CN108549700B - Page pre-search method and system, storage medium and electronic equipment - Google Patents
Page pre-search method and system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108549700B CN108549700B CN201810343604.4A CN201810343604A CN108549700B CN 108549700 B CN108549700 B CN 108549700B CN 201810343604 A CN201810343604 A CN 201810343604A CN 108549700 B CN108549700 B CN 108549700B
- Authority
- CN
- China
- Prior art keywords
- user
- search
- searching
- page
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a page pre-searching method and a system thereof, a storage medium and electronic equipment. The page pre-searching method comprises the following steps: recording historical click behaviors of a user in a search page, and generating a plurality of button path information according to the historical click behaviors; generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of behavior prediction comprises a plurality of path prediction information; receiving the current click behavior of a user; judging whether the current order of the clicking behaviors of the user accords with the path prediction information, if so, searching and loading a page pointed in the path prediction information of a filtering matching rule of the behavior prediction in advance, and caching the loaded data; receiving a user searching instruction; and judging whether the user search instruction hits the cached loading data, if so, displaying by using the cached loading data.
Description
Technical Field
The invention relates to a page pre-searching method and a system thereof, a storage medium and electronic equipment.
Background
At present, after a user initiates a search request (clicks a search button) for a page search process, the search request is submitted to a server for searching and loading, and a search result and a loaded result are displayed after the result is returned.
Conventional approaches to reducing latency include:
(1) reducing transmission delay, including optimizing a network and improving transmission bandwidth; reducing transmission messages and transmission quantity; improving the performance of serialization/deserialization, etc.
(2) And the performance of the service is optimized, and the service time consumption is shortened.
(3) The rendering performance of the front end is optimized, and the presentation time of the information is shortened.
The method has a limit on the effect of reducing the time delay, and has certain limitation, along with the improvement of the effect, higher cost is required for further improvement.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a page pre-searching method, a system, a storage medium and electronic equipment thereof, which can search and load possible search contents of a user in advance by predicting the clicking behavior of the user, so that the time delay of the display of a search result is reduced, and the user experience is improved.
According to one aspect of the present invention, a method for pre-searching a page is provided, which includes the following steps: s10: recording historical click behaviors of a user in a search page, and generating a plurality of button path information according to the historical click behaviors, wherein each button path information comprises all the historical click behaviors of the user in the same session and a target page pointed by final search; s20: generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of behavior prediction comprises a plurality of path prediction information; s30: receiving the current click behavior of a user; s40: judging whether the current order of the clicking behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction, if so, executing the step S50; s50: searching and loading a page pointed by the path prediction information of the filtering matching rule predicted according to the behavior in advance, and caching the loaded data; s60: receiving a user searching instruction; s70: judging whether the user search instruction hits the cached loading data, if so, executing step S80; s80: and using the cached loading data for presentation.
Preferably, the page pre-search method is used for an air ticket search page, and the air ticket search page at least comprises a date selection button and an arrival city selection button; the step S10 further includes the steps of: and setting buried points at the positions of the date selection button and the arrival city selection button, and recording the historical clicking behaviors of the user in the search page through the buried points.
Preferably, the page pre-search method is used in a mobile terminal, and after the step S50 is completed, the step S60 further includes the following steps: according to the flight time and arrival city information in the cached loading data, searching communication package information which is provided by a communication network operator to which the mobile terminal belongs and is adaptive to the flight time and arrival city information, and calculating corresponding cost; and adding the searched communication package information and the searched cost thereof to the loading data cached in the step S50.
Preferably, the flight time includes departure flight departure time and return flight departure time, and the step of searching for communication package information adapted to the flight time and arrival city information provided by a communication network operator to which the mobile terminal belongs and calculating corresponding costs further includes the following steps: calculating the residence time of the user in the arriving city according to the departure flight arriving time and the return flight departing time; searching the communication package information with the starting time corresponding to the arrival time of the departing flight; and calculating the price of the communication package according to the residence time.
Preferably, the step of generating the filtering matching rule of the behavior prediction in step S20 further includes the following steps: and dividing each button path information by taking a search button in a search page as a dividing point according to historical clicking behaviors of users in the same session in the search page, and constructing a positive and negative classification sample.
Preferably, clicking only the date select button and clicking only the arrival city select button without any click behavior is a negative example; click the date select button and click the reach city select button as a positive sample.
Preferably, after the step S20 is completed, the step S30 is preceded by the steps of: according to the generated filtering matching rule of the behavior prediction, establishing one-hot codes for the button path information which is not matched with the filtering matching rule of the behavior prediction, and constructing a path feature vector of a real-time click behavior dimension; constructing a user dimension feature vector according to all click behaviors in the historical click behaviors before clicking a search button; combining and constructing sample characteristics of a classification problem according to the path characteristic vector of the real-time click behavior dimension and the user dimension characteristic vector; constructing the pre-search classification recognition model through sample characteristics of the classification problem in a period of time; if the judgment result of the step S40 is no, classifying the current click behavior of the user through the pre-search classification recognition model, and judging that the classification result of the current click behavior of the user is positive, if so, searching and loading the target page pointed by the final search according to the historical click behavior, and caching the loaded data.
Preferably, if it is determined in the step S70 that the load data hits in the cache, the step S80 further includes the following steps: judging whether the loaded data in the step S50 is loaded and cached; if not, the loading of the loaded data in the step S50 is waited for and the caching is completed.
Preferably, if it is determined before the step S80 that the loaded data in the step S50 is loaded and cached, the method further includes the following steps: judging whether the loaded and cached loaded data is expired; and if the session is overdue, initiating search according to the click behavior of the user in the current session.
Preferably, if the determination result in the step S40 is negative, a search is initiated according to the click behavior of the user in the current session.
According to another aspect of the present invention, there is also provided a page pre-search system, including: the device comprises a recording module, a searching module and a searching module, wherein the recording module is used for recording historical clicking behaviors of a user in a searching page and generating a plurality of button path information according to the historical clicking behaviors, and each button path information comprises all the historical clicking behaviors of the user in the same conversation and a target page pointed by final searching; the rule generating module is used for generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of the behavior prediction comprises a plurality of path prediction information; the receiving module is used for receiving the current click behavior of the user; the first judgment module is used for judging whether the sequence of the current click behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction; the pre-searching module is used for searching and loading the page pointed by the path prediction information of the filtering matching rule predicted by the behavior in advance and caching the loaded data; the second judgment module is used for judging whether the user search instruction hits the cached loading data or not; and the data presentation module is used for presenting the cached loading data.
According to yet another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the above-described page pre-search method.
According to still another aspect of the present invention, there is also provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the steps of the above-described page pre-search method via execution of the executable instructions.
Compared with the prior art, the page pre-search method, the page pre-search system, the storage medium and the electronic device provided by the embodiment of the invention generate the filtering matching rule of the behavior prediction by recording the historical clicking behavior of the user in the search page, judge the current clicking behavior of the user (namely analyzing the habit of the clicking behavior of the user), search and load the page pointed in the path prediction information of the filtering matching rule of the behavior prediction in advance, cache the loaded data, and further directly use the cache information when the user actually searches, so that the waiting time of the user is reduced, and the limitations that the traditional method for reducing the real-time response speed, the network transmission speed and the like has limited promotion and high cost are broken through. In addition, the page pre-searching method has higher accuracy and higher recall rate, can cover nearly half of user searching behaviors, has smaller misjudgment rate, has less than 20% of redundant searching amount, can cover more user searching behaviors with smaller redundant searching amount, and obviously reduces the waiting time of user searching (about 40% reduction on average).
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow diagram of a method for pre-searching a page according to one embodiment of the invention;
fig. 2 is a schematic page diagram of an air ticket search page in a page pre-search method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a page of cached load data in a page pre-search method according to an embodiment of the present invention;
FIG. 4 is a block diagram illustrating a pre-search system for pages according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a computer-readable storage medium in an exemplary disclosed embodiment of the invention; and
fig. 6 is a schematic diagram of an electronic device in an exemplary embodiment of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their repetitive description will be omitted.
The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In some instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring the invention.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
According to the main idea of the invention, the page pre-searching method of the invention comprises the following steps: recording historical click behaviors of a user in a search page, and generating a plurality of button path information according to the historical click behaviors, wherein each button path information comprises all the historical click behaviors of the user in the same session and a target page pointed by final search; generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of behavior prediction comprises a plurality of path prediction information; receiving the current click behavior of a user; judging whether the current order of the clicking behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction, if so, searching and loading a page pointed in the path prediction information of the filtering matching rule of the behavior prediction in advance according to the behavior prediction, and caching the loaded data; receiving a user searching instruction; and judging whether the user search instruction hits the cached loading data, if so, displaying by using the cached loading data.
The technical contents of the present invention will be further described with reference to the accompanying drawings and examples.
Referring to fig. 1, a flow chart of a page pre-search method according to an embodiment of the invention is shown. Specifically, the page pre-search method of the invention is mainly used for carrying out conditional page search on computer network pages or mobile phone application pages. As shown in fig. 1, in the embodiment of the present invention, the method for pre-searching a page includes the following steps:
step S10: and recording historical click behaviors of the user in the search page, and generating a plurality of pieces of button path information according to the historical click behaviors. Specifically, in the embodiment of the present invention, the page pre-search method is used for the air ticket search page. At least a date selection button and an arrival city selection button are included in the ticket search page. The user may select the time of the flight by clicking on the date selection button and the arrival city of the flight by clicking on the arrival city selection button. In the preferred embodiment of the invention, by setting a buried point at the position of the date selection button and the position of the arrival city selection button, the historical clicking behavior of the user in the search page is recorded by using the buried point. Referring to fig. 2, a schematic page diagram of a ticket search page in a page pre-search method according to an embodiment of the present invention is shown. It should be noted that fig. 2 only roughly describes the buttons included in the ticket search page, and the layout of the specific page is not limited to this. In the embodiment shown in fig. 2, the date selection button comprises a departure time button and a return time button, the ticket search page further comprises a departure city button, and the positions of the buttons are provided with buried points. Further, each button path information includes all historical click behaviors of users in the same session and the target page to which the final search is directed. Specifically, the same session refers to a process in which an end user communicates with the interactive system, and in the embodiment of the present invention, refers to an entire process that is previously operated in a search page (ticket search page) until a search button is clicked. The target page pointed by the final search refers to the page searched by the user clicking according to all previous historical clicking behaviors in the same session.
Step S20: and generating a filtering matching rule of the behavior prediction according to the plurality of pieces of button path information. The filtering matching rule of the behavior prediction comprises a plurality of path prediction information. Specifically, in this step, the added redundant search amount and the amount of behavior of the user search that can be covered are integrated, and the appropriate button path information generated in step S10 is selected to generate the filter matching rule for behavior prediction. More specifically, the step of generating the filtering matching rule of the behavior prediction in step S20 further includes the following steps: and dividing the path information of each button by taking the search button in the search page as a dividing point according to the historical clicking behaviors of the users in the same session in the search page, and constructing a positive and negative classification sample. Specifically, in the embodiment of the present invention, for the air ticket search page, if the date selection button, the arrival city selection button, and the search button are included, the positive and negative classification samples may be structured as follows:
no click behavior, only click the date selection button and only click the arrival city selection button are negative samples; click the date select button and click the reach city select button as a positive sample. Wherein, no click behavior means that neither a date selection button nor an arrival city selection button is clicked; clicking only on the date select button means clicking only on the date select button, and not clicking on the arrival city select button (only the date is selected); clicking only on the date select button means clicking only on the arrival city select button, and not clicking on the date select button (only the arrival city is selected); clicking on the date select button and clicking on the reach city select button as a positive sample refers to clicking on the search button after the date is selected and the city is reached. Furthermore, through statistical analysis of historical click behaviors of the user, button path information which is high in trigger frequency (namely frequently clicked) and can be used for searching button clicks in subsequent click behaviors with high probability according to the click behaviors of the user is selected. For example, when the date is selected as "10 month 1" and the arrival city is selected as "shanghai", the user has a high probability of clicking a search button to browse relevant ticket information. And constructing a filtering matching rule of behavior prediction according to the button path information which is statistically analyzed and picked out. Furthermore, the filtering matching rule of the behavior prediction comprises a plurality of path prediction information.
Further, in a preferred embodiment of the present invention, the pre-search classification recognition model is generated based on the filtering matching rule of the behavior prediction generated in step S20. Where the pre-search classification recognition model may be understood as a supplement to the filtering matching rules for behavior prediction. Specifically, after the step S20 is completed, the step S30 is preceded by the steps of:
and according to the generated filtering matching rule of the behavior prediction, establishing one-hot codes for the button path information which is not matched with the filtering matching rule of the behavior prediction, and constructing a path feature vector of a real-time click behavior dimension. In other words, a one-hot code is established for the button path information which is low in trigger frequency and is small in probability of searching button clicks in subsequent clicking behaviors according to the clicking behaviors of the user, and a path feature vector of the real-time clicking behavior dimension is established.
And constructing a user dimension feature vector according to all click behaviors before clicking the search button in the historical click behaviors. All clicking behaviors before the search button is clicked comprise information such as the last clicked button before the search button is clicked, the average clicked button, whether the search button is clicked in the current day or not and the like.
And combining and constructing sample characteristics of a classification problem according to the path characteristic vector of the real-time click behavior dimension and the user dimension characteristic vector.
And constructing the pre-search classification recognition model through the sample characteristics of the classification problem in a period of time. The pre-search classification recognition model is constructed by adopting a common classification model, such as a decision tree, a random forest and the like.
In turn, the pre-search classification recognition model may classify the user's current click behavior.
Further, the following is an example of the above-described pre-search classification recognition model.
Specifically, the total number of features may be 80 dimensions, the first 56 dimensions being user path information, the middle 9 dimensions being user behavior of the day, and the last 15 bits being user dimension information.
1) 1-56-dimensional user path information:
the first 49 dimensions are one-hot codes (7 dimensions in each step) operated by each step of the user path, zero padding is performed for less than 7 steps, and only the last seven steps are taken for the more steps.
The last 7 dimensions are whether each button is clicked.
The button coding order is [ 'c _ preset _ single _ tab', 'c _ preset _ return _ tab', 'c _ preset _ prepare _ part _ city', 'c _ preset _ array _ city', 'c _ preset _ switch _ city', 'c _ preset _ single _ date', 'c _ preset _ round _ date' ]
The coding sample is as follows:
for a path: 'c _ preamble _ single _ tab-c _ preamble _ return _ tab'
Path coding: [00000000000000000000000000000000000100000001000001100000]
For a path: 'c _ preamble _ single _ tab'
Path coding: [00000000000000000000000000000000000000000010000001000000]
2) Dimension 57-65 is the real-time behavior of the user in the same day, and is the real-time searching frequency of the user in the same day, whether the current searching is the first searching (whether the searched time is 0 or not is 1), and the distribution of the last step button clicked by the user before the current searching.
If the user does not perform any search behavior on the same day, the corresponding vector is as follows:
[0,1,0,0,0,0,0,0,0]
the user searches once the day, the path is c _ preamble _ single _ tab-c _ preamble _ return _ tab-c _ preamble _ inquiry, and the corresponding vector is:
[1,0,0,1,0,0,0,0,0]
3) and the dimension of 66-80 is historical dimension information of the user:
the first 7 are average click times of the last step of the history of the user, the middle 7 are average click times of each button of the history, and the last is the ratio of the search times of the history clicks of the user to the maximum number of clicks of a single user.
Examples are as follows:
the user history clicks are: 'c _ preamble _ single _ tab-c _ preamble _ return _ tab-c _ preamble _ search _ inquiry' and 'c _ preamble _ single _ tab-c _ preamble _ inquiry', the number of user clicks with the largest number of history clicks is 10
The user dimension characteristics are as follows: [0.5,0.5,0.,0.,0.,0.,0.,1.,0.5,0.,0.,0.,0.,0.,0.2]
The modeling adopts a logistic regression model. The calculated coefficients are:
the intercept is:
clf.intercept_＝-0.13429851
the calculation logic:
point product of prob np.dot (testx, clf. coef.) + clf. interrupt _ coef. and feature vector plus interrupt \\
prob*＝-1
prob＝np.exp(prob)
prob+＝1
prob＝1.0/prob
Setting a threshold value:
thredshold：0.45
prob > thredshold 1: predicting as hit, pre-searching
prob < ═ thredshold 0: predict miss, do not pre-search
It should be noted that the foregoing is only an example of the pre-search classification recognition model, and the pre-search classification recognition model may be adjusted according to actual requirements, which is not limited to this.
Step S30: and receiving the current click behavior of the user.
Step S40: and judging whether the sequence of the current clicking behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction. Specifically, each click action performed by the user is matched with the path prediction information in the filtering matching rule of the action prediction in this step. For example, in the embodiment of the present invention, when the current click behavior of the user is the click date selection button and the selection date is "10 month 1", it is determined whether or not there is path prediction information whose date is selected as "10 month 1" in the path prediction information of the filtering matching rule of the behavior prediction, and further, when the user clicks the arrival city button again and selects the arrival city as "shanghai", it is further determined whether or not there is path prediction information whose date is selected as "10 month 1" and the arrival city is "shanghai" in the path prediction information of the filtering matching rule of the behavior prediction, and if there is, it is determined that the order of the current click behavior of the user matches the path prediction information, and step S50 is executed.
Step S50: and searching and loading the page pointed by the path prediction information of the filtering matching rule predicted by the behavior in advance, and caching the loaded data. Specifically, in this step, a page pointed to by one piece of route prediction information that matches the order of the current click behaviors of the user in the filtering and matching rule of the behavior prediction, for example, the above-mentioned search page pointed to by the route prediction information with the date of "10 months 1" and the arrival city of "shanghai", is used.
Step S60: a user search instruction is received. I.e., receiving an instruction from a user to click a search button in a search page.
It should be noted that if the determination result in the step S40 is no, the search is performed directly according to the actual search request after the user clicks the search button in the current session in the step S60.
Step S70: and judging whether the user search instruction hits the cached loading data, if so, executing the step S80. Specifically, in this step, it is determined whether the search request input by the user after actually clicking the search button in the current session is consistent with the search request (i.e., date selection, arrival city selection, etc.) in the route prediction information according to step S50. If yes, go to step S80.
Step S80: and using the cached loading data for presentation.
Further, since the search has a certain delay, there is a case that the data searched and loaded in step S50 (i.e. the result of the pre-search) has not been returned yet, and the user has clicked the search button on the search page, and further, in the preferred embodiment of the present invention, if it is determined in step S70 that the loaded data in the cache is hit, step S80 further includes the following steps before:
judging whether the loaded data in the step S50 is loaded and cached;
if not, the loading of the loaded data in the step S50 is waited for and the caching is completed.
Through the steps, repeated searching and loading can be avoided, and the pre-searching is always performed before the user actually clicks the searching button, so that the effect of saving the time for feeding back the searching result can be achieved.
Further, since the data searched and loaded in step S50 (i.e., the result of the pre-search) also has a certain timeliness (for example, the number of tickets in the page of the ticket search may change in real time), there may be a case that the data searched and loaded in step S50 (i.e., the result of the pre-search) is out of date, and further, in a preferred embodiment of the present invention, if it is determined before step S80 that the loaded data in step S50 is loaded and cached, the method further includes the following steps:
judging whether the loaded and cached loaded data is expired;
and if the session is overdue, initiating search according to the click behavior of the user in the current session.
Further, if the determination result in the step S70 is a miss, that is, the search condition according to which the user actually clicks the search button is different from the search condition in the path prediction information according to the step S50, the search is directly performed according to the actual search request after the user clicks the search button in the current session in the step S60.
Further, in a preferred embodiment of the present invention, the method for pre-searching a page is used in a mobile terminal, and after the step S50 is completed, the method further includes the following steps before the step S60:
and searching communication package information which is provided by a communication network operator to which the mobile terminal belongs and is adaptive to the flight time and the arrival city information according to the flight time and the arrival city information in the cached loading data, and calculating corresponding expenses. Specifically, the flight times include departure flight departure times and return flight departure times. Preferably, in this step, the step includes the steps of:
calculating the residence time of the user in the arriving city according to the departure flight arriving time and the return flight departing time;
searching the communication package information with the starting time corresponding to the arrival time of the departing flight;
and calculating the price of the communication package according to the residence time.
Adding the searched communication package information and the searched cost thereof to the loading data cached in the step S50. Specifically, please refer to fig. 3, which illustrates a page diagram of the cached load data in the page pre-search method according to an embodiment of the present invention. Taking the search result of the air ticket from shanghai to new york, which starts from 10 month and 1 day of the path prediction information as an example, as shown in fig. 3, the page of the loaded data displays the air ticket of 10 month and 1 day of the current time period from shanghai to new york and the corresponding price thereof, and the lower part of the page also displays the relevant communication suite of the communication network operator (for example, AT & T shown in fig. 3) provided by the communication network operator (for example, the mobile shown in fig. 3) of the current mobile terminal belonging to the new york local communication for the user to select according to the time of the flight and the arriving city. Therefore, the user is prevented from searching and selecting the communication mode additionally, and more convenience is provided for the user.
In the embodiment shown in fig. 1, in the page pre-search method of the present invention, a filtering matching rule for behavior prediction is generated by recording historical click behaviors of a user in a search page, and a current click behavior of the user (i.e., a habit of the click behavior of the user is analyzed) is determined, so that a page pointed in path prediction information of the filtering matching rule for behavior prediction is searched and loaded in advance, and loaded data is cached, and further, the cached information is directly used when the user actually searches, so that a user waiting time is reduced, and limitations such as limitation of promotion by reducing a real-time response speed and a network transmission speed and the like, and high cost are broken through in a conventional method. In addition, the page pre-searching method has higher accuracy and higher recall rate, can cover nearly half of user searching behaviors, has smaller misjudgment rate, has less than 20% of redundant searching amount, can cover more user searching behaviors with smaller redundant searching amount, and obviously reduces the waiting time of user searching (about 40% reduction on average).
Furthermore, the invention also provides a page pre-search system, which is used for realizing the page pre-search method. Specifically, please refer to fig. 6, which illustrates a module configuration diagram of the page pre-search system according to an embodiment of the invention. The page pre-search system at least comprises a recording module 1, a rule generating module 2, a receiving module 3, a first judging module 4, a pre-search module 5, a second judging module 6 and a data presentation module 7.
The recording module 1 is used for recording historical click behaviors of a user in a search page and generating a plurality of pieces of button path information according to the historical click behaviors. Wherein each button path information comprises all historical click behaviors of users in the same session and a target page pointed by the final search.
And the rule generating module 2 is used for generating a filtering matching rule of behavior prediction according to the button path information. The filtering matching rule of the behavior prediction comprises a plurality of path prediction information.
The receiving module 3 is used for receiving the current click behavior of the user.
The first judging module 4 is configured to judge whether the current order of the click behaviors of the user meets the path prediction information of the filtering matching rule of the behavior prediction.
The pre-search module 5 is used for searching and loading the page pointed in the path prediction information of the filtering matching rule predicted by the behavior in advance and caching the loaded data.
The second judging module 6 is configured to judge whether the user search instruction hits the cached load data.
The data presentation module 7 is configured to use the cached load data for presentation.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium is further provided, on which a computer program is stored, and the program, when executed by a processor for example, can implement the steps performed by the control system and the traffic system in the page pre-search method in any one of the above embodiments. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the pre-search method section of the page shown in fig. 1 above of this specification, when the program product is run on the terminal device.
Referring to fig. 5, a program product 300 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In an exemplary embodiment of the present disclosure, there is also provided an electronic device, which may include a processor, and a memory for storing executable instructions of the processor. Wherein the processor is configured to execute the executable instructions to perform the steps performed by the control system and the traffic system in the page pre-search method in any one of the above embodiments.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 6. The electronic device 600 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 that connects the various system components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the pre-search method section of the above-mentioned page of the present specification. For example, the processing unit 610 may perform the various steps performed by the control system and traffic system as shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the pre-search method of the above-mentioned page according to the embodiments of the present disclosure.
In summary, in the method and system for pre-searching a page, the storage medium, and the electronic device provided in the embodiments of the present invention, the filtering matching rule for behavior prediction is generated by recording the historical click behavior of the user in the search page, and the current click behavior of the user (i.e., the habit of the click behavior of the user is analyzed) is determined, so that the page pointed in the path prediction information of the filtering matching rule for behavior prediction is searched and loaded in advance, and the loaded data is cached, and further, the cache information is directly used when the user actually searches, so that the waiting time of the user is reduced, and the limitations that the traditional method for reducing the real-time response speed and the network transmission speed is limited, and the cost is high are broken. In addition, the page pre-searching method has higher accuracy and higher recall rate, can cover nearly half of user searching behaviors, has smaller misjudgment rate, has less than 20% of redundant searching amount, can cover more user searching behaviors with smaller redundant searching amount, and obviously reduces the waiting time of user searching (about 40% reduction on average).
Although the invention has been described with respect to alternative embodiments, it is not intended to be limited thereto. Various changes and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention is subject to the scope defined by the claims.
Claims (6)
1. A page pre-search method is characterized by comprising the following steps:
s10: recording historical click behaviors of a user in a search page, and generating a plurality of button path information according to the historical click behaviors, wherein each button path information comprises all the historical click behaviors of the user in the same session and a target page pointed by final search;
s20: generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of behavior prediction comprises a plurality of path prediction information;
s30: receiving the current click behavior of a user;
s40: judging whether the current order of the clicking behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction, if so, executing the step S50;
s50: searching and loading a page pointed by the path prediction information of the filtering matching rule predicted according to the behavior in advance, and caching the loaded data;
s60: receiving a user searching instruction;
s70: judging whether the user search instruction hits the cached loading data, if so, executing step S80;
s80: presenting using the cached load data;
the page pre-searching method is used for an air ticket searching page, and the air ticket searching page at least comprises a date selection button and an arrival city selection button;
the step S10 further includes the steps of:
setting buried points at positions of a date selection button and a position of a city arrival selection button, and recording historical click behaviors of a user in a search page through the buried points;
the page pre-search method is used in a mobile terminal, and after the step S50 is completed, the step S60 further includes the following steps:
according to the flight time and arrival city information in the cached loading data, searching communication package information which is provided by a communication network operator to which the mobile terminal belongs and is adaptive to the flight time and arrival city information, and calculating corresponding cost;
adding the searched communication package information and the searched cost thereof to the loading data cached in the step S50;
the flight time comprises departure flight take-off time and return flight take-off time, and the step of searching the communication package information which is provided by the communication network operator to which the mobile terminal belongs and is adaptive to the flight time and the arrival city information and calculating the corresponding cost further comprises the following steps:
calculating the residence time of the user in the arriving city according to the departure flight arriving time and the return flight departing time;
searching the communication package information with the starting time corresponding to the arrival time of the departing flight;
calculating the price of the communication package according to the residence time;
the step of generating the filtering matching rule of the behavior prediction in step S20 further includes the following steps:
dividing each button path information by taking a search button in a search page as a dividing point according to historical clicking behaviors of users in the same session in the search page, and constructing positive and negative classification samples;
no click behavior, only click the date selection button and only click the arrival city selection button are negative samples; clicking a date selection button and clicking an arrival city selection button as a positive sample;
after the step S20 is completed, the step S30 includes the following steps:
according to the generated filtering matching rule of the behavior prediction, establishing one-hot codes for the button path information which is not matched with the filtering matching rule of the behavior prediction, and constructing a path feature vector of a real-time click behavior dimension;
constructing a user dimension feature vector according to all click behaviors in the historical click behaviors before clicking a search button;
combining and constructing sample characteristics of a classification problem according to the path characteristic vector of the real-time click behavior dimension and the user dimension characteristic vector;
constructing a pre-search classification recognition model through the sample characteristics of the classification problem in a period of time;
if the judgment result of the step S40 is no, classifying the current click behavior of the user through the pre-search classification recognition model, judging whether the classification result of the current click behavior of the user is positive, if so, searching and loading a target page pointed by the final search according to the historical click behavior, and caching the loaded data; if not, initiating search according to the click behavior in the current session of the user.
2. The method for pre-searching for pages of claim 1, wherein if it is determined in the step S70 that the load data hit in the cache, the step S80 further comprises the following steps:
judging whether the loaded data in the step S50 is loaded and cached;
if not, the loading of the loaded data in the step S50 is waited for and the caching is completed.
3. The method for pre-searching for a page of claim 2, wherein if it is determined before the step S80 that the loaded data in the step S50 is loaded and cached, the method further comprises the following steps:
judging whether the loaded and cached loaded data is expired;
and if the session is overdue, initiating search according to the click behavior of the user in the current session.
4. A system for pre-searching pages, for implementing the method for pre-searching pages according to claim 1, the system comprising:
the device comprises a recording module, a searching module and a searching module, wherein the recording module is used for recording historical clicking behaviors of a user in a searching page and generating a plurality of button path information according to the historical clicking behaviors, and each button path information comprises all the historical clicking behaviors of the user in the same conversation and a target page pointed by final searching;
the rule generating module is used for generating a filtering matching rule of behavior prediction according to the button path information, wherein the filtering matching rule of the behavior prediction comprises a plurality of path prediction information;
the receiving module is used for receiving the current click behavior of the user;
the first judgment module is used for judging whether the sequence of the current click behaviors of the user accords with the path prediction information of the filtering matching rule of the behavior prediction;
the pre-searching module is used for searching and loading the page pointed by the path prediction information of the filtering matching rule predicted by the behavior in advance and caching the loaded data;
the second judgment module is used for judging whether the user search instruction hits the cached loading data or not;
and the data presentation module is used for presenting the cached loading data.
5. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for pre-searching a page according to any one of claims 1 to 3.
6. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the steps of the method of pre-searching for a page of any of claims 1 to 3 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810343604.4A CN108549700B (en) | 2018-04-17 | 2018-04-17 | Page pre-search method and system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810343604.4A CN108549700B (en) | 2018-04-17 | 2018-04-17 | Page pre-search method and system, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549700A CN108549700A (en) | 2018-09-18 |
| CN108549700B true CN108549700B (en) | 2021-06-29 |
Family
ID=63515356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810343604.4A Active CN108549700B (en) | 2018-04-17 | 2018-04-17 | Page pre-search method and system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549700B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182295B (en) * | 2019-07-05 | 2023-11-24 | 浙江宇视科技有限公司 | Service processing method and device based on behavior prediction and electronic equipment |
| CN110362266B (en) * | 2019-07-19 | 2020-12-18 | 北京字节跳动网络技术有限公司 | Prompt information display method, system, electronic equipment and computer readable medium |
| CN110532157A (en) * | 2019-08-28 | 2019-12-03 | 口碑(上海)信息技术有限公司 | Page monitoring method and device based on user behavior data |
| CN112905939B (en) * | 2021-02-25 | 2024-01-23 | 杭州思亿欧科技集团股份有限公司 | HTML5 page resource loading method, device, equipment and storage medium |
| CN113010079B (en) * | 2021-03-24 | 2022-07-08 | 数贸科技（北京）有限公司 | Button processing method and device based on front-end preprocessing |
| CN113553483A (en) * | 2021-07-02 | 2021-10-26 | 广联达科技股份有限公司 | Component retrieval method, component retrieval device, electronic equipment and readable storage medium |
| CN113900961B (en) * | 2021-12-08 | 2022-03-01 | 深圳市活力天汇科技股份有限公司 | Sample generation method, device, equipment and medium for automatic testing |
| CN117473144B (en) * | 2023-12-27 | 2024-03-29 | 深圳市活力天汇科技股份有限公司 | Method for storing route data, computer equipment and readable storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663012B (en) * | 2012-03-20 | 2017-07-04 | 北京搜狗信息服务有限公司 | A kind of webpage preloads method and system |
| US9424233B2 (en) * | 2012-07-20 | 2016-08-23 | Veveo, Inc. | Method of and system for inferring user intent in search input in a conversational interaction system |
| CN106339398B (en) * | 2015-07-09 | 2019-10-18 | 广州市动景计算机科技有限公司 | A kind of pre-reading method of Webpage, device and intelligent terminal |
| CN107025259A (en) * | 2016-12-16 | 2017-08-08 | 阿里巴巴集团控股有限公司 | A kind of deployment method of details page, equipment and mobile terminal |
-
2018
- 2018-04-17 CN CN201810343604.4A patent/CN108549700B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549700A (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108549700B (en) | Page pre-search method and system, storage medium and electronic equipment | |
| US11138381B2 (en) | Method, computer device and readable medium for user's intent mining | |
| CN110083688B (en) | Search result recall method, device, server and storage medium | |
| CN106982256B (en) | Information pushing method, device, equipment and storage medium | |
| CN110619076B (en) | Search term recommendation method and device, computer and storage medium | |
| CN109032381B (en) | Input method and device based on context, storage medium and terminal | |
| CN109710088B (en) | Information searching method and device | |
| CN111368063B (en) | Information pushing method based on machine learning and related device | |
| CN109558384B (en) | Log classification method, device, electronic equipment and storage medium | |
| KR20190031536A (en) | Application Information Triggering | |
| CN105706081A (en) | Structured informational link annotations | |
| US8538946B1 (en) | Creating model or list to identify queries | |
| CN110442803A (en) | Data processing method, device, medium and the calculating equipment executed by calculating equipment | |
| CN112416212A (en) | Program access method, device, electronic equipment and readable storage medium | |
| CN112100463A (en) | Information processing method and device, electronic equipment and readable storage medium | |
| CN110059243B (en) | Data engine optimization method, device, equipment and computer readable storage medium | |
| CN108052568B (en) | Feature screening method, device, terminal and medium | |
| CN110770716A (en) | Association word recommendation method, mobile terminal and computer-readable storage medium | |
| CN111954079A (en) | Image processing method, image processing apparatus, electronic device, and medium | |
| CN107832373B (en) | Data searching and displaying method and system, storage medium and electronic equipment | |
| CN112925878A (en) | Data processing method and device | |
| CN114035729B (en) | Electronic voting method and device and terminal equipment | |
| CN111414455B (en) | Public opinion analysis method, public opinion analysis device, electronic equipment and readable storage medium | |
| CN109214841B (en) | Method and device for obtaining advertisement predicted value and terminal | |
| CN112732542A (en) | Information processing method, information processing device and terminal 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |