CN112632378A - Information processing method based on big data and artificial intelligence and data server - Google Patents

Information processing method based on big data and artificial intelligence and data server Download PDF

Info

Publication number
CN112632378A
CN112632378A CN202011518316.1A CN202011518316A CN112632378A CN 112632378 A CN112632378 A CN 112632378A CN 202011518316 A CN202011518316 A CN 202011518316A CN 112632378 A CN112632378 A CN 112632378A
Authority
CN
China
Prior art keywords
content
information
event
attention
user
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
Application number
CN202011518316.1A
Other languages
Chinese (zh)
Other versions
CN112632378B (en
Inventor
高晓惠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Information Network Co.,Ltd.
Original Assignee
高晓惠
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 高晓惠 filed Critical 高晓惠
Priority to CN202011518316.1A priority Critical patent/CN112632378B/en
Publication of CN112632378A publication Critical patent/CN112632378A/en
Application granted granted Critical
Publication of CN112632378B publication Critical patent/CN112632378B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—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
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Abstract

The information processing method and the data server based on big data and artificial intelligence can successively identify the global level and the local level of the display records of the search contents of the marked users, carry out step-type refinement on the contents interested by the users, and simultaneously consider the sequencing condition of the display contents, thereby ensuring that the obtained local click identification information can be matched with the real intention of the users as much as possible. Based on the global click identification information and the local click identification information, user interest analysis can be achieved to accurately determine the user interest portrait. And actively inquiring the associated content corresponding to the display record based on the user interest portrait, and determining a target display mode of the inquiry result by combining the display area information corresponding to the display record. When the user searches the content subsequently, the query result can be queried in a target display mode, the user is prevented from repeatedly browsing the content browsed before, and the information searching efficiency is improved.

Description

Information processing method based on big data and artificial intelligence and data server
Technical Field
The application relates to the technical field of big data and artificial intelligence, in particular to an information processing method and a data server based on big data and artificial intelligence.
Background
With the development of the internet, users can query and search information through various search engines, so that the daily work and life needs are met. The development of big data enables the data processing function of the data server to be further optimized, so that the current search engine can display a large amount of data information for users to browse or use.
However, in the actual searching process, the user may not search for the information content desired by the user at the first time, and may repeatedly browse the previous content at the next searching, which may reduce the information searching efficiency.
Disclosure of Invention
The embodiment of the invention provides an information processing method based on big data and artificial intelligence, which comprises the following steps: acquiring a display record of search content of a marked user; identifying the display content of the display record of the search content of the marked user through a content identification model added with a global identification tag to obtain display content sequencing information of the display record of the search content of the marked user; performing global click operation identification and collection operation identification on the displayed content sorting information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information; performing local click operation identification on the displayed content sequencing information based on the global collection identification information through a content identification model added with a local identification tag to obtain local click identification information; the content identification model added with the local identification label is obtained by training a historical user behavior data set; analyzing the user interest of the global click identification information and the local click identification information to obtain a user interest portrait of a display record of the search content of the marked user; based on the user interest portrait, performing related content query on the display record to obtain a query result; and determining a target display mode of the query result according to the user interest picture and the display area information corresponding to the display record.
The embodiment of the invention also provides a data server, which comprises a processing engine, a network module and a memory; the processing engine and the memory communicate through the network module, and the processing engine reads the computer program from the memory and operates to perform the above-described method.
An embodiment of the present invention further provides a computer-readable signal medium, on which a computer program is stored, where the computer program is executed to implement the method described above.
The information processing method and the data server based on big data and artificial intelligence provided by the embodiment of the invention have the following technical effects: the method can sequentially identify the global level and the local level of the display records of the marked user search content, further carry out step-type refinement on the content interested by the user, and simultaneously consider the sequencing condition of the display content, thereby ensuring that the obtained local click identification information can be matched with the real intention of the user as much as possible. It can be understood that based on the global click identification information and the local click identification information, the user interest analysis of the marked user can be realized, and therefore the user interest portrait can be accurately determined. Furthermore, active query can be performed on the associated content corresponding to the display record based on the user interest portrait, and a target display mode of a query result is determined by combining the display area information corresponding to the display record. Therefore, when the user searches the content subsequently, the query result can be queried in a target display mode, so that the user is prevented from repeatedly browsing the previously browsed content, the user is helped to lock the interested content more quickly, the time consumption of the user in information searching is reduced, and the efficiency of information searching is improved.
In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
The methods, systems, and/or processes of the figures are further described in accordance with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which reference numerals represent similar mechanisms throughout the various views of the drawings.
FIG. 1 is a block diagram of an exemplary big data and artificial intelligence based information handling system, shown in accordance with some embodiments of the present invention.
Fig. 2 is a diagram illustrating the hardware and software components of an exemplary data server in accordance with some embodiments of the present invention.
FIG. 3 is a flow diagram illustrating an exemplary big data and artificial intelligence based information processing method and/or process according to some embodiments of the invention.
FIG. 4 is a block diagram of an exemplary big data and artificial intelligence based information processing apparatus, shown in accordance with some embodiments of the present invention.
Detailed Description
As described in the background, the inventors have studied and analyzed various large search engines and have found that these search engines almost all have the problem. In detail, for example, when the user searches for the related content of "how novice to exercise" for the first time, the first page of the presentation page of the corresponding search content may include content 1, content 2, content 3, and content 4. There may be nothing the user wants, and at this time, the user turns off the search engine and continues the content search of "how novice to exercise" after several days, and at this time, the first page of the page is still the content 1, the content 2, the content 3, and the content 4, and if the user forgets to browse the content 1, the content 2, the content 3, and the content 4 before, the browsing is performed again, which greatly reduces the efficiency of information search.
In order to solve the problems, the inventor innovatively provides an information processing method and a data server based on big data and artificial intelligence, which can identify the content of the search content of the user, thereby determining the user interest portrait of the user, and realizing the query of the related content of the previous display record, so that the query result can be pre-configured according to a target display mode, and the query result is displayed when the user searches next time, thereby avoiding the situation that the content of the user is the same when the user searches for multiple times, and further improving the efficiency of information search.
In order to better understand the technical solutions of the present invention, the following detailed descriptions of the technical solutions of the present invention are provided with the accompanying drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the examples of the present invention are the detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the examples of the present invention may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, systems, compositions, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the invention.
These and other features, functions, methods of execution, and combination of functions and elements of related elements in the structure and economies of manufacture disclosed in the present application may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this application. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. It should be understood that the drawings are not to scale.
Flowcharts are used herein to illustrate the implementations performed by systems according to embodiments of the present application. It should be expressly understood that the processes performed by the flowcharts may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, at least one other implementation may be added to the flowchart. One or more implementations may be deleted from the flowchart.
FIG. 1 is a block diagram illustrating an exemplary big data and artificial intelligence based information handling system 300, which big data and artificial intelligence based information handling system 300 may include a data server 100 and a user business device 200, according to some embodiments of the present invention. The user service device 200 may be a plurality of intelligent devices, such as a mobile phone and a computer.
In some embodiments, as shown in fig. 2, the data server 100 may include a processing engine 110, a network module 120, and a memory 130, the processing engine 110 and the memory 130 communicating through the network module 120.
Processing engine 110 may process the relevant information and/or data to perform one or more of the functions described herein. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the Processing engine 110 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.
Network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. Merely by way of example, the Network module 120 may include a cable Network, a wired Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a Wireless personal Area Network, a Near Field Communication (NFC) Network, and the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include wired or wireless network access points, such as base stations and/or network access points.
The Memory 130 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 130 is used for storing a program, and the processing engine 110 executes the program after receiving the execution instruction.
It will be appreciated that the configuration shown in fig. 2 is merely illustrative, and that the data server 100 may include more or fewer components than shown in fig. 2, or have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
Fig. 3 is a flowchart illustrating an exemplary big data and artificial intelligence based information processing method and/or process according to some embodiments of the present invention, which is applied to the data server 100 in fig. 1 and may specifically include the contents described in the following steps S110 to S150.
Step S110, obtaining the display record of the search content of the marked user. For example, the marked user may be a user corresponding to a user service device that is authorized to perform user image analysis to the data server in advance. For another example, the user C performs user portrait analysis authorization to the data server 100 through the user service device S, and when the user C logs in through the user service device S, the data server 100 may obtain a display record of the search content of the user C. As another example, the search content may be "how to customize the fitness program," and the presentation record may include fitness program customization program 1, fitness program customization program 2, and fitness program customization program 3.
Step S120, identifying the display content of the display record of the search content of the marked user through a content identification model added with a global identification tag to obtain the display content sequencing information of the display record of the search content of the marked user; and carrying out global click operation identification and collection operation identification on the displayed content sequencing information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information. For example, the global identification tag may show the recorded relevant show content from the whole reaction, and the content identification model may be a pre-trained network model. The display content ordering information may be used to represent the ordering of the display content, for example, the fitness plan customization scheme 2 is arranged at the first position, the fitness plan customization scheme 3 is arranged at the second position, and the fitness plan customization scheme 1 is arranged at the third position, which may be other situations, and is not limited herein. The click identification information and the collection identification information are used for reflecting the corresponding operations of the user on the above related content, and the click identification information and the collection identification information can be the operations which are performed after the user first sees the above content, so that here, "global" can be understood as the first browsing impression of the user on the presentation content.
Step S130, carrying out local click operation identification on the display content sequencing information based on the global collection identification information through a content identification model added with a local identification tag to obtain local click identification information; wherein the content identification model added with the local identification label is obtained by training a historical user behavior data set. For example, the local identification tag may be further identified based on the display content, where the local click identification information may be corresponding operation information when the user further clicks and browses on the display content, for example, the local click identification information may be corresponding identification information for further clicking on the fitness plan customization scheme 2, and then identification information for the shoulder training scheme f1 and the leg training scheme f2 in the fitness plan customization scheme 2.
Step S140, analyzing the user interest of the global click identification information and the local click identification information to obtain the user interest portrait of the display record of the search content of the marked user. For example, the user interest analysis is used to mine the content of interest to the user, for example, the user performs a multi-click browsing operation on the related content of the leg training scheme f2, and then the user's interest in leg training can be analyzed based on the global click recognition information and the local click recognition information, so that the user interest representation of the presentation record of the search content of the tagged user can be determined, and the subsequent query of the related content can be facilitated.
Step S150, based on the user interest portrait, performing related content query on the display record to obtain a query result; and determining a target display mode of the query result according to the user interest picture and the display area information corresponding to the display record. For example, the user interest representation may include content of interest to the user, or a set of tags after representation tag extraction by the data server 100 for the user. Continuing with the above example, if the user interest representation includes "the user is interested in leg training", then the content query associated with the presentation record may query for the relevant content of "leg training program", and the query result may also include "quadriceps femoris training program", "biceps femoris training program", and so on. The display area information can be used for representing the distribution condition of different contents when the contents are displayed. It will be appreciated that the presentation area information has some effect on whether the user clicks on the relevant presentation content, and in general, the user tends to click on the content of the most prominent presentation area. Therefore, the target display mode of the query result is determined by displaying the recorded display area information, and the display distribution condition of the associated content in the query result can be adjusted, so that the user can conveniently browse the query result subsequently, the user is helped to lock interested content more quickly, or the user is helped to acquire the desired content quickly, and the information searching efficiency is improved.
In summary, in the above-mentioned solution, the global level and the local level can be sequentially identified for the presentation record of the search content of the marked user, so as to further perform step-type refinement on the content interested by the user, and meanwhile, the ordering condition of the presentation content is considered, so that it can be ensured that the obtained local click identification information can be matched with the real intention of the user as much as possible. It can be understood that based on the global click identification information and the local click identification information, the user interest analysis of the marked user can be realized, and therefore the user interest portrait can be accurately determined. Furthermore, active query can be performed on the associated content corresponding to the display record based on the user interest portrait, and a target display mode of a query result is determined by combining the display area information corresponding to the display record. Therefore, when the user searches the content subsequently, the query result can be queried in a target display mode, so that the user is prevented from repeatedly browsing the previously browsed content, the user is helped to lock the interested content more quickly, the time consumption of the user in information searching is reduced, and the efficiency of information searching is improved.
In the following, some alternative embodiments will be described, which should be understood as examples and not as technical features essential for implementing the present solution.
In some examples, the performing, by the content identification model added with the global identification tag, content identification on the presentation record of the marked user 'S search content in step S120 to obtain presentation content ranking information of the presentation record of the marked user' S search content includes: and performing display content extraction and display content division processing on the display records of the marked user search content by using a display content processing model to obtain display content sequencing information of the display records of the marked user search content. For example, the display content processing model may be a pre-built neural network model, and the model parameters thereof may be selectively adjusted according to actual conditions, which will not be further described herein.
In some optional embodiments, the performing, as described in step S120, presentation content identification on the presentation record of the search content of the tagged user, and the step of obtaining presentation content ranking information of the presentation record of the search content of the tagged user includes: global display content identification is carried out on the display record of the search content of the marked user to obtain global content sequencing information; and carrying out local display content identification on the global content sequencing information to obtain local content sequencing information.
Further, the step S120 of performing global click operation recognition and collection operation recognition on the displayed content ranking information through the content recognition model added with the global recognition tag to obtain global click recognition information and global collection recognition information includes: and carrying out global click operation identification and collection operation identification on the local content sequencing information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information.
In some possible embodiments, in step S130, the step of identifying the displayed content ranking information by a local click operation through the content identification model with the added local identification tag based on the global collection identification information includes the following steps S131 and S132.
Step S131, performing content association on the global collection identification information and the global content ordering information to obtain content-associated display content ordering information. For example, the content association may be associating content having the same meaning as the text.
Step S132, carrying out local click operation identification on the displayed content sequencing information after the content association to obtain local click identification information.
On the basis of the above content, the step of performing local click operation recognition on the displayed content ranking information after the content association in step S132 to obtain local click recognition information may further include the content described in the following step S1321 to step S1323.
Step S1321, carrying out sorting information clustering processing on the display content sorting information after the content association to obtain the display content sorting information after sorting information clustering. For example, the clustering process may be performed according to an existing clustering algorithm, which is not described herein.
Step S1322 is to perform user click trajectory identification on the display content ranking information after the ranking information clustering, and obtain click guidance prompt information of the display content ranking information after the ranking information clustering. For example, the user click trajectory may be a mouse click trajectory or a touch click trajectory of the user.
And step S1323, performing local click operation identification by using the click guidance prompt information to obtain the local click identification information.
By such design, based on the content described in the above steps S1321 to S1323, the causal relationship between the click trajectory of the user and the corresponding click guidance prompt information can be considered, so as to ensure that the local click identification information can be matched with the real intention of the user as much as possible.
For some possible embodiments, in order to determine the user interest representation completely and in real time, deep mining and analysis of the intention tendency information of the user are required, and for this purpose, the step of performing user interest analysis on the global click identification information and the local click identification information to obtain the user interest representation of the presentation record of the search content of the marked user, which is described in step S140, specifically includes the following steps S141 to S143.
Step S141, global click intention analysis is carried out on the global click identification information, and first intention tendency information corresponding to the global click identification information is obtained.
And step S142, carrying out local click intention analysis on the local click identification information to obtain second intention tendency information corresponding to the local click identification information.
And step S143, analyzing the user interest based on the first intention tendency information and the second intention tendency information to obtain the user interest portrait of the display record of the search content of the marked user.
Thus, by performing the above steps S141 to S143, the user interest image can be completely determined in real time by determining different intention tendency information by analyzing the click intention of the click identification information, and by taking the intention tendency information of the user into consideration when determining the user interest image.
In a further embodiment, the step of performing the user interest analysis based on the first intention tendency information and the second intention tendency information in step S143 to obtain the user interest representation of the presentation record of the marked user' S search content specifically includes the following steps S1431 to S1435.
Step S1431, a user real-time attention content corresponding to the first intention tendency information and a user initial attention content corresponding to the second intention tendency information are obtained through respective query, where the user real-time attention content and the user initial attention content respectively include a plurality of content events with different content attention heat degrees. For example, the user is interested in content in real time to characterize the content that the user suddenly is interested in during the search, and the user is initially interested in content to characterize the content that the user was interested in prior to the search.
Step S1432, obtaining an initial event attention matching result of the first intention tendency information in any content event of the user real-time attention content, and determining a content event with the minimum content attention heat in the user initial attention content as a content event to be attended.
Step S1433, the initial event attention matching result is mapped to the content event to be attended according to the global click identification information and the local click identification information, an initial attention mapping result is obtained in the content event to be attended, and interest portrait association information between the first intention tendency information and the second intention tendency information is generated according to the initial event attention matching result and the initial attention mapping result.
Step S1434, obtaining an event attention updating result in the content event to be attended by taking the initial attention mapping result as a reference result, mapping the event attention updating result to the content event where the initial event attention matching result is located according to the user interest feedback data corresponding to the interest portrait association information, obtaining event heat change information corresponding to the event attention updating result in the content event where the initial event attention matching result is located, and determining a content event updating record of the event heat change information.
Step S1435, obtaining an event attention point mapping record of mapping the initial event attention degree matching result to the content event to be attended; according to the event matching information between the event heat degree change information and the target attention events corresponding to the plurality of attention point information on the event attention point mapping record, sequentially acquiring updated content event combinations corresponding to the content event update records in the initial attention content of the user according to timeliness information of the attention content, stopping acquiring the updated content event combinations in the next content event until the event search indexes of the content events in which the acquired updated content event combinations are located are consistent with the event search indexes of the content event update records in the real-time attention content of the user, and determining content event preference information between the content event update record and the last acquired updated content event combination, and determining the user interest portrait of the display record of the search content of the marked user based on the content event preference information.
By implementing the contents described in the above steps S1431 to S1435, the content which the user pays attention to in real time, the content which the user pays attention to initially, and the attention degree can be analyzed, and further, mapping processing is performed on different content events, attention degree changes, and event heat degree changes, and the event search index of the content event is considered, so that the content event preference information between the content event update record and the updated content event combination acquired last time can be accurately determined in real time, and the user interest image can be completely and timely determined.
For a further embodiment, the step of separately querying to obtain the real-time attention content of the user corresponding to the first intention tendency information and the initial attention content of the user corresponding to the second intention tendency information described in step S1431 may include step S1431a and step S1431 b.
Step S1431a, the user real-time attention content corresponding to the first intention tendency information is obtained by querying according to the key content information corresponding to the content attention heat degree, and the event preference information between any two content events having the same event label in the user real-time attention content is the key content information corresponding to the content attention heat degree.
Step S1431b, the user initial attention content corresponding to the second intention tendency information is obtained by querying according to the key content information corresponding to the content attention heat degree, and the event preference information between any two content events having the same event label in the user initial attention content is the key content information corresponding to the content attention heat degree.
For a further embodiment, the mapping the initial event attention matching result to the content event to be attended according to the global click identification information and the local click identification information, obtaining an initial attention mapping result in the content event to be attended, and generating interest portrait association information between the first intention trend information and the second intention trend information according to the initial event attention matching result and the initial attention mapping result, which is described in step S1433, may include the following steps S1433 a-S1433 d.
Step S1433a, mapping the initial event attention degree matching result to the content event to be attended according to the global click identification information and the local click identification information, and obtaining the initial attention degree mapping result in the content event to be attended.
Step S1433b, obtaining selected event information from the content event where the initial event attention matching result is located, where the selected event information is the event information within a preset effective attention duration with reference to the initial event attention matching result. For example, the preset effective attention duration may be adjusted according to actual situations, and is not limited herein.
Step S1433c, map the selected event information to the content event to be attended according to the global click identification information and the local click identification information, and obtain a related attention mapping result in the content event to be attended.
Step S1433d, generating the interest portrait related information between the first intention tendency information and the second intention tendency information according to the association relationship between the initial event attention matching result and the selected event information, the initial attention mapping result, and the association attention mapping result.
In this way, by implementing the above-described steps S1433 a-S1433 d, it is possible to ensure timeliness of the interest figure-related information between the first intention tendency information and the second intention tendency information, taking into account the effective attention duration.
For a further embodiment, in step S1433a, the mapping the initial event attention matching result to the content event to be attended according to the global click identification information and the local click identification information, and obtaining the initial attention mapping result in the content event to be attended may include the following steps S1433a1 to S1433a 4.
Step S1433a1, according to the global click identification information and the global click indication tag, mapping the initial event attention matching result to a target attention content event having time sequence continuity with the content event to be attended, so as to obtain a target attention mapping result.
Step S1433a2, according to the intention similarity information and the intention change information between the global intention tendency trajectory corresponding to the first intention tendency information and the local intention tendency trajectory corresponding to the second intention tendency information, maps the target attention degree mapping result to the marked content event of the second intention tendency information, and obtains an attention degree change result.
Step S1433a3, map the attention degree change result to the pushed content event with the hotspot push record under the marked content event of the second intention tendency information, so as to obtain a historical attention degree mapping result.
Step S1433a4, performing attention degree level adjustment on the historical attention degree mapping result, and mapping the historical attention degree mapping result after the attention degree level adjustment to the content event to be attended according to the global click identification information, to obtain the initial attention degree mapping result.
Further, according to the event matching information between the event heat degree change information and the target attention events corresponding to the plurality of attention point information on the event attention point mapping record described in step S1435, sequentially acquiring updated content event combinations corresponding to the content event update records in the initial attention content of the user according to timeliness information of the attention content, stopping acquiring the updated content event combinations in the next content event until the event search indexes of the content events in which the acquired updated content event combinations are located are consistent with the event search indexes of the content event update records in the real-time attention content of the user, and determining content event preference information between the content event update record and the last acquired updated content event combination may include steps S1435 a-S1435 c as follows.
Step S1435a, determining, according to the event heat degree change information and the event matching information between the target attention events corresponding to the multiple pieces of attention point information on the event attention point mapping record, a content event combination of the content event update record in the content event to be attended as an updated content event combination.
Step S1435b, if the event search index of the content event to be attended is greater than the event search index of the content event update record in the user real-time content to be attended, mapping the updated content event combination and the event attention point mapping record to a next content event of the content event to be attended, determining a content event combination in the next content event based on the mapped updated content event combination and the mapped event attention point mapping record, determining the next content event as the content event to be attended, and determining a content event combination in the next content event as the updated content event combination.
Step S1435c, if the event search index of the content event to be attended in the initial content of interest of the user is consistent with the event search index of the content event update record in the real-time content of interest of the user, determining content event preference information between the content event update record and the last determined updated content event combination.
In practical applications, the inventor finds that, in order to ensure the integrity of the associated content query, different data access paths need to be considered, and for this reason, in step S150, the associated content query is performed on the presentation record based on the user interest representation to obtain a query result, which may include the following steps S150 a-S150 d.
Step S150a, determining query link information for the presentation record based on the multi-level portrait classification result corresponding to the user interest portrait, where the query link information for the presentation record is related to the access path of the event content search engine that has been included.
Step S150b, generating a plurality of content query paths of the query link information for the presentation record.
Step S150c, obtaining query content indication information corresponding to each of the plurality of content query paths; the query content indication information is obtained by arranging a plurality of display record collection information.
Step S150d, based on the query content indication information corresponding to each of the plurality of content query paths, perform the associated content query of the local database and/or the remote database for the corresponding content query path, so as to obtain the associated content query result corresponding to each of the plurality of content query paths.
By implementing the steps S150 a-S150 d, query link information related to the access path of the event content search engine that has been recorded can be determined, and a plurality of content query paths can be determined, so that query content indication information can be determined, and related content queries of the local database and/or the remote database can be performed through the content query paths. This allows different data access paths to be taken into account, thereby ensuring the integrity of the queried associated content.
Further, the step S150a of determining the query link information for the presentation record includes: acquiring access flow information of an access path of the event content search engine in real time; when the access flow information of the access path has the access flow heat identification, taking an event content search engine corresponding to the access path with the abnormality as the query link information aiming at the display record; wherein the access path corresponding to the query link information for the presentation record comprises a plurality of access paths.
Further, the generating the plurality of content query paths for the query link information of the presentation record described in step S150b includes: respectively carrying out content index analysis on the multiple access paths to obtain access content indication information corresponding to the multiple access paths; and taking the access content indication information corresponding to the multiple access paths as multiple content query paths of the query link information aiming at the presentation record.
Further, the content query performed by the step S150d on the local database and/or the remote database for the corresponding content query path based on the query content indication information corresponding to the multiple content query paths to obtain the associated content query result corresponding to the multiple content query paths may include the following content described in steps S150d1 to S150d 3.
Step S150d1, performing query content integration analysis on the corresponding content query paths based on the query content indication information corresponding to each of the plurality of content query paths, to obtain query content integration results corresponding to each of the plurality of content query paths.
Step S150d2, when the query content integration result corresponding to each of the plurality of content query paths does not match the preset interest content integration result, determining that the associated content query result corresponding to each of the plurality of content query paths is a derived content query result.
Step S150d3, when the query content integration result corresponding to each of the plurality of content query paths matches the preset interest content integration result, obtaining database identification information corresponding to each of the plurality of content query paths, and when the database identification information corresponding to each of the plurality of content query paths is updated, determining that the associated content query result corresponding to each of the plurality of content query paths is an entertainment content query result; and when the identification information of the database corresponding to each of the plurality of content query paths is not updated, determining the associated content query result corresponding to each content query path as an office content query result.
In this way, based on the above steps S150d 1-S150 d3, the matching condition of the query content integration result and the preset interest content integration result can be respectively determined to determine different types of query results, thereby ensuring the integrity of the query results.
For an alternative embodiment, the step of obtaining the presentation record of the search content of the tagged user described in step S110 further includes step S100: and training the content identification model added with the global identification label and the content identification model added with the local identification label.
Further, the step of training the content identification model added with the global identification tag and the content identification model added with the local identification tag, which is described in step S100, specifically includes: the method for training the content recognition model added with the global recognition label comprises the following steps: acquiring a global historical user behavior data set, wherein the global historical user behavior data set comprises a plurality of non-real-time behavior data, and the non-real-time behavior data are behavior data carrying user identity information and user operation information of a marked user; inputting the non-real-time behavior data into a global network model to be trained to obtain global display content sequencing information; identifying the global display content sequencing information to obtain global identity updating information and global operation updating information of the marked user; obtaining label training data corresponding to the global identification label through the query of the global identity updating information, the user identity information, the global operation updating information and the user operation information; and performing iterative training on the global network model to be trained by using the label training data corresponding to the global identification labels to obtain the content identification model added with the global identification labels.
Further, the step of training the content identification model added with the global identification tag and the content identification model added with the local identification tag, which is described in step S100, specifically includes: the method for training the content recognition model added with the local recognition label comprises the following steps: acquiring a local historical user behavior data set, wherein the local historical user behavior data set comprises a plurality of real-time behavior data, and the real-time behavior data is behavior data carrying user identity information and user operation information of a marked user; identifying the real-time behavior data through the content identification model added with the global identification tag to obtain transition content sequencing information and identity updating information corresponding to the transition content sequencing information; inputting the transition content ordering information and the identity updating information corresponding to the global display content ordering information into a local network model to be trained to obtain local display content ordering information; identifying the local display content sequencing information to obtain local operation updating information of the marked user; label training data corresponding to the local identification label is obtained through the local operation updating information and the user operation information inquiry; and performing iterative training on the local network model to be trained by using the label training data corresponding to the local identification labels to obtain the content identification model added with the local identification labels.
For an alternative embodiment, the step S150 of determining the target display manner of the query result through the user interest image and the display area information corresponding to the display record may include the following steps S151 to S154.
Step S151, in response to a user query operation that does not perform display record storage, obtaining display content legacy information of the display record.
Step S152, respectively carrying out content area matching processing on the display content left information and the area position relation of the plurality of display area information corresponding to the display records through the user interest portrait to obtain the display record content display modes and the display area information content display modes, wherein the display record content display modes comprise output mode use records of a plurality of content output modes, the display area information content display modes comprise output mode use records of a plurality of content output modes, and the total number of the content output modes in the display area information content display modes is consistent with the total number of the content output modes in the display record content display modes.
Step S153, for each piece of display area information, determining user usage feedback data of output mode usage records corresponding to each other in the content display modes of the display records and the content display modes of the display area information, and determining a user attention index between the display records and the display area information according to multiple groups of determined user usage feedback data.
Step S154, according to the user attention degree indexes between the display records and the plurality of display area information, determining the target display mode of the query result.
By the design, when the target display mode of the query result is determined, different content display modes and content output modes can be considered, so that the attention index of the user is determined, the target display mode of the query result can be determined in a targeted manner according to the attention index of the user, and the subsequent browsing and viewing of the user are facilitated.
FIG. 4 is a block diagram illustrating an exemplary big data and artificial intelligence based information processing apparatus 140, the big data and artificial intelligence based information processing apparatus 140 including the following functional modules, according to some embodiments of the present invention.
The obtaining module 141 is configured to obtain a display record of the search content of the marked user.
The first identification module 142 is configured to perform display content identification on the display record of the search content of the marked user through a content identification model to which a global identification tag is added, so as to obtain display content ranking information of the display record of the search content of the marked user; and carrying out global click operation identification and collection operation identification on the displayed content sequencing information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information.
The second identification module 143 is configured to perform local click operation identification on the display content ranking information based on the global collection identification information through the content identification model to which the local identification tag is added, so as to obtain local click identification information; wherein the content identification model added with the local identification label is obtained by training a historical user behavior data set.
And the analysis module 144 is configured to perform user interest analysis on the global click identification information and the local click identification information to obtain a user interest representation of a display record of the search content of the marked user.
The query module 145 is configured to perform related content query on the display record based on the user interest representation to obtain a query result; and determining a target display mode of the query result according to the user interest picture and the display area information corresponding to the display record.
The description of the functional modules may refer to the description of the method shown in fig. 3, and will not be further described here.
Based on the same inventive concept, an information processing system based on big data and artificial intelligence is also provided, and further description about the system is as follows.
An information processing system based on big data and artificial intelligence comprises user service equipment of data servers which are communicated with each other; wherein the data server is configured to:
acquiring a display record of search content of a marked user;
identifying the display content of the display record of the search content of the marked user through a content identification model added with a global identification tag to obtain display content sequencing information of the display record of the search content of the marked user; performing global click operation identification and collection operation identification on the displayed content sorting information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information;
performing local click operation identification on the displayed content sequencing information based on the global collection identification information through a content identification model added with a local identification tag to obtain local click identification information; the content identification model added with the local identification label is obtained by training a historical user behavior data set;
analyzing the user interest of the global click identification information and the local click identification information to obtain a user interest portrait of a display record of the search content of the marked user;
based on the user interest portrait, performing related content query on the display record to obtain a query result; and determining a target display mode of the query result according to the user interest picture and the display area information corresponding to the display record.
The above description of the system may refer to the description of the method shown in fig. 3, and will not be further described here.
It should be understood that, for technical terms that are not noun-explained in the above, a person skilled in the art can deduce and unambiguously determine the meaning of the present invention from the above disclosure, for example, for some values, coefficients, weights, indexes, factors and other terms, a person skilled in the art can deduce and determine from the logical relationship between the above and the below, and the value range of these values can be selected according to the actual situation, for example, 0 to 1, for example, 1 to 10, and for example, 50 to 100, which is not limited herein.
The skilled person can unambiguously determine some preset, reference, predetermined, set and target technical features/terms, such as threshold values, threshold intervals, threshold ranges, etc., from the above disclosure. For some technical characteristic terms which are not explained, the technical solution can be clearly and completely implemented by those skilled in the art by reasonably and unambiguously deriving the technical solution based on the logical relations in the previous and following paragraphs. Prefixes of unexplained technical feature terms, such as "first", "second", "previous", "next", "current", "history", "latest", "best", "target", "specified", and "real-time", etc., can be unambiguously derived and determined from the context. Suffixes of technical feature terms not to be explained, such as "list", "feature", "sequence", "set", "matrix", "unit", "element", "track", and "list", etc., can also be derived and determined unambiguously from the foregoing and the following.
The foregoing disclosure of embodiments of the present invention will be apparent to those skilled in the art. It should be understood that the process of deriving and analyzing technical terms, which are not explained, by those skilled in the art based on the above disclosure is based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific terminology to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of at least one embodiment of the present application may be combined as appropriate.
In addition, those skilled in the art will recognize that the various aspects of the application may be illustrated and described in terms of several patentable species or contexts, including any new and useful combination of procedures, machines, articles, or materials, or any new and useful modifications thereof. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as a "unit", "component", or "system". Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in at least one computer readable medium.
A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the execution of aspects of the present application may be written in any combination of one or more programming languages, including object oriented programming, such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, or similar conventional programming languages, such as the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages, such as Python, Ruby, and Groovy, or other programming languages. The programming code may execute entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order of the process elements and sequences described herein, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods unless otherwise indicated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it should be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware means, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
It should also be appreciated that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. However, this method of disclosure is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Claims (10)

1. An information processing method based on big data and artificial intelligence is characterized by comprising the following steps:
acquiring a display record of search content of a marked user;
identifying the display content of the display record of the search content of the marked user through a content identification model added with a global identification tag to obtain display content sequencing information of the display record of the search content of the marked user; performing global click operation identification and collection operation identification on the displayed content sorting information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information;
performing local click operation identification on the displayed content sequencing information based on the global collection identification information through a content identification model added with a local identification tag to obtain local click identification information; the content identification model added with the local identification label is obtained by training a historical user behavior data set;
analyzing the user interest of the global click identification information and the local click identification information to obtain a user interest portrait of a display record of the search content of the marked user;
based on the user interest portrait, performing related content query on the display record to obtain a query result; and determining a target display mode of the query result according to the user interest picture and the display area information corresponding to the display record.
2. The big data and artificial intelligence based information processing method according to claim 1, wherein the step of performing the shown content recognition on the shown record of the marked user's search content through the content recognition model added with the global recognition tag to obtain the shown content ranking information of the shown record of the marked user's search content comprises:
and performing display content extraction and display content division processing on the display records of the marked user search content by using a display content processing model to obtain display content sequencing information of the display records of the marked user search content.
3. The big data and artificial intelligence based information processing method according to claim 1, wherein:
the step of identifying the display content of the display record of the search content of the marked user to obtain the display content sequencing information of the display record of the search content of the marked user comprises the following steps: global display content identification is carried out on the display record of the search content of the marked user to obtain global content sequencing information; performing local display content identification on the global content sequencing information to obtain local content sequencing information;
the step of performing global click operation recognition and collection operation recognition on the displayed content sorting information through the content recognition model added with the global recognition tag to obtain global click recognition information and global collection recognition information comprises the following steps: performing global click operation identification and collection operation identification on the local content sorting information through the content identification model added with the global identification tag to obtain global click identification information and global collection identification information;
the step of identifying the local click operation of the displayed content sorting information by the content identification model added with the local identification tag based on the global collection identification information to obtain the local click identification information comprises the following steps: performing content association on the global collection identification information and the global content ordering information to obtain display content ordering information after content association; and carrying out local click operation identification on the displayed content sequencing information after the content association to obtain local click identification information.
4. The big data and artificial intelligence based information processing method according to claim 3, wherein the step of identifying the local click operation on the displayed content ranking information after the content association to obtain local click identification information comprises:
performing sorting information clustering processing on the displayed content sorting information after the content association to obtain the displayed content sorting information after sorting information clustering;
identifying the clicking track of the display content sorting information after the sorting information clustering is carried out, and obtaining the clicking guide prompt information of the display content sorting information after the sorting information clustering;
and carrying out local click operation identification by using the click guidance prompt information to obtain the local click identification information.
5. The big data and artificial intelligence based information processing method according to claim 1, wherein the step of performing user interest analysis on the global click identification information and the local click identification information to obtain the user interest representation of the presentation record of the search content of the tagged user specifically comprises:
performing global click intention analysis on the global click identification information to obtain first intention tendency information corresponding to the global click identification information;
performing local click intention analysis on the local click identification information to obtain second intention tendency information corresponding to the local click identification information;
and analyzing the user interest based on the first intention tendency information and the second intention tendency information to obtain a user interest portrait of a display record of the search content of the marked user.
6. The big data and artificial intelligence based information processing method according to claim 5, wherein the step of performing user interest analysis based on the first intention tendency information and the second intention tendency information to obtain the user interest representation of the presentation record of the marked user's search content specifically comprises:
respectively inquiring to obtain user real-time attention content corresponding to first intention tendency information and user initial attention content corresponding to second intention tendency information, wherein the user real-time attention content and the user initial attention content respectively comprise a plurality of content events with different content attention heat degrees;
acquiring an initial event attention degree matching result of the first intention tendency information in any content event of the user real-time attention content, and determining the content event with the minimum content attention degree in the user initial attention content as a content event to be attended;
mapping the initial event attention matching result to the content event to be attended according to global click identification information and local click identification information, obtaining an initial attention mapping result in the content event to be attended, and generating interest portrait association information between the first intention tendency information and the second intention tendency information according to the initial event attention matching result and the initial attention mapping result;
obtaining an event attention updating result in the content event to be attended by taking the initial attention mapping result as a reference result, mapping the event attention updating result to the content event of the initial event attention matching result according to user interest feedback data corresponding to the interest portrait association information, obtaining event heat change information corresponding to the event attention updating result in the content event of the initial event attention matching result, and determining a content event updating record of the event heat change information;
obtaining an event attention point mapping record which maps the initial event attention degree matching result to the content event to be attended; according to the event matching information between the event heat degree change information and the target attention events corresponding to the plurality of attention point information on the event attention point mapping record, sequentially acquiring updated content event combinations corresponding to the content event update records in the initial attention content of the user according to timeliness information of the attention content, stopping acquiring the updated content event combinations in the next content event until the event search indexes of the content events in which the acquired updated content event combinations are located are consistent with the event search indexes of the content event update records in the real-time attention content of the user, and determining content event preference information between the content event update record and the last acquired updated content event combination, and determining the user interest portrait of the display record of the search content of the marked user based on the content event preference information.
7. The method according to claim 1, wherein the separately querying for the user real-time attention content corresponding to the first intention tendency information and the user initial attention content corresponding to the second intention tendency information comprises:
inquiring according to key content information corresponding to content attention heat to obtain the user real-time attention content corresponding to the first intention tendency information, wherein event preference information between any two content events with the same event label in the user real-time attention content is the key content information corresponding to the content attention heat;
querying according to key content information corresponding to content attention heat to obtain the user initial attention content corresponding to the second intention tendency information, wherein event preference information between any two content events with the same event label in the user initial attention content is the key content information corresponding to the content attention heat;
mapping the initial event attention matching result to the content event to be attended according to global click identification information and local click identification information, obtaining an initial attention mapping result in the content event to be attended, and generating interest portrait association information between the first intention tendency information and the second intention tendency information according to the initial event attention matching result and the initial attention mapping result, including:
mapping the initial event attention matching result to the content event to be attended according to the global click identification information and the local click identification information, and obtaining the initial attention mapping result in the content event to be attended;
acquiring selected event information in the content event where the initial event attention matching result is located, wherein the selected event information is event information which is within a preset effective attention duration and takes the initial event attention matching result as a reference;
mapping the selected event information to the content event to be attended according to the global click identification information and the local click identification information, and obtaining a correlation attention mapping result in the content event to be attended;
generating interest portrait correlation information between the first intention tendency information and the second intention tendency information according to the correlation between the initial event attention matching result and the selected event information, the initial attention mapping result and the correlation attention mapping result;
wherein the mapping the initial event attention matching result to the content event to be attended according to the global click identification information and the local click identification information to obtain the initial attention mapping result in the content event to be attended includes:
mapping the initial event attention matching result to a target attention content event having time sequence continuity with the content event to be attended according to the global click identification information and a global click indication label to obtain a target attention mapping result;
mapping the target attention degree mapping result to a marked content event of the second intention tendency information according to intention similarity information and intention change information between a global intention tendency track corresponding to the first intention tendency information and a local intention tendency track corresponding to the second intention tendency information to obtain an attention degree change result;
mapping the attention degree change result to a pushed content event with a hotspot pushing record under the marked content event of the second intention tendency information to obtain a historical attention degree mapping result;
performing attention degree grade adjustment on the historical attention degree mapping result, and mapping the historical attention degree mapping result after the attention degree grade adjustment to the content event to be attended according to the global click identification information to obtain an initial attention degree mapping result;
wherein, according to the event matching information between the event heat change information and the target attention events corresponding to the multiple attention point information on the event attention point mapping record, sequentially acquiring the updated content event combination corresponding to the content event update record in the initial attention content of the user according to the timeliness information of the attention content, stopping acquiring the updated content event combination in the next content event until the event search index of the content event where the acquired updated content event combination is located is consistent with the event search index of the content event update record in the real-time attention content of the user, and determining the content event preference information between the content event update record and the last acquired updated content event combination, the method includes:
determining a content event combination of the content event update record in the content event to be attended as an updated content event combination according to event matching information between the event heat change information and target attended events corresponding to the plurality of attended point information on the event attended point mapping record;
if the event search index of the content event to be attended is greater than the event search index of the content event update record in the real-time content to be attended by the user, mapping the updated content event combination and the event attention point mapping record into a next content event of the content event to be attended, determining the content event combination in the next content event based on the mapped updated content event combination and the mapped event attention point mapping record, determining the next content event as the content event to be attended, and determining the content event combination in the next content event as the updated content event combination;
and if the event search index of the content event to be attended in the initial content to be attended by the user is consistent with the event search index of the content event update record in the real-time content to be attended by the user, determining content event preference information between the content event update record and the updated content event combination determined last time.
8. The information processing method based on big data and artificial intelligence as claimed in claim 1, wherein performing a content-related query on the presentation record based on the user interest representation to obtain a query result comprises:
determining query link information aiming at the display record based on a multi-level portrait classification result corresponding to the user interest portrait, wherein the query link information aiming at the display record is related to an access path of a recorded event content search engine;
generating a plurality of content query paths of the query link information for the presentation record;
acquiring query content indication information corresponding to the plurality of content query paths; the query content indication information is obtained by arranging a plurality of display record collection information;
based on the query content indication information corresponding to the plurality of content query paths, performing associated content query of a local database and/or a remote database on the corresponding content query paths to obtain associated content query results corresponding to the plurality of content query paths;
wherein the determining query link information for the presentation record comprises:
acquiring access flow information of an access path of the event content search engine in real time;
when the access flow information of the access path has the access flow heat identification, taking an event content search engine corresponding to the access path with the abnormality as the query link information aiming at the display record; wherein the access path corresponding to the query link information for the presentation record comprises a plurality of access paths;
the generating a plurality of content query paths for the query link information for the presentation record includes:
respectively carrying out content index analysis on the multiple access paths to obtain access content indication information corresponding to the multiple access paths;
taking the access content indication information corresponding to each of the plurality of access paths as a plurality of content query paths of the query link information for the presentation record;
wherein, the performing, based on the query content indication information corresponding to each of the plurality of content query paths, the associated content query of the local database and/or the remote database for the corresponding content query path to obtain the associated content query result corresponding to each of the plurality of content query paths includes:
performing query content integration analysis on the corresponding content query paths based on the query content indication information corresponding to the plurality of content query paths to obtain query content integration results corresponding to the plurality of content query paths;
when the query content integration result corresponding to each of the plurality of content query paths is not matched with the preset interest content integration result, determining the associated content query result corresponding to each of the plurality of content query paths as a derived content query result;
when the query content integration result corresponding to each of the plurality of content query paths is matched with the preset interest content integration result, acquiring database identification information corresponding to each of the plurality of content query paths, and when the database identification information corresponding to each of the plurality of content query paths is updated, determining the associated content query result corresponding to each of the plurality of content query paths as an entertainment content query result; and when the identification information of the database corresponding to each of the plurality of content query paths is not updated, determining the associated content query result corresponding to each content query path as an office content query result.
9. A data server comprising a processing engine, a network module and a memory; the processing engine and the memory communicate through the network module, the processing engine reading a computer program from the memory and operating to perform the method of any of claims 1-8.
10. A computer-readable signal medium, on which a computer program is stored which, when executed, implements the method of any one of claims 1-8.
CN202011518316.1A 2020-12-21 2020-12-21 Information processing method based on big data and artificial intelligence and data server Active CN112632378B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011518316.1A CN112632378B (en) 2020-12-21 2020-12-21 Information processing method based on big data and artificial intelligence and data server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011518316.1A CN112632378B (en) 2020-12-21 2020-12-21 Information processing method based on big data and artificial intelligence and data server

Publications (2)

Publication Number Publication Date
CN112632378A true CN112632378A (en) 2021-04-09
CN112632378B CN112632378B (en) 2021-08-24

Family

ID=75320740

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011518316.1A Active CN112632378B (en) 2020-12-21 2020-12-21 Information processing method based on big data and artificial intelligence and data server

Country Status (1)

Country Link
CN (1) CN112632378B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114169523A (en) * 2022-02-10 2022-03-11 一道新能源科技(衢州)有限公司 Solar cell use data analysis method and system
CN114357324A (en) * 2022-03-21 2022-04-15 南京师范大学 Generation method of big data exploratory label map
CN114415612A (en) * 2021-12-31 2022-04-29 旭昇智能科技(常熟)有限公司 Intelligent production monitoring method based on artificial intelligence and server

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046804A (en) * 2006-03-30 2007-10-03 国际商业机器公司 Method for searching order in file system and correlation search engine
US20080059298A1 (en) * 2006-02-15 2008-03-06 Liquidity Services Inc. Dynamic keyword auctioning system, method and computer program product
CN101140588A (en) * 2007-10-10 2008-03-12 华为技术有限公司 Method and apparatus for ordering incidence relation search result
US20090254971A1 (en) * 1999-10-27 2009-10-08 Pinpoint, Incorporated Secure data interchange
CN103365901A (en) * 2012-04-01 2013-10-23 上海聚力传媒技术有限公司 Method for obtaining information on clicked webpage objects, device for obtaining information on clicked webpage objects and equipment for obtaining information on clicked webpage objects
CN104111989A (en) * 2014-07-02 2014-10-22 百度在线网络技术（北京）有限公司 Providing method and device of search results
CN104679743A (en) * 2013-11-26 2015-06-03 阿里巴巴集团控股有限公司 Method and device for determining preference model of user
CN106407425A (en) * 2016-09-27 2017-02-15 北京百度网讯科技有限公司 A method and a device for information push based on artificial intelligence
CN106407346A (en) * 2016-09-06 2017-02-15 百度在线网络技术（北京）有限公司 Retrieval processing method and apparatus based on artificial intelligence
CN107153684A (en) * 2017-04-24 2017-09-12 北京小米移动软件有限公司 Display methods, device and the equipment of PUSH message
CN108387316A (en) * 2018-05-17 2018-08-10 中国科学院西安光学精密机械研究所 A kind of video-type adaptive targets identification device and method
CN109858565A (en) * 2019-02-28 2019-06-07 南京邮电大学 The home interior scene recognition method of amalgamation of global characteristics and local Item Information based on deep learning
CN110008367A (en) * 2019-03-18 2019-07-12 北京工业大学 A kind of image recommendation method that the manifold based on multi-modal collaboration is propagated
CN111191122A (en) * 2019-12-20 2020-05-22 重庆邮电大学 Learning resource recommendation system based on user portrait
CN111310731A (en) * 2019-11-15 2020-06-19 腾讯科技（深圳）有限公司 Video recommendation method, device and equipment based on artificial intelligence and storage medium
CN111444428A (en) * 2020-03-27 2020-07-24 腾讯科技（深圳）有限公司 Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium
CN111932386A (en) * 2020-09-09 2020-11-13 腾讯科技（深圳）有限公司 User account determining method and device, information pushing method and device, and electronic equipment

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090254971A1 (en) * 1999-10-27 2009-10-08 Pinpoint, Incorporated Secure data interchange
US20080059298A1 (en) * 2006-02-15 2008-03-06 Liquidity Services Inc. Dynamic keyword auctioning system, method and computer program product
CN101046804A (en) * 2006-03-30 2007-10-03 国际商业机器公司 Method for searching order in file system and correlation search engine
CN101140588A (en) * 2007-10-10 2008-03-12 华为技术有限公司 Method and apparatus for ordering incidence relation search result
CN103365901A (en) * 2012-04-01 2013-10-23 上海聚力传媒技术有限公司 Method for obtaining information on clicked webpage objects, device for obtaining information on clicked webpage objects and equipment for obtaining information on clicked webpage objects
CN104679743A (en) * 2013-11-26 2015-06-03 阿里巴巴集团控股有限公司 Method and device for determining preference model of user
CN104111989A (en) * 2014-07-02 2014-10-22 百度在线网络技术（北京）有限公司 Providing method and device of search results
CN106407346A (en) * 2016-09-06 2017-02-15 百度在线网络技术（北京）有限公司 Retrieval processing method and apparatus based on artificial intelligence
CN106407425A (en) * 2016-09-27 2017-02-15 北京百度网讯科技有限公司 A method and a device for information push based on artificial intelligence
CN107153684A (en) * 2017-04-24 2017-09-12 北京小米移动软件有限公司 Display methods, device and the equipment of PUSH message
CN108387316A (en) * 2018-05-17 2018-08-10 中国科学院西安光学精密机械研究所 A kind of video-type adaptive targets identification device and method
CN109858565A (en) * 2019-02-28 2019-06-07 南京邮电大学 The home interior scene recognition method of amalgamation of global characteristics and local Item Information based on deep learning
CN110008367A (en) * 2019-03-18 2019-07-12 北京工业大学 A kind of image recommendation method that the manifold based on multi-modal collaboration is propagated
CN111310731A (en) * 2019-11-15 2020-06-19 腾讯科技（深圳）有限公司 Video recommendation method, device and equipment based on artificial intelligence and storage medium
CN111191122A (en) * 2019-12-20 2020-05-22 重庆邮电大学 Learning resource recommendation system based on user portrait
CN111444428A (en) * 2020-03-27 2020-07-24 腾讯科技（深圳）有限公司 Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium
CN111932386A (en) * 2020-09-09 2020-11-13 腾讯科技（深圳）有限公司 User account determining method and device, information pushing method and device, and electronic equipment

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
OLIVIER CHAPELLE 等: "A dynamic bayesian network click model for web search ranking", 《WORLD WIDE WEB》 *
王晓迪: "基于搜索引擎的查询推荐算法研究", 《软件导刊》 *
贾博研 等: "基于搜索引擎的提高用户粘性优化研究", 《无线互联科技》 *
高晓惠: "高光谱数据处理技术研究", 《中国博士学位论文全文数据库基础科学辑》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114415612A (en) * 2021-12-31 2022-04-29 旭昇智能科技(常熟)有限公司 Intelligent production monitoring method based on artificial intelligence and server
CN114169523A (en) * 2022-02-10 2022-03-11 一道新能源科技(衢州)有限公司 Solar cell use data analysis method and system
CN114169523B (en) * 2022-02-10 2022-05-31 一道新能源科技(衢州)有限公司 Solar cell use data analysis method and system
CN114357324A (en) * 2022-03-21 2022-04-15 南京师范大学 Generation method of big data exploratory label map
CN114357324B (en) * 2022-03-21 2022-06-14 南京师范大学 Method for generating big data exploratory label map

Also Published As

Publication number Publication date
CN112632378B (en) 2021-08-24

Similar Documents

Publication Publication Date Title
CN112632378B (en) Information processing method based on big data and artificial intelligence and data server
CN110866181B (en) Resource recommendation method, device and storage medium
CN109033386B (en) Search ranking method and device, computer equipment and storage medium
CN109634698B (en) Menu display method and device, computer equipment and storage medium
CN108959644B (en) Search ranking method and device, computer equipment and storage medium
US20200110842A1 (en) Techniques to process search queries and perform contextual searches
WO2020019562A1 (en) Search sorting method and device, electronic device, and storage medium
CN109564573A (en) Platform from computer application metadata supports cluster
CN110781204B (en) Identification information determining method, device, equipment and storage medium of target object
CN111460248A (en) System and method for online-to-offline services
CN113254630B (en) Domain knowledge map recommendation method for global comprehensive observation results
CN110880006A (en) User classification method and device, computer equipment and storage medium
CN109145129A (en) Depth measure learning method and its device based on level triple loss function
CN110580278A (en) personalized search method, system, equipment and storage medium according to user portrait
CN109300041A (en) Typical karst ecosystem recommended method, electronic device and readable storage medium storing program for executing
CN107451280B (en) Data communication method and device and electronic equipment
CN112132238A (en) Method, device, equipment and readable medium for identifying private data
CN114911992A (en) Intelligent interactive data processing method based on intelligent lock
CN109271416A (en) Time management recommended method, electronic device and readable storage medium storing program for executing
CN112612901A (en) Medical knowledge map intelligent management retrieval platform
CN112817442A (en) Situation information classification recommendation system and method under multi-task condition based on FFM
CN111475720A (en) Recommendation method, recommendation device, server and storage medium
CN113409014A (en) Big data service processing method based on artificial intelligence and artificial intelligence server
CN114861818A (en) Main data matching method, device, equipment and storage medium based on artificial intelligence
CN115018608A (en) Risk prediction method and device and computer equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210803

Address after: 510000 floor 14, material building, No. 12, beijiaochangheng Road, Yuexiu District, Guangzhou City, Guangdong Province

Applicant after: Guangdong Information Network Co.,Ltd.

Address before: Room 1625, 16th floor, building B, Yunnan Copper Compaq building, Kegao Road, high tech Zone, Kunming, Yunnan 650000

Applicant before: Gao Xiaohui

GR01 Patent grant
GR01 Patent grant