CN117493677A - Personalized search information recommendation system and method based on user portraits - Google Patents
Personalized search information recommendation system and method based on user portraits Download PDFInfo
- Publication number
- CN117493677A CN117493677A CN202311496558.9A CN202311496558A CN117493677A CN 117493677 A CN117493677 A CN 117493677A CN 202311496558 A CN202311496558 A CN 202311496558A CN 117493677 A CN117493677 A CN 117493677A
- Authority
- CN
- China
- Prior art keywords
- preset
- training
- user
- time length
- information recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 186
- 238000012545 processing Methods 0.000 claims abstract description 55
- 230000003993 interaction Effects 0.000 claims description 23
- 230000005484 gravity Effects 0.000 description 14
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of computers, in particular to a personalized search information recommendation system and method based on user portraits, comprising a server group, a client, a data processing module, a training module and a central control module, wherein the central control module is used for judging whether the operation parameters of the data processing module accord with preset standards according to the total clicking time of each link in a recommended page by a user and the browsing time of the recommended page by the user, so that when the operation parameters of the data processing module are judged not to accord with the preset standards, the central control module is used for adjusting the preset training time or the proportion of the preference field of each associated user in information recommendation, thereby effectively improving the retrieval efficiency of the user.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a personalized search information recommendation system and method based on user portraits.
Background
With the rapid development of internet technology, the internet can provide users with rich information resources. By acquiring the interest tags of the users, information recommendation, advertisement delivery, crowd orientation and the like are performed according to the interest tags.
In a common user interest determining mode, interest labels are marked on users according to historical data of the users, the score of each interest label is calculated, and one or more interest labels which are ranked at the top are used as the interest labels of the users.
According to the interest tag determined by the method, the tag is single, so that the requirements of information recommendation which is required to be oriented by a user aiming at a platform cannot be met due to numerous refinement requirements, and the benefit maximization of information recommendation cannot be realized.
CN104679848B discloses a search recommendation method and device, the search recommendation method comprises receiving search words and obtaining recommendation content according to the search words; generating a title of the recommended content according to the search word and the recommended content, wherein the title comprises association information of the search word and association information of the recommended content; displaying the recommended content and the title of the recommended content; it follows that the prior art has the following problems: the corresponding preference field is not considered according to the retrieval time of the user, and the link of the preference field of the associated user added into the recommendation page is not considered to influence the accuracy of information recommendation, so that the retrieval efficiency of the user is influenced.
Disclosure of Invention
Therefore, the invention provides a personalized search information recommendation system and method based on user portraits, which are used for solving the problems that in the prior art, the corresponding preference field is not considered according to the search time of a user, the accuracy of information recommendation is affected by adding links of the preference field of the associated user into a recommendation page, and the search efficiency of the user is further affected.
In one aspect, the present invention provides a personalized search information recommendation system based on user portraits, comprising:
the server group comprises a plurality of fields, each field is provided with a plurality of links, and each link corresponds to a plurality of search keywords;
the client is connected with the server group and used for matching the search information of the user with each search keyword in the corresponding field to select a corresponding link as information recommendation of a recommendation page; for a single client it may be associated with the remaining clients to form an associated user, and the single user may interact with the associated user information;
the data processing module is connected with the client and used for counting the total interaction times of information interaction between a single user and each associated user, and selecting a plurality of time nodes in a single day as training nodes according to the acquired historical search records of the user;
the training module is respectively connected with the data processing module and the client and is used for selecting historical search records of each training time period in a preset training period according to each training node to train so as to acquire field preference for each training node; wherein each training time period comprises a preset training time length before each training node and a preset training time length after each training node;
the central control module is respectively connected with the client and the data processing module and is used for judging whether the operation parameters of the data processing module meet preset standards according to the total clicking time of each link in the recommended page by a user and the browsing time of the recommended page by the user, so that the specific weight of the information recommendation occupied by the preset training time or the preference field of each associated user is adjusted when the operation parameters of the data processing module are judged not to meet the preset standards.
Further, the data processing module acquires a historical search record of the user in a preset training period, so as to draw a time-search total frequency graph N (t) for the user according to the search total frequency of each time node in a single day in the preset training period in the historical search record, and respectively calculates each maximum value Li of the time-search total frequency graph N (t), wherein i=1, 2,3 … …, k and k are the total number of the maximum values of the time-search total frequency graph N (t);
the data processing module is used for arranging the maximum values Li in a descending order to obtain maximum values Li of the preset pole number, and marking the selected maximum values Li as training nodes;
aiming at a single training node training module, taking the time corresponding to the single training node as an anchor point, and training the acquired historical search records of the preset training duration before and after the anchor point so as to acquire the field preference aiming at the anchor point;
when a user searches, the domain preference of the anchor point closest to the current time node is used as the domain preference for the current search.
Further, the central control module determines whether the operation parameters of the data processing module meet the preset standard or not based on the total clicking time length of each link in the recommended page by the user, and adjusts the preset training time length to a corresponding value according to the difference value between the first preset total clicking time length and the total clicking time length when the operation parameters of the data processing module are judged not to meet the preset standard,
or when the operation parameters of the data processing module are primarily judged to be not in accordance with the preset standard, whether the operation parameters of the data processing module are in accordance with the preset standard is secondarily judged according to the browsing time length of the recommended page by the user.
Further, the central control module determines whether the operation parameters of the data processing module meet the preset standard or not based on the browsing duration of the recommended page by the user, and adjusts the preset training duration to the corresponding value according to the difference value between the first preset browsing duration and the browsing duration when the operation parameters of the data processing module are not determined to meet the preset standard,
or, according to the total interaction times of the user and each associated user, the proportion of the preference field of the associated user to the information recommendation is adjusted to a corresponding value.
Further, the central control module is provided with a plurality of time length adjusting modes aiming at the preset training time length based on the calculated click difference value between the first preset click total time length and the click total time length, and the adjusting amplitude of each time length adjusting mode aiming at the preset training time length is different.
Further, the central control module is provided with a plurality of training adjustment modes aiming at the preset training time based on the calculated browsing difference value between the first preset browsing time and the browsing time, and the adjustment amplitudes of the training adjustment modes aiming at the preset training time are different.
Further, the central control module is provided with a plurality of recommendation adjustment modes aiming at the proportion of the preference field of the associated user to the information recommendation based on the total interaction times of the user and each associated user, and the adjustment amplitudes of the recommendation adjustment modes aiming at the proportion of the preference field of the associated user to the information recommendation are different.
Further, under the condition that the adjustment of the preset training time length is completed, the central control module is provided with a plurality of adjustment modes for the specific gravity of the information recommendation of the preference field of the associated user based on the calculated training difference value of the preset training time length after the adjustment and the preset training time length before the adjustment, and the adjustment amplitudes of the specific gravity adjustment modes for the specific gravity of the information recommendation of the preference field of the associated user are different.
Further, the central control module compares the adjusted preset training time length with the preset maximum time length under the condition of completing adjustment of the preset training time length, and if the adjusted preset training time length is smaller than or equal to the preset maximum time length, the central control module judges that the adjusted preset training time length is used as an operation parameter of the training module; and if the adjusted preset training time period is longer than the preset maximum time period, the central control module judges that the preset maximum time period is used as the operation parameter of the training module, and adjusts the preset pole number to a corresponding value by using a preset pole adjusting coefficient.
On the other hand, the invention also provides a personalized search information recommending method using the personalized search information recommending system based on the user portrait, which comprises the steps of,
determining a plurality of training nodes according to the acquired historical search records of the user in a preset training period;
selecting a preset training time length before the training node and a preset training time length after each training node as a training time period for the training node according to the training nodes;
training historical search records of each day in a preset training period in a training time period to obtain domain preference aiming at a corresponding time node;
when a user searches, the client selects corresponding domain preference according to the searching time to select a corresponding link as information recommendation of a recommendation page in the corresponding domain;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user are not in accordance with the preset standard, adjusting the preset training time length or adjusting the proportion of the preference field of each associated user associated with the client to the information recommendation;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user meet the preset standard, maintaining the current operation parameter operation, or when the corresponding parameter adjustment is completed, using the adjusted parameter operation.
Compared with the prior art, the method determines the domain preference of the user at different time nodes in a single day, and meets the search requirements of the user for each time period in the single day, so that the search efficiency is improved.
Further, whether the operation parameters of the data processing module meet preset standards is judged according to the specific retrieval condition of the user, when the total clicking time of each link in the recommended page is too low, the training time period for each anchor point is judged to be increased so as to increase the training amount for the time node, and therefore the accuracy of information recommendation is effectively improved.
Further, when the total clicking time of the user on each link in the recommended page is low, acquiring the browsing time of the user on the recommended page, so as to judge that the user can finish acquiring the search content only by browsing the recommended page when the browsing time is long; when the browsing duration is short, the proportion of the preference field of the associated user to the information recommendation is judged to be higher, and the accuracy of the information recommendation is effectively improved by adding the link of the preference field of the associated user into the recommendation page.
Further, after the adjustment of the preset training time is completed, the proportion of the preference field of the associated user to the information recommendation is coordinated according to the specific adjustment condition of the preset training time, so that the accuracy of the information recommendation is effectively improved, and meanwhile, the searching convenience of the user is greatly improved.
Further, if the adjusted preset training time length reaches a preset critical value, the preset pole number is adjusted, and the preference fields of all time periods of the user are finely divided, so that the accuracy of information recommendation is effectively improved.
Further, the corresponding preference field is determined according to the retrieval time of the user, and the accuracy of information recommendation is effectively improved by adding the link of the preference field of the associated user into the recommendation page, so that the retrieval efficiency of the user is improved.
Drawings
FIG. 1 is a block diagram of a personalized search information recommendation system based on user portraits in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a personalized search information recommendation method based on user portraits according to an embodiment of the present invention;
FIG. 3 is a flowchart of a data determination method in which a central control module determines whether an operation parameter of a data processing module meets a preset standard according to a total clicking duration of each link in a recommended page by a user;
fig. 4 is a flowchart of a data secondary judgment mode in which a central control module determines whether an operation parameter of a data processing module accords with a preset standard according to browsing time of a user on a recommended page in the embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, fig. 2, fig. 3, and fig. 4, the block diagrams of the personalized search information recommendation system based on user portraits, the step flowcharts of the personalized search information recommendation method, the data determination mode flowcharts of determining whether the operation parameters of the data processing module meet the preset standard according to the total clicking duration of each link in the recommended page by the user, and the data secondary determination mode flowcharts of determining whether the operation parameters of the data processing module meet the preset standard according to the browsing duration of the recommended page by the user are shown in the embodiments of the invention; the embodiment of the invention discloses a personalized search information recommendation system and a personalized search information recommendation method based on user portraits, comprising the following steps:
the server group comprises a plurality of fields, each field is provided with a plurality of links, and each link corresponds to a plurality of search keywords;
the server combination can be connected with a plurality of clients;
the client is connected with the server group and used for matching the search information of the user with each search keyword in the corresponding field to select a corresponding link as information recommendation of a recommendation page; for a single client it may be associated with the remaining clients to form an associated user, and the single user may interact with the associated user information;
the data processing module is connected with the client and used for counting the total interaction times of information interaction between a single user and each associated user, and selecting a plurality of corresponding time nodes in a single day as training nodes according to the acquired historical search records of the user;
the training module is respectively connected with the data processing module and the client and is used for selecting historical search records of each training time period in a preset training period according to each training node to train so as to acquire field preference for each training node; wherein each training time period comprises a preset training time length before each training node and a preset training time length after each training node;
the central control module is respectively connected with the client and the data processing module and is used for judging whether the operation parameters of the data processing module meet preset standards according to the total clicking time of each link in the recommended page by a user and the browsing time of the recommended page by the user, so that the specific weight of the information recommendation occupied by the preset training time or the preference field of each associated user is adjusted when the operation parameters of the data processing module are judged not to meet the preset standards.
The search keywords correspond to the keywords of the search information to select corresponding links as information recommendation of the recommendation page; the user has associated users in the client, and can interact with the associated users in information, and the data processing module can count the total interaction times of the information interaction;
specifically, the data processing module acquires a historical search record of a user in a preset training period, so as to draw a time-search total frequency graph N (t) for the user according to the search total frequency of each time node in a single day in the preset training period in the historical search record, and respectively calculates each maximum value Li of the time-search total frequency graph N (t), wherein i=1, 2,3 … …, k and k are the total number of the maximum values of the time-search total frequency graph N (t);
the data processing module is used for arranging the maximum values Li in a descending order to obtain maximum values Li of the preset pole number, and marking the selected maximum values Li as training nodes;
aiming at a single training node training module, taking the time corresponding to the single training node as an anchor point, and training the acquired historical search records of the preset training duration before and after the anchor point so as to acquire the field preference aiming at the anchor point;
when a user searches, the domain preference of the anchor point closest to the current time node is used as the domain preference for the current search.
And determining the domain preference of the user at different time nodes in a single day, and fitting the search requirements of the user for each time period in the single day, thereby improving the search efficiency.
Specifically, the central control module determines whether the operation parameters of the data processing module meet the data judging mode of the preset standard according to the total clicking time length of each link in the recommended page under the condition that the user searches, wherein:
the first data judging mode is that the central control module judges that the operation parameters of the data processing module do not accord with preset standards, and the preset training time length is adjusted to a corresponding value according to the difference value between the first preset clicking total time length and the clicking total time length; the first data judging mode meets the condition that the total clicking duration is smaller than or equal to a first preset total clicking duration;
the second data judging mode is that the central control module preliminarily judges that the operation parameters of the data processing module do not accord with preset standards, and judges whether the operation parameters of the data processing module accord with the preset standards or not for the second time according to the browsing time length of the recommended page by the user; the second data judging mode meets the condition that the total clicking time length is smaller than or equal to a second preset clicking time length and larger than the first preset clicking time length, and the first preset clicking time length is smaller than the second preset clicking time length;
the third data judging mode is that the central control module judges that the operation parameters of the data processing module meet preset standards and controls the data processing module to maintain the current operation parameters to operate; the third data judging mode meets the condition that the total clicking duration is longer than the second preset total clicking duration.
Judging whether the operation parameters of the data processing module meet preset standards according to specific retrieval conditions of users, and when the total clicking time length of each link in the recommended page is too low, judging that the training time period for each anchor point is increased so as to increase the training amount for the time node, thereby effectively improving the accuracy of information recommendation.
Specifically, the central control module determines, in the second data determination manner, whether the operation parameters of the data processing module meet the data secondary determination manner of the preset standard according to the browsing duration of the user on the recommended page, where:
the first data secondary judging mode is that the central control module judges that the operation parameters of the data processing module do not accord with preset standards, and the preset training time length is adjusted to a corresponding value according to the difference value between the first preset browsing time length and the browsing time length; the first data secondary judgment mode meets the condition that the browsing duration is smaller than or equal to a first preset browsing duration;
the second data secondary judging mode is that the central control module judges that the operation parameters of the data processing module do not accord with preset standards, and the proportion of the preference field occupation information recommendation of the associated user is adjusted to a corresponding value according to the total interaction times of the user and each associated user; the second data secondary judgment mode meets the condition that the browsing duration is smaller than or equal to a second preset browsing duration and larger than the first preset browsing duration, and the first preset browsing duration is smaller than the second preset browsing duration;
the third data secondary judging mode is that the central control module judges that the operation parameters of the data processing module meet preset standards, and controls the data processing module to maintain the current operation parameters to operate; the third data secondary judgment mode meets the condition that the browsing time length is longer than the second preset browsing time length.
When the total clicking time of the user on each link in the recommended page is low, acquiring the browsing time of the user on the recommended page, so as to judge that the user can finish acquiring the search content only by browsing the recommended page when the browsing time is long; when the browsing duration is short, the proportion of the preference field of the associated user to the information recommendation is judged to be higher, and the accuracy of the information recommendation is effectively improved by adding the link of the preference field of the associated user into the recommendation page.
Specifically, the central control module determines a duration adjustment mode for the preset training duration according to a calculated click difference value between a first preset click total duration and the click total duration in the first data determination mode, wherein:
the first time length adjusting mode is that the central control module adjusts the preset training time length to a corresponding value by using a first preset time length adjusting coefficient; the first time length adjusting mode meets the condition that the click difference value is smaller than or equal to a first preset click difference value;
the second time length adjusting mode is that the central control module adjusts the preset training time length to a corresponding value by using a second preset time length adjusting coefficient; the second time length adjustment mode meets the condition that the click difference value is smaller than or equal to a second preset click difference value and larger than the first preset click difference value, and the first preset click difference value is smaller than the second preset click difference value;
the third time length adjusting mode is that the central control module adjusts the preset training time length to a corresponding value by using a third preset time length adjusting coefficient; the third duration adjustment mode satisfies that the click difference value is larger than the second preset click difference value.
Specifically, the central control module determines a training adjustment mode for the preset training time length according to the calculated browsing difference value between the first preset browsing time length and the browsing time length in the first data secondary judgment mode, wherein:
the first training adjustment mode is that the central control module adjusts the preset training duration to a corresponding value by using a first preset training adjustment coefficient; the first training adjustment mode meets the condition that the browsing difference value is smaller than or equal to a first preset browsing difference value;
the second training adjustment mode is that the central control module adjusts the preset training duration to a corresponding value by using a second preset training adjustment coefficient; the second training adjustment mode meets the condition that the browsing difference value is smaller than or equal to a second preset browsing difference value and larger than the first preset browsing difference value, and the first preset browsing difference value is smaller than the second preset browsing difference value;
the third training adjustment mode is that the central control module adjusts the preset training time length to a corresponding value by using a third preset training adjustment coefficient; the third training adjustment mode meets the condition that the browsing difference value is larger than the second preset browsing difference value.
Specifically, the central control module determines a recommendation adjustment mode of the preference field of the associated user accounting for the proportion of the information recommendation according to the total interaction times of the user and each associated user in the second data secondary judgment mode, wherein:
the first recommendation adjustment mode is that the central control module adjusts the proportion of the preference field occupation information recommendation of the associated user to a corresponding value by using a first preset recommendation adjustment coefficient; the first recommended adjustment mode meets the condition that the total interaction times are smaller than or equal to first preset interaction times;
the second recommendation adjustment mode is that the central control module adjusts the proportion of the preference field occupation information recommendation of the associated user to a corresponding value by using a second preset recommendation adjustment coefficient; the second recommended adjustment mode meets the condition that the total interaction times are smaller than or equal to second preset interaction times and larger than the first preset interaction times, and the first preset interaction times are smaller than the second preset interaction times;
the third recommendation adjustment mode is that the central control module adjusts the proportion of the preference field occupation information recommendation of the associated user to a corresponding value by using a third preset recommendation adjustment coefficient; the third recommended adjustment mode satisfies that the total interaction times are larger than the second preset interaction times.
Specifically, the central control module determines, under the condition that adjustment for a preset training duration is completed, an adjustment mode of the proportion of the preference field of the associated user to the information recommendation according to a calculated training difference value between the preset training duration after adjustment and the preset training duration before adjustment, wherein:
the first specific gravity adjusting mode is that the central control module adjusts the specific gravity recommended by the preference field occupation information of the associated user to a corresponding value by using a first preset specific gravity adjusting coefficient; the first weight adjustment mode meets the condition that the training difference value is smaller than or equal to a first preset training difference value;
the second specific gravity adjusting mode is that the central control module uses a second preset specific gravity adjusting coefficient to adjust the specific gravity recommended by the preference field occupation information of the associated user to a corresponding value; the second specific gravity adjusting mode meets the condition that the training difference value is smaller than or equal to a second preset training difference value and larger than the first preset training difference value, and the first preset training difference value is smaller than the second preset training difference value;
the third specific gravity adjusting mode is that the central control module adjusts the specific gravity recommended by the preference field occupation information of the associated user to a corresponding value by using a third preset specific gravity adjusting coefficient; the third specific gravity adjusting mode meets the condition that the training difference value is larger than the second preset training difference value.
Specifically, the central control module compares the adjusted preset training time length with the preset maximum time length under the condition of completing the adjustment of the preset training time length, and if the adjusted preset training time length is smaller than or equal to the preset maximum time length, the central control module judges that the adjusted preset training time length is used as an operation parameter of the training module; and if the adjusted preset training time period is longer than the preset maximum time period, the central control module judges that the preset maximum time period is used as the operation parameter of the training module, and adjusts the preset pole number to a corresponding value by using a preset pole adjusting coefficient.
Specifically, determining a plurality of training nodes according to the obtained historical search records of the user in a preset training period;
selecting a preset training time length before the training node and a preset training time length after each training node as a training time period for the training node according to the training nodes;
training historical search records of each day in a preset training period in a training time period to obtain domain preference aiming at a corresponding time node;
when a user searches, the client selects corresponding domain preference according to the searching time to select a corresponding link as information recommendation of a recommendation page in the corresponding domain;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user are not in accordance with the preset standard, adjusting the preset training time length or adjusting the proportion of the preference field of each associated user associated with the client to the information recommendation;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user meet the preset standard, maintaining the current operation parameter operation, or when the corresponding parameter adjustment is completed, using the adjusted parameter operation.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An associated user, and a single user may interact with the associated user information;
the data processing module is connected with the client and used for counting the total interaction times of information interaction between a single user and each associated user, and selecting a plurality of time nodes in a single day as training nodes according to the acquired historical search records of the user;
the training module is respectively connected with the data processing module and the client and is used for selecting historical search records of each training time period in a preset training period according to each training node to train so as to acquire field preference for each training node; wherein each training time period comprises a preset training time length before each training node and a preset training time length after each training node;
the central control module is respectively connected with the client and the data processing module and is used for judging whether the operation parameters of the data processing module meet preset standards according to the total clicking time of each link in the recommended page by a user and the browsing time of the recommended page by the user, so that the specific weight of the information recommendation occupied by the preset training time or the preference field of each associated user is adjusted when the operation parameters of the data processing module are judged not to meet the preset standards.
2. The personalized search information recommendation system based on user portraits according to claim 1, wherein the data processing module obtains a history search record of the user in a preset training period to draw a time-search total number graph N (t) for the user according to a search total number of each time node in a single day in the preset training period in the history search record, and the data processing module calculates each maximum value Li of the time-search total number graph N (t), wherein i = 1,2,3 … …, k, k is a total number of maximum values of the time-search total number graph N (t);
the data processing module is used for arranging the maximum values Li in a descending order to obtain maximum values Li of the preset pole number, and marking the selected maximum values Li as training nodes;
aiming at a single training node training module, taking the time corresponding to the single training node as an anchor point, and training the acquired historical search records of the preset training duration before and after the anchor point so as to acquire the field preference aiming at the anchor point;
when a user searches, the domain preference of the anchor point closest to the current time node is used as the domain preference for the current search.
3. The personalized search information recommendation system based on user portraits according to claim 2, wherein the central control module determines whether the operation parameters of the data processing module meet the preset standard based on the total clicking time length of each link in the recommended page by the user, and adjusts the preset training time length to a corresponding value according to the difference value between the first preset total clicking time length and the total clicking time length when the operation parameters of the data processing module are judged not to meet the preset standard,
or when the operation parameters of the data processing module are primarily judged to be not in accordance with the preset standard, whether the operation parameters of the data processing module are in accordance with the preset standard is secondarily judged according to the browsing time length of the recommended page by the user.
4. The personalized search information recommendation system based on user portraits according to claim 3, wherein the central control module determines whether the operation parameters of the data processing module meet a preset standard based on the browsing duration of the recommended page by the user, and adjusts the preset training duration to a corresponding value according to the difference between the first preset browsing duration and the browsing duration when the operation parameters of the data processing module are determined not to meet the preset standard,
or, according to the total interaction times of the user and each associated user, the proportion of the preference field of the associated user to the information recommendation is adjusted to a corresponding value.
5. The personalized search information recommendation system based on user portraits according to claim 4, wherein the central control module is provided with a plurality of time length adjustment modes aiming at the preset training time length based on a calculated click difference value between a first preset click total time length and the click total time length, and adjustment amplitudes of all the time length adjustment modes aiming at the preset training time length are different.
6. The personalized search information recommendation system based on user portraits according to claim 5, wherein the central control module is provided with a plurality of training adjustment modes aiming at the preset training duration based on the calculated browsing difference value between the first preset browsing duration and the browsing duration, and the adjustment amplitudes of the training adjustment modes aiming at the preset training duration are different.
7. The personalized search information recommendation system based on user portraits according to claim 6, wherein the central control module is provided with a plurality of recommendation adjustment modes aiming at the proportion of the preference field of the associated user to the information recommendation based on the total interaction times of the user and each associated user, and the adjustment amplitudes of the recommendation adjustment modes aiming at the proportion of the preference field of the associated user to the information recommendation are different.
8. The personalized search information recommendation system based on user portraits according to claim 7, wherein the central control module is provided with a plurality of adjustment modes aiming at the proportion of the preference field of the associated user to the information recommendation based on the calculated training difference value of the preset training time length after adjustment and the preset training time length before adjustment under the condition that the adjustment aiming at the preset training time length is completed, and the adjustment amplitude of each proportion adjustment mode aiming at the proportion of the preference field of the associated user to the information recommendation is different.
9. The personalized search information recommendation system based on user portraits according to claim 8, wherein the central control module compares the adjusted preset training time length with a preset maximum time length under the condition that adjustment for the preset training time length is completed, and if the adjusted preset training time length is smaller than or equal to the preset maximum time length, the central control module judges that the adjusted preset training time length is used as an operation parameter of the training module; and if the adjusted preset training time period is longer than the preset maximum time period, the central control module judges that the preset maximum time period is used as the operation parameter of the training module, and adjusts the preset pole number to a corresponding value by using a preset pole adjusting coefficient.
10. A personalized search information recommendation method using the personalized search information recommendation system based on a user portrayal according to any one of claims 1 to 9, comprising,
determining a plurality of training nodes according to the acquired historical search records of the user in a preset training period;
selecting a preset training time length before the training node and a preset training time length after each training node as a training time period for the training node according to the training nodes;
training historical search records of each day in a preset training period in a training time period to obtain domain preference aiming at a corresponding time node;
when a user searches, the client selects corresponding domain preference according to the searching time to select a corresponding link as information recommendation of a recommendation page in the corresponding domain;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user are not in accordance with the preset standard, adjusting the preset training time length or adjusting the proportion of the preference field of each associated user associated with the client to the information recommendation;
when the total clicking time length of each link in the recommended page of the user and the browsing time length of the recommended page of the user meet the preset standard, maintaining the current operation parameter operation, or when the corresponding parameter adjustment is completed, using the adjusted parameter operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311496558.9A CN117493677B (en) | 2023-11-10 | 2023-11-10 | Personalized search information recommendation system and method based on user portraits |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311496558.9A CN117493677B (en) | 2023-11-10 | 2023-11-10 | Personalized search information recommendation system and method based on user portraits |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117493677A true CN117493677A (en) | 2024-02-02 |
| CN117493677B CN117493677B (en) | 2024-05-28 |
Family
ID=89672312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311496558.9A Active CN117493677B (en) | 2023-11-10 | 2023-11-10 | Personalized search information recommendation system and method based on user portraits |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493677B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118041981A (en) * | 2024-03-19 | 2024-05-14 | 北京时代龙马国际会议展览有限公司 | Data analysis method based on exhibition management information |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7644427B1 (en) * | 2001-04-04 | 2010-01-05 | Microsoft Corporation | Time-centric training, interference and user interface for personalized media program guides |
| WO2017028096A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Method and user recommendation system for recommending nearby user according to website browsing time |
| WO2018023259A1 (en) * | 2016-07-31 | 2018-02-08 | 杨洁 | Television channel recommendation method and television |
| CN111310011A (en) * | 2020-01-20 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113420209A (en) * | 2021-06-21 | 2021-09-21 | 北京搜狗科技发展有限公司 | Recommendation method, device and equipment based on weather search and storage medium |
| CN114065038A (en) * | 2021-11-17 | 2022-02-18 | 中国银行股份有限公司 | Big data-based head information recommendation method and device |
| WO2022151649A1 (en) * | 2021-01-15 | 2022-07-21 | 稿定（厦门）科技有限公司 | Deep interest network-based topic recommendation method and apparatus |
| CN114896501A (en) * | 2022-05-19 | 2022-08-12 | 文楚霞 | Cloud computing and block chain based service recommendation method and cloud computing system |
| CN114969530A (en) * | 2022-05-31 | 2022-08-30 | 中国银行股份有限公司 | Service data processing method and device and server |
-
2023
- 2023-11-10 CN CN202311496558.9A patent/CN117493677B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7644427B1 (en) * | 2001-04-04 | 2010-01-05 | Microsoft Corporation | Time-centric training, interference and user interface for personalized media program guides |
| WO2017028096A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Method and user recommendation system for recommending nearby user according to website browsing time |
| WO2018023259A1 (en) * | 2016-07-31 | 2018-02-08 | 杨洁 | Television channel recommendation method and television |
| CN111310011A (en) * | 2020-01-20 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Information pushing method and device, electronic equipment and storage medium |
| WO2022151649A1 (en) * | 2021-01-15 | 2022-07-21 | 稿定（厦门）科技有限公司 | Deep interest network-based topic recommendation method and apparatus |
| CN113420209A (en) * | 2021-06-21 | 2021-09-21 | 北京搜狗科技发展有限公司 | Recommendation method, device and equipment based on weather search and storage medium |
| CN114065038A (en) * | 2021-11-17 | 2022-02-18 | 中国银行股份有限公司 | Big data-based head information recommendation method and device |
| CN114896501A (en) * | 2022-05-19 | 2022-08-12 | 文楚霞 | Cloud computing and block chain based service recommendation method and cloud computing system |
| CN114969530A (en) * | 2022-05-31 | 2022-08-30 | 中国银行股份有限公司 | Service data processing method and device and server |
Non-Patent Citations (5)
| Title |
|---|
| YAN ZHU; SONG LIU; HAN GUO; SHUAIJUN JIN: "Design of Adaptive Electrician Learning System Based on User Model", 2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY IN MEDICINE AND EDUCATION (ITME), 13 July 2017 (2017-07-13), pages 513 - 516 * |
| 李广明;付剑锋: "基于用户搜索状态的动态推荐模型研究", 情报理论与实践, vol. 44, no. 7, 31 July 2021 (2021-07-31), pages 166 - 172 * |
| 邵秀丽;乜聚科;田振雷;侯乐彩;: "用户个性化推荐系统的设计与实现", 计算机工程与设计, no. 20, 28 October 2009 (2009-10-28), pages 4681 - 4685 * |
| 高晨峰;: "深度神经网络视频新媒体短视频个性化推荐系统研究", 卫星电视与宽带多媒体, no. 05, 5 March 2019 (2019-03-05), pages 16 - 20 * |
| 黄丽;石松芳;: "基于用户关注度的个性化推荐系统研究", 软件导刊, no. 05, 15 May 2018 (2018-05-15), pages 90 - 92 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118041981A (en) * | 2024-03-19 | 2024-05-14 | 北京时代龙马国际会议展览有限公司 | Data analysis method based on exhibition management information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117493677B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220266020A1 (en) | Personalized network searching | |
| US11861531B2 (en) | Methods, systems, and media for providing direct and hybrid data acquisition approaches | |
| US8666979B2 (en) | Recommending interesting content using messages containing URLs | |
| CN117493677B (en) | Personalized search information recommendation system and method based on user portraits | |
| US6314420B1 (en) | Collaborative/adaptive search engine | |
| CN101189608B (en) | Systems and methods for analyzing a user's Web history | |
| US9087129B2 (en) | Methods, systems, and software for automated growth of intelligent on-line communities | |
| US8190556B2 (en) | Intellegent data search engine | |
| US7451161B2 (en) | Compatibility scoring of users in a social network | |
| KR101377799B1 (en) | Clustered search processing | |
| CN107256267A (en) | Querying method and device | |
| US20090271350A1 (en) | Apparatus and method for adaptively recommending service, system and method for adaptively recommending service, apparatus and method for recommending service based on user's favorite base | |
| CN110597962B (en) | Search result display method and device, medium and electronic equipment | |
| US20080160490A1 (en) | Seeking Answers to Questions | |
| US20060282312A1 (en) | Advertisements in an alert interface | |
| US20070256033A1 (en) | System and method for flagging information content | |
| US20070100795A1 (en) | System and method for associating an unvalued search term with a valued search term | |
| JP2007517269A (en) | System and method for improving ranking of news articles | |
| US20080147635A1 (en) | System, apparatus and method for providing weight to information gathering engine according to situation of user and computer readable medium processing the method | |
| JP2009545810A (en) | Temporal ranking of search results | |
| CN106326413A (en) | Personalized video recommending system and method | |
| CN107657347A (en) | Method is recommended in a kind of tourism towards group | |
| CN112100504B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| WO2009031759A1 (en) | Method and system for generating search collection of query | |
| EP1006458A1 (en) | Methods and apparatus for information retrieval |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |