CN111984869A - Article information pushing method and device, electronic equipment and computer readable medium - Google Patents

Article information pushing method and device, electronic equipment and computer readable medium Download PDF

Info

Publication number
CN111984869A
CN111984869A CN202010863636.4A CN202010863636A CN111984869A CN 111984869 A CN111984869 A CN 111984869A CN 202010863636 A CN202010863636 A CN 202010863636A CN 111984869 A CN111984869 A CN 111984869A
Authority
CN
China
Prior art keywords
information
algorithm
score value
article
algorithm information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010863636.4A
Other languages
Chinese (zh)
Inventor
李志豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Missfresh Ecommerce Co Ltd
Original Assignee
Beijing Missfresh Ecommerce Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Missfresh Ecommerce Co Ltd filed Critical Beijing Missfresh Ecommerce Co Ltd
Priority to CN202010863636.4A priority Critical patent/CN111984869A/en
Publication of CN111984869A publication Critical patent/CN111984869A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/219—Managing data history or versioning

Abstract

The embodiment of the disclosure discloses an article information pushing method and device, electronic equipment and a computer readable medium. One embodiment of the method comprises: acquiring a user behavior log information group set and a recommendation algorithm information set; generating a score value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information in the user behavior log information group corresponding to the recommendation algorithm information to obtain a score value set; selecting a score value meeting a predetermined condition from the score value set as a target score value; selecting algorithm information corresponding to the target score value from all algorithm information included in the recommendation algorithm information set as target algorithm information; and pushing the information of each recommended article corresponding to the target algorithm information to display equipment. The implementation mode improves the interest degree of the related users in the received recommended item information, so that the time for searching the item information on the Internet by the related users is reduced.

Description

Article information pushing method and device, electronic equipment and computer readable medium
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to an article information pushing method, an article information pushing device, electronic equipment and a computer readable medium.
Background
With the development of internet technology and electronic commerce, the article information shows an explosive growth trend, and the article information push technology is also in the process of transportation. The article information pushing technology refers to a technology for actively pushing article information for a user. At present, when pushing article information, the mode that usually adopts is: firstly, determining an algorithm for recommending article information, and recommending the article information for related users by using the algorithm; then, evaluating the algorithm respectively from three aspects of clicking article information webpage link, browsing article information webpage duration and article circulation to obtain three evaluation results; and finally, generating recommended article information by adopting the algorithm in response to the fact that the three evaluation results meet the preset conditions, and pushing the recommended article information to the user.
However, when the above-mentioned manner is adopted for pushing the article information, the following technical problems often exist:
firstly, the range of the algorithm for recommending the article information is single, and when the evaluation result is determined, the comprehensive influence on the evaluation result in the aspects of clicking article information webpage link, browsing article information webpage duration and article circulation is not utilized. Furthermore, the item information is recommended by adopting a determined algorithm, and the possibility that the recommended item information is low in likeability exists. Users expect to be able to receive recommended item information of more interest, thereby reducing the time period for searching for item information on the internet.
Secondly, the influence of interaction among three aspects of clicking item information webpage link, browsing item information webpage duration and item circulation on the evaluation result cannot be utilized, and the comprehensiveness and objectivity of the evaluation result need to be improved.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a method, an apparatus, an electronic device and a computer-readable medium for pushing item information to solve one or more of the technical problems mentioned in the above background section.
In a first aspect, some embodiments of the present disclosure provide a method for pushing item information, where the method includes: acquiring a user behavior log information group set and a recommendation algorithm information set, wherein a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information comprises click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information comprises algorithm information and a recommended article information set; generating a scoring value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information for algorithm information included in each recommendation algorithm information of the recommendation algorithm information set to obtain a scoring value set; selecting a score value meeting a preset condition from the score value set as a target score value; selecting algorithm information corresponding to the target score value from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information; and pushing each piece of recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information.
In a second aspect, some embodiments of the present disclosure provide an article information pushing device, including: the system comprises an acquisition unit, a recommendation processing unit and a recommendation processing unit, wherein the acquisition unit is configured to acquire a user behavior log information group set and a recommendation algorithm information set, a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information comprises click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information comprises algorithm information and recommended article information; a generating unit configured to generate a score value of the algorithm information based on each click operation information, each browsing duration information, and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information, for algorithm information included in each recommendation algorithm information of the recommendation algorithm information set, to obtain a score value set; a first selection unit configured to select, as a target score value, a score value that meets a predetermined condition from the score value set; a second selection unit configured to select, as target algorithm information, algorithm information corresponding to the target score value from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set; and the pushing unit is configured to push each piece of recommended article information of a recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information.
In some embodiments, the generating a scoring value of the algorithm information based on the click rate, the mean value, the item flow operation amount, and the number of the user behavior log information includes:
inputting the click quantity, the average value, the article circulation operation quantity and the user behavior log information into the following formula to generate the score value of the algorithm information:
Figure BDA0002649007930000031
wherein i represents the serial number of the recommendation algorithm information in the recommendation algorithm information set, SiThe value of the score of the algorithm information included in the ith recommendation algorithm information is represented, X represents the click rate, L represents the number of the user behavior log information, Y represents the article circulation operation amount, and Z represents the mean value.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement the method as described in the first aspect.
In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in the first aspect.
The above embodiments of the present disclosure have the following advantages: firstly, for algorithm information included in each piece of recommendation algorithm information of an acquired recommendation algorithm information set, generating a score value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each piece of user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information, and obtaining a score value set. Therefore, the method and the device can comprehensively utilize each click operation information, each browsing duration information and each article circulation operation information to quantitatively evaluate each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set. Then, a score value meeting a predetermined condition is selected from the above score value set as a target score value. And then, selecting algorithm information corresponding to the target score value from the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information. Therefore, according to the quantitative evaluation of each algorithm information, the algorithm information with the grade value meeting the preset condition is selected from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as the target algorithm information. And finally, pushing each piece of recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information. Therefore, the method and the device can enable the related users to acquire the recommended article information. Furthermore, the method and the device can improve the interest degree of the related users in the received recommended article information, so that the time for searching article information on the Internet by the users is reduced.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
Fig. 1 is a schematic diagram of an application scenario of an item information pushing method of some embodiments of the present disclosure;
fig. 2 is a flow diagram of some embodiments of an item information push method according to the present disclosure;
fig. 3 is a flow chart of further embodiments of an item information push method according to the present disclosure;
fig. 4 is a schematic structural diagram of some embodiments of an item information pushing device according to the present disclosure;
FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of an item information pushing method according to some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may obtain a set of user behavior log information groups 102 and a set of recommendation algorithm information 103. Then, for the algorithm information included in each recommendation algorithm information in the recommendation algorithm information set 103, the computing device 101 may generate a score value of the algorithm information based on each click operation information, each browsing duration information, and each article circulation operation information of each user behavior log information in the user behavior log information group corresponding to the recommendation algorithm information, so as to obtain a score value set 104. Then, the computing device 101 may select, as the target score value 105, a score value that meets a predetermined condition from the above-described score value set 104. Then, the computing device 101 may select, as the target algorithm information 106, algorithm information corresponding to the target score value 105 from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set 103. Finally, the computing device 101 may push each piece of recommended item information 107 of the recommended item information set included in the recommended algorithm information corresponding to the target algorithm information 106 to each display device 108 having a display function, respectively, so that a relevant user can implement an item circulation operation according to the recommended item information.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.
With continued reference to fig. 2, a flow 200 of some embodiments of an item information push method according to the present disclosure is shown. The item information pushing method comprises the following steps:
step 201, obtaining a user behavior log information group set and a recommendation algorithm information set.
In some embodiments, an executing entity (e.g., the computing device 101 shown in fig. 1) of the item information pushing method may obtain the user behavior log information group set and the recommendation algorithm information set from the terminal through a wired connection manner or a wireless connection manner. And the user behavior log information groups in the user behavior log information group set correspond to the recommendation algorithm information in the recommendation algorithm information set one by one. The user behavior log information includes click operation information, browsing duration information, and article circulation operation (e.g., purchase operation) information. The recommendation algorithm information comprises algorithm information and a recommended article information set. The above algorithm information refers to information characterizing an algorithm for recommending item information. The recommended item information set is a set of information on recommended items generated by executing the algorithm for recommending item information. The user behavior log information group refers to a set of user behavior information triggered after the algorithm for recommending the article information is run. The user behavior log information refers to behavior information of a user triggered after the algorithm for recommending the article information is run. The click operation information refers to behavior information of clicking a webpage link representing the recommended article information by a user on a webpage where the recommended article information is located. The browsing duration information is duration for the user to browse page content on the webpage represented by the webpage link in response to the user clicking the webpage link. The article circulation operation information is used for describing circulation operation of recommended articles, which is implemented by the user aiming at the recommended articles represented by the recommended article information in response to the user clicking the webpage link, and comprises information related to the circulation operation.
As an example, the user behavior log information set may be [ [ [ yes, 10, yes ], [ yes, 4, no ], [ yes, 2, yes ], [ no, 0, no ] ], [ [ yes, 2, no ], [ yes, 6, yes ], [ yes, 10, no ], [ yes, 8, no ] ], [ [ yes, 4, yes ], [ no, 0, no ], [ yes, 2, no ], [ no, 0, no ] ]. The recommended set of algorithm information may be [ algorithm 001, [ skim milk, whole wheat bread, raw pork, baby dish ] ], [ algorithm 002, [ whole wheat bread, raw pork, purple potato, raw pork ] ], [ algorithm 003, [ skim milk, purple potato, whole wheat bread, raw pork ] ]. The 1 st user behavior log information group [ [ yes, 10, yes ], [ yes, 4, no ], [ yes, 2, yes ], [ no, 0, no ] ] in the user behavior log information group corresponds to the 1 st recommended algorithm information [ algorithm 001, [ skim milk, whole wheat bread, raw pork, baby dish ] ] in the recommended algorithm information group, and after the [ algorithm 001] is operated, the click operation information of the relevant user to the recommended article information [ skim milk ] in the 1 st user behavior log information group [ yes, 10, yes ], the browsing time length information to the recommended article information [ skim milk ] is [10], and the article circulation operation information to the recommended article information [ skim milk ] is [ yes ]; the click operation information of the 2 nd user behavior log information [ yes, 4, no ] in the 1 st user behavior log information group on the recommended article information [ wholewheat bread ] by the relevant user is [ yes ], the browsing duration information on the recommended article information [ wholewheat bread ] is [4], and the article circulation operation information on the recommended article information [ wholewheat bread ] is [ no ]. The click operation information of the 3 rd user behavior log information [ yes, 2, yes ] in the 1 st user behavior log information group to the recommended item information [ raw pork ] by the relevant user is [ yes ], the browsing duration information to the recommended item information [ raw pork ] is [2], and the item transfer operation information to the recommended item information [ raw pork ] is [ yes ]. The click operation information of the 4 th user behavior log information [ no, 0, no ] in the 1 st user behavior log information group on the recommended article information [ baby dish ] by the relevant user is [ no ], the browsing duration information on the recommended article information [ baby dish ] is [0], and the article transfer operation information on the recommended article information [ baby dish ] is [ no ]. The 2 nd user behavior log information group in the user behavior log information group set corresponds to the 2 nd recommendation algorithm information in the recommendation algorithm information set. The 3 rd user behavior log information group in the user behavior log information group set corresponds to the 3 rd recommendation algorithm information in the recommendation algorithm information set. The [ algorithm 001] in the 1 st recommended algorithm information [ algorithm 001, [ skim milk, whole wheat bread, raw pork, baby cabbage ] ] represents the algorithm information. The [ skim milk, whole wheat bread, raw pork, baby cabbage ] in the 1 st recommended algorithm information [ algorithm 001, [ skim milk, whole wheat bread, raw pork, baby cabbage ] represents the recommended item information set.
Step 202, for the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set, generating a score value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each user behavior log information in the user behavior log information group corresponding to the recommendation algorithm information, and obtaining a score value set.
In some embodiments, for the algorithm information included in each piece of recommendation algorithm information of the recommendation algorithm information set, based on each piece of click operation information, each piece of browsing duration information, and each piece of article circulation operation information of each piece of user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information, the execution main body may generate a score value of the algorithm information by the following steps, so as to obtain a score value set:
first, the number of click operation information items whose click operation information items include [ yes ] is divided by the number of click operation information items included in each click operation information item, thereby generating a click operation rate. The above-mentioned click operation rate can retain two decimal places.
As an example, the user behavior log information group corresponding to the 1 st recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 is [ [ yes, 10, yes][ yes, 4, no]And is 2 is]And no, 0, no]]. On the upper part4 click operation information in 4 user behavior log information in the user behavior log information group is [ yes ]]Is]Is][ NO)]. The click operation information included in the 4-click operation information is [ yes ]]The number of pieces of click operation information of (2) is 3. The number of click operation information included in the 4-click operation information is 4. The click operation rate can be reserved with two decimal places. The click operation rate generated by the execution subject is
Figure BDA0002649007930000081
And secondly, determining the sum of the browsing time length information, and taking the sum as the sum of the browsing time lengths.
As an example, the user behavior log information sets corresponding to the 1 st recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 are [ [ yes, 10, yes ], [ yes, 4, no ], [ yes, 2, yes ], [ no, 0, no ] ]. The sum of the browsing duration information of 4 pieces of user behavior log information in the user behavior log information group is 10+4+2+0 — 16. And 16 is taken as the sum of the browsing durations.
And thirdly, determining the product of the number of the browsing duration information included in each browsing duration information and the preset browsing duration. The preset browsing duration represents the average duration of the webpage browsed by the user on the webpage where the recommended article information which is interested by the user is located. Here, the setting of the predetermined browsing time period is not limited.
As an example, the predetermined browsing time period may be 5. The user behavior log information group corresponding to the 1 st recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 is [ [ yes, 10, yes ], [ yes, 4, no ], [ yes, 2, yes ], [ no, 0, no ] ]. The number of browsing duration information included in 4 browsing duration information of 4 user behavior log information in the user behavior log information group is 4. The execution subject may determine a product of the number 4 of the browsing time length information included in each of the browsing time length information and a predetermined browsing time length 5. The product was determined to be 4 × 5 ═ 20.
And fourthly, dividing the sum of the browsing duration and the product to generate a browsing duration ratio. The browsing time length ratio can be reserved with two decimal numbers.
As an example, the execution subject may divide the sum 16 of the browsing time durations in the second step example by the product 20 in the third step example. The generated browsing time length ratio can keep two decimal parts. The browsing duration ratio generated by the execution subject is
Figure BDA0002649007930000091
And a fifth step of dividing the number of the article circulation operation information in which the article circulation operation information included in each article circulation operation information is [ yes ] by the number of the article circulation operation information included in each article circulation operation information to generate an article circulation operation rate. The article circulation operation rate can be reserved with two decimal places.
As an example, the user behavior log information group corresponding to the 1 st recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 is [ [ yes, 10, yes][ yes, 4, no]And is 2 is]And no, 0, no]]. 4 article circulation operation information in 4 user behavior log information in the user behavior log information group is [ yes ]][ NO)]Is][ NO)]. The article circulation operation information included in the 4 article circulation operation information items is [ yes ]]The number of article circulation operation information of (2). The number of article circulation operation information included in the 4 article circulation operation information is 4. The resulting article circulation operation rate can be reserved for two decimals. The article circulation operation rate generated by the execution body is
Figure BDA0002649007930000092
Sixthly, generating the scoring value of the algorithm information by using the following formula:
Figure BDA0002649007930000093
wherein i represents the recommendation algorithm information set recommendation calculationThe serial number of the legal information. SiAnd a score value representing algorithm information included in the ith recommendation algorithm information. A represents the click operation rate. And B represents the browsing time length ratio. C represents the above article circulation operation rate. The above scoring values may retain two decimal places.
As an example, the execution subject may generate the algorithm information [ algorithm 001] included in the 1 st recommended algorithm information in the recommended algorithm information set illustrated in step 201]Value of (S)1. A was 0.75. B was 0.80. C is 0.50. The generated score value may retain two decimals. Then
Figure BDA0002649007930000101
And seventhly, obtaining a score value set.
As an example, for the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set illustrated in step 201, the executing entity may generate the score value of the algorithm information according to the first step to the sixth step. Generated [ Algorithm 001]Value of (S)1Was 68.33. Generated [ Algorithm 002]Value of (S)2It was 93.33. Generated [ Algorithm 003]]Value of (S)3It was 35.00. The resulting score set was [68.33, 93.33, 35.00]]。
Through step 202, each piece of algorithm information included in each piece of recommendation algorithm information of the recommendation algorithm information set can be quantitatively evaluated by using each piece of click operation information, each piece of browsing duration information, and each piece of article circulation operation information.
Step 203, selecting the score value meeting the predetermined condition from the score value set as a target score value.
In some embodiments, the predetermined condition may be "a highest value of the score value", and the executing subject may select a highest value of the score value target score value from the score value set.
As an example, the executing entity may select a score value with the largest value from the set of score values [68.33, 93.33, 35.00] exemplified in step 202. The highest score value of the above values is [93.33 ]. The value of [93.33] was taken as the target score.
And 204, selecting algorithm information corresponding to the target score value from the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information.
In some embodiments, the executing body may select, as the target algorithm information, algorithm information corresponding to the target score value from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set. In this way, algorithm information having a score value that meets a predetermined condition can be selected as target algorithm information from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set according to the quantitative evaluation of the respective algorithm information.
As an example, the 3 pieces of algorithm information included in each piece of recommended algorithm information of the recommended algorithm information set exemplified in step 201 are [ algorithm 001], [ algorithm 002], [ algorithm 003], respectively. The execution subject may select algorithm information corresponding to the target score value [93.33] exemplified in step 203 from among the 3 algorithm information. The algorithm information corresponding to the target score value [93.33] exemplified in step 203 is [ algorithm 002 ]. The [ algorithm 002] can be used as the target algorithm information.
Step 205, pushing each recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function, so that a relevant user can implement article circulation operation according to the recommended article information.
In some embodiments, the executing entity may first determine recommendation algorithm information corresponding to the target algorithm information, and then may determine a recommended item information set included in the recommendation algorithm information. And finally, pushing each piece of recommended article information of the recommended article information set to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information. Therefore, the related user can be made to acquire the recommended article information. The article circulation operation refers to an operation performed by the user to circulate the recommended article with respect to the recommended article represented by the recommended article information.
As an example, the execution subject may first determine recommended algorithm information corresponding to the target algorithm information [ algorithm 002] illustrated in step 204. The recommended algorithm information corresponding to the algorithm 002 is algorithm 002, [ whole wheat bread, raw pork, purple sweet potato, raw pork ] ]. Then, a recommended item information set included in recommended algorithm information [ algorithm 002, [ whole wheat bread, raw pork, purple sweet potato, raw pork ] ] can be determined. The recommended item information set included in the recommended algorithm information [ algorithm 002, [ wholewheat bread, raw pork, purple sweet potato, raw pork ] is [ wholewheat bread, raw pork, purple sweet potato, raw pork ]. Finally, the 4 pieces of recommended item information of the recommended item information set [ wholewheat bread, raw pork, purple sweet potato, raw pork ] can be pushed to the 4 display devices "XS 001", "XS 002", "XS 003", and "XS 004" with display functions, respectively, so that the user "YH 001" related to the display device "XS 001", the user "YH 002" related to the display device "XS 002", the user "YH 003" related to the display device "XS 003", and the user "YH 004" related to the display device "XS 004" can be subjected to item transfer operations according to the recommended item information [ wholewheat bread ], [ raw pork ], [ purple sweet potato ], [ raw pork ], respectively.
The above embodiments of the present disclosure have the following advantages: firstly, for algorithm information included in each piece of recommendation algorithm information of an acquired recommendation algorithm information set, generating a score value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each piece of user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information, and obtaining a score value set. Therefore, the method and the device can comprehensively utilize each click operation information, each browsing duration information and each article circulation operation information to quantitatively evaluate each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set. Then, a score value meeting a predetermined condition is selected from the above score value set as a target score value. And then, selecting algorithm information corresponding to the target score value from the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information. Therefore, according to the quantitative evaluation of each algorithm information, the algorithm information with the grade value meeting the preset condition is selected from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as the target algorithm information. And finally, pushing each piece of recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information. Therefore, the method and the device can enable the related users to acquire the recommended article information. Furthermore, the method and the device can improve the interest degree of the related users in the received recommended article information, so that the time for searching article information on the Internet by the users is reduced.
With further reference to fig. 3, a flow 300 of further embodiments of an item information push method is illustrated. The flow 300 of the item information pushing method includes the following steps:
step 301, obtaining a user behavior log information group set and a recommendation algorithm information set.
In some embodiments, the specific implementation of step 301 and the technical effect brought by the implementation may refer to step 201 in those embodiments corresponding to fig. 2, and are not described herein again.
Step 302, performing normalization processing on each browsing duration information to generate a normalized browsing duration information set.
In some embodiments, the executing entity may first generate the normalized browsing duration information set by:
the first step is to determine the maximum value of the browsing duration information included in each browsing duration information.
And secondly, determining the minimum value of the browsing duration information included in each piece of browsing duration information.
Thirdly, generating normalized browsing duration information of the browsing duration information by using the following formula based on the maximum value and the minimum value for each browsing duration information in each browsing duration information:
Figure BDA0002649007930000131
wherein t represents the sequence number of the browsing duration information in each browsing duration information. ltAnd indicating the t-th browsing duration information in each browsing duration information. G (l)t) Is represented bytThe normalized browsing duration information of (1). P represents the minimum value of the browsing duration information included in each of the browsing duration information. O represents the maximum value of the browsing time length information included in each of the browsing time length information. Therefore, normalization processing can be performed on each browsing duration information in each browsing duration information to obtain a normalized browsing duration information set.
As an example, the 2 nd user behavior log information group [ [ Yes, 2, No ] in the user behavior log information group set exemplified in step 201]And [ is, 6 is][ yes, 10, no][ yes, 8, no]]The browsing time length information is [2]]，[6]，[10]，[8]. The execution subject may view the respective browsing duration information [2]]，[6]，[10]，[8]And carrying out normalization processing on each browsing time length information. The maximum value of the browsing duration information included in the 4 browsing duration information may be determined. The maximum value is [10]]. The minimum value of the browsing duration information included in the 4 browsing duration information may be determined. The above minimum value is [2]]. Generated 1 st browsing duration information [2]]Normalized browsing duration information of
Figure BDA0002649007930000132
Generated 2 nd browsing duration information [6 ]]Normalized browsing duration information of
Figure BDA0002649007930000133
Generated 3 rd browsing duration information [10]Normalized browsing duration information of
Figure BDA0002649007930000134
Generated 4 th browsing duration information [8 ]]Normalized browsing duration informationIs composed of
Figure BDA0002649007930000135
The obtained normalized browsing time length information set is [0, 0.5, 1, 0.75]]。
And 303, generating click volume based on the click operation information.
In some embodiments, an executing subject (e.g., the computing device 101 shown in fig. 1) of the item information pushing method may determine the number of click operation information whose click operation information is [ yes ] included in each of the click operation information. The number of pieces of click operation information having click operation information [ yes ] included in each piece of click operation information is used as the click amount.
As an example, the user behavior log information sets corresponding to the 2 nd recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 are [ [ yes, 2, no ], [ yes, 6, yes ], [ yes, 10, no ], [ yes, 8, no ] ]. The 4 click operation information in the 4 pieces of user behavior log information in the user behavior log information group are [ yes ], and [ yes ], respectively. The number of click operation information items whose click operation information items included in the 4-click operation information item are [ yes ] is 4. The click volume may be 4.
And 304, determining the average value of each normalized browsing duration information in the normalized browsing duration information set.
In some embodiments, the execution subject may first determine a sum of the normalized browsing-time-length information included in the normalized browsing-time-length information set. Then, the number of the normalized browsing duration information included in the normalized browsing duration information set may be determined. And secondly, dividing the sum of the normalized browsing time length information by the number of the normalized browsing time length information to generate a ratio. Finally, the ratio may be used as an average value of each normalized browsing duration information in the normalized browsing duration information set.
As an example, the execution subject may first determine the sum of the normalized browsing-time-length information included in the normalized browsing-time-length information set [0, 0.5, 1, 0.75] illustrated in step 303. The sum of the normalized viewing duration information is 2.25. Then, the execution subject may determine the number of pieces of normalized browsing-time-length information included in the normalized browsing-time-length information set [0, 0.5, 1, 0.75] exemplified in step 303. The number of the normalized browsing time length information is 4. Next, the execution subject may divide the sum of the normalized viewing time length information 2.25 by the number of the normalized viewing time length information 4 to generate a ratio of 0.5625. Finally, the executing body may use the generated ratio of 0.5625 as a mean value of each normalized browsing duration information in the normalized browsing duration information set. The average value of the normalized viewing time length information is 0.5625.
Step 305, generating article circulation operation amount based on the article circulation operation information.
In some embodiments, the executing body may determine the number of the article circulation operation information whose article circulation operation information included in each article circulation operation information is [ yes ]. The number of article transfer operation information items whose article transfer operation information items included in the article transfer operation information items are [ yes ] is used as the article transfer operation amount.
As an example, the user behavior log information sets corresponding to the 2 nd recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 are [ [ yes, 2, no ], [ yes, 6, yes ], [ yes, 10, no ], [ yes, 8, no ] ]. The 4 article circulation operation information items in the 4 pieces of user behavior log information in the user behavior log information group are respectively no, yes, no and no. The number of article circulation operation information items whose article circulation operation information items included in the 4 article circulation operation information items are [ yes ] is 1. The execution body may take 1 as the article circulation operation amount.
Step 306, determining the number of the user behavior log information included in the user behavior log information group.
In some embodiments, the execution subject may determine an amount of user behavior log information included in the user behavior log information group.
As an example, the user behavior log information sets corresponding to the 2 nd recommendation algorithm information in the recommendation algorithm information set exemplified in step 201 are [ [ yes, 2, no ], [ yes, 6, yes ], [ yes, 10, no ], [ yes, 8, no ] ]. The number of user behavior log information included in the user behavior log information group is 4.
And 307, generating a score value of the algorithm information based on the click quantity, the average value, the article circulation operation quantity and the quantity of the user behavior log information.
In some embodiments, the executing entity may input the click rate, the average value, the article circulation operation amount, and the amount of the user behavior log information into the following formula, and generate a score value of the algorithm information:
Figure BDA0002649007930000151
wherein i represents the serial number of the recommendation algorithm information in the recommendation algorithm information set. SiAnd a score value representing algorithm information included in the ith recommendation algorithm information. X represents the click rate. L represents the number of the user behavior log information. Y represents the above-mentioned article circulation operation amount. Z represents the above average value. The above scoring values may retain two decimal places.
As an example, for the 2 nd recommendation algorithm information in the recommendation algorithm information set illustrated in step 201, the executing entity may input the click rate 4 illustrated in step 302, the average value 0.56 illustrated in step 304, the item circulation operation amount 1 illustrated in step 305, and the number 4 of user behavior log information illustrated in step 306 into a formula for generating the score value of the above algorithm information. The score value of the 2 nd recommendation algorithm information may be reserved with two decimal places. The score of the 2 nd algorithm information may be obtained as
Figure BDA0002649007930000161
Through the steps 302-307, the percentage evaluation value of the algorithm information can be generated by utilizing the mutual influence among three aspects of clicking the item information webpage link, browsing the item information webpage and article circulation, so that the evaluation value can represent the evaluation result of the algorithm information comprehensively and objectively. Therefore, the comprehensiveness and objectivity of the evaluation value are improved. The formula for generating the scoring value of the algorithm information is one aspect of the embodiment of the present disclosure. The ratio of the operation amount of the article circulation to the click amount is processed, and the influence between the click article information webpage link and the article circulation is considered. The click rate, the average value, the article circulation operation amount and the sum of the click rate, the average value and the article circulation operation amount are processed in a ratio mode, and the interaction effects among the three aspects of clicking article information webpage link, browsing article information webpage time and article circulation are considered. Thus, the comprehensiveness of the evaluation value is improved. The average value processing is carried out on the ratio of the click quantity, the average value, the sum of the article circulation operation quantity and the click quantity, the average value and the sum of the article circulation operation quantity to one third, and the mutual influence among the aspects of clicking article information webpage link, browsing article information webpage duration and article circulation is balanced. Therefore, the objectivity of the evaluation value is improved. Therefore, the technical problem II mentioned in the background technology is solved, namely the influence of the interaction among the three aspects of clicking the item information webpage link, browsing the item information webpage time and item circulation on the evaluation result cannot be utilized, and the comprehensiveness and objectivity of the evaluation result are to be improved.
And 308, sequencing each score value in the score value set in a descending order mode to obtain a score value sequence.
In some embodiments, the execution subject may sort the score values in the score value set in descending order to obtain a score value sequence.
As an example, according to steps 302-307, the executing agent may generate a score value of each piece of recommendation algorithm information in the recommendation algorithm information set illustrated in step 201, and the obtained score value set is [58.35, 66.95, 46.21 ]. The execution subject may sort the respective score values in the score value sets [58.35, 66.95, 46.21] in descending order. The resulting score series was [66.95, 58.35, 46.21 ].
Step 309, selecting the score value meeting the predetermined condition from the score value sequence as the target score value.
In some embodiments, the execution subject may select a score value satisfying a predetermined condition from the score value sequence as a target score value. The predetermined condition may be "the first score value".
As an example, the execution subject may select the score value as the first score value from the score value sequence [66.95, 58.35, 46.21] exemplified in step 308. The above-mentioned score value, which is the first score value, is [66.95 ]. The execution subject may take [66.95] as the target score value.
Through steps 308-309, the executing entity may first sort the score values in the score value set in descending order to obtain a score value sequence. Therefore, the scoring value sequence can indirectly represent the likeness degree of the recommended article information pushed by adopting the various algorithm information. Then, the execution subject may select a first score value in the sequence from the score value sequence as a target score value. Therefore, recommended article information can be pushed for the user according to the algorithm information corresponding to the target score value, and support is provided for improving the interest degree of the relevant user in the received recommended article information and reducing the time for searching article information on the Internet by the relevant user.
Step 310, selecting algorithm information corresponding to the target score value from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information.
Step 311, pushing each recommended item information of the recommended item information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function, so that a relevant user can implement an item circulation operation according to the recommended item information.
In some embodiments, the detailed implementation and technical effects of steps 310 to 311 may refer to steps 204 to 205 in those embodiments corresponding to fig. 2, and are not described herein again.
One of the above-described various embodiments of the present disclosure has the following advantageous effects: first, the click amount is generated based on the click operation information. Then, each browsing duration information in each browsing duration information is normalized to generate normalized browsing duration information, and a normalized browsing duration information set is obtained. And then, determining the average value of each normalized browsing time length information in the normalized browsing time length information set. Next, an article circulation operation amount is generated based on the article circulation operation information. Secondly, the number of the user behavior log information included in the user behavior log information group is determined. And then, generating a scoring value of the algorithm information based on the click quantity, the average value, the article circulation operation quantity and the quantity of the user behavior log information. Therefore, the evaluation value of the algorithm information can be generated by utilizing the mutual influence among three aspects of clicking the item information webpage link, browsing the item information webpage and article circulation, so that the evaluation result of the algorithm information can be represented comprehensively and objectively by the evaluation value. Further, the comprehensiveness and objectivity of the evaluation value are improved. The formula for generating the scoring value of the algorithm information is one aspect of the embodiment of the present disclosure. The ratio of the operation amount of the article circulation to the click amount is processed, and the influence between the click article information webpage link and the article circulation is considered. The click rate, the average value, the article circulation operation amount and the sum of the click rate, the average value and the article circulation operation amount are processed in a ratio mode, and the interaction effects among the three aspects of clicking article information webpage link, browsing article information webpage time and article circulation are considered. Thus, the comprehensiveness of the evaluation value is improved. The average value processing is carried out on the ratio of the click quantity, the average value, the sum of the article circulation operation quantity and the click quantity, the average value and the sum of the article circulation operation quantity to one third, and the mutual influence among the aspects of clicking article information webpage link, browsing article information webpage duration and article circulation is balanced. Therefore, the objectivity of the evaluation value is improved. Therefore, the technical problem II mentioned in the background technology is solved, namely the influence of the interaction among the three aspects of clicking the item information webpage link, browsing the item information webpage time and item circulation on the evaluation result cannot be utilized, and the comprehensiveness and objectivity of the evaluation result are to be improved. And then, performing descending order arrangement on the score values in the score value set to obtain a score value sequence. Therefore, the scoring value sequence can indirectly represent the likeness degree of the recommended article information pushed by adopting the various algorithm information. Next, the first score value in the sequence is selected from the above score value sequence as a target score value. Therefore, recommended article information can be pushed for the user according to the algorithm information corresponding to the target score value, and support is provided for improving the interest degree of the relevant user in the received recommended article information and reducing the time for searching article information on the Internet by the relevant user.
With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an article information pushing device, which correspond to those shown in fig. 2, and which can be applied in various electronic devices.
As shown in fig. 4, the item information pushing apparatus 400 of some embodiments includes: an acquisition unit 401, a generation unit 402, a first selection unit 403, a second selection unit 404, and a push unit 405. The obtaining unit 401 is configured to obtain a user behavior log information group set and a recommendation algorithm information set, where a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information includes click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information includes algorithm information and recommended article information; the generating unit 402 is configured to generate a score value of the algorithm information based on each click operation information, each browsing duration information, and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information, for algorithm information included in each recommendation algorithm information of the recommendation algorithm information set, so as to obtain a score value set; the first selection unit 403 is configured to select, as a target score value, a score value that meets a predetermined condition from the above-described score value set; the second selecting unit 404 is configured to select, as target algorithm information, algorithm information corresponding to the target score value from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set; the pushing unit 405 is configured to push each piece of recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function, respectively, so that a relevant user performs an article circulation operation according to the recommended article information.
In an optional implementation manner of some embodiments, the first selecting unit 403 of the item information pushing device 400 is further configured to: sorting the score values in the score value set in a descending order to obtain a score value sequence; and selecting a score value meeting a preset condition from the score value sequence as a target score value.
It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.
Referring now to FIG. 5, a block diagram of an electronic device (e.g., computing device 101 of FIG. 1)500 suitable for use in implementing some embodiments of the present disclosure is shown. The server shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the apparatus; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a user behavior log information group set and a recommendation algorithm information set, wherein a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information comprises click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information comprises algorithm information and a recommended article information set; generating a scoring value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information for algorithm information included in each recommendation algorithm information of the recommendation algorithm information set to obtain a scoring value set; selecting a score value meeting a preset condition from the score value set as a target score value; selecting algorithm information corresponding to the target score value from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information; and pushing each piece of recommended article information of the recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a generation unit, a first selection unit, a second selection unit, and a pushing unit. Here, the names of the units do not constitute a limitation to the unit itself in some cases, and for example, the first selection unit may also be described as a "unit that selects a score value that meets a predetermined condition from the above-described score value set as a target score value".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims (8)

1. An item information pushing method, comprising:
acquiring a user behavior log information group set and a recommendation algorithm information set, wherein a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information comprises click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information comprises algorithm information and a recommended article information set;
generating a scoring value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information for algorithm information included in each recommendation algorithm information of the recommendation algorithm information set to obtain a scoring value set;
selecting a score value meeting a preset condition from the score value set as a target score value;
selecting algorithm information corresponding to the target score value from each algorithm information included in each recommendation algorithm information of the recommendation algorithm information set as target algorithm information;
and pushing each piece of recommended article information of a recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so that a related user can implement article circulation operation according to the recommended article information.
2. The method according to claim 1, wherein the generating of the score value of the algorithm information for the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set based on each click operation information, each browsing duration information, and each article circulation operation information of each user behavior log information in the user behavior log information group corresponding to the recommendation algorithm information comprises:
normalizing each browsing duration information to generate a normalized browsing duration information set;
and generating a score value of the algorithm information based on each click operation information, the normalized browsing time length information set and each article circulation operation information.
3. The method according to claim 2, wherein the generating of the score value of the algorithm information based on the respective click operation information, the normalized browsing duration information set, and the respective item circulation operation information includes:
generating click rate based on each click operation information;
determining the average value of each normalized browsing duration information in the normalized browsing duration information set;
generating article circulation operation amount based on the article circulation operation information;
determining the number of user behavior log information included in the user behavior log information group;
and generating a scoring value of the algorithm information based on the click quantity, the average value, the article circulation operation quantity and the quantity of the user behavior log information.
4. The method according to claim 3, wherein the normalizing the respective browsing-time-length information to generate a normalized browsing-time-length information set comprises:
determining the maximum value of the browsing duration information included in each browsing duration information;
determining the minimum value of the browsing duration information included in each browsing duration information;
and normalizing each browsing duration information in each browsing duration information based on the maximum value and the minimum value to generate normalized browsing duration information, so as to obtain a normalized browsing duration information set.
5. The method of claim 4, wherein said selecting a score value from the set of score values that meets a predetermined condition as a target score value comprises:
sorting the score values in the score value set in a descending order to obtain a score value sequence;
and selecting a score value meeting a preset condition from the score value sequence as a target score value.
6. An article information pushing device comprises:
the system comprises an acquisition unit, a recommendation processing unit and a recommendation processing unit, wherein the acquisition unit is configured to acquire a user behavior log information group set and a recommendation algorithm information set, a user behavior log information group in the user behavior log information group set corresponds to recommendation algorithm information in the recommendation algorithm information set one by one, the user behavior log information comprises click operation information, browsing duration information and article circulation operation information, and the recommendation algorithm information comprises algorithm information and recommended article information;
the generating unit is configured to generate a score value of the algorithm information based on each click operation information, each browsing duration information and each article circulation operation information of each user behavior log information in a user behavior log information group corresponding to the recommendation algorithm information to obtain a score value set for the algorithm information included in each recommendation algorithm information of the recommendation algorithm information set;
a first selection unit configured to select, as a target score value, a score value that meets a predetermined condition from the score value set;
a second selection unit configured to select, as target algorithm information, algorithm information corresponding to the target score value from among the respective algorithm information included in the respective recommendation algorithm information of the recommendation algorithm information set;
and the pushing unit is configured to push each piece of recommended article information of a recommended article information set included in the recommended algorithm information corresponding to the target algorithm information to each display device with a display function respectively so as to enable a related user to implement article circulation operation according to the recommended article information.
7. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
8. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-5.
CN202010863636.4A 2020-08-25 2020-08-25 Article information pushing method and device, electronic equipment and computer readable medium Pending CN111984869A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010863636.4A CN111984869A (en) 2020-08-25 2020-08-25 Article information pushing method and device, electronic equipment and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010863636.4A CN111984869A (en) 2020-08-25 2020-08-25 Article information pushing method and device, electronic equipment and computer readable medium

Publications (1)

Publication Number Publication Date
CN111984869A true CN111984869A (en) 2020-11-24

Family

ID=73443530

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010863636.4A Pending CN111984869A (en) 2020-08-25 2020-08-25 Article information pushing method and device, electronic equipment and computer readable medium

Country Status (1)

Country Link
CN (1) CN111984869A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110288907A1 (en) * 2008-04-14 2011-11-24 Tra, Inc. Using consumer purchase behavior for television targeting
KR20160118195A (en) * 2016-09-30 2016-10-11 에스케이플래닛 주식회사 Method for providing recommended item, storage medium recording program and device therefor
CN109753601A (en) * 2018-11-28 2019-05-14 北京奇艺世纪科技有限公司 Recommendation information clicking rate determines method, apparatus and electronic equipment
CN110337012A (en) * 2019-05-08 2019-10-15 未来电视有限公司 Intelligent recommendation method and apparatus based on internet television platform
US20190342616A1 (en) * 2018-05-07 2019-11-07 Apple Inc. User interfaces for recommending and consuming content on an electronic device
CN111401974A (en) * 2020-06-03 2020-07-10 北京每日优鲜电子商务有限公司 Information sending method, information sending device, electronic equipment and computer readable medium
CN111429203A (en) * 2020-03-02 2020-07-17 北京明略软件系统有限公司 Commodity recommendation method and device based on user behavior data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110288907A1 (en) * 2008-04-14 2011-11-24 Tra, Inc. Using consumer purchase behavior for television targeting
KR20160118195A (en) * 2016-09-30 2016-10-11 에스케이플래닛 주식회사 Method for providing recommended item, storage medium recording program and device therefor
US20190342616A1 (en) * 2018-05-07 2019-11-07 Apple Inc. User interfaces for recommending and consuming content on an electronic device
CN109753601A (en) * 2018-11-28 2019-05-14 北京奇艺世纪科技有限公司 Recommendation information clicking rate determines method, apparatus and electronic equipment
CN110337012A (en) * 2019-05-08 2019-10-15 未来电视有限公司 Intelligent recommendation method and apparatus based on internet television platform
CN111429203A (en) * 2020-03-02 2020-07-17 北京明略软件系统有限公司 Commodity recommendation method and device based on user behavior data
CN111401974A (en) * 2020-06-03 2020-07-10 北京每日优鲜电子商务有限公司 Information sending method, information sending device, electronic equipment and computer readable medium

Similar Documents

Publication Publication Date Title
CN108804450B (en) Information pushing method and device
CN110363604B (en) Page generation method and device
CN111125574B (en) Method and device for generating information
CN111414543B (en) Method, device, electronic equipment and medium for generating comment information sequence
CN111881361B (en) Article information pushing method and device, electronic equipment and computer readable medium
CN112182370A (en) Method and device for pushing item category information, electronic equipment and medium
CN112684899A (en) Client operation control method and device, electronic equipment and computer readable medium
CN112035753B (en) Recommendation page generation method and device, electronic equipment and computer readable medium
CN111932321B (en) Method and device for pushing article information for user, electronic equipment and medium
CN112036990B (en) Article information pushing method and device, electronic equipment and computer readable medium
CN112102043B (en) Item recommendation page generation method and device, electronic equipment and readable medium
CN111813815B (en) Data table display method and device, electronic equipment and computer readable medium
CN112561606B (en) Shelf placement method and device based on user behaviors, electronic equipment and medium
CN112547569B (en) Article sorting equipment control method, device, equipment and computer readable medium
CN111984869A (en) Article information pushing method and device, electronic equipment and computer readable medium
CN113191840A (en) Article information display method and device, electronic equipment and computer readable medium
CN109408716B (en) Method and device for pushing information
CN109947830B (en) Method and apparatus for outputting information
CN111339124A (en) Data display method and device, electronic equipment and computer readable medium
CN113763080A (en) Method and device for determining recommended article, electronic equipment and storage medium
CN112464039A (en) Data display method and device of tree structure, electronic equipment and medium
CN112184370A (en) Method and device for pushing product
CN112200643B (en) Article information pushing method and device, electronic equipment and computer readable medium
CN111932323B (en) Article information interface display method, device, equipment and computer readable medium
CN111666481A (en) Data mining method and device, computer readable medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination