target gain coefficient can be calculated.

[0108] Therefore, in an optional implementation of the embodiment of the present application, the step 202 may include, for example, the following steps C1 to C2:

[0109] Step C1: obtaining a gain amplification factor and a normalization constant corresponding to the preset function; the gain amplification factor is determined based on an upper limit value of the preset function, and the normalization constant is determined based on the gain amplification factor.

[0110] Step C2: Obtain the target gain coefficient according to the recent average heat, the historical average heat, the preset function, the gain amplification factor and the normalization constant; wherein the normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1.

[0111] Based on the above example, as an example, when the preset function is a logistic function, the calculation formula of the target gain coefficient can be as follows:

[0112]

[0113] Wherein, a represents the gain amplification coefficient corresponding to the logistic function; b represents the normalization constant corresponding to the logistic function; gain(M, N) represents the target gain coefficient.

[0114] The normalization constant b is used to satisfy: when the recent average heat recent(M) is the same as the historical average heat history(N), the target gain coefficient gain(M, N) is 1. For example, assuming that the gain amplification factor a = 3.72, that is, based on the characteristic that the upper limit value of the logistic function is 1, the upper limit value of the target gain coefficient gain(M, N) is 3.72; in order to satisfy that when the recent average heat of the entity recent(M) is the same as the historical average heat of the entity history(N), the target gain coefficient gain(M, N) is 1, b≈2, the specific derivation is as follows:

[0115]

[0116]

[0117] e -(1-b) =2.72

[0118] b≈2Step 203: Obtain the optimized value of the entity heat according to the recent average heat, the historical average heat and the target gain coefficient.

[0119] In the embodiment of the present application, the target gain coefficient is obtained in step 202, and based on the known recent average heat and historical average heat of the entity, the recent average heat and historical average heat of the entity are optimized through the target gain coefficient. That is, when calculating the heat of an entity, the dimension of the incremental change coefficient of the entity's recent average heat relative to the historical average heat is added to obtain the optimized heat value of the entity. The heat optimization value data of the entity comprehensively reflects the user's attention to the data in different dimensions, which can not only solve the problem that the historical average heat of the entity cannot well reflect the recent heat of the data, but also avoid the problem that the recent average heat of the entity and the weighted average heat of the recent average heat and the historical average heat introduce large volatility.

[0120] When step 203 is specifically implemented, since the recent average data of the entity only considers the popularity of the entity in the recent period and has the characteristic of greater volatility, it is necessary to integrate the historical average heat of the entity and pay attention to the popularity of the entity in the historical period to reduce part of the volatility. When integrating the recent average heat and the historical average heat of the entity, it is necessary to set the weight of the historical average heat of the entity to be greater than the recent average heat of the entity. Based on this, the weighted average heat of the entity can be obtained by performing a weighted average operation. On the basis of the weighted average heat of the entity, it is also necessary to further combine the target gain coefficient to optimize the weighted average heat of the entity; that is, the product of the weighted average heat of the entity and the target gain coefficient is used as the heat optimization value of the entity. Therefore, in an optional implementation of the embodiment of the present application, the step 203 described in obtaining the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient may include the following steps D1-D3:

[0121] Step D1: Determine the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat.

[0122] Step D2: According to the weight of the recent average heat and the weight of the historical average heat, perform weighted averaging on the recent average heat and the historical average heat to obtain the weighted average heat of the entity.

[0123] Step D3: multiply the weighted average heat and the target gain coefficient to obtain the heat optimization value of the entity.

[0124] Based on the above example, as an example, the calculation formula for the heat optimization value of an entity can be as follows:

[0125]

[0126] Among them, k represents the weight of the historical average heat of the entity; the weight of the recent average heat of the entity is 1; result represents the optimized heat value of the entity.

[0127] In the embodiment of the present application, the heat optimization value of the entity obtained in step 203 can comprehensively reflect the user's attention to the data in different dimensions, that is, it can more truly and effectively reflect the user's attention to the entity; then in the entity recommendation scenario, the entity heat optimization value is used to replace the original entity's historical average heat, recent average heat, and the weighted average heat of the former two, so that the accuracy of entity recommendation is higher. Therefore, in an optional implementation of the embodiment of the present application, the method may also include: performing an entity recommendation operation according to the heat optimization value of the entity.

[0128] In addition, in the embodiment of the present application, since the heat optimization value of the entity is obtained by first weighted averaging the recent average heat and the historical average heat of the entity, and then multiplying it by the target gain coefficient, the heat optimization value of the entity is consistent with the measurement unit of the recent average heat and the historical average heat of the entity, so that the heat optimization value of the entity is comparable with the recent average heat and the historical average heat of the entity. After obtaining the optimized value of the entity heat in step 202, the historical average heat of the entity, the recent average heat of the entity, and the heat optimization value of the entity can also be compared and analyzed to analyze the degree of optimization of the heat optimization value of the entity under the historical average heat and the recent average heat. Therefore, in an optional implementation of the embodiment of the present application, the method may also include, for example: comparing and analyzing the historical average heat, the recent average heat, and the heat optimization value.

[0129] For example, the historical average heat of an entity, the recent average heat, the optimized value of the entity heat, and the optimization description are shown in Table 1 below:

[0130] Table 1 The historical average heat of the entity, the recent average heat, the optimized value of the entity heat, and the optimization description

[0131]

[0132] Through the various implementation methods provided by this embodiment, first, the recent average heat of the entity is calculated through the historical relevant data of the entity in the first historical period, and the historical average heat of the entity is calculated through the historical relevant data of the entity in the second historical period; wherein the start time of the second historical period is before the start time of the first historical period. Then, the target gain coefficient is calculated by combining the recent average heat and the historical average heat, using a preset function with a limited upper limit value. Finally, the heat optimization value of the entity is calculated by combining the recent average heat and the historical average heat, and combining the target gain coefficient. It can be seen that on the basis of obtaining the recent average heat and the historical average heat of the entity, the incremental change coefficient of the recent average heat relative to the historical average heat is expressed by calculating the target gain coefficient; the heat optimization value of the entity is calculated by combining the recent average heat, the historical average heat and the target gain coefficient, which can comprehensively reflect the user's attention to the entity in a more real and effective way, thereby accurately recommending the entity according to the heat optimization value of the entity in the entity recommendation scenario.

[0133] Exemplary Devices

[0134] See also Figure 3 , showing a schematic diagram of the structure of a data processing device in an embodiment of the present application.

[0135] In this embodiment, the device may specifically include, for example:

[0136] The first obtaining unit 301 is used to obtain the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period; and obtain the historical average popularity of the entity according to the historical relevant data of the entity in the second historical period; the start time of the second historical period is before the start time of the first historical period;

[0137] The second obtaining unit 302 is used to obtain a target gain coefficient according to the recent average heat, the historical average heat and a preset function of a limited upper limit value; the target gain coefficient is an incremental change coefficient of the recent average heat relative to the historical average heat;

[0138] The third obtaining unit 303 is used to obtain the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient.

[0139] In an optional implementation manner of the embodiment of the present application, the second obtaining unit is used to:

[0140] Obtaining a gain amplification factor and a normalization constant corresponding to the preset function; the gain amplification factor is determined based on an upper limit value of the preset function, and the normalization constant is determined based on the gain amplification factor;

[0141] Obtaining the target gain coefficient according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant;

[0142] The normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1.

[0143] In an optional implementation manner of the embodiment of the present application, the third obtaining unit is used to:

[0144] Determine the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat;

[0145] According to the weight of the recent average heat and the weight of the historical average heat, weighted average processing is performed on the recent average heat and the historical average heat to obtain the weighted average heat of the entity;

[0146] The weighted average heat and the target gain coefficient are multiplied to obtain the heat optimization value of the entity.

[0147] In an optional implementation manner of the embodiment of the present application, the first obtaining unit is used to:

[0148] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0149] Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0150] In an optional implementation manner of the embodiment of the present application, the first obtaining unit is further used to:

[0151] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0152] Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M;

[0153] A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0154] In an optional implementation manner of the embodiment of the present application, the first obtaining unit is further used to:

[0155] According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period;

[0156] Perform arithmetic averaging on the heat of the entity at the jth time unit from the second end time to obtain the recent average heat of the entity.

[0157] Through the various implementation methods provided by this embodiment, first, the recent average heat of the entity is calculated through the historical relevant data of the entity in the first historical period, and the historical average heat of the entity is calculated through the historical relevant data of the entity in the second historical period; wherein the start time of the second historical period is before the start time of the first historical period. Then, the target gain coefficient is calculated by combining the recent average heat and the historical average heat, using a preset function with a limited upper limit value. Finally, the heat optimization value of the entity is calculated by combining the recent average heat and the historical average heat, and combining the target gain coefficient. It can be seen that on the basis of obtaining the recent average heat and the historical average heat of the entity, the incremental change coefficient of the recent average heat relative to the historical average heat is expressed by calculating the target gain coefficient; the heat optimization value of the entity is calculated by combining the recent average heat, the historical average heat and the target gain coefficient, which can comprehensively reflect the user's attention to the entity in a more real and effective way, thereby accurately recommending the entity according to the heat optimization value of the entity in the entity recommendation scenario.

[0158] Figure 4 4 is a block diagram of a device 400 for data processing according to an exemplary embodiment. For example, the device 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0159] Reference Figure 4 , the device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0160] The processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0161] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0162] The power supply component 406 provides power to the various components of the device 400. The power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0163] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0164] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0165] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0166] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and the temperature change of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0167] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0168] In an exemplary embodiment, the apparatus 400 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0169] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, and the instructions can be executed by a processor 420 of the device 400 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0170] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to perform a data processing method, the method comprising:

[0171] According to the historical relevant data of the entity in the first historical period, the recent average popularity of the entity is obtained; according to the historical relevant data of the entity in the second historical period, the historical average popularity of the entity is obtained; the start time of the second historical period is before the start time of the first historical period;

[0172] According to the preset function of the recent average heat, the historical average heat and the limited upper limit value, a target gain coefficient is obtained; the target gain coefficient is the incremental change coefficient of the recent average heat relative to the historical average heat;

[0173] The heat optimization value of the entity is obtained according to the recent average heat, the historical average heat and the target gain coefficient.

[0174] In an optional implementation of the embodiment of the present application, obtaining the target gain coefficient according to the preset function of the recent average heat, the historical average heat and the limited upper limit value includes:

[0175] Obtaining a gain amplification factor and a normalization constant corresponding to the preset function; the gain amplification factor is determined based on an upper limit value of the preset function, and the normalization constant is determined based on the gain amplification factor;

[0176] Obtaining the target gain coefficient according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant;

[0177] The normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1.

[0178] In an optional implementation of the embodiment of the present application, obtaining the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient includes:

[0179] Determine the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat;

[0180] According to the weight of the recent average heat and the weight of the historical average heat, weighted average processing is performed on the recent average heat and the historical average heat to obtain the weighted average heat of the entity;

[0181] The weighted average heat and the target gain coefficient are multiplied to obtain the heat optimization value of the entity.

[0182] In an optional implementation of the embodiment of the present application, obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period includes:

[0183] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0184] Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0185] In an optional implementation of the embodiment of the present application, obtaining the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period includes:

[0186] According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period;

[0187] Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M;

[0188] A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

[0189] In an optional implementation of the embodiment of the present application, obtaining the historical average popularity of the entity according to the historical related data of the entity in the second historical period includes:

[0190] According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period;

[0191] Perform arithmetic averaging on the heat of the entity at the jth time unit from the second end time to obtain the historical average heat of the entity.

[0192] Figure 5: is a schematic diagram of the structure of the server in the embodiment of the present application. The server 500 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 522 (for example, one or more processors) and a memory 532, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 542 or data 544. Among them, the memory 532 and the storage medium 530 can be short-term storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 522 can be configured to communicate with the storage medium 530 and execute a series of instruction operations in the storage medium 530 on the server 500.

[0193] The server 500 may also include one or more power supplies 526, one or more wired or wireless network interfaces 550, one or more input and output interfaces 558, one or more keyboards 556, and / or one or more operating systems 541, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0194] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0195] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0196] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprises a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0197] The above is only a preferred embodiment of the present application and does not constitute any formal limitation to the present application. Although the present application has been disclosed as above with a preferred embodiment, it is not intended to limit the present application. Any technician familiar with the art can make many possible changes and modifications to the technical solution of the present application using the methods and technical contents disclosed above without departing from the scope of the technical solution of the present application, or modify it into an equivalent embodiment of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application still fall within the scope of protection of the technical solution of the present application.

Claims

1. A method for data processing, characterized in that: include: According to the historical relevant data of the entity in the first historical period, the recent average popularity of the entity is obtained; according to the historical relevant data of the entity in the second historical period, the historical average popularity of the entity is obtained; the start time of the second historical period is before the start time of the first historical period; According to the recent average heat, the historical average heat and a preset function with a limited upper limit value, a target gain coefficient is obtained, which includes: obtaining a gain amplification coefficient and a normalization constant corresponding to the preset function; the gain amplification coefficient is determined based on the upper limit value of the preset function, and the normalization constant is determined based on the gain amplification coefficient; according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant, the target gain coefficient is obtained; wherein the normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1; the target gain coefficient is the incremental change coefficient of the recent average heat relative to the historical average heat; According to the recent average heat, the historical average heat and the target gain coefficient, the heat optimization value of the entity is obtained, which includes: determining the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat; according to the weight of the recent average heat and the weight of the historical average heat, performing weighted averaging processing on the recent average heat and the historical average heat to obtain the weighted average heat of the entity; performing product processing on the weighted average heat and the target gain coefficient to obtain the heat optimization value of the entity; An entity recommendation operation is performed according to the heat optimization value of the entity.

2. The method according to claim 1, characterized in that The obtaining, according to the historical relevant data of the entity in the first historical period, the recent average popularity of the entity includes: According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period; Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

3. The method according to claim 1, characterized in that The obtaining, according to the historical relevant data of the entity in the first historical period, the recent average popularity of the entity includes: According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period; Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M; A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

4. The method according to claim 1, characterized in that The obtaining, according to the historical relevant data of the entity in the second historical period, the historical average popularity of the entity comprises: According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period; Perform arithmetic averaging on the heat of the entity at the j-th time unit from the second end time to obtain the historical average heat of the entity.

5. A data processing device, characterized in that: include: A first obtaining unit is used to obtain the recent average popularity of the entity according to the historical relevant data of the entity in the first historical period; and obtain the historical average popularity of the entity according to the historical relevant data of the entity in the second historical period; the start time of the second historical period is before the start time of the first historical period; The second obtaining unit is used to obtain a target gain coefficient according to the recent average heat, the historical average heat and a preset function with a limited upper limit value, which includes: obtaining a gain amplification coefficient and a normalization constant corresponding to the preset function; the gain amplification coefficient is determined based on the upper limit value of the preset function, and the normalization constant is determined based on the gain amplification coefficient; the target gain coefficient is obtained according to the recent average heat, the historical average heat, the preset function, the gain amplification coefficient and the normalization constant; wherein the normalization constant is used to satisfy: when the recent average heat is the same as the historical average heat, the target gain coefficient is 1; the target gain coefficient is the incremental change coefficient of the recent average heat relative to the historical average heat; The third obtaining unit is used to obtain the heat optimization value of the entity according to the recent average heat, the historical average heat and the target gain coefficient, which includes: determining the weight of the recent average heat and the weight of the historical average heat; the weight of the historical average heat is greater than the weight of the recent average heat; according to the weight of the recent average heat and the weight of the historical average heat, performing weighted averaging on the recent average heat and the historical average heat to obtain the weighted average heat of the entity; performing multiplication processing on the weighted average heat and the target gain coefficient to obtain the heat optimization value of the entity; performing entity recommendation operation according to the heat optimization value of the entity.

6. The device according to claim 5, characterized in that The first obtaining unit is used for: According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period; Perform arithmetic averaging on the heat of the entity within the i-th time unit from the first end time to obtain the recent average heat of the entity.

7. The device according to claim 5, characterized in that The first obtaining unit is further used for: According to the historical relevant data of the entity in the first historical period, respectively determine the popularity of the entity in the i-th time unit from the first end time; i=1, 2, ..., M; i and M are both positive integers; the first historical period is divided into M time units; the first end time is the end time of the first historical period; Determine the weights corresponding to the heat of the entity at the i-th time unit from the first end time according to i and M; A weighted average processing is performed according to the weights corresponding to the heat of the entity in the i-th time unit from the first end time and the heat of the entity in the i-th time unit from the first end time to obtain the recent average heat of the entity.

8. The device according to claim 5, characterized in that The first obtaining unit is further used for: According to the historical relevant data of the entity in the second historical period, respectively determine the popularity of the entity at the j-th time unit from the second end time; j=1, 2, ..., N; j and N are both positive integers; the second historical period is divided into N time units; the second end time is the end time of the second historical period; Perform arithmetic averaging on the heat of the entity in the j-th time unit from the second end time to obtain the recent average heat of the entity.

9. A device for data processing, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to perform the data processing method according to any one of claims 1 to 4.

10. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes an apparatus to perform the data processing method according to any one of claims 1 to 4.

Images