CN110516147B - Page data generation method, device, computer equipment and storage medium - Google Patents
Page data generation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110516147B CN110516147B CN201910662200.6A CN201910662200A CN110516147B CN 110516147 B CN110516147 B CN 110516147B CN 201910662200 A CN201910662200 A CN 201910662200A CN 110516147 B CN110516147 B CN 110516147B
- Authority
- CN
- China
- Prior art keywords
- data
- user
- displayed
- reading data
- reading
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000000463 material Substances 0.000 claims abstract description 153
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 151
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000001914 filtration Methods 0.000 claims abstract description 38
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 230000006399 behavior Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 9
- 238000007781 pre-processing Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 239000012769 display material Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06F16/90—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
- G06F16/9536—Search customisation based on social or collaborative filtering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a page data generation method, a device, computer equipment and a storage medium, wherein the page data generation method comprises the following steps: acquiring a reading request sent by a client, wherein the reading request comprises a user identifier; acquiring user data from a database based on the user identification; determining a type of the user based on the user data; if the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data; sorting the three groups of initial reading data to obtain target reading data; and generating page display data according to the target reading data, and sending the page display data to the client. According to the technical scheme provided by the invention, the strategy of page display data is determined through the user data, and then the display reading materials conforming to the user interest points are matched through a plurality of algorithms, so that the accuracy of the reading materials displayed to the user is improved.
Description
Technical Field
The present invention relates to the field of electronic information reading technologies, and in particular, to a method and apparatus for generating page data, a computer device, and a storage medium.
Background
With the continuous development of the field of electronic commerce, electronic reading has become a new reading mode which is popular with more and more people, and meanwhile, the amount of electronic reading information is increased in an explosive manner, so that it is difficult for users to find useful information matched with the interests of the users on the internet.
Currently, numerous electronic reading pages or electronic reading related applications present specific pages to different users on the top page or specific page. Typically, the page will present to the user the reading material that the user may be interested in, as embodied by page data generated by the server through a particular algorithm. The client loads after receiving the page data, thereby generating the specific page. However, current page data does not very accurately show the reading material that the user may be interested in.
Disclosure of Invention
The embodiment of the invention provides a page data generation method, a device, computer equipment and a storage medium, which are used for solving the problem that page data in an electronic reading page is not accurate enough at present.
A page data generation method, comprising:
acquiring a reading request sent by a client, wherein the reading request comprises a user identifier;
acquiring user data from a database based on the user identification;
determining a type of the user based on the user data;
If the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data;
Sorting the three groups of initial reading data to obtain target reading data;
Generating page display data according to the target reading data, and sending the page display data to a client.
A page data generating apparatus comprising:
The reading request acquisition module is used for acquiring a reading request sent by the client, wherein the reading request comprises a user identifier;
the user data acquisition module is used for acquiring user data from a database based on the user identification;
a user type determining module for determining the type of the user based on the user data;
The algorithm processing module is used for processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data when the type of the user is an active user to obtain three groups of initial reading data;
the display data acquisition module is used for sequencing the three groups of initial reading data to obtain target reading data;
and the data display module is used for generating page display data according to the target reading data and sending the page display data to the client.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the above page data generation method when executing the computer program.
A computer readable storage medium storing a computer program which, when executed by a processor, implements the page data generation method described above.
The page data generating method, the device, the computer equipment and the storage medium, wherein the page data generating method comprises the following steps: acquiring a reading request sent by a client, wherein the reading request comprises a user identifier; acquiring user data from a database based on the user identification; determining a type of the user based on the user data; if the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data; sorting the three groups of initial reading data to obtain target reading data; generating page display data according to the target reading data, and sending the page display data to a client. The strategy of page display data is determined through the user data, and then display reading materials conforming to the interest points of the user are matched through a plurality of algorithms, so that the problem that the display data is not accurate enough due to the limitation of different algorithms is avoided, and the accuracy of the reading materials displayed to the user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an application environment of a page data generating method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a page data generation method according to an embodiment of the invention;
FIG. 3 is another flow chart of a page data generation method in an embodiment of the invention;
FIG. 4 is another flow chart of a page data generation method in an embodiment of the invention;
FIG. 5 is another flow chart of a page data generation method in an embodiment of the invention;
FIG. 6 is another flow chart of a page data generation method in an embodiment of the invention;
FIG. 7 is another flow chart of a page data generation method in an embodiment of the invention;
FIG. 8 is a schematic block diagram of a page data generating method according to an embodiment of the present invention;
FIG. 9 is a schematic block diagram of an algorithm processing module in the apparatus for generating page data according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The page data generation method provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, wherein a client communicates with a server through a network. The method comprises the steps that a server side obtains a reading request sent by a client side, wherein the reading request comprises a user identifier; then based on the user identification, obtaining user data from a database; determining a type of the user based on the user data; if the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data; sorting the three groups of initial reading data to obtain target reading data; and generating page display data according to the target reading data, and sending the page display data to the client. The computer device/terminal device/page data generating method may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The server may be implemented by a stand-alone server or a server cluster formed by a plurality of servers.
In one embodiment, a method for generating page data is provided, which is illustrated by taking a server side in fig. 2 as an example, and includes the following steps:
s10: and acquiring a reading request sent by the client, wherein the reading request comprises a user identifier.
The reading request can be obtained through the client, and further, the reading request can be a request initiated by a user through triggering an application program or a browser on the client. The client may trigger the reading request by monitoring a predetermined action of the user, optionally, when the client detects that the user clicks a trigger action of entering a certain application program/browser, the reading request is triggered to be generated, or the client detects that the user clicks a refresh key in a certain application program/browser. After the client generates the reading request, the reading request is sent to the server, and the server acquires the reading request.
The user identifier is an identifier for distinguishing the user triggering the reading request, and optionally, the user identifier may be a mobile phone number, a user account number, an identity card number, or the like.
S20: based on the user identification, user data is obtained from a database.
The user data refers to data which is collected by a server side and related to the reading behavior of a user in the process of reading materials. Alternatively, the category of reading material may include articles, pictures, video, music, and the like.
Alternatively, the user data of the user may be obtained from a system database based on the user identification.
S30: based on the user data, a type of user is determined.
Alternatively, the user data may include a user reading amount, a user registration time, or a user reading duration, etc. In which the type of user may be determined based on the user reading amount, the user reading duration, or the user registration time in the user data.
Optionally, the user is determined to be an active user according to whether the user reading amount exceeds a preset threshold, wherein the user reading amount refers to the number of the read materials, and the preset threshold is a preset number value. Alternatively, the preset threshold may be 3, 10, 50, 100, or the like. Specifically, if the user reading amount exceeds a preset threshold, the user is determined to be an active user, and if the user reading amount does not exceed the preset threshold, the user is determined to be an inactive user.
Optionally, determining that the user is an active user according to whether the user reading time exceeds a preset time threshold, wherein the user reading time refers to the total time for the user to read the material, and the preset time threshold is a preset time. The preset duration threshold may be 5 hours, 10 hours, 60 hours, etc. Specifically, if the user registration time exceeds a preset duration threshold, determining that the user is an active user. If the reading time of the user does not exceed the preset time threshold, judging that the user is an inactive user.
In one embodiment, a number of factors may be considered in combination to determine the type of user, for example, whether the user is an active user may be determined based on the user's reading volume and reading duration. Specifically, if the reading amount of the user exceeds a preset threshold and the registration time of the user exceeds a preset duration threshold, determining that the user is an active user. If the user reading time does not exceed the preset threshold or the user reading time does not exceed the preset time threshold, judging that the user is an inactive user.
S40: and if the type of the user is active, processing the information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data.
The information to be displayed is reading information to be displayed to the user in the database. Initial reading data refers to reading material that may be of interest to the user. The initial reading data includes an identification of the initial reading presentation. Further, the initial reading data also comprises initial reading display content. Wherein, the identification of the initial reading display content can comprise at least one item of numbers, letters, symbols or Chinese characters. For example, the initial reading data is 3 articles, where the 3 articles are identified {1,3,5}.
The user data may also include user characteristics and historical reading information. The user characteristics refer to attribute information of a user of the user. The history reading information refers to the history information of the material that the user has read.
Specifically, in this step, based on the user characteristics and the historical reading information in the user data, a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm are respectively adopted to process the information to be displayed, so as to obtain three groups of initial reading data. For example, based on the historical reading information, a collaborative filtering algorithm is adopted for processing to obtain a group of initial reading data.
Optionally, the method further comprises a process of preprocessing the information to be displayed, wherein the preprocessing process comprises removing the read materials of the user in the information to be displayed in the system database, the preprocessing process further comprises removing the data with the release time exceeding the preset release time period, and further, the preprocessing process can be set by comprehensively considering the two conditions. The release time refers to the time when new reading material is added to the database, i.e., the storage time of the reading material in the system database. The preset release time period is a preset time value. For example, the preset release time period may be 7 days, 14 days, 30 days, or the like. The preprocessing process may be set before the collaborative filtering algorithm, the content correlation algorithm, and the statistical recommendation algorithm are adopted. Further, the preprocessing process may also be set after the three sets of initial reading data are obtained.
Preferably, based on the user data, the information to be displayed is processed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm respectively to obtain the display score of each piece of information to be displayed, and each piece of information to be displayed is ordered according to the display score of each piece of information to be displayed to obtain three groups of initial reading data. Optionally, a preset display value is preset, where the preset display value refers to a preset display value. The preset display value can be determined according to the display number or the display degree. The display quantity refers to the maximum quantity of initial reading data, and the display degree refers to the average display score of the materials to be displayed. Specifically, the display number of each set of initial reading data to be displayed can be preset, and then the initial reading data with the corresponding number in the forefront ranking order is selected according to the display number. Or the display degree of each group of initial reading data can be preset, and the initial reading data with the display score being greater than or equal to the display degree can be selected. Further, the arrangement may be made in consideration of both the above cases. For example, the number of initial reading data greater than or equal to the display degree is first determined, and if the number is greater than the preset display number, further screening is performed. If the number is smaller than the preset display number, the part of initial reading data is directly selected. The preset display value is set to limit the display quantity of each group of initial reading data, so that the display quantity of each group of initial reading data is prevented from being unbalanced, and the display accuracy is reduced. And the excessive or low initial reading data is prevented from causing excessive reading quantity or insufficient reading content for users.
S50: and sequencing the three groups of initial reading data to obtain target reading data.
The target reading data refers to the determined reading materials displayed to the user. And sequencing the three groups of initial reading data to obtain target reading data. The target reading data includes an identification of the target reading presentation content. Further, the target reading data also comprises target reading display content. The identification of the target reading display content can comprise at least one item of numbers, letters, symbols or Chinese characters. The sorting of the three groups of initial reading data can be realized by adopting sorting modes such as algorithm priority sorting, cross combination sorting or preset calculation rules.
Optionally, the three groups of initial reading data are subjected to algorithm priority ranking, wherein an algorithm priority mechanism refers to a mechanism formulated according to an algorithm. For example, according to the system, the algorithm priority mechanism is analyzed to be the collaborative filtering algorithm priority, the content correlation algorithm is next, and the statistical recommendation algorithm is finally. Specifically, the initial read data {5,3,1,8, 13} generated by the collaborative filtering algorithm; initial reading data {4,6,2,7,9} generated by the content correlation algorithm; and carrying out algorithm priority ranking on the three groups of initial reading data {11, 10, 20, 52, 33} generated by the statistical recommendation algorithm to obtain target reading data {5,3,1,8, 13,4,6,2,7,9, 11, 10, 20, 52, 33}.
Optionally, performing cross-combination ordering on the three groups of initial reading data, wherein the cross-combination ordering refers to cross-combination ordering on the initial reading data of the three algorithms, which are complementary to each other; if the two algorithms generate the same initial reading data, the target reading display content only needs to push the same initial reading data once, so that repeated display is avoided. Specifically, the initial read data {5,3,1,8, 13} generated by the collaborative filtering algorithm; initial reading data {4,6,2,7,9} generated by the content correlation algorithm; and carrying out cross combination sequencing on three groups of initial reading data {11, 10, 20, 52, 33} generated by the statistical recommendation algorithm to obtain target reading data {5,4, 11,3,6, 10,1,2, 20,8,7, 52, 13,9, 33}.
Optionally, sorting the three groups of initial reading data by adopting a preset calculation rule, wherein the preset calculation rule refers to a preset formula, calculating each material to be displayed according to the preset formula to obtain a display score, and sorting the materials to be displayed according to the display score.
S60: generating page display data according to the target reading data, and sending the page display data to a client.
The page display data refers to background data of page data displayed for a user to read. Generating page display data according to the target reading data, and sending the page display data to a client. The target reading data also comprises target reading display content. Specifically, the server generates page display data according to the target reading data, sends the target reading data to the client, loads the page display data, and displays the content of the page data on a user reading interface.
In this embodiment, after obtaining a reading request sent by a user terminal, user data is obtained from a database based on a user identifier in the reading request; determining a type of the user based on the user data; if the user is an active user, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data; sorting the three groups of initial reading data to obtain target reading data; generating page display data according to the target reading data, and sending the page display data to a client. The strategy of page display data is determined through the user data, and then display reading materials conforming to the interest points of the user are matched through a plurality of algorithms, so that the problem that the display data is not accurate enough due to the limitation of different algorithms is avoided, and the accuracy of the reading materials displayed to the user is improved.
In an embodiment, as shown in fig. 3, if the user type is active, based on the user data, a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm are respectively adopted to process information to be displayed, so as to obtain three groups of initial reading data, and the method specifically comprises the following steps:
S41: based on the user data, historical reading information and user characteristics are obtained.
The historical reading information refers to the historical information of the reading materials read by the user. The user characteristics refer to attribute information of the user. Specifically, the server side obtains user history reading information and user characteristics according to the user data.
S42: and processing the information to be displayed by adopting a collaborative filtering algorithm based on the historical reading information to obtain a first group of initial reading data.
The history reading information may include history content information. The historical content information refers to related information of the reading materials read by the user, for example: the name of the read material, the read time period, or the read time period of each read material, etc. Based on the historical content information in the historical reading information, a collaborative filtering algorithm is adopted for processing, the collaborative filtering algorithm calculates the similarity between the users by using the matrix of < users, items >, the statistical information is used for searching the target users with the same or similar reading materials read by the current users, and the similar reading materials read by the target users are obtained as a first group of initial reading data by using similarity sorting according to the historical reading information of the target users.
S43: and obtaining a content label of the user based on the historical reading information, and processing the information to be displayed by adopting a content correlation algorithm based on the content label to obtain a second group of initial reading data.
Content tags refer to tags that embody the type of different reading material. Alternatively, the content tags may include a first content tag, a second content tag, a third content tag, and the like. The specific arrangement of content tags may also vary from field to field or from circle to circle. For example, the content tags for a wreath may include security, claims, violations, etc., and the content tags for a movie wreath may include thrill, comedy, drama, etc. The content correlation algorithm utilizes the item to extract some characteristics to represent the item, utilizes the characteristic data of the item of the user to learn the preference characteristics of the user, compares the preference characteristics of the user with the characteristics of the candidate items, and displays a group of items with the greatest correlation for the user. Specifically, firstly, a server acquires content tags of users from a historical reading information database, and based on the content tags, a content correlation algorithm is adopted to count the reading amount corresponding to each content tag. And then, according to the reading quantity corresponding to each content tag, acquiring the weight corresponding to each content tag, and processing the information to be displayed according to the weight corresponding to each content tag to obtain a second group of initial reading data. If the number of reads corresponding to the content tag is larger, the weight of the content tag is higher.
S44: and processing the information to be displayed by adopting a statistical recommendation algorithm based on the user characteristics to obtain a third group of initial reading data.
And processing by adopting a statistical recommendation algorithm according to the attribute information corresponding to the user characteristics and the reading materials corresponding to the user characteristics to obtain a third group of initial reading data.
Alternatively, the user characteristics may include the gender, age and region of the user, etc. Further, the user characteristics may also include claims count, insurance count, violation count, and mileage on drive, etc.
For example, the server side inquires the user characteristics of the current user in the database of the system, wherein the user characteristics comprise gender men, age 20-25 years old, regional Shenzhen, 5 times of claims settlement, 1 time of insurance application, 0 time of rule breaking and 50 kilometers of driving uploading mileage, the materials {1,5,8,9, 41} corresponding to the user characteristics of the gender men, the materials {5,7, 15, 56} corresponding to the user characteristics of the age 20-25 years old, the materials {7,8,5, 23, 16} corresponding to the user characteristics of the regional Shenzhen, the materials {6, 7} corresponding to the user characteristics of the claim settlement times 5 times, 55, 33,5}, the materials {9, 11, 13,6,2} corresponding to the user features with 1 guarantee time, the materials {3, 41, 12,6,7} corresponding to the user features with 0 violation times, the materials {4, 14, 12,5, 54},4} corresponding to the user features with 50 kilometers of driving uploading mileage, and if repeated materials are included in the materials corresponding to each attribute information, the weight of the materials is increased, and then a third set of initial reading data {5,7,8,6,9, 12,1, 41, 15, 56, 23, 16, 55, 33,5, 11, 13,2,3, 41,4, 14, 54} is obtained.
In this embodiment, based on the user data, history reading information and user characteristics are acquired; based on the historical reading information, a collaborative filtering algorithm is adopted for processing, and a first group of initial reading data is obtained; based on the historical reading information, obtaining a content tag of a user, and based on the content tag, processing the information to be displayed by adopting a content correlation algorithm to obtain a second group of initial reading data; and processing by adopting a statistical recommendation algorithm based on the user characteristics to obtain a third group of initial reading data. Aiming at user data in different situations, reading materials matched with the interests of the user are displayed for the user by adopting different algorithms, the problem of inaccurate displayed data caused by different applicable scenes of different recommendation algorithms is avoided, and the accuracy of the reading materials displayed to the user is improved.
In an embodiment, each set of the initial reading data includes at least one material to be displayed; in step S50, three groups of the initial reading data are ordered to obtain target reading data, as shown in fig. 4, which specifically includes the following steps:
s511: calculating each material to be displayed in the three groups of initial reading data by adopting a display score formula to obtain the display score of each material to be displayed:
Wherein a S is a display score of each material to be displayed, m i is an algorithm weight value of each material to be displayed, n j is a sequence number weight value of each material to be displayed, a ij is a sequence number true-false value of each material to be displayed, wherein if a ij is true, the sequence number true-false value is 1, and if a ij is false, the sequence number true-false value is 0; m is the number of the groups of the initial reading data, and N is the number of materials to be displayed in each group of the initial reading data.
Optionally, the display score of each material to be displayed is determined by an algorithm weight value of each material to be displayed and a sequence number weight value of each material to be displayed.
The algorithm weight value of each material to be displayed is determined by the algorithm itself, and the algorithm weight value of each material to be displayed is set according to the result of big data statistics. For example, the collaborative filtering algorithm may be set to a higher weight value, the content-related algorithm may be set to a lower weight value, and the statistical recommendation algorithm may be set to a lowest weight value. For example, the weight value of the collaborative filtering algorithm is designed to be 1 according to the actual requirement, the weight value of the content correlation algorithm is 0.8, and the weight value of the statistical recommendation algorithm is 0.6.
The serial number weight value of each material to be displayed is determined by the position. The serial number weight of each material to be displayed is reduced in sequence according to the front-back arrangement sequence of the position of the material to be displayed. For example, if the initial reading data {5,3,1,8,6} produced by the collaborative filtering algorithm, the material to be displayed with the sequence number of 5 is located in the first column, the weight value of the material is set to 1, the content to be displayed with the sequence number of 3 is located in the second column, the weight value of the material to be displayed with the sequence number of 3 is set to 0.8, the material to be displayed with the sequence number of 1 is located in the third column, the weight value of the material to be displayed with the sequence number of 1 is set to 0.6, and so on.
Specifically, by the formulaAnd (3) obtaining the display score of each material to be displayed. The display score of each material to be displayed is the algorithm weight value of each material to be displayed, the sequence number weight value of each material to be displayed is the sequence number true-false value of each material to be displayed, wherein if the existence is true, the sequence number true-false value is 1, and if the existence is false, the sequence number true-false value is 0; m is the number of the groups of the initial reading data, and N is the number of materials to be displayed in each group of the initial reading data.
For example, the initial read data {5,3,1,8,6} produced by the collaborative filtering algorithm; initial reading data {4,3,2,7,9} generated by the content correlation algorithm; initial reading data {11, 10, 20, 52, 33} generated by the statistical recommendation algorithm. The display score of the material to be displayed with the sequence number of 5: 1*1 = 1; the material to be displayed with the sequence number of 3 is displayed in the collaborative filtering algorithm and the content correlation algorithm, and the display score of the material to be displayed with the sequence number of 3 is calculated according to the position of the material to be displayed with the sequence number of 3 in the collaborative filtering algorithm and the content correlation algorithm: 1x 0.8+0.8 x 0.8=1.44, number 1, display score of the material to be displayed: 1x 0.6=0.6, number 8, display score of the material to be displayed: 1x 0.4=0.4, etc.
S512: and sorting the three groups of initial reading data according to the display scores of the materials to be displayed to obtain target reading data.
And sorting the identifications of the initial reading display contents in the three groups of initial reading data according to the display score of each material to be displayed to obtain target reading data.
For example, the collaborative filtering algorithm produces initial reading data {5,3,1,8,6}; initial reading data {4,3,2,7,9} generated by the content correlation algorithm; and (3) counting initial reading data {11, 10, 20, 52, 33} generated by a recommendation algorithm, obtaining the highest display score of the material to be displayed with the sequence number of 3 according to the calculation result, obtaining the next highest display score of the material to be displayed with the sequence number of 5, and so on, and finally obtaining target reading data {3,5,4,1, 11,2, 10,8, 20,7, 52,6,9, 33}.
Preferably, if the display scores of at least two materials to be displayed are the same, a collaborative filtering algorithm may be adopted for preference, and secondly, ordering the content related algorithm in a final ordering mode of the statistical recommendation algorithm.
In this embodiment, a display score formula is adopted to calculate each material to be displayed in three groups of initial reading data, so as to obtain a display score of each material to be displayed, and the three groups of initial reading data are ordered according to the display score of each material to be displayed, so as to obtain target reading data. The weight value of each algorithm and the serial number weight value of each material to be displayed are reasonably distributed through the display score formula, the material to be displayed is calculated, the display score corresponding to each material to be displayed is obtained, the problem that the display score judgment standard is not clear due to the fact that the calculation rules of different algorithms are different is avoided, the inaccuracy of the display material is caused, and the accuracy of the reading material displayed to a user is improved.
In another embodiment, in step S50, three sets of the initial reading data are ordered to obtain target reading data, as shown in fig. 5, specifically including the following steps:
S521: and obtaining the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table.
The user preference table is a table created from content tags. The preference scores in the user preference table are determined by the tag scores in the content tags, each content tag corresponding to a different tag score. Specifically, a label score corresponding to a content label corresponding to each material to be displayed is obtained from a preset and established user preference table, and the label score is accumulated and calculated to obtain a preference score of each material to be displayed in each initial reading data.
Optionally, a tag score corresponding to each content tag in the user preference table is determined according to the user preference behavior. The user preference behavior refers to that the user sets an associated mark for a certain reading material. For example, user preference tagging behaviors may include praise, comment, collection, and mask behaviors.
Specifically, for each preference-tagged behavior, a corresponding behavior score is set, e.g., praise 2 score, comment 1 score, collection 3 score, mask-3 score. And accumulating the behavior scores of the user on each reading material to obtain the initial behavior score of the reading material. And obtaining the initial behavior score of the content tag corresponding to each reading material. And comprehensively considering user preference behaviors of the same content tag of a plurality of reading materials, and calculating an average value of a plurality of initial behavior scores to obtain a target behavior score. According to the steps, the target action scores corresponding to the different content labels are repeatedly calculated, and the corresponding label scores are set according to the target action scores of the different content labels, wherein the higher the target action score corresponding to the content label is, the higher the label score of the content label is.
S522: and sorting the three groups of initial reading data according to the preference scores of the materials to be displayed to obtain target reading data.
And sorting the identifications of the initial reading display contents in the three groups of initial reading data according to the preference scores of the materials to be displayed, so as to obtain target reading data.
For example, the collaborative filtering algorithm produces initial reading data {5,3,1,8,6}; initial reading data {4,3,2,7,9} generated by the content correlation algorithm; and (3) counting initial reading data {11, 10, 20, 52, 33} generated by a recommendation algorithm, obtaining the highest preference score of the material to be displayed with the sequence number of 3 according to the calculation result, obtaining the next highest preference score of the material to be displayed with the sequence number of 5, and so on, and finally obtaining target reading data {3,5,4,1, 11,2, 10,8, 20,7, 52,6,9, 33}.
Preferably, if the preference scores of at least two materials to be displayed are the same, a collaborative filtering algorithm may be employed for preference, and secondly, ordering the content related algorithm in a final ordering mode of the statistical recommendation algorithm.
In the embodiment corresponding to fig. 5, the preference score of each material to be displayed in each set of the initial reading data is obtained from a pre-created user preference table; and sorting the three groups of initial reading data according to the preference scores of the materials to be displayed to obtain target reading data. And reasonably distributing the behavior scores corresponding to each preference marking behavior through a pre-established user preference table, determining the tag scores according to the behavior scores, acquiring the tag scores corresponding to the content tags corresponding to each material to be displayed, accumulating the tag scores to obtain the preference scores of each material to be displayed in each initial reading data, and improving the accuracy of the reading materials displayed to the user.
In another embodiment, each set of the initial reading data includes at least one material to be displayed and a display score for each material to be displayed; in step S50, three groups of initial reading data are ordered to obtain target reading data, as shown in fig. 6, which specifically includes the following steps:
S531: and obtaining the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table.
And calculating the preference score corresponding to each group of initial reading display materials from a preset established user preference table. The specific process may be the same as step S521, and will not be described here again.
S532: and obtaining target reading data according to the preference scores and the display scores corresponding to each material to be displayed in each group of initial display data.
And calculating to obtain the preference scores corresponding to each material to be displayed in each group of initial display data according to the pre-established user preference table. Then, the display score corresponding to each material to be displayed in each set of initial display data is obtained through calculation, and the specific process may be the same as that in step S511, which is not described herein. And processing the preference scores and the display scores corresponding to each material to be displayed in the three groups of initial display data by adopting preset operation to obtain the target score of each material to be displayed. Wherein the preset operation may comprise an addition. And sorting according to the target score of each material to be displayed to obtain target reading data.
Optionally, adding the preference score and the display score corresponding to each material to be displayed to obtain a target score of each material to be displayed. And sorting according to the target score of each material to be displayed to obtain target reading data.
In this embodiment, a preference score of each material to be displayed in each set of initial reading data is obtained from a pre-created user preference table; and obtaining target reading data according to the preference scores and the display scores corresponding to each material to be displayed in each group of initial display data. The preference behavior of the user and various algorithms are combined to further judge the displaying strategy, the preference table and various algorithms of the user are used for calculating the materials to be displayed, the obtained preference score and the displaying score are used for displaying the reading materials for the user, and the score obtained by carrying out preset operation processing on the preference score and the displaying score is used for increasing the sensory factors of the behavior of the user on the reading materials and improving the accuracy of the reading materials displayed to the user.
In an embodiment, after step S30, that is, after determining the type of the user based on the user data, as shown in fig. 7, the page data generating method provided in the embodiment of the present invention further includes:
S71: and if the type of the user is an inactive user, acquiring user characteristics based on the user data.
And if the user is an inactive user, indicating that the reading quantity of the user does not exceed a preset threshold value. And the server side queries attribute information corresponding to the user characteristics and reading materials corresponding to the user characteristics in a database of the system, and adopts a statistical recommendation algorithm to process the attribute information and the reading materials to obtain initial reading data generated by a group of statistical recommendation algorithm.
S72: and processing the information to be displayed by adopting a statistical recommendation algorithm to obtain a group of initial reading data.
And sequencing the initial reading data generated by the statistical recommendation algorithm, wherein the sequencing mode can be realized by adopting a preset calculation rule, so as to obtain target reading data.
S73: and sequencing a group of initial reading data to obtain target reading data.
In this embodiment, for an inactive user lacking a certain reading amount, based on the user characteristics, a statistical recommendation algorithm is adopted to perform processing, so as to obtain initial reading data generated by a group of statistical recommendation algorithms. And sequencing the initial reading data generated by the statistical recommendation algorithm, wherein the sequencing mode can be realized by adopting a preset calculation rule, so as to obtain target reading data. The problem that the system database lacks historical reading data is solved, and the accuracy of display is improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, a page data generating apparatus is provided, which corresponds to the page data generating method in the above embodiment one by one. As shown in fig. 8, the page data generating apparatus includes a reading request acquiring module 10, a user data acquiring module 20, a user type determining module 30, an algorithm processing module 40, a presentation data acquiring module 50, and a data presentation module 60. The functional modules are described in detail as follows:
the reading request obtaining module 10 is configured to obtain a reading request sent by the client, where the reading request includes a user identifier.
And the user data acquisition module 20 is used for acquiring the user data from the database based on the user identification.
A user type determining module 30, configured to determine a type of the user based on the user data.
And the algorithm processing module 40 is used for processing the information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data when the type of the user is an active user, so as to obtain three groups of initial reading data.
The display data acquisition module 50 is configured to sort the three sets of initial reading data to obtain target reading data.
The data display module 60 is configured to generate page display data according to the target reading data, and send the page display data to a client.
Preferably, as shown in fig. 9, the algorithm processing module 40 includes an information acquisition unit 41, a first data acquisition unit 42, a second data acquisition unit 43, and a third data acquisition unit 44.
An information acquisition unit 41 for acquiring history reading information and user characteristics based on the user data.
The first data obtaining unit 42 is configured to obtain a first set of initial reading data by performing processing with a collaborative filtering algorithm based on the historical reading information.
The second data obtaining unit 43 obtains a content tag of the user based on the historical reading information, and processes the information to be displayed by adopting a content correlation algorithm based on the content tag to obtain a second set of initial reading data.
The third data obtaining unit 44 processes by using a statistical recommendation algorithm based on the user characteristics to obtain a third set of initial reading data.
Preferably, the presentation data acquisition module 50 includes a presentation score acquisition unit and a first target data acquisition unit.
The display score obtaining unit is used for calculating each material to be displayed in the three groups of initial reading data by adopting a display score formula to obtain the display score of each material to be displayed.
And the first target data acquisition unit is used for sequencing the three groups of initial reading data according to the display scores of the materials to be displayed to obtain target reading data.
Preferably, the presentation data acquisition module 50 further includes a preference score acquisition unit and a second target data acquisition unit.
And the preference score acquisition unit is used for acquiring the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table.
And the second target data acquisition unit is used for sequencing the three groups of initial reading data according to the preference scores of the materials to be displayed to obtain target reading data.
Preferably, the presentation data acquisition module 50 further includes a preference score acquisition unit and a third target data acquisition unit.
The preference score obtaining unit is used for obtaining the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table;
And the third target data acquisition unit is used for acquiring target reading data according to the preference scores and the display scores corresponding to each material to be displayed in each group of initial display data.
Preferably, the page data generating apparatus provided in this embodiment further includes an inactive user processing module, where the inactive user processing module includes a user feature acquiring unit, an initial reading data acquiring unit, and a fourth target data acquiring unit.
And the user characteristic acquisition unit is used for acquiring the user characteristic based on the user data if the type of the user is an inactive user.
The initial reading data acquisition unit is used for processing the information to be displayed by adopting a statistical recommendation algorithm to obtain a group of initial reading data.
And the fourth target data acquisition unit is used for sequencing the initial reading data to obtain target reading data.
The specific limitation of the page data generating apparatus may be referred to the limitation of the page data generating method hereinabove, and will not be described herein. The respective modules in the above-described page data generating apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing user data, information to be displayed, initial reading data, target reading data, historical reading information, user characteristics and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a page data generation method.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring a reading request sent by a client, wherein the reading request comprises a user identifier;
acquiring user data from a database based on the user identification;
determining a type of the user based on the user data;
If the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data;
Sorting the three groups of initial reading data to obtain target reading data;
Generating page display data according to the target reading data, and sending the page display data to a client.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a reading request sent by a client, wherein the reading request comprises a user identifier;
acquiring user data from a database based on the user identification;
determining a type of the user based on the user data;
If the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data;
Sorting the three groups of initial reading data to obtain target reading data;
Generating page display data according to the target reading data, and sending the page display data to a client.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (7)
1. A page data generation method, characterized by comprising:
acquiring a reading request sent by a client, wherein the reading request comprises a user identifier;
acquiring user data from a database based on the user identification;
determining a type of the user based on the user data;
If the type of the user is active, processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data;
Sorting the three groups of initial reading data to obtain target reading data;
Generating page display data according to the target reading data, and sending the page display data to a client;
Each group of initial reading data comprises at least one material to be displayed and a display score of each material to be displayed;
the sorting the three groups of initial reading data to obtain target reading data comprises the following steps:
Obtaining the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table;
obtaining target reading data according to the preference scores and the display scores corresponding to each material to be displayed in each group of initial display data;
The method comprises the steps of calculating each material to be displayed in three groups of initial reading data by adopting the following display score formula to obtain the display score of each material to be displayed:
Wherein a S is a display score of each material to be displayed, m i is an algorithm weight value of each material to be displayed, n j is a sequence number weight value of each material to be displayed, a ij is a sequence number true-false value of each material to be displayed, wherein if a ij is true, the sequence number true-false value is 1, and if a ij is false, the sequence number true-false value is 0; m is the number of the groups of the initial reading data, and N is the number of materials to be displayed in each group of the initial reading data.
2. The method for generating page data according to claim 1, wherein if the user type is active, processing information to be displayed by respectively adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data to obtain three groups of initial reading data, including:
Acquiring historical reading information and user characteristics based on the user data;
Based on the historical reading information, processing the information to be displayed by adopting a collaborative filtering algorithm to obtain a first group of initial reading data;
Based on the historical reading information, obtaining a content tag of a user, and based on the content tag, processing the information to be displayed by adopting a content correlation algorithm to obtain a second group of initial reading data;
and processing the information to be displayed by adopting a statistical recommendation algorithm based on the user characteristics to obtain a third group of initial reading data.
3. The page data generating method according to claim 1, wherein after said judging the type of the user based on the user data, the page data generating method further comprises:
If the type of the user is an inactive user, acquiring user characteristics based on the user data;
processing the information to be displayed by adopting a statistical recommendation algorithm to obtain a group of initial reading data;
And sequencing a group of initial reading data to obtain target reading data.
4. A page data generating apparatus, comprising:
The reading request acquisition module is used for acquiring a reading request sent by the client, wherein the reading request comprises a user identifier;
the user data acquisition module is used for acquiring user data from a database based on the user identification;
the user type determining module is used for determining the type of the user based on the user data;
The algorithm processing module is used for processing information to be displayed by adopting a collaborative filtering algorithm, a content correlation algorithm and a statistical recommendation algorithm based on the user data when the type of the user is an active user to obtain three groups of initial reading data;
the display data acquisition module is used for sequencing the three groups of initial reading data to obtain target reading data;
the data display module is used for generating page display data according to the target reading data and sending the page display data to a client;
Each group of initial reading data comprises at least one material to be displayed and a display score of each material to be displayed;
the sorting the three groups of initial reading data to obtain target reading data comprises the following steps:
Obtaining the preference score of each material to be displayed in each group of initial reading data from a pre-established user preference table;
obtaining target reading data according to the preference scores and the display scores corresponding to each material to be displayed in each group of initial display data;
The method comprises the steps of calculating each material to be displayed in three groups of initial reading data by adopting the following display score formula to obtain the display score of each material to be displayed:
Wherein a S is a display score of each material to be displayed, m i is an algorithm weight value of each material to be displayed, n j is a sequence number weight value of each material to be displayed, a ij is a sequence number true-false value of each material to be displayed, wherein if a ij is true, the sequence number true-false value is 1, and if a ij is false, the sequence number true-false value is 0; m is the number of the groups of the initial reading data, and N is the number of materials to be displayed in each group of the initial reading data.
5. The page data generating apparatus according to claim 4, comprising: the algorithm processing module comprises an information acquisition unit, a first group of data acquisition unit, a second group of data acquisition unit and a third group of data acquisition unit;
the information acquisition unit is used for acquiring historical reading information and user characteristics based on the user data;
the first data acquisition unit is used for processing by adopting a collaborative filtering algorithm based on the historical reading information to obtain a first group of initial reading data;
The second data acquisition unit is used for obtaining a content tag of a user based on the historical reading information, and processing the information to be displayed by adopting a content correlation algorithm based on the content tag to obtain a second group of initial reading data;
And the third data acquisition unit is used for processing by adopting a statistical recommendation algorithm based on the user characteristics to obtain a third group of initial reading data.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the page data generation method of any of claims 1 to 3 when the computer program is executed.
7. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the page data generation method of any one of claims 1 to 3.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910662200.6A CN110516147B (en) | 2019-07-22 | 2019-07-22 | Page data generation method, device, computer equipment and storage medium |
| PCT/CN2020/093353 WO2021012790A1 (en) | 2019-07-22 | 2020-05-29 | Page data generation method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910662200.6A CN110516147B (en) | 2019-07-22 | 2019-07-22 | Page data generation method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110516147A CN110516147A (en) | 2019-11-29 |
| CN110516147B true CN110516147B (en) | 2024-08-09 |
Family
ID=68623342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910662200.6A Active CN110516147B (en) | 2019-07-22 | 2019-07-22 | Page data generation method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110516147B (en) |
| WO (1) | WO2021012790A1 (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516147B (en) * | 2019-07-22 | 2024-08-09 | 平安科技（深圳）有限公司 | Page data generation method, device, computer equipment and storage medium |
| CN111753220A (en) * | 2020-06-28 | 2020-10-09 | 北京金山安全软件有限公司 | Recommendation information display method, device and equipment |
| CN113934482A (en) * | 2020-07-14 | 2022-01-14 | 北京奇虎科技有限公司 | Page display method, equipment, storage medium and device |
| CN112015976A (en) * | 2020-07-24 | 2020-12-01 | 上海淇玥信息技术有限公司 | Page data sending method and device and electronic equipment |
| CN112149019A (en) * | 2020-09-15 | 2020-12-29 | 北京字节跳动网络技术有限公司 | Method, apparatus, electronic device, and computer-readable medium for displaying information |
| CN112558958B (en) * | 2020-12-16 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Template-based push content generation method and device and computer equipment |
| CN112733023A (en) * | 2020-12-30 | 2021-04-30 | 平安科技（深圳）有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
| CN113468451A (en) * | 2021-07-14 | 2021-10-01 | 深圳市点购电子商务控股股份有限公司 | Page display method and device |
| CN113741895B (en) * | 2021-08-24 | 2023-08-15 | 上海数禾信息科技有限公司 | Method and device for manufacturing put materials, computer equipment and storage medium |
| CN114328896A (en) * | 2021-12-20 | 2022-04-12 | 南京尚网网络科技有限公司 | Detail page folding method and device and electronic equipment |
| CN116205612A (en) * | 2023-05-04 | 2023-06-02 | 国网山东省电力公司滨州市沾化区供电公司 | Method, system, terminal and storage medium for assisting in generating power grid maintenance scheme |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944033A (en) * | 2017-12-13 | 2018-04-20 | 北京百度网讯科技有限公司 | Associate topic and recommend method and apparatus |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6334127B1 (en) * | 1998-07-17 | 2001-12-25 | Net Perceptions, Inc. | System, method and article of manufacture for making serendipity-weighted recommendations to a user |
| KR20120003362A (en) * | 2010-07-02 | 2012-01-10 | 아코지토(주) | Recommendation system on personalized favorite programs/channels for internet protocol tv users by using collaborative filtering algorithm |
| US20130073568A1 (en) * | 2011-09-21 | 2013-03-21 | Vladimir Federov | Ranking structured objects and actions on a social networking system |
| CN103578007A (en) * | 2012-07-20 | 2014-02-12 | 三星电子（中国）研发中心 | Mixed recommendation system and method for intelligent device |
| US9721019B2 (en) * | 2012-12-10 | 2017-08-01 | Aol Inc. | Systems and methods for providing personalized recommendations for electronic content |
| US20160055541A1 (en) * | 2014-08-21 | 2016-02-25 | Everyday Health Inc. | Personalized recommendation system and methods using automatic identification of user preferences |
| CN106649482B (en) * | 2016-09-30 | 2022-05-27 | 网易（杭州）网络有限公司 | Information pushing method and device |
| CN106682152B (en) * | 2016-12-23 | 2020-04-14 | 西安电子科技大学 | Personalized message recommendation method |
| CN107807958B (en) * | 2017-09-30 | 2021-11-19 | 广东南都全媒体网络科技有限公司 | Personalized article list recommendation method, electronic equipment and storage medium |
| CN108228873B (en) * | 2018-01-17 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Object recommendation and release content pushing method and device, storage medium and equipment |
| CN108304556B (en) * | 2018-02-06 | 2019-06-07 | 中国传媒大学 | The personalized recommendation method combined based on content with collaborative filtering |
| CN108763519A (en) * | 2018-05-30 | 2018-11-06 | 深圳市零度智控科技有限公司 | The recommendation method, apparatus and readable storage medium storing program for executing of reading |
| CN109977316A (en) * | 2019-03-29 | 2019-07-05 | 厦门铠甲网络股份有限公司 | A kind of parallel type article recommended method, device, equipment and storage medium |
| CN110516147B (en) * | 2019-07-22 | 2024-08-09 | 平安科技（深圳）有限公司 | Page data generation method, device, computer equipment and storage medium |
-
2019
- 2019-07-22 CN CN201910662200.6A patent/CN110516147B/en active Active
-
2020
- 2020-05-29 WO PCT/CN2020/093353 patent/WO2021012790A1/en active Application Filing
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944033A (en) * | 2017-12-13 | 2018-04-20 | 北京百度网讯科技有限公司 | Associate topic and recommend method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110516147A (en) | 2019-11-29 |
| WO2021012790A1 (en) | 2021-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516147B (en) | Page data generation method, device, computer equipment and storage medium | |
| CN109145216B (en) | Network public opinion monitoring method, device and storage medium | |
| CN109145215B (en) | Network public opinion analysis method, device and storage medium | |
| CN108629043B (en) | Webpage target information extraction method, device and storage medium | |
| CN108959644B (en) | Search ranking method and device, computer equipment and storage medium | |
| CN111192025A (en) | Occupational information matching method and device, computer equipment and storage medium | |
| CN102782680A (en) | Information processing device, information processing method, and recording medium that has recorded information processing program | |
| CN110377558A (en) | Document searching method, device, computer equipment and storage medium | |
| CN111178949B (en) | Service resource matching reference data determining method, device, equipment and storage medium | |
| CN111612610A (en) | Risk early warning method and system, electronic equipment and storage medium | |
| US20190354638A1 (en) | Action indicators for search operation output elements | |
| CN109542923B (en) | Nuclear protection method, device, computer equipment and storage medium | |
| CN111651670A (en) | Content retrieval method, device terminal and storage medium based on user behavior map | |
| CN111177568B (en) | Object pushing method based on multi-source data, electronic device and storage medium | |
| CN115098803A (en) | Book recommendation algorithm and system based on mobile library | |
| CN113468441A (en) | Search sorting method, device, equipment and storage medium based on weight adjustment | |
| CN112989824A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN110532229B (en) | Evidence file retrieval method, device, computer equipment and storage medium | |
| CN113706249B (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN114938458A (en) | Object information display method and device, electronic equipment and storage medium | |
| CN112182390B (en) | Mail pushing method, device, computer equipment and storage medium | |
| CN113434762A (en) | Association pushing method, device and equipment based on user information and storage medium | |
| CN110659347B (en) | Associated document determining method, device, computer equipment and storage medium | |
| CN111985467A (en) | Chat record screenshot processing method and device, computer equipment and storage medium | |
| CN115544342A (en) | Method and system based on website content search engine |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |