CN111966935A - Information preloading method and device, computer equipment and storage medium - Google Patents
Information preloading method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111966935A CN111966935A CN202010709709.4A CN202010709709A CN111966935A CN 111966935 A CN111966935 A CN 111966935A CN 202010709709 A CN202010709709 A CN 202010709709A CN 111966935 A CN111966935 A CN 111966935A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- label
- intention
- tag
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000004044 response Effects 0.000 claims abstract description 18
- 230000006399 behavior Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 101100150905 Caenorhabditis elegans ham-3 gene Proteins 0.000 description 1
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036316 preload Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9574—Browsing optimisation, e.g. caching or content distillation of access to content, e.g. by caching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application relates to an information preloading method, an information preloading device, computer equipment and a storage medium. The method comprises the steps of obtaining login information of a user by responding to system login operation of the user, obtaining label information representing characteristic information of the user according to the login information, obtaining intention scores of different information in a system corresponding to the user according to the label information corresponding to the user and label information related to each item of information in the system, determining target information with the maximum user access intention from a plurality of items of information contained in the system according to the intention scores, and caching the target information. Compared with the traditional mode that after a user triggers a relevant instruction, the terminal acquires corresponding data and pages from the database or an external server, the scheme obtains the access intention of the user to different information by using the user tag, so that the corresponding information is cached, the user can quickly call when accessing the information, and the effect of reducing the information access response time is realized.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information preloading method and apparatus, a computer device, and a storage medium.
Background
Users generally need to handle various services in life, along with the development of computer technology, users gradually shift to online handling services, and when users handle services, terminals generally need to call corresponding pages or data according to the related operations of users. However, communication with an external server is often required when retrieving information or pages, or multiple servers and databases are invoked, resulting in slow response times.
Therefore, the current information loading method has the defect of long response time.
Disclosure of Invention
In view of the above, it is necessary to provide an information preloading method, apparatus, computer device and storage medium capable of reducing response time in view of the above technical problems.
A method of preloading information, the method comprising:
responding to the system login operation of a user, and acquiring login information of the user;
acquiring label information corresponding to the user according to the login information; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system;
according to the label information corresponding to the user and the label information associated with each item of information, obtaining the intention of the user for different information in the system; the intention score represents the magnitude of the user's access intention for different information in the system;
and according to the intention score, determining the target information with the maximum user access intention from a plurality of items of information contained in the system, and caching the target information.
In one embodiment, before obtaining the login information of the user in response to the login operation of the user, the method further includes:
acquiring personal information of the user and behavior information in the system;
generating a plurality of personal information tags based on the personal information; each personal information tag is associated with a first information of the plurality of items of information; the first information characterizes transaction information of the user;
generating a plurality of behavior information tags based on the behavior information; each behavior information tag is associated with a second information of the plurality of information; the second information represents the service application information of the user;
and obtaining label information corresponding to the user according to the plurality of personal information labels and the plurality of behavior information labels.
In one embodiment, the method further comprises the following steps:
acquiring a plurality of labels corresponding to each item of information contained in the system;
according to the number of the plurality of labels, taking the average score of the preset total score as the initial score corresponding to each label;
in one embodiment, the obtaining the intention score of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each item of information includes:
acquiring label information corresponding to the user in the label information associated with the current item information as a target label participating in calculation;
and acquiring the sum of products of the initial scores of the plurality of target tags and the weights corresponding to the target tags to obtain the intention score.
In one embodiment, the method further comprises the following steps:
acquiring target label information corresponding to a user who successfully accesses the target information within a preset period; the target label information comprises a plurality of labels;
and adjusting the weight of each label according to the number of each label in the target label information.
In one embodiment, the adjusting the weight of each type of tag according to the number of each type of tag in the target tag information includes:
obtaining the occupation ratio of each label according to the number of each label in the target label information;
subtracting preset values from the current weight of each label, and taking the sum of the preset values subtracted by the various labels as the weight to be distributed;
and respectively obtaining the products of the weight to be distributed and the occupation ratio of each label, and adding the weight of each label after subtracting the preset value and the corresponding product to obtain the adjusted weight corresponding to each label.
In one embodiment, the method further comprises the following steps:
and if the adjusted weight value corresponding to the label is smaller than a preset threshold value and the weight value corresponding to the label is in a continuous descending trend within preset time, deleting the label from the system.
In one embodiment, the obtaining the intention score of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each item of information includes:
obtaining a first intention point corresponding to the user according to the label information corresponding to the user and the label information associated with the first information; the first intent score characterizes a magnitude of intent of the user to access the first information;
obtaining a second intention score corresponding to the user according to the label information corresponding to the user and the label information associated with the second information; the second intention score characterizes the amount of intention of the user to access the second information;
the determining, according to the intention score, target information with the maximum user access intention from a plurality of items of information contained in the system, and caching the target information, includes:
if the first intention score is larger than the second intention score, determining that the first information is the target information, and caching the first information through redis;
and if the first intention score is smaller than the second intention score, determining that the second information is the target information, and caching the second information through redis.
An information preloading device, the device comprising:
the response module is used for responding to the system login operation of the user and acquiring the login information of the user;
the first acquisition module is used for acquiring the label information corresponding to the user according to the login information; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system;
the second acquisition module is used for acquiring the intention scores of the users for different information in the system according to the label information corresponding to the users and the label information associated with each item of information; the intention score represents the magnitude of the user's access intention for different information in the system;
and the determining module is used for determining the target information with the maximum user access intention from a plurality of items of information contained in the system according to the intention score and caching the target information.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the information preloading method, the information preloading device, the computer equipment and the storage medium, login information of a user is obtained by responding to system login operation of the user, label information representing characteristic information of the user is obtained according to the login information, intention scores of different information in a system corresponding to the user are obtained according to the label information corresponding to the user and label information associated with each item of information in the system, objective information with the maximum user access intention is determined from multiple items of information contained in the system according to the size of the intention scores, and the objective information is cached. Compared with the traditional mode that after a user triggers a relevant instruction, the terminal acquires corresponding data and pages from the database or an external server, the scheme obtains the access intention of the user to different information by using the user tag, so that the corresponding information is cached, the user can quickly call when accessing the information, and the effect of reducing the information access response time is realized.
Drawings
FIG. 1 is a diagram of an application environment of a method for preloading information in one embodiment;
FIG. 2 is a flow chart illustrating a method for preloading information according to an embodiment;
FIG. 3 is a flowchart illustrating the tag information generation step in one embodiment;
FIG. 4 is a flowchart illustrating a method for preloading information according to another embodiment;
FIG. 5 is a flowchart illustrating a method for preloading information according to another embodiment;
FIG. 6 is a block diagram of an information preloading device according to an embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The information preloading method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may obtain login information of a user in the system, for example, the user inputs the login information or obtains corresponding login information according to physical characteristics of the user, the terminal 102 may send the login information to the server 104 after obtaining login operation of the user, the server 104 may obtain corresponding tag information according to the login information, obtain intention scores of the user for different information in the system according to the tag information corresponding to the user and tag information associated with each item of information in the system, determine target information with the maximum user access intention from a plurality of items of information included in the system according to the intention scores, and cache the target information. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an information preloading method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
step S202, responding to the system login operation of the user, and acquiring the login information of the user.
The user can be a user needing to log in the system, the system can be a system giving corresponding services to the user based on a plurality of items of information, and the login information can comprise account password information of the user, personal information of the user and the like. The terminal 102 may obtain login information of the user, where the login information may be information input by the user, or the terminal 102 may obtain corresponding login information locally obtained by identifying corresponding features of the user, for example, by identifying physical features of the user, such as an iris, a fingerprint, or a face, and then obtain corresponding login information, the terminal 102 may send the login information corresponding to the user to the server 104 after the user triggers a system login operation, for example, after recognizing that the user clicks a login button, and the server 104 may obtain the login information sent by the terminal 102 in response to the system login operation of the user.
Step S204, acquiring label information corresponding to the user according to the login information; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system.
The login information may be system login information corresponding to the user sent by the terminal 102, each user may have corresponding tag information, the tag information corresponding to each user may be multiple, the multiple tag information of each user may form a user figure of the user, that is, feature information representing the user, the multiple tags of each user may be stored in a database of the server 104, and the multiple tag information may be associated with at least one item of information in the system.
In an embodiment, the information in the system may include first information and second information, specifically, the first information may be transaction information, the second information may be application information, and the association relationship between the tag information and each item of information in the system may be as shown in table 1 below:
table 1: association relation between system information and tag information
The server 104 may obtain the tag information of the user according to the login information of the user, where the tag information of the user may be established according to a plurality of items of information of the user, and specifically, the plurality of items of information of the user may include user filling material information, user equipment acquisition data, user external data, user operation behavior data, and user system data, where the user filling material information may be personal information filled by the user, such as unit information and address information in table 1. The user equipment acquisition data may be additional information acquired by the user's equipment, such as a handset, such as LBS (latitude and longitude) information in table 1. The external data of the user may be external user-related data obtained through the internet, such as in table 1, company revenue analysis, personal income, housing estate prices of home addresses, and the like. The user operation behavior data may be the user's browsing of the posting related page and the real-time operation behavior, such as the time to enter the page, the time to exit the page, the transaction times, etc. in table 1. The user system data may be user data generated by the system after the user submits the data authentication, such as user limit information in table 1.
Step S206, according to the label information corresponding to the user and the label information associated with each item of information, the intention of the user to different information in the system is obtained; the intent score characterizes how much the user has access to different information in the system.
The tag information corresponding to the user may be obtained from the server 104 according to the login information of the user, and as shown in table 1, each item of information may have its associated tag information, and the server 104 may obtain the intention of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each item of information. Wherein the intent score may characterize the amount of access intent of the user to different information in the system.
Specifically, in one embodiment, obtaining the intention score of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each item of information includes: according to the label information corresponding to the user and the label information associated with the first information, obtaining a first intention point corresponding to the user; the first intention score characterizes the intention of the user to access the first information; obtaining a second intention score corresponding to the user according to the label information corresponding to the user and the label information associated with the second information; the second intent score characterizes how much the user intends to access the second information. In this embodiment, the plurality of items of information in the system may include first information and second information, the intention score may include a first intention score and a second intention score, the server 104 may obtain the first intention score corresponding to the user according to the tag information corresponding to the user and the tag information associated with the first information, and may also obtain the second intention score corresponding to the user according to the tag information corresponding to the user and the tag information associated with the second information. The first intention score may indicate the magnitude of the user's access intention to the first information, and the second intention score may indicate the magnitude of the user's access intention to the second information.
And step S208, according to the intention score, determining the target information with the maximum user access intention from the multiple items of information contained in the system, and caching the target information.
The intention score may be an index of the magnitude of the access intention of the user to different information in the system, and the server 104 may determine target information with the maximum user access intention from a plurality of items of information included in the system according to the intention score, and cache the target information.
Specifically, the intention score may include the first intention score and the second intention score, and if the first intention score is greater than the second intention score, the server 104 may determine that the first information is the target information and cache the first information; if the first intent score is less than the second intent score, the server 104 may determine that the second information is the target information and cache the second information. Wherein, the server 104 may cache the first and second information by using Redis. In addition, when the first intent and the second intent are the same, the server 104 may cache the first information and the second information into Redis at the same time.
According to the information preloading method, login information of a user is obtained by responding to system login operation of the user, label information representing characteristic information of the user is obtained according to the login information, intention scores of different information in a system corresponding to the user are obtained according to the label information corresponding to the user and label information related to each item of information in the system, target information with the maximum user access intention is determined from multiple items of information contained in the system according to the intention scores, and the target information is cached. Compared with the traditional mode that after a user triggers a relevant instruction, the terminal acquires corresponding data and pages from the database or an external server, the scheme obtains the access intention of the user to different information by using the user tag, so that the corresponding information is cached, the user can quickly call when accessing the information, and the effect of reducing the information access response time is realized.
In one embodiment, before obtaining the login information of the user in response to the login operation of the user, the method further includes: acquiring personal information of a user and behavior information in a system; generating a plurality of personal information tags based on the personal information; each personal information tag is associated with a first information of the plurality of items of information; the first information represents the transaction information of the user; generating a plurality of behavior information tags based on the behavior information; each behavior information tag is associated with second information in the plurality of items of information; the second information represents the service application information of the user; and obtaining label information corresponding to the user according to the plurality of personal information labels and the plurality of behavior information labels.
In this embodiment, as shown in fig. 3, fig. 3 is a schematic flow chart of a tag information generating step in one embodiment. The server 104 may obtain personal information of the user and behavior information in the system, and form tag information of the user, where the personal information may include user filling material information, user equipment acquisition data, user external data, user system data, and the like, where the user filling material information may be personal information filled by the user, such as unit information and address information in table 1; the user equipment acquisition data may be additional information acquired by the user's equipment, such as a handset, such as LBS (latitude and longitude) information in table 1; the external data of the user can be external user related data acquired through the internet, for example, in table 1, company revenue, personal income, housing estate prices of home addresses and the like are analyzed; the user system data may be user data generated by the system after the user submits the data authentication, such as user limit information in table 1. The behavior information in the system may include user operation behavior data, which may be user browsing and posting related pages and real-time operation behaviors, such as time to enter a page, time to exit a page, transaction times, etc. in table 1. The server 104 may generate corresponding tags according to the identification rules and the configured threshold, as shown in table 1 above, for the obtained user-related information and data.
The labels generated by the personal information and the behavior information can be respectively associated with information in the system. Specifically, the personal information tag may be associated with first information in the system, for example, associated with user transaction information; the behavior information may be associated with second information in the system, for example, associated with service application information of the user. Note that, as shown in table 1, each tag may be associated with both the first information and the second information, and the association relationship between the personal information and the behavior information and each item of information in the system may be as shown in table 1. The server 104 may obtain tag information corresponding to the user based on the plurality of personal information tags and the plurality of behavior information tags of the user.
Specifically, the server 104 may record the tag value on the user when the data of the user meets a certain condition, that is, the tag value is considered to be valid, and may also classify the data according to the tag, which is mainly classified into application tags, transaction tags, and the like. For example, when the overall benefit of the unit where the user is located is reduced, the income of the user is reduced, and the user has room loan pressure, the system considers that the borrowing tendency of the user is increased, the borrowing condition is met, and the unit information label is printed on the user and classified as a transaction label. Each behavior has different labels, and the intention score of the user is comprehensively calculated through the different labels. The label generation process is described below using graduate transaction labels as an example.
The first step is as follows: the data is analyzed for aggregability and then the tags are defined. Graduates, as a large group of clients, the server 104 can analyze that it is easiest for users of graduate years to generate transactions, and if the data is evenly distributed, the data is not unique enough to be a label. For example, in table 3 below, the server 104 counts the transaction percentage based on the user graduation year, and finds that the main transaction group is a group of users with graduation 3 and 4 years, and has the condition of becoming a label.
Table 3: graduation year and number of trade people relation table
The second step is that: the server 104 generates corresponding tags according to the personal information of the user and the behavior information in the system, which may be performed according to specific generation conditions, and the server 104 may customize the generation conditions for the tags, and generate the user tags if the conditions are met. As shown in table 3, the users in graduation 3 and 4 years occupy 50% of the number of trades, that is, when the users are in the age range of graduation 3 and 4 years, the probability of trading is 50%, and the intention of the user trading is half as much, the graduate trading label can be generated. The condition may be automatically generated according to different information of the user, and the condition may be adjusted, and the initial value may be 50%.
Through the embodiment, the server 104 can generate corresponding tag information according to a plurality of information of the user, so that the access intention of the user on different information in the system can be calculated according to the tag information, and data and information with large access intention can be cached, thereby reducing the response time of the user on accessing the information in the system.
In one embodiment, further comprising: acquiring a plurality of labels corresponding to each item of information contained in the system; and taking the average score of the preset total score as the initial score corresponding to each label according to the number of the labels.
In this embodiment, the system may include multiple items of information, each item of information may have multiple corresponding tags, before calculating the intent score of each item of information, the server 104 may allocate an initial score to the multiple tags corresponding to each item of information, and the server 104 may use an average score of the preset total score as the initial score corresponding to each tag according to the number of the multiple tags corresponding to each item of information in the system.
Specifically, if the information in the system is the first information, and if the number of the tags corresponding to the first information is 5, the preset total score may be 100, and the server 104 may equally allocate 100 scores to the score of each tag corresponding to the first information, that is, each tag may obtain 20 scores, which is used as the initial score of each tag.
In one embodiment, obtaining the intention of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each item of information includes: acquiring label information corresponding to a user in label information associated with the current item information as a target label participating in calculation; and obtaining the sum of the products of the initial scores of the plurality of target tags and the weights corresponding to the target tags to obtain the intention score.
In this embodiment, each user may have corresponding tag information, each item of information in the system may also be associated with corresponding tag information, the server 104 may obtain, from the tag information associated with the current item of information, the tag information corresponding to the user as a target tag participating in the calculation, and may obtain a sum of a plurality of target tags and a product of an initial score and a weight corresponding to the target tag to obtain the intention score, which may be the intention score corresponding to the current item of information.
Specifically, the server 104 may obtain the intention score corresponding to the current item information according to the following formula:
where h is the initial score of the label, akIs the weight of the label, bkThe presence of the tag is indicated, that is, the tag is corresponding to the user, the presence is 1, and the absence is 0. The initial score of the tag is calculated based on the customer category and the currently existing tags, for example, 4 tags are applied, the score of the tag is 100/4-25, one tag is added, and the value is 100/5-20. The initial score of the tags is linearly proportional to the number of tags. And the weight value of the label is dynamically calculated according to the effective condition of the label, the initial value is 1, and the total number of the labels is equal to the number of the labels. When both tags are present, the model is divided into 100.
The plurality of items of information in the system may include first information and second information, where the first information may be transaction information, and the score of the graduates' intention to access the transaction information is calculated as an example, as shown in table 4:
| label (R) | Fraction (100/label number) | Initialization weight | Whether or not a tag is present |
| Graduate trade label | 20 | 1 | 1 |
| Unit impact tag | 20 | 1 | 0 |
| Housing influence label | 20 | 1 | 0 |
| Limit page browsing label | 20 | 1 | 1 |
| Transaction number label | 20 | 1 | 1 |
Table 4: intention score calculation table
As shown in table 4 above, taking the transaction as an example, there are five tags in total, and at initialization, the weight of each tag is the same, i.e. the coefficients are all 1, where the unit affects the tag and the housing affects the tag, two tags are not present. The calculation result is as follows: the intention for the transaction information is divided into 60 points, i.e., 20 × 1+20 × 1 × 0+20 × 1 ═ 60 points.
In addition, the server 104 may also pre-process and cache information for users meeting certain conditions, such as users with an intent greater than a certain value. Specifically, since preprocessing consumes server resources, a threshold determination needs to be performed on the model score, preprocessing is performed only when the condition is met, the server 104 may record all users with model scores greater than 0 in a preset time, for example, in one week, then rank the users according to the scores, the larger the score is, the more the label is, the more the intention is clear, then take the first 50% of the users, the user model score with the lowest score is used as the threshold score for comparison in the next week, for example, the last user model score of the first 50% is 60, then the user with model score greater than or equal to 60 in the next week participates in preprocessing and caching of information, thereby implementing dynamic adjustment of the intention score.
Through the embodiment, the server 104 can obtain the intention score corresponding to the current item information by using the number, the weight and the initial score of the tags, so that the corresponding information is cached according to the size of the intention score, and the effect of reducing the response time of the access information is realized.
In one embodiment, further comprising: acquiring target label information corresponding to a user who successfully accesses the target information within a preset period; the target label information comprises a plurality of labels; and adjusting the weight of each label according to the number of each label in the target label information.
In this embodiment, a preset period may be set according to an actual situation, for example, two months, the target tag information may be tag information corresponding to a user who successfully accesses the information after the server 104 preloads and caches the information in the system, and the server 104 may obtain the target tag information corresponding to the user who successfully accesses the cached target information in the preset period, and adjust a weight of each tag according to the number of each tag in the target tag information. Specifically, the weight of a tag may be increased when the number of tags is larger, and the weight of a tag may be decreased when the number of tags is smaller.
Through the embodiment, the server 104 may adjust the weight of each type of tag information according to the tag information corresponding to the user who successfully accesses the target information, so as to improve the accuracy of the user intention judgment, achieve the effect of more accurately judging the intention size of the information in the system accessed by the user, and cache the corresponding information.
In one embodiment, adjusting the weight of each type of tag according to the number of each type of tag in the target tag information includes: obtaining the occupation ratio of each label according to the number of each label in the target label information; subtracting preset values from the current weight of each label, and taking the sum of the subtracted preset values of the plurality of labels as the weight to be distributed; and respectively obtaining the products of the weight to be distributed and the occupation ratio of each label, and adding the weight of each label after subtracting the preset value and the corresponding product to obtain the adjusted weight corresponding to each label.
In this embodiment, the target tag information may be tag information corresponding to the user who successfully accesses the target information, and the target table tag information may include multiple types of tag information, where there may be one or more types of tag information. The server 104 may adjust the weight of each tag according to the number of each tag in the target tag. The server 104 may obtain, according to the number of each type of tag in the target tag information, a ratio of the total number of each type of tag in the target tag information, for example, by normalization processing, subtract a preset value, for example, subtract 0.1, from the current weight of each type of tag, and use a sum of the preset values subtracted from the plurality of types of tags as a weight to be allocated, or may obtain products of the weight to be allocated and the ratio of each type of tag, respectively, and add the weight of each type of tag subtracted from the preset value and the corresponding products to obtain an adjusted weight corresponding to each type of tag.
Specifically, taking each tag in table 3 as an example, the server 104 may record a period, for example, user tags that successfully transact within 2 months, perform normalization processing according to a tag proportion to obtain a usage rate of each tag, where each tag is given a competition value each time, this example is 0.1, the total number of five tags is 0.5, the server 104 may initialize a coefficient of each tag to be 1, and each coefficient is taken out 0.1 per period to participate in competition. The total competition value is 0.5, normalization processing is carried out according to the successful number to obtain a competition result, the competition result is summed with the rest value to obtain a final result shown in the table 5, and a new coefficient can be used in the next calculation.
| Label (R) | Number of successes | Normalization | Contention allocation value | Residual value | End result |
| Graduate trade label | 543 | 0.58 | 0.29 | 0.9 | 1.19 |
| Unit impact tag | 246 | 0.26 | 0.13 | 0.9 | 1.03 |
| Housing influence label | 30 | 0.03 | 0.02 | 0.9 | 0.92 |
| Limit page browsing label | 100 | 0.11 | 0.05 | 0.9 | 0.95 |
| Transaction number label | 20 | 0.02 | 0.01 | 0.9 | 0.91 |
| Total number of | 939 | 1.00 | 0.50 | 5 |
Table 5: weight value adjusting table
In addition, the server 104 may also adjust the generation threshold of each label according to the weight value of each label after adjusting the weight value. Specifically, when the label weight of the user is increased, the description effectiveness is improved, and the influence of the label is increased, so that the identification condition of the label can be improved, and the identification rate of the label is increased. Taking the graduate transaction label in table 5 as an example, the competition is improved by 19%, which shows that the influence of the label is large, and the identification range of the graduate transaction label should be increased. If the initial value is the first 50% of the graduation year, if the competition participation value is 25%, 50% -25% + (1+ 19%) 25% is about 55%, the identification of the graduation label is promoted to the graduation 2, 3, 4 year user by the graduation 3, 4 year user, otherwise, if the identification is attenuated, the graduation 3 year user can be identified as the graduation trade label.
Through the embodiment, the server 104 may readjust the weight of each tag according to the ratio of the number of each tag in the target tag, so as to improve the accuracy of the user intention determination, achieve the effect of more accurately determining the intention size of the information in the system accessed by the user, and cache the corresponding information.
In one embodiment, further comprising: and if the adjusted weight value corresponding to the label is smaller than the preset threshold value and the weight value corresponding to the label is in a continuous descending trend within the preset time, deleting the label from the system.
In this embodiment, the server 104 may remove an invalid tag from the system, and after adjusting the threshold of each tag, the server 104 may determine the weight of each tag, and if the weight of each tag is smaller than a preset threshold, for example, 0.15, and the weight of each tag is not increased within a preset time, for example, within half a year, and is in a continuously decreasing trend, the server 104 may determine that the tag is an invalid tag, and may remove the tag from the system.
By the embodiment, the server 104 can remove the invalid tag from the system, so that the effect of improving the user intention judgment accuracy can be achieved.
In one embodiment, as shown in fig. 4, fig. 4 is a schematic flow chart of an information preloading method in another embodiment. In this embodiment, the server 104 may first perform data acquisition on the information of the user, and obtain a plurality of tags corresponding to the user information through data analysis, that is, tag initialization, and may also calculate a model score according to the tags, that is, calculate an intention score of the user, the server 104 may also determine whether the model score, that is, the intention score satisfies a threshold value for preprocessing, if yes, may preprocess the corresponding data, if no, does not preprocess, the server 104 may also acquire a result of whether the user finally has access to a corresponding page, and adjust a weight of the tag according to the result.
In one embodiment, as shown in fig. 5, fig. 5 is a schematic flow chart of an information preloading method in another embodiment. In this embodiment, a user may log in a system by using an app or an H5 page in the terminal 102, after the user logs in, the terminal 102 may send login information to the server 104, the server 104 may obtain a tag corresponding to the user according to the login information of the user, perform an intent score calculation for intentions of different information in the system, determine data to be cached, such as transaction data or application data, according to an intent score, and may also cache the transaction data or the application data, specifically, may cache the transaction data or the application data in Redis, when the user enters the application page, the server 104 may retrieve the cached application data from the Redis, thereby responding to an operation of the user on the application page, and when the user enters the transaction page, the server 104 may retrieve the cached transaction data from the Redis, thereby responding to an operation of the user on the transaction page.
Through the embodiment, the server 104 can obtain the access intention of the user to different information in the system according to the tag information of the user, so that corresponding data and information are cached, and the effect of reducing the access response time of the user is realized.
It should be understood that although the various steps in the flowcharts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps or stages.
In one embodiment, as shown in fig. 6, there is provided an information preloading device including: a response module 500, a first obtaining module 502, a second obtaining module 504, and a determination module 506, wherein:
the response module 500 is configured to obtain login information of a user in response to a system login operation of the user.
A first obtaining module 502, configured to obtain, according to the login information, tag information corresponding to the user; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system.
A second obtaining module 504, configured to obtain, according to the tag information corresponding to the user and the tag information associated with each item of information, an intention score of the user for different information in the system; the intent score characterizes how much the user has access to different information in the system.
The determining module 506 is configured to determine, according to the intention score, target information with the greatest user access intention from multiple items of information included in the system, and cache the target information.
In one embodiment, the above apparatus further comprises: the generating module is used for acquiring personal information of a user and behavior information in the system; generating a plurality of personal information tags based on the personal information; each personal information tag is associated with a first information of the plurality of items of information; the first information represents the transaction information of the user; generating a plurality of behavior information tags based on the behavior information; each behavior information tag is associated with second information in the plurality of items of information; the second information represents the service application information of the user; and obtaining label information corresponding to the user according to the plurality of personal information labels and the plurality of behavior information labels.
In one embodiment, the above apparatus further comprises: the distribution module is used for acquiring a plurality of labels corresponding to each item of information contained in the system; and taking the average score of the preset total score as the initial score corresponding to each label according to the number of the labels.
In an embodiment, the second obtaining module 504 is specifically configured to obtain, as a target tag participating in calculation, tag information corresponding to a user in tag information associated with current item information; and obtaining the sum of the products of the initial scores of the plurality of target tags and the weights corresponding to the target tags to obtain the intention score.
In one embodiment, the above apparatus further comprises: the adjusting module is used for acquiring target label information corresponding to a user who successfully accesses the target information within a preset period; the target label information comprises a plurality of labels; and adjusting the weight of each label according to the number of each label in the target label information.
In an embodiment, the adjusting module is specifically configured to obtain a ratio of each type of tag according to the number of each type of tag in the target tag information; subtracting preset values from the current weight of each label, and taking the sum of the subtracted preset values of the various labels as the weight to be distributed; and respectively obtaining the products of the weight to be distributed and the occupation ratio of each label, and adding the weight of each label after subtracting the preset value and the corresponding product to obtain the adjusted weight corresponding to each label.
In one embodiment, the above apparatus further comprises: and the eliminating module is used for deleting the label from the system if the adjusted weight corresponding to the label is smaller than a preset threshold and the weight corresponding to the label is in a continuous descending trend within a preset time.
In an embodiment, the second obtaining module 504 is specifically configured to obtain the first intention score corresponding to the user according to the tag information corresponding to the user and the tag information associated with the first information; the first intention score characterizes the intention of the user to access the first information; obtaining a second intention score corresponding to the user according to the label information corresponding to the user and the label information associated with the second information; the second intent score characterizes how much the user intends to access the second information.
In an embodiment, the determining module 506 is specifically configured to determine that the first information is the target information and cache the first information through redis if the first intention score is greater than the second intention score; and if the first intention score is smaller than the second intention score, determining that the second information is the target information, and caching the second information through redis.
For specific limitations of the information preloading device, reference may be made to the above limitations of the information preloading method, which will not be described herein again. The modules in the information preloading device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface 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 comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store a plurality of items of information and data in the system. 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 an information preloading method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the information preloading method.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the information preloading method as described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An information preloading method, characterized in that the method comprises:
responding to the system login operation of a user, and acquiring login information of the user;
acquiring label information corresponding to the user according to the login information; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system;
according to the label information corresponding to the user and the label information associated with each item of information, obtaining the intention of the user for different information in the system; the intention score represents the magnitude of the user's access intention for different information in the system;
and according to the intention score, determining the target information with the maximum user access intention from a plurality of items of information contained in the system, and caching the target information.
2. The method of claim 1, wherein before obtaining the login information of the user in response to the login operation of the user, the method further comprises:
acquiring personal information of the user and behavior information in the system;
generating a plurality of personal information tags based on the personal information; each personal information tag is associated with a first information of the plurality of items of information; the first information characterizes transaction information of the user;
generating a plurality of behavior information tags based on the behavior information; each behavior information tag is associated with a second information of the plurality of information; the second information represents the service application information of the user;
and obtaining label information corresponding to the user according to the plurality of personal information labels and the plurality of behavior information labels.
3. The method of claim 2, further comprising:
acquiring a plurality of labels corresponding to each item of information contained in the system;
according to the number of the plurality of labels, taking the average score of the preset total score as the initial score corresponding to each label;
the obtaining the intention of the user for different information in the system according to the label information corresponding to the user and the label information associated with each item of information includes:
acquiring label information corresponding to the user in the label information associated with the current item information as a target label participating in calculation;
and acquiring the sum of products of the initial scores of the plurality of target tags and the weights corresponding to the target tags to obtain the intention score.
4. The method of claim 3, further comprising:
acquiring target label information corresponding to a user who successfully accesses the target information within a preset period; the target label information comprises a plurality of labels;
and adjusting the weight of each label according to the number of each label in the target label information.
5. The method according to claim 4, wherein the adjusting the weight of each type of tag according to the number of each type of tag in the target tag information comprises:
obtaining the occupation ratio of each label according to the number of each label in the target label information;
subtracting preset values from the current weight of each label, and taking the sum of the preset values subtracted by the various labels as the weight to be distributed;
and respectively obtaining the products of the weight to be distributed and the occupation ratio of each label, and adding the weight of each label after subtracting the preset value and the corresponding product to obtain the adjusted weight corresponding to each label.
6. The method of claim 5, further comprising:
and if the adjusted weight value corresponding to the label is smaller than a preset threshold value and the weight value corresponding to the label is in a continuous descending trend within preset time, deleting the label from the system.
7. The method according to claim 2, wherein obtaining the intention score of the user for different information in the system according to the tag information corresponding to the user and the tag information associated with each information comprises:
obtaining a first intention point corresponding to the user according to the label information corresponding to the user and the label information associated with the first information; the first intent score characterizes a magnitude of intent of the user to access the first information;
obtaining a second intention score corresponding to the user according to the label information corresponding to the user and the label information associated with the second information; the second intention score characterizes the amount of intention of the user to access the second information;
the determining, according to the intention score, target information with the maximum user access intention from a plurality of items of information contained in the system, and caching the target information, includes:
if the first intention score is larger than the second intention score, determining that the first information is the target information, and caching the first information through redis;
and if the first intention score is smaller than the second intention score, determining that the second information is the target information, and caching the second information through redis.
8. An information preloading device, comprising:
the response module is used for responding to the system login operation of the user and acquiring the login information of the user;
the first acquisition module is used for acquiring the label information corresponding to the user according to the login information; the label information represents the characteristic information of the user; each tag information is associated with at least one item of information in the system;
the second acquisition module is used for acquiring the intention scores of the users for different information in the system according to the label information corresponding to the users and the label information associated with each item of information; the intention score represents the magnitude of the user's access intention for different information in the system;
and the determining module is used for determining the target information with the maximum user access intention from a plurality of items of information contained in the system according to the intention score and caching the target information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010709709.4A CN111966935B (en) | 2020-07-22 | 2020-07-22 | Information preloading method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010709709.4A CN111966935B (en) | 2020-07-22 | 2020-07-22 | Information preloading method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111966935A true CN111966935A (en) | 2020-11-20 |
| CN111966935B CN111966935B (en) | 2023-12-12 |
Family
ID=73364419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010709709.4A Active CN111966935B (en) | 2020-07-22 | 2020-07-22 | Information preloading method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966935B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160004724A1 (en) * | 2013-02-19 | 2016-01-07 | Digitalglobe, Inc. | System and method for large scale crowdsourcing of map data cleanup and correction |
| US20160044127A1 (en) * | 2014-08-08 | 2016-02-11 | Facebook, Inc. | Identifying and caching content for offline use |
| CN109325024A (en) * | 2018-07-27 | 2019-02-12 | 平安科技（深圳）有限公司 | Label display method, apparatus, terminal device and the storage medium of project |
| US20190079977A1 (en) * | 2016-05-12 | 2019-03-14 | Alibaba Group Holding Limited | Method for determining user behavior preference, and method and device for presenting recommendation information |
| CN109740084A (en) * | 2019-01-10 | 2019-05-10 | 湖南快乐阳光互动娱乐传媒有限公司 | APP interface based on user behavior analysis preloads method and system |
| CN110610376A (en) * | 2019-08-01 | 2019-12-24 | 招联消费金融有限公司 | Behavior data response method and device, computer equipment and storage medium |
| CN110852338A (en) * | 2019-07-26 | 2020-02-28 | 平安科技（深圳）有限公司 | User portrait construction method and device |
| CN110910199A (en) * | 2019-10-16 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Item information sorting method and device, computer equipment and storage medium |
-
2020
- 2020-07-22 CN CN202010709709.4A patent/CN111966935B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160004724A1 (en) * | 2013-02-19 | 2016-01-07 | Digitalglobe, Inc. | System and method for large scale crowdsourcing of map data cleanup and correction |
| US20160044127A1 (en) * | 2014-08-08 | 2016-02-11 | Facebook, Inc. | Identifying and caching content for offline use |
| US20190079977A1 (en) * | 2016-05-12 | 2019-03-14 | Alibaba Group Holding Limited | Method for determining user behavior preference, and method and device for presenting recommendation information |
| CN109325024A (en) * | 2018-07-27 | 2019-02-12 | 平安科技（深圳）有限公司 | Label display method, apparatus, terminal device and the storage medium of project |
| CN109740084A (en) * | 2019-01-10 | 2019-05-10 | 湖南快乐阳光互动娱乐传媒有限公司 | APP interface based on user behavior analysis preloads method and system |
| CN110852338A (en) * | 2019-07-26 | 2020-02-28 | 平安科技（深圳）有限公司 | User portrait construction method and device |
| CN110610376A (en) * | 2019-08-01 | 2019-12-24 | 招联消费金融有限公司 | Behavior data response method and device, computer equipment and storage medium |
| CN110910199A (en) * | 2019-10-16 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Item information sorting method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111966935B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109345374B (en) | Risk control method and device, computer equipment and storage medium | |
| KR20160121806A (en) | Determining a temporary transaction limit | |
| CN111340616B (en) | Method, device, equipment and medium for approving online loan | |
| CN111400600A (en) | Message pushing method, device, equipment and storage medium | |
| CN115082209A (en) | Business data risk early warning method and device, computer equipment and storage medium | |
| CN112418673A (en) | Case allocation method, device and medium | |
| CN111061948B (en) | User tag recommendation method and device, computer equipment and storage medium | |
| CN109325796B (en) | Potential user screening method, device, computer equipment and storage medium | |
| CN112950347B (en) | Resource data processing optimization method and device, storage medium and terminal | |
| CN112784168A (en) | Information push model training method and device, and information push method and device | |
| CN110162535B (en) | Search method, apparatus, device and storage medium for performing personalization | |
| CN111966935B (en) | Information preloading method, device, computer equipment and storage medium | |
| CN113256422B (en) | Method and device for identifying bin account, computer equipment and storage medium | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN113806682A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN113076339A (en) | Data caching method, device, equipment and storage medium | |
| CN110852392A (en) | User grouping method, device, equipment and medium | |
| CN111429232A (en) | Product recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN113538020B (en) | Method and device for acquiring association degree of group of people features, storage medium and electronic device | |
| CN110941714A (en) | Classification rule base construction method, application classification method and device | |
| CN113657711B (en) | Method and device for evaluating influence of media, storage medium and computer equipment | |
| CN110610200B (en) | Vehicle and merchant classification method and device, computer equipment and storage medium | |
| CN113673547A (en) | User classification method and device, computer equipment and storage medium | |
| CN112070593A (en) | Data processing method, device, equipment and storage medium | |
| CN113159957A (en) | Transaction processing method and device |
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 | ||
| CP03 | Change of name, title or address |
Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee after: Zhaolian Consumer Finance Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: MERCHANTS UNION CONSUMER FINANCE Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |