Information recommendation method, device, electronic device and storage medium

Abstract

The embodiments of the present invention provide an information recommendation method, device, electronic device and storage medium, which relate to the field of data processing technology. The information recommendation method includes: receiving behavior information of a target user sent by a terminal, the behavior information includes: relevant data of the target user's target operation on the area where the target component in the page is located, the relevant data at least includes: the number of times the terminal receives the target operation within at least one operation cycle, and the time interval between two consecutive times the terminal receives the target operation within the operation cycle is less than a set duration; calculating a first discrete degree of the number; determining the information to be pushed based on the relationship between the first discrete degree and the degree threshold; and pushing the information to be pushed to the terminal. The present application implements an information recommendation method with a high degree of association with individual users.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an information recommendation method, device, electronic device and storage medium. Background Art

[0002] Among various software products, recommending relevant information of software products to users is a common way to promote products and increase user retention. Currently, information related to products with high click-through rates or information related to recently launched products is usually pushed to users. However, the product-related information pushed by this push method has a low degree of relevance to individual users, so there is an urgent need for an information recommendation method with a high degree of relevance to individual users. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide an information recommendation method, device, electronic device and storage medium to achieve an information recommendation method with a high degree of relevance to individual users. The specific technical solution is as follows:

[0004] In a first aspect of the present invention, a method for information recommendation is provided, the method comprising:

[0005] receiving behavior information of a target user sent by a terminal, the behavior information including: relevant data of a target operation of the target user on an area where a target component is located in a page, the relevant data including at least: the number of times the terminal receives the target operation in at least one operation cycle, and the time interval between two consecutive times the terminal receives the target operation in the operation cycle is less than a set time length;

[0006] Calculating a first discrete degree of the number of times;

[0007] Determining the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold;

[0008] Pushing the information to be pushed to the terminal.

[0009] Optionally, the relevant data further includes: the duration of the operation cycle; the method further includes: calculating a second discrete degree of the duration; and determining the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold, including:

[0010] When the first discrete degree is less than or equal to a first degree threshold, and the second discrete degree is less than or equal to a second degree threshold, determining that the information to be pushed is the first information;

[0011] When the first discrete degree is greater than the second discrete degree threshold, or when the second discrete degree is greater than the second discrete degree threshold, it is determined that the information to be pushed is the second information.

[0012] Optionally, the first degree of dispersion is represented by the mean difference, standard deviation or range of the number of times; the second degree of dispersion is represented by the mean difference, standard deviation or range of the duration.

[0013] Optionally, there are multiple target components, and the behavior information includes: relevant data corresponding to the multiple target components, and determining the information to be pushed according to the relationship between the first discrete degree and the degree threshold includes:

[0014] The information to be pushed is determined according to the size relationships respectively corresponding to the plurality of related data.

[0015] Optionally, determining the information to be pushed according to the size relationship respectively corresponding to the plurality of related data includes:

[0016] When the first target number of the first discrete degrees are all smaller than the degree threshold, determining that the information to be pushed is the first information;

[0017] When the second target quantity and the first discrete degree are both greater than the degree threshold, it is determined that the information to be pushed is the second information, and the sum of the first target quantity and the second target quantity is the quantity of the target components.

[0018] Optionally, the target component satisfies at least one of the following conditions:

[0019] The user's operation frequency on the target component is greater than a frequency threshold;

[0020] The area of ​​the target component in the page is smaller than the area threshold;

[0021] The target component is used to trigger the terminal to implement a set function.

[0022] In a second aspect of the present invention, there is also provided an information recommendation method, the method comprising:

[0023] When receiving a target operation performed by a target user in the area where the target component is located in the page, the number of target operations received by the terminal in the area during the operation cycle is recorded, and the time interval between two consecutive receptions of the target operations by the terminal during the operation cycle is less than the set time length;

[0024] Generate behavior information of the target user, the behavior information comprising: relevant data of the target operation of the target user on the area, the relevant data at least comprising: the number of times the terminal receives the target operation in at least one operation cycle;

[0025] The behavior information is sent to the server.

[0026] Optionally, the method further includes: when a target operation performed by a target user is received in an area where a target component is located in the page, recording the duration of the operation cycle; the related data further includes: the duration of the operation cycle.

[0027] Optionally, the target component satisfies at least one of the following conditions:

[0028] The user's operation frequency on the target component is greater than a frequency threshold;

[0029] The area of ​​the target component in the page is smaller than the area threshold;

[0030] The target component is used to trigger the terminal to implement a set function.

[0031] In a third aspect of the present invention, there is also provided an information recommendation device, the device comprising:

[0032] A receiving module, configured to receive behavior information of a target user sent by a terminal, wherein the behavior information includes: relevant data of a target operation of the target user on the area where the target component is located in the page, wherein the relevant data includes at least: the number of times the terminal receives the target operation within at least one operation cycle, and the time interval between two consecutive times the terminal receives the target operation within the operation cycle is less than a set time length;

[0033] A calculation module, used for calculating a first discrete degree of the number of times;

[0034] A determination module, configured to determine the information to be pushed according to a magnitude relationship between the first discrete degree and a degree threshold;

[0035] The push module is used to push the information to be pushed to the terminal.

[0036] In a fourth aspect of the present invention, there is also provided an information recommendation device, the device comprising:

[0037] A recording module, configured to record, when receiving a target operation performed by a target user in an area where a target component is located in a page, the number of target operations received by the terminal in the area within an operation period, wherein the time interval between two consecutive receptions of the target operations by the terminal in the operation period is less than a set time length;

[0038] A generating module, configured to generate behavior information of the target user, wherein the behavior information includes: relevant data of the target operation of the target user for the area, wherein the relevant data includes at least: the number of times the terminal receives the target operation in at least one operation cycle;

[0039] The sending module is used to send the behavior information to the server.

[0040] In a fifth aspect of the present invention, there is also provided an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0041] Memory, used to store computer programs;

[0042] The processor is used to implement any method as described in the first aspect above, or implement any method as described in the second aspect above, when executing the program stored in the memory.

[0043] In a fifth aspect of the present invention, an information recommendation system is provided, including a terminal and a server, wherein the terminal is used to implement any method described in the first aspect. The server is used to implement any method described in the second aspect.

[0044] In a sixth aspect of the present invention, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is run on a computer, the computer executes any of the above-mentioned information recommendation methods.

[0045] In a seventh aspect of the implementation of the present invention, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the above-mentioned information recommendation methods.

[0046] The information recommendation method, device, electronic device and storage medium provided in the embodiments of the present application receive the behavior information of the target user sent by the terminal, and the behavior information includes: the relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data at least includes: the number of target operations received by the terminal in at least one operation cycle, and the time interval between two adjacent target operations received by the terminal in the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page in at least one operation cycle, the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, so that the information to be pushed has a correlation with the user's behavior. Compared with the related art, a method for recommending information with a higher degree of correlation with individual users is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0048] Figure 1 A schematic diagram of an implementation environment of an information recommendation method provided in an embodiment of the present application.

[0049] Figure 2 A flowchart of an information recommendation method provided in an embodiment of the present application.

[0050] Figure 3 A page schematic diagram provided for an embodiment of the present application.

[0051] Figure 4 A flowchart of another information recommendation method provided in an embodiment of the present application.

[0052] Figure 5 A block diagram of an information recommendation device provided in an embodiment of the present application.

[0053] Figure 6 A block diagram of another information recommendation device provided in an embodiment of the present application.

[0054] Figure 7 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0056] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment of an information recommendation method provided by an embodiment of the present application. Figure 1 As shown, the implementation environment includes: a terminal 101 and a server 102. The terminal 101 and the server 102 are connected via a wired network or a wireless network. For example, the terminal can be a mobile phone, a tablet computer, a personal computer, or a wearable device. The server can be one or more servers, or a cloud service cluster. It should be noted that the number of terminals that can be included in the implementation environment can be one or more. Figure 1 Take the implementation environment including a terminal as an example for explanation, that is, Figure 1 The number of terminals in the implementation environment shown does not limit the number of terminals that may be included in the implementation environment provided by the embodiments of the present application.

[0057] Please refer to Figure 2 , which shows a flow chart of an information recommendation method provided by an embodiment of the present application. The information recommendation method can be applied to Figure 1 In the implementation environment shown. Figure 2 As shown, the information recommendation method includes:

[0058] Step 201: When a terminal receives a target operation performed by a target user in an area where a target component is located in a page, the number of target operations received by the terminal in the area during an operation cycle is recorded. The time interval between two consecutive target operations received by the terminal during the operation cycle is less than a set time length.

[0059] In the embodiment of the present application, the target user refers to the user holding the terminal. The number of target components in the page can be one or more, and the embodiment of the present application takes the number of target components as one as an example for explanation. The target user can perform at least one target operation in the area where the target component is located in the page. Optionally, the target operation can be a click operation, a long press operation, a sliding operation, etc.

[0060] Each time the terminal receives a target operation from the target user for the area where the target component in the page is located, the terminal can record the time when the target operation is received. The terminal can calculate the time interval between each two adjacent target operations received, and compare the time interval with the set duration. When the time interval is greater than or equal to the set duration, it indicates that the target user has performed two target operations in a longer duration. When the time interval is less than the set duration, it indicates that the target user has performed two target operations in a shorter duration, and therefore, the two target operations can be considered as two consecutive operations. The terminal can treat the two target operations with a time interval less than the set duration as target operations within the same operation cycle based on the relationship between the time interval between each two adjacent target operations received and the set duration, and record the number of all target operations received by the terminal in the area where the target component is located within the operation cycle. Among them, the number of operation cycles can be one or more. The time interval between two adjacent target operations received by the terminal in any operation cycle is less than the set duration.

[0061] For example, the times at which the terminal receives the target operation performed by the target user in the area where the target component is located are: 8:01:01, 8:01:03, 8:01:07, 8:01:10, 8:02:01, 8:02:05, and 8:02:10. Assuming that the set duration is 30 seconds, the terminal determines that the operation cycle of the target user includes: the first operation cycle and the second operation cycle according to the relationship between the time interval between each two adjacent target operations received and the set duration. Among them, the times at which the target operation is received in the first operation cycle are: 8:01:01, 8:01:03, 8:01:07, and 8:01:10. The number of target operations received by the terminal in the first operation cycle is 4. The times at which the target operation is received in the second operation cycle are: 8:02:01, 8:02:05, and 8:02:10. The number of target operations received by the terminal in the second operation cycle is 3.

[0062] It should be noted that, optionally, the area where the target component is located may refer to the display area of ​​the target component in the page. Alternatively, the area where the target component is located may include the display area of ​​the target component in the page, and the adjacent area adjacent to the target component in the page. For example, the area where the target component is located includes the display area of ​​the target component and the adjacent area surrounding the target component. The adjacent area and the display area may be centrally overlapped areas, and the total area S of the adjacent area and the display area may satisfy: S = m × S bx , S bx is the area of ​​the display region of the target component in the page, that is, the area of ​​the target component. Wherein, m is a constant, and m>0. Optionally, m can be 1, 1.1 and 1.5.

[0063] For examples, please refer to Figure 3 , which shows a page schematic diagram provided by an embodiment of the present application. Figure 3 As shown, the target page 300 includes five target components, which are target components 301 to 305 (b1-b5). Taking target component b3 as an example, the display area ( Figure 3 The area indicated by the dashed line is S b3 , the area where the target component b3 is located ( Figure 3 The area indicated by the solid line pointed to by the 303 mark is S3.

[0064] Optionally, the target component may satisfy at least one of the following conditions: the user's operation frequency on the target component is greater than a frequency threshold; the area of ​​the target component in the page is less than an area threshold; the target component is used to trigger the terminal to implement a set function. For example, the frequency threshold is greater than 0. For example, the frequency threshold is 2 times / second or 2 times / second, etc. Area threshold S valid > 0. For example, the area threshold can be 1cm 2 or 1.5cm 2 The setting function may be a function of jumping to other pages except the currently displayed page, and / or the setting function may also be a function of posting comments, etc.

[0065] Step 202: The terminal generates behavior information of the target user. The behavior information includes: data related to the target operation of the target user on the area, and the related data at least includes: the number of times the terminal receives the target operation in at least one operation cycle.

[0066] In the embodiment of the present application, the terminal can generate the target user's behavior information according to the number of target operations received by the terminal in the area during the recorded operation period. Optionally, the target user's behavior information can also include: the target user's identity identifier U id , the component identifier bx of the target component.

[0067] For example, when the number of operation cycles is 1, the behavior information may include: the identity identifier U of the target user id And the target user's target operation data for the area where the target component bx is located {bx:[1:{Cx_1}]}. Among them, Cx_1 is the number of target operations for the target component bx received by the terminal in the first operation cycle. That is, Cx_1 is the number of target operations for the target component bx when the target user performs the first continuous operation (i.e., the first operation cycle).

[0068] When the number of operation cycles is greater than 1, that is, n>1, the behavior information may include: the identity identifier U of the target user id And the target user's target operation data for the area where the target component bx is located {bx:[1:{Cx_1},......,n-1:{Cx_n-1},n:{Cx_n}]}. Among them, n is the number of operation cycles. Cx_n is the number of target operations on the target component bx when the target user performs the nth continuous operation (i.e., the nth operation cycle). That is, Cx_n is the number of target operations on the target component bx received by the terminal in the nth operation cycle.

[0069] When the number of operation cycles is greater than 1 and the number of target components is greater than 1, it is assumed that the multiple target components include: target component b1...target component by-1 and target component by. The behavior information may include: the identity identifier U of the target user id And the target user's target operation data for the area where y target components (b1 to by) are located {b1:[1:{C1_1},......,n-1:{C1_n-1},n:{C1_n}],......,by-1:[1:{Cy-1_1},......,n-1:{Cy-1_n-1},n:{Cy-1_n}],by:[1:{Cy_1},......,n-1:{Cy_n-1},n:{Cy_n}]}. Wherein, n is the number of operation cycles. Cy_n is the number of target operations performed by the target user on the target component by when the target user performs the nth continuous operation (i.e., the nth operation cycle).

[0070] For example, the operation cycle is 3, and the number of target components is 3, that is, the target components include the first target component b1, the second target component b2 and the third target component b3. The target user's behavior information includes: the target user's identity U idAnd the relevant data of the target user's target operations on the areas where the three target components are located {b1:[1:{C1_1}, 2:{C1_2}, 3:{C1_3}], b2:[1:{C2_1}, 2:{C2_2}, 3:{C2_3}], b3:[1:{C3_1}, 2:{C3_2}, 3:{C3_3}]}.

[0071] Optionally, the terminal may generate the behavior information of the target user according to the generation time limit rule. The generation time limit rule may be: each time the number of target operations for a set number of operation cycles is recorded, the behavior information of the target user is generated. The behavior information includes the number of a set number of operation cycles. The set number may be 1, 2 or 3. Alternatively, the generation time limit rule may be: after the terminal jumps to a page, the behavior information of the target user is generated. The behavior information includes: the number of target operations for the target component in the page before the jump, within at least one operation cycle, performed by the terminal.

[0072] Step 203: The terminal sends the target user's behavior information to the server.

[0073] In the embodiment of the present application, the terminal can send the behavior information of the target user to the server through the network connected between the terminal and the server.

[0074] Step 204: The server calculates a first discrete degree of the number of times in the received behavior information.

[0075] In an embodiment of the present application, the server can calculate the first discrete degree of the number of target operations for the target component received by the terminal within at least one operation cycle after receiving the behavior information of the target user sent by the terminal. The first offline degree reflects the degree of difference in the number of target operations for the target component received by the terminal within each operation cycle. It should be noted that, in the case where there are multiple target components, the server calculates the first discrete degree of the number of target operations for each target component within the operation cycle in the received behavior information. That is, for any target component, the first discrete degree of the number of target operations for the target component received by the terminal within at least one operation cycle in the behavior information is calculated.

[0076] Optionally, the first degree of dispersion is characterized by the mean deviation, standard deviation or range of the number of times. For example, the first offline degree is characterized by the standard deviation of the number of times. Meaning of standard deviation: When the data distribution is relatively dispersed (that is, the data fluctuates greatly around the mean), the sum of the squares of the differences between each data and the mean is large, and the standard deviation is large. When the data distribution is relatively concentrated, the sum of the squares of the differences between each data and the mean is small, and the standard deviation is small. Therefore, the greater the fluctuation of each data for calculating the standard deviation, the greater the standard deviation; the smaller the fluctuation of each data, the smaller the standard deviation. The standard deviation is used to characterize the degree of fluctuation of each data, that is, the degree of difference. For the embodiment of the present application, when the first degree of dispersion adopts the standard deviation, the greater the value of the first offline degree, the greater the degree of fluctuation of the number of target operations for the target component received by the terminal in each operation cycle; the smaller the value of the first offline degree, the smaller the degree of fluctuation of the number of target operations for the target component received by the terminal in each operation cycle.

[0077] The process of calculating the first discrete degree of the number of times in the received behavior information by the server includes: the server calculates the first average value of the number of target operations on the target component in the operation cycle in the received behavior information, and calculates the standard deviation of the number of target operations on the target component in the operation cycle based on the first average value.

[0078] That is, the server uses the first target formula to calculate the first average value ΔCarg of the number of times. The first target formula satisfies:

[0079] ΔCarg=(Cx_1+…+Cx_n) / n;

[0080] Wherein, ΔCarg represents the first average number of target operations for the target component in the operation cycle. Cx_1 represents the number of target operations for the target component bx received by the terminal in the first operation cycle. Cx_n represents the number of target operations for the target component bx received by the terminal in the nth operation cycle. n represents the number of operation cycles.

[0081] The server uses the second target formula to calculate the standard deviation σc of the number of times based on the first average value. The second target formula satisfies:

[0082]

[0083] Wherein, σc represents the standard deviation of the number of target operations for the target component in the operation cycle. ΔCarg represents the first average value of the number of target operations for the target component in the operation cycle. Cx_1 represents the number of target operations for the target component bx received by the terminal in the first operation cycle. Cx_2 represents the number of target operations for the target component bx received by the terminal in the second operation cycle. Cx_n represents the number of target operations for the target component bx received by the terminal in the nth operation cycle.

[0084] Step 205: The server determines the information to be pushed according to the relationship between the first discrete degree and the degree threshold.

[0085] In an embodiment of the present application, the value of the degree threshold can reflect the moderate degree of fluctuation in the number of times the target operation is received for the target component within multiple operation cycles. Optionally, when the first offline degree is less than or equal to the degree threshold, it indicates that the fluctuation in the number of times the target operation is received for the target component within multiple operation cycles is small. The terminal determines that the information to be pushed is the first information. When the first offline degree is greater than the degree threshold, it indicates that the fluctuation in the number of times the target operation is received for the target component within multiple operation cycles is large. The terminal determines that the information to be pushed is the second information, and the second information is different from the first information. Among them, the value of the degree threshold can be determined according to actual needs.

[0086] In the case where there are multiple target components, the behavior information includes relevant data corresponding to the multiple target components. Accordingly, the terminal calculates the first discrete degree of the number of target operations received within the operation cycle for each target component in the behavior information. Based on this, the process of determining the information to be pushed by the server based on the size relationship between the first discrete degree and the degree threshold may include: determining the information to be pushed based on the size relationship corresponding to multiple relevant data. That is, the server can determine the size relationship between the first offline degree of the number of target operations received by the terminal in the relevant data within the operation cycle and the degree threshold for each relevant data. The server determines the information to be pushed based on the size relationship corresponding to each relevant data.

[0087] In an optional implementation, the process of determining the information to be pushed by the server according to the size relationship corresponding to the plurality of related data may include:

[0088] When the first discrete degrees of the first target quantity are all less than the degree threshold, the information to be pushed is determined to be the first information; when the first discrete degrees of the second target quantity are all greater than the degree threshold, the information to be pushed is determined to be the second information, and the sum of the first target quantity and the second target quantity is the number of target components.

[0089] Among them, when the first target number and the first discrete degree are all less than the degree threshold, it indicates that the number of target components with a small fluctuation degree of the number of times the terminal receives the target operation in multiple operation cycles is relatively large. It further indicates that the number of times corresponding to multiple components fluctuates relatively small as a whole, and the terminal determines that the information to be pushed is the first information. When the second target number and the first discrete degree are all less than the degree threshold, it indicates that the number of target components with a small fluctuation degree of the number of times the terminal receives the target operation in multiple operation cycles is relatively small. It further indicates that the number of times corresponding to multiple components fluctuates relatively large as a whole, and the terminal determines that the information to be pushed is the second information.

[0090] Optionally, the server may store a set value, which represents the proportion of target components whose first discrete degree is less than the degree threshold to the total number of target components. Exemplarily, the set value is a percentage. After receiving the behavior information, the server may count the total number of target components. The product of the total number of target components and the set value is taken as the first target number. Correspondingly, the server may take the difference between the total number of target components and the first target number as the second target number.

[0091] In another optional implementation, the process of determining the information to be pushed by the server based on the size relationship corresponding to the multiple related data may include: the number of target components whose first discrete degree is less than the degree threshold is greater than or equal to the third target number, determining that the information to be pushed is the first information; the number of target components whose first discrete degree is greater than the degree threshold is less than the third target number, determining that the information to be pushed is the second information. Optionally, the third target number can be 2, 3 or 4. It should be noted that the value of the third target number can be determined according to actual conditions. For example, the value of the third target number is proportional to the number of target components in a page.

[0092] Step 206: The server pushes the information to be pushed to the terminal.

[0093] In an embodiment of the present application, the server can push the information to be pushed to the terminal through the network connected between it and the terminal. Optionally, the information to be pushed determined by the server may refer to a specific piece of information. Or, the information to be pushed determined by the server may also refer to a certain type of information. That is, the server can determine the category of information to be pushed based on the relationship between the first discrete degree and the degree threshold. Based on this, the process of the server pushing the information to be pushed to the terminal may include: the server can use a target algorithm to select the target push information from all the information corresponding to the category of information to be pushed, and push the target push information to the terminal. Among them, the target algorithm may include a logistic regression (LR) model, a field-aware factorization machine (FFM) model, or a priority algorithm, etc.

[0094] Optionally, the relevant data in the behavior information sent by the terminal to the server may further include: the duration of each operation cycle in at least one operation cycle.

[0095] For example, when the number of operation cycles is 1, the relevant data of the target user's target operation on the area where the target component bx is located in the behavior information is {bx:[1:{Cx_1, Tx_1}]}. Among them, Cx_1 is the number of target operations on the target component bx received by the terminal in the first operation cycle. In other words, Cx_1 is the number of target operations on the target component bx when the target user performs the first continuous operation (i.e., the first operation cycle). Tx_1 is the duration of the first operation cycle.

[0096] When the number of operation cycles is greater than 1, that is, n>1, the relevant data of the target user's target operation on the area where the target component bx is located in the behavior information is {bx:[1:{Cx_1, Tx_1},......,n-1:{Cx_n-1, Tx_n-1},n:{Cx_n, Tx_n}]}. Among them, n is the number of operation cycles. Cx_n is the number of target operations on the target component bx received by the terminal in the nth operation cycle. That is, Cx_n is the number of target operations on the target component bx when the target user performs the nth continuous operation (i.e., the nth operation cycle). Tx_n is the duration of the nth operation cycle.

[0097] When the number of operation cycles is greater than 1 and the number of target components is greater than 1, it is assumed that the multiple target components include: target component b1...target component by-1 and target component by. The relevant data of the target operation of the target user on the area where y target components (b1 to by) are located in the behavior information {b1:[1:{C1_1,T1_1},......,n-1:{C1_n-1,T1_n-1},n:{C1_n,T1_n}],......,by-1:[1:{Cy-1_1,Ty-1_1},......,n-1:{Cy-1_n-1,Ty-1_n-1},n:{Cy-1_n,Ty-1_n}],by:[1:{Cy_1,Ty_1},......,n-1:{Cy_n-1,Ty_n-1},n:{Cy_n,Ty_n}]}. Wherein, n is the number of operation cycles. Cy_n is the number of target operations on the target component by when the target user performs the nth continuous operation (i.e., the nth operation cycle). Ty_n is the duration of the nth operation cycle corresponding to the target component by.

[0098] For example, the operation cycle is 3, and the number of target components is 3, that is, the target components include the first target component b1, the second target component b2 and the third target component b3. The target user's behavior information includes: the target user's identity U id And the relevant data of the target user's target operations on the areas where the three target components are located {b1:[1:{C1_1,T1_1},2:{C1_2,T1_2},3:{C1_3,T1_3}],b2:[1:{C2_1,T2_1},2:{C2_2,T2_2},3:{C2_3,T2_3}],b3:[1:{C3_1,T3_1},2:{C3_2,T3_2},3:{C3_3,T3_3}]}.

[0099] Before step 205, the method further includes: calculating a second discrete degree of the duration of each operation cycle in at least one operation cycle. The second offline degree reflects the degree of difference in the duration of each operation cycle. It should be noted that, when there are multiple target components, the server calculates the second discrete degree of the duration of at least one operation cycle in the received behavior information for each target component.

[0100] Optionally, the second discrete degree is characterized by a mean difference, a standard deviation, or a range of the duration. For example, the second discrete degree is characterized by a standard deviation. In the embodiment of the present application, when the second discrete degree is characterized by a standard deviation, the larger the value of the second discrete degree is, the greater the fluctuation of the duration of each operation cycle is; the smaller the value of the second discrete degree is, the smaller the fluctuation of the duration of each operation cycle is.

[0101] The process of the server calculating the second discrete degree of the duration of at least one operation cycle in the received behavior information includes: the server calculating the second average value of the duration of the operation cycle in the received behavior information, and calculating the standard deviation of the duration of the operation cycle based on the second average value.

[0102] That is, the server uses the third target formula to calculate the second average value ΔTarg of the duration. The third target formula satisfies:

[0103] ΔTarg=(Tx_1+…+Tx_n) / n;

[0104] Wherein, ΔTarg represents the second average value of the duration of the operation cycle. Tx_1 represents the duration of the first operation cycle. Tx_n represents the duration of the nth operation cycle. n represents the number of operation cycles.

[0105] The server calculates the standard deviation σt of the duration using the fourth target formula based on the second average value. The fourth target formula satisfies:

[0106]

[0107] Wherein, σt represents the standard deviation of the duration of the operation cycle. ΔTarg represents the second average value of the duration of the operation cycle. Tx_1 represents the duration of the first operation cycle. Tx_2 represents the duration of the second operation cycle. Tx_n represents the duration of the nth operation cycle.

[0108] Based on this, the process of determining the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold by the server in step 205 may include: when the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, determining that the information to be pushed is the first information. When the first discrete degree is greater than the second degree threshold, or the second discrete degree is greater than the second degree threshold, determining that the information to be pushed is the second information.

[0109] The value of the first degree threshold σc_valid can reflect the moderate degree of fluctuation of the number of times the target component receives the target operation in multiple operation cycles. The value of the second degree threshold σt_valid can reflect the moderate degree of fluctuation of the duration of multiple operation cycles. The values ​​of the first degree threshold and the second degree threshold can be determined according to actual needs.

[0110] When the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, it indicates that the fluctuation of the number of target operations received for the target component within multiple operation cycles is small, and the fluctuation of the duration of multiple operation cycles is small. The terminal determines that the information to be pushed is the first information. When the first discrete degree is greater than the second degree threshold, or the second discrete degree is greater than the second degree threshold, it indicates that the fluctuation of the number of target operations received for the target component within multiple operation cycles is large, or the fluctuation of the duration of multiple operation cycles is large. Then the terminal determines that the information to be pushed is the second information.

[0111] In summary, the information recommendation method provided by the embodiment of the present application receives the behavior information of the target user sent by the terminal, and the behavior information includes: the relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data at least includes: the number of target operations received by the terminal within at least one operation cycle, and the time interval between two consecutive target operations received by the terminal within the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page within at least one operation cycle, the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, and thus the information to be pushed has a correlation with the user's behavior. Compared with the related art, an information recommendation method with a higher degree of correlation with individual users is implemented.

[0112] In daily life, people may have negative emotions such as anger, depression, and irritability. When people have negative emotions, their behavior often becomes rude. For example, when a user is upset, he or she may click on a component on the page multiple times to vent his or her emotions while using the application. In particular, when the area of ​​the component on the page is small, if the user has negative emotions, he or she is more likely to click on the component repeatedly.

[0113] In this scenario, the information recommendation method provided by the embodiment of the present application can determine the target user's emotional type based on the target user's execution of the target operation in the area where the target component is located in the page. By pushing information corresponding to the target user's emotional type to the target user, the accuracy of information push is improved and the efficiency of information push is improved. For example, when the target user's emotional type is judged to be a bad emotion based on the target user's execution of the target operation on the target component, information for the environment user's emotions (e.g., funny text / audio / video, psychotherapy text / audio / video, etc.) can be pushed to the target user.

[0114] Please refer to Figure 4 , which shows a flow chart of another information recommendation method provided by an embodiment of the present application. The information recommendation method can be applied to Figure 1 In the implementation environment shown. Figure 4 As shown, the information recommendation method includes:

[0115] Step 401: When a terminal receives a target operation performed by a target user in an area where a target component is located in a page, the number of target operations received by the terminal in the area during an operation cycle is recorded. The time interval between two consecutive target operations received by the terminal during the operation cycle is less than a set time length.

[0116] The explanation and implementation of this step can refer to the explanation and implementation of the aforementioned step 201, and will not be elaborated in detail in the embodiment of the present application.

[0117] Step 402: The terminal generates behavior information of the target user. The behavior information includes: data related to the target operation of the target user on the area, and the related data includes: the number of target operations received by the terminal in at least one operation cycle, and the duration of each operation cycle in at least one operation cycle.

[0118] The explanation and implementation of this step can refer to the explanation and implementation of the aforementioned step 202 and related contents, and will not be elaborated in detail in the embodiments of the present application.

[0119] Step 403: The terminal sends the target user's behavior information to the server.

[0120] Step 404: The server calculates a first discrete degree of the number of times in the received behavior information, and calculates a second discrete degree of the duration in the received behavior information.

[0121] The explanation and implementation of this step can refer to the explanation and implementation of the aforementioned step 204 and related contents, and will not be elaborated in detail in the embodiments of the present application.

[0122] Step 405: When the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, determine that the information to be pushed is the first information.

[0123] The explanation and implementation of this step can refer to the explanation and implementation of the aforementioned step 205 and related contents, and will not be elaborated in detail in the embodiments of the present application.

[0124] It should be noted that when the first discrete degree is less than or equal to the first degree threshold, it indicates that the fluctuation of the number of target operations received by the target component in multiple operation cycles is small, which further indicates that the user's repeated operations on the target component in multiple operation cycles are persistent for a long time.

[0125] When the second discrete degree is less than or equal to the second degree threshold, it indicates that the duration fluctuation of multiple operation cycles is small. This indicates that the user's repeated operation on the target component is periodic. And because the time interval between two adjacent target operations in the operation cycle is less than the set duration, it also indicates that the user's repeated operation on the target component is highly intensive.

[0126] Therefore, when the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, it indicates that the user's repeated operation on the target component in multiple operation cycles is long-lasting, periodic, and highly intensive. This further indicates that the user has low patience in performing the target operation on the target component in the multiple operation cycles, and the user's emotion type is a negative emotion. The first information determined by the terminal can be information corresponding to the negative emotion.

[0127] Step 406: When the first discrete degree is greater than the second discrete degree threshold, or when the second discrete degree is greater than the second discrete degree threshold, determine that the information to be pushed is the second information.

[0128] The explanation and implementation of this step can refer to the explanation and implementation of the aforementioned step 205 and related contents, and will not be elaborated in detail in the embodiments of the present application.

[0129] It should be noted that when the first discrete degree is greater than the first degree threshold, it indicates that the number of target operations received by the target component in multiple operation cycles fluctuates greatly, which further indicates that the user's repeated operations on the target component in multiple operation cycles are less stable.

[0130] When the second discrete degree is greater than the second degree threshold, it indicates that the duration of multiple operation cycles fluctuates greatly, which further indicates that the user's repeated operation on the target component is less persistent and less dense.

[0131] Therefore, when the first discrete degree is greater than the second discrete degree threshold, or the second discrete degree is greater than the second discrete degree threshold, it indicates that the user has high patience in performing the target operation on the target component during the multiple operation cycles, and the user's emotion type is a good emotion. Then the second information determined by the terminal can be information corresponding to the good emotion.

[0132] Step 407: The server pushes the information to be pushed to the terminal.

[0133] Optionally, when there are multiple target components, the behavior information includes relevant data corresponding to the multiple target components. Accordingly, the terminal calculates the first discrete degree of the number of target operations received within the operation cycle and the second discrete degree of the duration of the operation cycle for each target component in the behavior information.

[0134] Based on this, step 405 can be replaced by: when the first discrete degree is less than or equal to the first degree threshold, and the number of target components whose second discrete degree is less than or equal to the second degree threshold is greater than or equal to the third target number, determine that the information to be pushed is the first information. When the first discrete degree is less than or equal to the first degree threshold, and the number of target components whose second discrete degree is less than or equal to the second degree threshold is less than the third target number, determine that the information to be pushed is the second information.

[0135] Among them, when the number of target components whose first discrete degree is less than or equal to the first degree threshold and whose second discrete degree is less than or equal to the second degree threshold is greater than or equal to the third target number, it indicates that the number of target components whose fluctuation degree of the number of times the terminal receives the target operation in multiple operation cycles is small is large, indicating that the user's behavior of repeatedly operating multiple target components in multiple operation cycles is long-lasting, periodic, and highly intensive. This further indicates that the user has low patience in performing the target operation on the target component in the multiple operation cycles, and the user's emotion type is negative emotion. Then the first information determined by the terminal can be information corresponding to negative emotion.

[0136] When the number of target components whose first discrete degree is less than or equal to the first degree threshold and whose second discrete degree is less than or equal to the second degree threshold is less than the third target number, it indicates that the number of target components whose fluctuation degree of the number of times the terminal receives the target operation in multiple operation cycles is small is small, indicating that the user's behavior of repeatedly operating more target components in multiple operation cycles is less stable, less persistent, and less intensive. This further indicates that the user has high patience in performing the target operation on the target component in the multiple operation cycles, and the user's emotion type is good emotion. Then the second information determined by the terminal can be information corresponding to good emotion.

[0137] In summary, the information recommendation method provided by the embodiment of the present application receives the behavior information of the target user sent by the terminal, and the behavior information includes: the relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data at least includes: the number of target operations received by the terminal within at least one operation cycle, and the time interval between two consecutive target operations received by the terminal within the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page within at least one operation cycle, the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, and thus the information to be pushed has a correlation with the user's behavior. Compared with the related art, an information recommendation method with a higher degree of correlation with individual users is implemented.

[0138] Further, in the technical solution, the first discrete degree can reflect the fluctuation degree of the number of times the terminal receives the target operation for the target component within multiple operation cycles. The second discrete degree can reflect the fluctuation degree of the duration of multiple operation cycles. In actual applications, the smaller the fluctuation degree of the number of times the terminal receives the target operation for the target component within multiple operation cycles, the longer the persistence of the user's repeated operation on the target component within multiple operation cycles. The smaller the fluctuation degree of the duration of multiple operation cycles, the more periodic and dense the user's repeated operation on the target component is. Therefore, when the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, it is determined that the user's patience in performing the target operation on the target component within the multiple operation cycles is low, and the user's emotion type is bad emotion. Then the first information corresponding to the bad emotion is pushed to the terminal. When the first discrete degree is greater than the second degree threshold, or the second discrete degree is greater than the second degree threshold, it is determined that the user's patience in performing the target operation on the target component within the multiple operation cycles is high, and the user's emotion type is good emotion. Then the second information corresponding to the good emotion is pushed to the terminal. In this way, the target user's emotion type is determined according to the target user's execution of the target operation in the area where the target component is located on the page. By pushing information corresponding to the target user's emotion type to the target user, the accuracy of information push is improved and the efficiency of information push is improved.

[0139] Please refer to Figure 5 , which shows a block diagram of an information recommendation device provided by an embodiment of the present application. Figure 5 As shown, the information recommendation device 500 includes: a receiving module 501 , a calculating module 502 , a determining module 503 and a sending module 504 .

[0140] The receiving module 501 is used to receive the behavior information of the target user sent by the terminal, the behavior information includes: the relevant data of the target operation of the target user on the area where the target component is located in the page, and the relevant data at least includes: the number of target operations received by the terminal in at least one operation cycle, and the time interval between two consecutive target operations received by the terminal in the operation cycle is less than the set time length;

[0141] A calculation module 502, used for calculating a first discrete degree of times;

[0142] A determination module 503, configured to determine the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold;

[0143] The sending module 504 is used to push the information to be pushed to the terminal.

[0144] In an embodiment of the present application, the behavior information of the target user sent by the receiving terminal includes: relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data includes at least: the number of target operations received by the terminal within at least one operation cycle, and the time interval between two consecutive target operations received by the terminal within the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page within at least one operation cycle, the information to be pushed is determined based on the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, and thus the information to be pushed has a correlation with the user's behavior. Compared with the related art, a method for recommending information with a higher degree of correlation with individual users is implemented.

[0145] Optionally, the relevant data also includes: the duration of the operation cycle; the calculation module 502 is further used to calculate the second discrete degree of the duration;

[0146] The determination module 503 is further used for:

[0147] When the first discrete degree is less than or equal to the first degree threshold, and the second discrete degree is less than or equal to the second degree threshold, determining that the information to be pushed is the first information;

[0148] When the first discrete degree is greater than the second discrete degree threshold, or the second discrete degree is greater than the second discrete degree threshold, it is determined that the information to be pushed is the second information.

[0149] Optionally, the first discrete degree is represented by the mean difference, standard deviation or range of the number of times; the second discrete degree is represented by the mean difference, standard deviation or range of the duration.

[0150] Optionally, there are multiple target components, and the behavior information includes: relevant data corresponding to the multiple target components. The determination module 503 is further used to determine the information to be pushed according to the size relationship corresponding to the multiple relevant data.

[0151] Optionally, the determination module 503 is further configured to:

[0152] When the first discrete degrees of the first target quantity are all less than the degree threshold, the information to be pushed is determined to be the first information; when the first discrete degrees of the second target quantity are all greater than the degree threshold, the information to be pushed is determined to be the second information, and the sum of the first target quantity and the second target quantity is the number of target components.

[0153] Optionally, the target component meets at least one of the following conditions:

[0154] The user's operation frequency on the target component is greater than the frequency threshold;

[0155] The area of ​​the target component in the page is smaller than the area threshold;

[0156] The target component is used to trigger the terminal to implement the set function.

[0157] In summary, the information recommendation device provided by the embodiment of the present application receives the behavior information of the target user sent by the terminal, and the behavior information includes: the relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data at least includes: the number of target operations received by the terminal in at least one operation cycle, and the time interval between two adjacent target operations received by the terminal in the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page in at least one operation cycle, the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, and thus the information to be pushed has a correlation with the user's behavior. Compared with the related art, a method for recommending information with a higher degree of correlation with individual users is implemented.

[0158] Please refer to Figure 6 , which shows a block diagram of an information recommendation device provided by an embodiment of the present application. Figure 6 As shown, the information recommendation device 600 includes: a recording module 601 , a generating module 602 and a sending module 603 .

[0159] The recording module 601 is used to record the number of target operations received by the terminal in the area where the target component is located within an operation period when a target operation performed by a target user is received in the area where the target component is located in the page, and the time interval between two consecutive receptions of the target operations by the terminal in the operation period is less than a set time length;

[0160] A generating module 602 is used to generate behavior information of the target user, wherein the behavior information includes: relevant data of the target operation of the target user for the area, wherein the relevant data at least includes: the number of times the terminal receives the target operation in at least one operation cycle;

[0161] The sending module 603 is used to send the behavior information to the server.

[0162] Optionally, the recording module 601 is further used to record the duration of the operation cycle when receiving a target operation performed by a target user in the area where the target component is located in the page; the relevant data also includes: the duration of the operation cycle.

[0163] Optionally, the target component satisfies at least one of the following conditions:

[0164] The user's operation frequency on the target component is greater than a frequency threshold;

[0165] The area of ​​the target component in the page is smaller than the area threshold;

[0166] The target component is used to trigger the terminal to implement a set function.

[0167] In the embodiment provided by the present application, the behavior information of the target user sent by the receiving terminal includes: the relevant data of the target operation of the target user on the area where the target component in the page is located, and the relevant data includes at least: the number of target operations received by the terminal in at least one operation cycle, and the time interval between two consecutive target operations received by the terminal in the operation cycle is less than the set duration. By calculating the first discrete degree of the number of times the target user performs the target operation on the target component in the page in at least one operation cycle, the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, so as to push the information to be pushed to the terminal. In this technical solution, the information to be pushed to the terminal is determined based on the target user's operation behavior on the target component in the page, and thus the information to be pushed has a correlation with the user's behavior. Compared with the related art, a method for recommending information with a higher degree of correlation with individual users is implemented.

[0168] The embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, it includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.

[0169] Memory 703, used for storing computer programs;

[0170] The processor 701 is used to execute the program stored in the memory 703 to implement the following steps:

[0171] receiving behavior information of a target user sent by a terminal, the behavior information including: relevant data of a target operation of the target user on an area where a target component is located in a page, the relevant data including at least: the number of times the terminal receives the target operation in at least one operation cycle, and the time interval between two consecutive times the terminal receives the target operation in the operation cycle is less than a set time length;

[0172] Calculating a first discrete degree of the number of times;

[0173] Determining the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold;

[0174] Pushing the information to be pushed to the terminal.

[0175] Alternatively, implement the following steps:

[0176] When receiving a target operation performed by a target user in the area where the target component is located in the page, the number of target operations received by the terminal in the area during the operation cycle is recorded, and the time interval between two consecutive receptions of the target operations by the terminal during the operation cycle is less than the set time length;

[0177] Generate behavior information of the target user, the behavior information comprising: relevant data of the target operation of the target user on the area, the relevant data at least comprising: the number of times the terminal receives the target operation in at least one operation cycle;

[0178] The behavior information is sent to the server.

[0179] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0180] The communication interface is used for communication between the above terminal and other devices.

[0181] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0182] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0183] In another embodiment provided by the present invention, a computer-readable storage medium is further provided, in which instructions are stored. When the instructions are executed on a computer, the computer executes the steps executed by the terminal in the information recommendation method described in any of the above embodiments. Alternatively, when the instructions are executed on a computer, the computer executes the steps executed by the server in the information recommendation method described in any of the above embodiments.

[0184] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the steps executed by the terminal in any of the information recommendation methods described in the above embodiments. Alternatively, enables the computer to execute the steps executed by the server in any of the information recommendation methods described in the above embodiments.

[0185] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0186] 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. Moreover, the terms "include", "comprise" 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 sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0187] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0188] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An information recommendation method, characterized in that: The method comprises: receiving behavior information of a target user sent by a terminal, the behavior information including: relevant data of a target operation of the target user on an area where a target component is located in a page, the relevant data including at least: the number of times the terminal receives the target operation in at least one operation cycle, and the duration of the operation cycle, wherein the time interval between two consecutive times the terminal receives the target operation in the operation cycle is less than a set duration; Calculating a first discrete degree of the number of times and a second discrete degree of the duration; Determining the information to be pushed according to the magnitude relationship between the first discrete degree and the degree threshold; Pushing the information to be pushed to the terminal, The step of determining the information to be pushed according to the relationship between the first discrete degree and the degree threshold comprises: When the first discrete degree is less than or equal to a first degree threshold, and the second discrete degree is less than or equal to a second degree threshold, determining that the information to be pushed is the first information; When the first discrete degree is greater than the second discrete degree threshold, or when the second discrete degree is greater than the second discrete degree threshold, it is determined that the information to be pushed is the second information.

2. The method according to claim 1, characterized in that: The first discrete degree is represented by the mean difference, standard deviation or range of the number of times; the second discrete degree is represented by the mean difference, standard deviation or range of the duration.

3. The method according to claim 1, characterized in that The number of the target components is multiple, the behavior information includes: relevant data corresponding to the multiple target components, and the information to be pushed is determined according to the relationship between the first discrete degree and the degree threshold, including: The information to be pushed is determined according to the size relationships respectively corresponding to the plurality of related data.

4. The method according to claim 3, characterized in that: The determining the information to be pushed according to the size relationships respectively corresponding to the plurality of related data includes: When the first target number of the first discrete degrees are all smaller than the degree threshold, determining that the information to be pushed is the first information; When the second target quantity and the first discrete degree are both greater than the degree threshold, it is determined that the information to be pushed is the second information, and the sum of the first target quantity and the second target quantity is the quantity of the target components.

5. The method according to claim 1, characterized in that The target component meets at least one of the following conditions: The user's operation frequency on the target component is greater than a frequency threshold; The area of ​​the target component in the page is smaller than the area threshold; The target component is used to trigger the terminal to implement a set function.

6. An information recommendation device, characterized in that: The device comprises: A receiving module, configured to receive behavior information of a target user sent by a terminal, wherein the behavior information includes: relevant data of a target operation of the target user on the area where the target component is located in the page, wherein the relevant data includes at least: the number of times the terminal receives the target operation in at least one operation cycle, and the duration of the operation cycle, wherein the time interval between two consecutive times the terminal receives the target operation in the operation cycle is less than a set duration; A calculation module, used for calculating a first discrete degree of the number of times and a second discrete degree of the duration; A determination module, configured to determine the information to be pushed according to a magnitude relationship between the first discrete degree and a degree threshold; A push module, used to push the information to be pushed to the terminal, Wherein, the determining module is further used for: When the first discrete degree is less than or equal to a first degree threshold, and the second discrete degree is less than or equal to a second degree threshold, determining that the information to be pushed is the first information; When the first discrete degree is greater than the second discrete degree threshold, or when the second discrete degree is greater than the second discrete degree threshold, it is determined that the information to be pushed is the second information.

7. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, configured to implement the method according to any one of claims 1 to 5 when executing a program stored in a memory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images