CN110110191B - Search processing method and apparatus, and computer-readable storage medium - Google Patents
Search processing method and apparatus, and computer-readable storage medium Download PDFInfo
- Publication number
- CN110110191B CN110110191B CN201910245155.4A CN201910245155A CN110110191B CN 110110191 B CN110110191 B CN 110110191B CN 201910245155 A CN201910245155 A CN 201910245155A CN 110110191 B CN110110191 B CN 110110191B
- Authority
- CN
- China
- Prior art keywords
- search
- channel
- click
- record
- evaluation parameter
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
-
- 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
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)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a search processing method and device and a computer readable storage medium, wherein the method comprises the following steps: obtaining at least one search segmentation word included in the search word; acquiring a plurality of channels corresponding to each search participle; acquiring channel evaluation parameters of each search word; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle; and finally, according to the channel evaluation parameters, carrying out channel distribution prediction on the search terms. In summary, the present application considers that the search term generally includes at least one search segmentation word, so that a channel evaluation parameter of each search segmentation word can be obtained, and further, a distribution prediction of a channel is performed on the search term based on the channel evaluation parameter. Therefore, the channel evaluation parameters in the method are determined based on the click behaviors, so that the distribution prediction results are more consistent with the search intention, and the distribution prediction results provide data support for the display sequence of the search results corresponding to different channels, thereby shortening the search time.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a search processing method and apparatus, and a computer-readable storage medium.
Background
At present, a large number of video resources generally exist in a video playing platform, and each video resource has a corresponding channel, for example, "a seniority attack" belongs to a tv drama channel, "a blossoming saying" belongs to a comprehensive channel, "my world" belongs to an online tour channel, "a sepia king" belongs to an animation channel, and the like, so that a user can conveniently and quickly find a video to be watched by setting a corresponding channel for each video resource.
However, for some video search terms, there may be multiple channels, for example, if the video search term is "dishonest interference", the search result may be a movie played by the guchi owner, belonging to a movie channel, and may also be a fantasy program played by the mengkong, belonging to a fantasy channel, so that it is usually necessary to acquire the movie and fantasy program that are "dishonest interference", but since it is difficult to determine the search intention of the user (i.e. the target channel corresponding to the video search term) according to the video search term input by the user at present, the display order of the search results of different channels is random, so that the user searches for the video to be viewed from the randomly displayed search results in sequence, which results in a tedious search operation and consumes a lot of time.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present application provide a search processing method and apparatus, and a computer-readable storage medium, so as to solve the above-mentioned problems that since the display sequence of search results of different channels is random, a user searches videos to be viewed from the displayed search results in sequence, so that the search operation is cumbersome, and a large amount of time is consumed.
According to a first aspect of embodiments of the present application, there is provided a search processing method, including:
obtaining at least one search segmentation word included in the search word;
acquiring a plurality of channels corresponding to each search participle;
acquiring a channel evaluation parameter of each search word; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle;
and according to the channel evaluation parameters, performing distribution prediction on the channels on the search terms.
According to a second aspect of embodiments of the present application, there is provided a search processing apparatus including:
the search segmentation acquisition module is used for acquiring at least one search segmentation included in the search terms;
a channel obtaining module, configured to obtain multiple channels corresponding to each search word;
the evaluation parameter acquisition module is used for acquiring the channel evaluation parameter of each search word; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle;
and the distribution prediction module is used for performing distribution prediction on the channels on the search terms according to the channel evaluation parameters.
According to a third aspect of embodiments of the present application, there is provided a search processing apparatus including a processor and a memory, wherein,
the processor executes the computer program code stored in the memory to implement the steps of the search processing method described herein.
According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the search processing method described herein.
The embodiment of the application has the following advantages: the method includes the steps that at least one search segmentation word included in a search word is obtained; then acquiring a plurality of channels corresponding to each search participle; then obtaining channel evaluation parameters of each search participle; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle; and finally, performing distribution prediction of the channels on the search terms according to the channel evaluation parameters. In summary, the present application considers that the search term generally includes at least one search term, so that a channel evaluation parameter of each search term can be obtained, and further, channel distribution prediction is performed on the search term based on the channel evaluation parameter, so that the channel evaluation parameter in the present application is a parameter determined based on a click behavior, so that the distribution prediction result better conforms to a search intention, and the distribution prediction result provides data support for a display sequence of search results corresponding to different channels, thereby facilitating to preferentially view the search result to be viewed, shortening the search time, and avoiding the problems of complicated search operation and time consumption caused by random display of search results of different channels in the prior art.
Drawings
FIG. 1 is a flow chart of the steps of one embodiment of a search processing method of the present application;
FIG. 2 is a schematic illustration of a click parameter of a search segment of the present application;
FIG. 3 is a flow chart of the steps of an alternative embodiment of a search processing method of the present application;
FIG. 4 is a block diagram of a search processing apparatus according to an embodiment of the present application;
FIG. 5 is a block diagram of an alternative embodiment of a search processing apparatus of the present application;
FIG. 6 is a block diagram of an alternative embodiment of a search processing apparatus of the present application;
FIG. 7 is a block diagram of an alternative embodiment of a search processing apparatus of the present application;
FIG. 8 is a block diagram of an alternative embodiment of a search processing apparatus of the present application;
FIG. 9 is a block diagram of an alternative embodiment of a search processing apparatus of the present application;
FIG. 10 is a block diagram of an alternative embodiment of a search processing apparatus according to the present application
Fig. 11 is a schematic hardware structure diagram of a search processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
The present application will be described in detail with reference to specific examples.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a search processing method according to the present application is shown, and specifically may include the following steps:
In this embodiment of the present application, the search term may be a character input by a user in a search box, and the search term may be in a text form or a speech form, where in the case that the search term is in the speech form, the search term in the speech form needs to be converted into the text form, so that in the subsequent step, distribution prediction of a channel is performed based on the search term in the text form, where the foregoing examples are merely illustrative, and the present application is not limited to this.
It should be noted that, since the search term in the present application may include: common words or non-common words. For the common words, the click parameters of the common words by the user can be obtained, so that word segmentation processing is not required to be performed on the search words, the click parameters comprise parameters of different channels corresponding to the common words, and the click parameters can be click times and/or click rate; for the non-common words, since the click behavior of the non-common words is less, a large number of click parameters cannot be obtained, and therefore, the search word needs to be subjected to word segmentation processing to obtain at least one search word. In summary, the present application needs to first determine a word type of a search word, and specifically, determine whether the number of search times of the search word is greater than or equal to a preset number of times; in the step, under the condition that the search times of the search terms are larger than or equal to the preset times, the search terms are common terms, at least one search participle is determined to be a search term, under the condition that the search times of the search terms are smaller than the preset times, the search terms are common terms, and the search terms are participled to obtain at least one search participle. For example, the search times may be an average value of the search times per unit time in a preset time period, for example, if the search term is "dishonest do not disturb", the preset time period is nearly one month, and the unit time is 24h, the search times per day of "dishonest do not disturb" in the nearly one month may be collected, the sum of the search times per day in the nearly one month may be calculated to obtain a total search time, and then a ratio of the total search time to the number of days in the nearly one month is calculated to obtain the average value of the search times.
Since the corresponding channels are preset for each search participle in advance, a plurality of channels corresponding to each search participle can be obtained in the step.
According to the method and the device, historical search terms can be collected, at least one search segmentation record included in the historical search terms is obtained, a plurality of channels corresponding to each search segmentation record are obtained, and then the click parameters of each search segmentation record are obtained; the click parameters comprise parameters of each channel corresponding to the search participle records, and then according to the click parameters, channel evaluation parameter records of each search participle record are obtained; the channel evaluation parameter records comprise evaluation parameters of each channel corresponding to the search word segmentation records; thus, the step can obtain the channel evaluation parameter of each search participle from the channel evaluation parameter record. Wherein, the click parameters comprise click times and/or click rate.
For example, as shown in fig. 2, if the search segmentation includes "devil house", the corresponding plurality of channels includes: the movie channel, the documentary channel, the synthesis channel, and the film flower channel, where the click parameter includes click times and click rate, then at this time, the click times corresponding to each channel and the click rate corresponding to each channel may be obtained, the column in fig. 2 is used to represent the click times, the broken line is used to represent the click rate, the left ordinate is a coordinate corresponding to the click times, the right ordinate is a coordinate corresponding to the click rate, and the abscissa is a coordinate corresponding to different channels.
And 104, performing channel distribution prediction on the search terms according to the channel evaluation parameters.
In this step, when the search frequency of the search term is greater than or equal to the preset frequency, the channel evaluation parameter of the search term can be obtained in the above process, so that the channel distribution prediction of the search term is directly performed according to the channel evaluation parameter of the search term; under the condition that the search times of the search terms are smaller than the preset times, the step can acquire target channel evaluation parameters of each channel to which the search terms belong according to the channel evaluation parameters; and according to the target channel evaluation parameters, performing distribution prediction of the channels on the search terms.
By adopting the method, at least one search segmentation word included in the search word can be obtained firstly; then acquiring a plurality of channels corresponding to each search participle; then obtaining channel evaluation parameters of each search participle; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle; and finally, performing distribution prediction of the channels on the search terms according to the channel evaluation parameters. In summary, the present application considers that the search term generally includes at least one search term, so that a channel evaluation parameter of each search term can be obtained, and further, channel distribution prediction is performed on the search term based on the channel evaluation parameter, so that the channel evaluation parameter in the present application is a parameter determined based on a click behavior, so that the distribution prediction result better conforms to a search intention, and the distribution prediction result provides data support for a display sequence of search results corresponding to different channels, thereby facilitating to preferentially view the search result to be viewed, shortening the search time, and avoiding the problems of complicated search operation and time consumption caused by random display of search results of different channels in the prior art.
Referring to fig. 3, a flowchart illustrating steps of an embodiment of a search processing method according to the present application is shown, and specifically may include the following steps:
In this embodiment of the present application, the search term may be a character input by a user in a search box, and the search term may be in a text form or a speech form, where in the case that the search term is in the speech form, the search term in the speech form needs to be converted into the text form, so that in the subsequent step, distribution prediction of a channel is performed based on the search term in the text form, where the foregoing examples are merely illustrative, and the present application is not limited to this.
Since the search terms in the present application may include: common words or non-common words. For the common words, the click parameters of the common words by the user can be obtained, so that word segmentation processing is not required to be performed on the search words, the click parameters comprise parameters of different channels corresponding to the common words, and the click parameters can be click times and/or click rate; for the non-common words, since the click behavior of the non-common words is less, a large number of click parameters cannot be obtained, and therefore, the search word needs to be subjected to word segmentation processing to obtain at least one search word. In summary, the present application needs to first determine a word type of a search word, and specifically, determine whether the number of times of searching the search word is greater than or equal to a preset number of times.
Executing step 302 to step 304 when the number of times of searching for the search term is greater than or equal to a preset number of times;
in the case where the number of searches for the search term is less than the preset number, steps 305 to 308 are performed.
Thus, since the search term is a common term, the at least one search term can be determined to be the search term without performing a term segmentation process on the common term.
It should be noted that, in order to facilitate the distribution prediction of the channels, before executing this step, at least one search segmentation record included in the historical search terms needs to be obtained in advance; acquiring a plurality of channels corresponding to each search word segmentation record; then, acquiring a click parameter of each search participle record; the click parameters comprise parameters of each channel corresponding to the search word segmentation records; acquiring a channel evaluation parameter record of each search participle record according to the click parameter; the channel evaluation parameter records comprise evaluation parameters of each channel corresponding to the search word segmentation records. It can be seen that, if the search term is a common term, the search segmentation record matched with the common term can be obtained, so that the channel evaluation parameter record corresponding to the matched search segmentation record is determined as the channel evaluation parameter of the search term.
The corresponding channels are preset in the search result of each search participle, so that the channels of all the search results can be obtained. For example, if the search participle record is "beginner", the search result may be a movie of "beginner", or may be a documentary of "beginner", or may be an art program of "beginner" and a movie of "beginner", and thus, the plurality of channels corresponding to the search participle record "beginner" include a movie channel, a documentary channel, an art channel, and a movie channel.
Therefore, through the above process, the channel evaluation parameter record of each search word segmentation record can be obtained in advance, so that the channel evaluation parameters of the search words can be obtained from the channel evaluation parameter records in the step. For example, if the search term is "beginner", since the "beginner" is a commonly used term, that is, there is a channel evaluation parameter record corresponding to the "beginner" in the channel evaluation parameter record, at this time, the at least one search participle is "beginner", and at this time, the channel evaluation parameter record corresponding to the "beginner" may be obtained from the channel evaluation parameter record, and it is determined that the channel evaluation parameter record corresponding to the "beginner" is the channel evaluation parameter of the "beginner".
Further, the obtaining of the channel evaluation parameter record of each search participle record according to the click parameter includes:
firstly, acquiring the click probability of each search participle record according to the click parameters; the click probability includes the probability that the search participle record corresponds to each of the channels.
In the present application, the click probability can be obtained through the following three ways:
in the first mode, when the click parameter is the number of clicks, the click probability of each channel corresponding to the search participle record can be obtained according to the number of clicks, and the calculation formula of the click probability is
Wherein, PhIndicating the click probability of the h channel corresponding to the search participle record, ShRepresenting the number of clicks of the search participle record corresponding to the h-th channel, SfThe number of clicks of the f channel corresponding to the search participle is represented, and k represents the total number of channels corresponding to the search participle record.
In the second way, under the condition that the click parameter is click rate, the click probability of each channel corresponding to the search participle record can be obtained according to the click rate, and the calculation formula of the click probability is
Wherein, PhIndicating the probability of click of the h channel corresponding to the search participle record, LhIndicating the click rate, L, of the search participle record corresponding to the h-th channelfThe click rate of the f channel corresponding to the search participle record is shown, and k represents the total number of the channels corresponding to the search participle record.
In a third mode, under the condition that the click parameter is the click times and the click rate, the click probability of each channel corresponding to the search participle record can be obtained according to the click times and the click rate, and the calculation formula of the click probability is
Wherein, PhIndicating the click probability of the h channel corresponding to the search participle record, ShRepresenting the number of clicks of the search participle record corresponding to the h-th channel, SfRepresenting the number of clicks of the f channel corresponding to the search participle record, k representing the total number of channels corresponding to the search participle record, LhIndicating the click rate, L, of the search participle record corresponding to the h-th channelfIndicating the click rate of the search participle record corresponding to the f channel.
And then, acquiring the channel evaluation parameter record of each search participle record according to the click probability.
After the click probability is obtained by any one of the above manners, in a possible implementation manner, it may be determined that the click probability is a channel evaluation parameter record; in another possible implementation manner, a channel evaluation parameter record of the search participle record may be obtained according to the click probability, and a calculation formula of the channel evaluation parameter record may be expressed as
Wherein, FhChannel rating parameter records, P, representing the search participle records corresponding to the h-th channelhIndicating the probability of click of the h channel corresponding to the search participle record, PfIndicating the click probability of the f channel corresponding to the search participle record, k indicating the search participleThe word records the total number of corresponding channels.
And step 304, performing channel distribution prediction on the search terms according to the channel evaluation parameters.
In the embodiment of the present application, if the channel evaluation parameter of the target channel is larger, it is determined that the probability that the search term belongs to the target channel is higher, and conversely, if the channel evaluation parameter of the target channel is smaller, it is determined that the probability that the search term belongs to the target channel is lower, and the target channel is any channel. In addition, the search results of each channel can be sorted based on the distribution prediction result, for example, the search result of the channel corresponding to the maximum channel evaluation parameter can be preferentially displayed, so that the display result is more consistent with the click behavior of the user, the user can conveniently and quickly find required information from the display result, and the consumption of a large amount of search time is avoided.
The word segmentation process may include various methods, such as a method of character matching, that is, a mechanical word segmentation method, specifically, search words are sequentially matched with entries in a preset dictionary, and if a certain entry corresponding to a search word is found in the preset dictionary, the matching is successful, so as to identify a word segmentation word. Therefore, in order to solve the problem, in another embodiment of the present disclosure, after performing word segmentation processing on a search word to obtain at least one search word, a stop word may be removed, so that a word without actual meaning can be removed, thereby reducing the complexity of subsequent calculation under the condition of ensuring accurate channel distribution prediction. As can be seen, the search term is split into at least one search segmentation of the common term type by the segmentation process. For example, if the search term is "Yanxi Xiao splendid", three search terms of "Yanxi Xiao", "of" and "splendid" may be obtained through the term segmentation process.
In order to solve the problem, the search word is subjected to word segmentation processing to obtain a search word segmentation record matched with the unusual word, the search word segmentation is a common word, so that the search word segmentation record matched with the search word segmentation can be obtained, and then a channel evaluation parameter record corresponding to the matched search word segmentation record is determined to be a channel evaluation parameter of the search word, wherein the process of obtaining the channel evaluation parameter record of each search word record refers to step 303 and is not repeated.
For example, if the search term is "the wonderful highlights of the seniority attack and the skilful highlights" is a very used term, that is, the channel evaluation parameter record does not have the channel evaluation parameter record corresponding to the wonderful highlights of the seniority attack and the skilful highlights ", so that the channel evaluation parameters corresponding to the wonderful highlights of the seniority attack and the skilful highlights" are obtained by performing a word segmentation process on the wonderful highlights of the seniority attack and the channel evaluation parameter record, and the three search terms are common terms, so that the channel evaluation parameters corresponding to the wonderful attack, the channel evaluation parameter record, and the channel evaluation parameter record can be obtained respectively. Further, the plurality of channels corresponding to "the senil attack" are a and B, "the plurality of channels corresponding to" are A, B, C and D, "the plurality of channels corresponding to" the highlight collection "are A, B and E, and then the obtained channel evaluation parameters may include: "the channel rating parameters of" the Yanxi Across "belong to A, B, C and D and E," the channel rating parameters of "the" A, B, C and D and E, and "the highlight highlights" belong to A, B, C and D and E, wherein, for the search participle "Yanxi Xiao", since the channels corresponding to "Yanxi Xiao" are A and B, the channels C, D and E are not included in the search result of "Yanxi Xiao", therefore, there is no click behavior on the channels C, D, and E, so that the channel evaluation parameters of the channels C, D, and E corresponding to "senil aggressive leap" are all 0, similarly, "the channel evaluation parameter of the channel E corresponding to" 0, "the channel evaluation parameters of the channels C and D corresponding to" wonderful highlights "are all 0, the above example is only an example, and the present application is not limited thereto.
And 307, acquiring target channel evaluation parameters of each channel to which the search terms belong according to the channel evaluation parameters.
Since there is a difference in the degree of influence of the obtained at least one search participle on the search result, where the more a certain search participle is focused on a certain channel, the higher the degree of influence of the certain search participle is, for example, if the search term is "premium highlights of lingxi attack", and the at least one search participle includes "lingxi attack", "of" and "premium highlights", the more the "lingxi attack" is focused on the tv drama channel, and the "highlight highlights" and "of" may be scattered on various channels, so the degree of influence of the "lingxi attack" on the search result is higher than the degree of influence of the "highlight highlights" and "of" on the search result.
Therefore, in order to better fit a channel corresponding to at least one search word, the weight of each search word can be obtained according to the channel evaluation parameter, and the weight is used for representing the influence degree of the search word on the search result. Specifically, according to the channel evaluation parameter, the weight of each search word is calculated by the following formula:
wherein, wiRepresenting the weight of the ith search word; e.g. of the typemaxWhich represents a normalization parameter, is given by,
n represents the total number of channels; e.g. of the typeiThe entropy of the information representing the ith search term,
Pija channel rating parameter indicating that the ith search term belongs to the jth channel.
Thus, as is known from the characteristic of the information entropy, eiThe larger the number of channels, the more scattered the channels representing the ith search word are, and thus the lower the weight of the ith search word is, and conversely, eiThe smaller the search word, the more concentrated the respective channels representing the ith search word, and thus the higher the weight of the ith search word.
Then, after the weight is obtained, the target channel evaluation parameter of each channel to which the search term belongs can be obtained according to the weight.
The target click probability that the search term belongs to each channel can be obtained according to the weight, and the target channel evaluation parameter that the search term belongs to each channel can be obtained according to the target click probability.
Further, according to the weight, the target click probability of the search term belonging to each channel can be obtained through the following formula:
wherein Q isjRepresenting the target click probability of the search term belonging to the jth channel; pijA channel evaluation parameter indicating that the ith search word belongs to the jth channel; m represents the total number of search tokens; w is aiRepresenting the weight of the ith search term.
Of course, the weight values of the search participles may also be set to be the same numerical value, so that, if the weight values are set to be the reciprocal of the total number of at least one search participle, at this time, the parameter mean value of the channel evaluation parameters of all the search participles belonging to the same channel may be calculated, and the parameter mean value is determined to be the target click probability.
After the target click probability is obtained by the method, in a possible implementation manner, the target click probability can be determined as a target channel evaluation parameter; in another possible implementation, the target point may be based onThe hit probability obtains the target channel evaluation parameter of each channel to which the search term belongs, and the calculation formula of the target channel evaluation parameter can be expressed as
Wherein E isjA target channel rating parameter, Q, representing the search term corresponding to the jth channeljRepresenting the probability of a search term clicking on a target corresponding to the jth channel, QvRepresenting the target click probability of the search term corresponding to the v-th channel, and n representing the total number of channels.
And 308, performing channel distribution prediction on the search terms according to the target channel evaluation parameters.
The specific process may refer to step 304, and is not described in detail.
By adopting the method, at least one search segmentation word included in the search word can be obtained firstly; then acquiring a plurality of channels corresponding to each search participle; then obtaining channel evaluation parameters of each search participle; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle; and finally, performing distribution prediction of the channels on the search terms according to the channel evaluation parameters. In summary, the present application considers that the search term generally includes at least one search term, so that a channel evaluation parameter of each search term can be obtained, and further, channel distribution prediction is performed on the search term based on the channel evaluation parameter, so that the channel evaluation parameter in the present application is a parameter determined based on a click behavior, so that the distribution prediction result better conforms to a search intention, and the distribution prediction result provides data support for a display sequence of search results corresponding to different channels, thereby facilitating to preferentially view the search result to be viewed, shortening the search time, and avoiding the problems of complicated search operation and time consumption caused by random display of search results of different channels in the prior art.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
Referring to fig. 4, a block diagram of a search processing apparatus 400 according to an embodiment of the present application is shown, which may specifically include the following modules:
a search segmentation obtaining module 401, configured to obtain at least one search segmentation included in a search term;
a channel obtaining module 402, configured to obtain multiple channels corresponding to each search word;
an evaluation parameter obtaining module 403, configured to obtain a channel evaluation parameter of each search word; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle;
and a distribution prediction module 404, configured to perform distribution prediction on the channel for the search term according to the channel evaluation parameter.
Referring to fig. 5, in an alternative embodiment of the present application, the apparatus 400 further comprises:
a segmentation record obtaining module 405, configured to obtain at least one search segmentation record included in the historical search terms;
a word segmentation record channel obtaining module 406, configured to obtain multiple channels corresponding to each search word segmentation record;
a click parameter obtaining module 407, configured to obtain a click parameter of each search segmentation record; the click parameters comprise parameters of each channel corresponding to the search participle records;
an evaluation parameter record obtaining module 408, configured to obtain, according to the click parameter, a channel evaluation parameter record of each search participle record; the channel evaluation parameter records comprise evaluation parameters of each channel corresponding to the search word segmentation records;
the evaluation parameter obtaining module 403 is configured to obtain a channel evaluation parameter of each search word from the channel evaluation parameter record.
Referring to fig. 6, in an alternative embodiment of the present application, the evaluation parameter record obtaining module 408 includes:
the click probability obtaining submodule 4081 is used for obtaining the click probability of each search participle record according to the click parameters; the click probability comprises the probability that the search word segmentation record corresponds to each channel; the click parameters comprise click times and/or click rate;
and the evaluation parameter record obtaining sub-module 4082 is configured to obtain, according to the click probability, a channel evaluation parameter record of each search participle record.
Referring to fig. 7, in an alternative embodiment of the present application, the apparatus further comprises:
a judging module 409, configured to judge whether the search times of the search terms are greater than or equal to a preset time;
the search segmentation obtaining module 401 is configured to determine that the at least one search segmentation is the search term when the search frequency of the search term is greater than or equal to the preset frequency;
and under the condition that the searching times of the searching terms are smaller than the preset times, performing word segmentation processing on the searching terms to obtain the at least one searching word.
Referring to fig. 8, in an alternative embodiment of the present application, in the case that the number of searches of the search term is less than the preset number, the distribution prediction module 404 includes:
a target evaluation parameter obtaining sub-module 4041, configured to obtain, according to the channel evaluation parameter, a target channel evaluation parameter for which the search term belongs to each of the channels;
and the distribution prediction submodule 4042 is configured to perform distribution prediction on the channel for the search term according to the target channel evaluation parameter.
Referring to fig. 9, in an alternative embodiment of the present application, the target evaluation parameter obtaining sub-module 4041 includes:
a weight obtaining unit 40411, configured to calculate, according to the channel evaluation parameter, a weight of each word segmentation according to the following formula:
wherein, wiRepresenting the weight of the ith search word; e.g. of the typemaxWhich represents a normalization parameter, is given by,
n represents the total number of channels; e.g. of the typeiThe entropy of the information representing the ith search term,
Pija channel evaluation parameter indicating that the ith search word belongs to the jth channel;
and a target evaluation parameter obtaining unit 40412, configured to obtain, according to the weight, a target channel evaluation parameter that the search term belongs to each of the channels.
Referring to fig. 10, in an alternative embodiment of the present application, the target evaluation parameter obtaining unit 40412 includes:
a probability obtaining subunit 404121, configured to obtain, according to the weight, a target click probability that the search term belongs to each channel;
a target evaluation parameter obtaining subunit 404122, configured to obtain, according to the target click probability, a target channel evaluation parameter that the search term belongs to each of the channels.
Optionally, the probability obtaining subunit 404121 is configured to obtain, according to the weight, a target click probability that the search term belongs to each channel according to the following formula:
wherein Q isjRepresenting the target click probability of the search term belonging to the jth channel; pijA channel evaluation parameter indicating that the ith search word belongs to the jth channel; m represents the total number of search tokens; w is aiRepresenting the weight of the ith search term.
By adopting the device, at least one search segmentation word included in the search word is firstly obtained; then acquiring a plurality of channels corresponding to each search participle; then obtaining channel evaluation parameters of each search participle; the channel evaluation parameters comprise evaluation parameters of each channel corresponding to the search participle; and finally, performing distribution prediction of the channels on the search terms according to the channel evaluation parameters. In summary, the present application considers that the search term generally includes at least one search term, so that a channel evaluation parameter of each search term can be obtained, and further, channel distribution prediction is performed on the search term based on the channel evaluation parameter, so that the channel evaluation parameter in the present application is a parameter determined based on a click behavior, so that the distribution prediction result better conforms to a search intention, and the distribution prediction result provides data support for a display sequence of search results corresponding to different channels, thereby facilitating to preferentially view the search result to be viewed, shortening the search time, and avoiding the problems of complicated search operation and time consumption caused by random display of search results of different channels in the prior art.
The present application further provides a non-volatile readable storage medium, where one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to a terminal device, the one or more modules may cause the terminal device to execute instructions (instructions) of method steps in the present application.
Fig. 11 is a schematic hardware structure diagram of a search processing apparatus according to an embodiment of the present application. As shown in fig. 11, the search processing device of the present embodiment includes a processor 111 and a memory 112.
The processor 111 executes the computer program code stored in the memory 112 to implement the search processing method of fig. 1 and 3 in the above-described embodiments.
The memory 112 is configured to store various types of words to support operations in the search processing method. Examples of such terms include instructions for any application or method operating on the search processing device, such as messages, pictures, videos, and so forth. The memory 112 may include a Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
Optionally, the processor 111 is provided in the processing assembly 110. The search processing apparatus may further include: a communication component 113, a power component 114, a multimedia component 115, an audio component 116, an input/output interface 117 and/or a sensor component 118. The components specifically included in the search processing device are set according to actual requirements, which is not limited in this embodiment.
The processing component 110 generally controls the overall operation of the search processing device. The processing component 110 may include one or more processors 111 to execute instructions to perform all or part of the steps of the methods of fig. 1 and 2 described above. Further, the processing component 110 can include one or more modules that facilitate interaction between the processing component 110 and other components. For example, the processing component 110 may include a multimedia module to facilitate interaction between the multimedia component 115 and the processing component 110.
The power component 114 provides power to the various components of the search processing device. The power components 114 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the search processing device.
The multimedia component 115 includes a display screen that provides an output interface between the search processing device and the user. In some embodiments, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
The audio component 116 is configured to output and/or input audio signals. For example, audio component 116 includes a Microphone (MIC). The received audio signal may further be stored in the memory 112 or transmitted via the communication component 113. In some embodiments, audio component 116 further includes a speaker for outputting audio signals.
The input/output interface 117 provides an interface between the processing component 110 and peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include, but are not limited to: a volume button, a start button, and a lock button.
The sensor component 118 includes one or more sensors for providing various aspects of state assessment for the search processing device. For example, the sensor component 118 can detect an open/closed state of the search processing device, a relative positioning of the components, a presence or absence of user contact with the search processing device. The sensor assembly 118 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. In some embodiments, the sensor assembly 118 may also include a camera or the like.
The communication component 113 is configured to facilitate wired or wireless communication between the search processing apparatus and other devices. The search processing device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
From the above, the communication component 113, the audio component 116, the input/output interface 117 and the sensor component 118 referred to in the embodiment of fig. 11 can be implemented as input devices.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable word processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable word processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable word processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable word processing terminal device to cause a series of operational steps to be performed on the computer or other programmable terminal device to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The search processing method and apparatus and the computer-readable storage medium provided by the present application are introduced in detail, and a specific example is applied to illustrate the principle and the implementation manner of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (17)
1. A method of search processing, the method comprising:
obtaining at least one search segmentation word included in the search word;
acquiring a plurality of channels corresponding to each search participle;
acquiring a first channel evaluation parameter of each search word; the channel evaluation parameters comprise second channel evaluation parameters of each channel corresponding to the search participle;
and performing distribution prediction of the channel on the search terms according to the first channel evaluation parameter.
2. The method of claim 1, wherein prior to said obtaining the first channel rating parameter for each of said search participles, further comprising:
obtaining at least one search segmentation record included in the historical search terms;
acquiring a plurality of channels corresponding to each search word segmentation record;
acquiring a first click parameter of each search segmentation record; the click parameters comprise second click parameters of each channel corresponding to the search participle records;
acquiring a channel evaluation parameter record of each search participle record according to the first click parameter; the channel evaluation parameter records comprise second channel evaluation parameters of each channel corresponding to the search word segmentation records;
the obtaining of the first channel evaluation parameter of each search segmentation includes: and acquiring the first channel evaluation parameter of each search participle from the channel evaluation parameter record.
3. The method according to claim 2, wherein the obtaining of the channel rating parameter record of each search participle record according to the first click parameter comprises:
acquiring a first click probability of each search segmentation record according to the first click parameters; the first click probability comprises a second click probability of each channel corresponding to the search participle record; the first click parameters comprise click times and/or click rates;
and acquiring the channel evaluation parameter record of each search participle record according to the first click probability.
4. The method of claim 1, wherein prior to said obtaining at least one search segmentation included in the search term, further comprising: judging whether the searching times of the searching words are larger than or equal to the preset times or not;
the obtaining of the at least one search segmentation included in the search term includes:
determining at least one search word included in the search word as the search word under the condition that the search times of the search word are greater than or equal to the preset times;
and under the condition that the searching times of the searching terms are smaller than the preset times, performing word segmentation processing on the searching terms to obtain the at least one searching word.
5. The method according to claim 4, wherein in a case that a number of times of searching for the search term is less than the preset number of times, the performing distribution prediction of the channel on the search term according to the first channel evaluation parameter includes:
acquiring target channel evaluation parameters of each channel to which the search terms belong according to the first channel evaluation parameters;
and performing distribution prediction of the channels on the search terms according to the target channel evaluation parameters.
6. The method according to claim 5, wherein said obtaining a target channel evaluation parameter for each of the channels to which the search term belongs according to the first channel evaluation parameter comprises:
according to the first channel evaluation parameter, calculating the weight of each search word by the following formula:
wherein, wiRepresenting the weight of the ith search word; e.g. of the typemaxWhich represents a normalization parameter, is given by,
n represents the total number of channels; e.g. of the typeiThe entropy of the information representing the ith search term,
Pija second channel rating parameter indicating that the ith search term belongs to the jth channel;
and acquiring target channel evaluation parameters of each channel to which the search terms belong according to the weight.
7. The method according to claim 6, wherein said obtaining, according to the weight, a target channel evaluation parameter to which the search term belongs to each of the channels comprises:
according to the weight, acquiring the target click probability of the search word belonging to each channel;
and acquiring target channel evaluation parameters of each channel to which the search terms belong according to the target click probability.
8. The method according to claim 7, wherein the obtaining a target click probability that the search term belongs to each channel according to the weight comprises:
according to the weight, obtaining the target click probability of the search term belonging to each channel through the following formula:
wherein Q isjPresentation instrumentThe target click probability that the search term belongs to the jth channel; pijA second channel rating parameter indicating that the ith search term belongs to the jth channel; m represents the total number of search tokens; w is aiRepresenting the weight of the ith search term.
9. A search processing apparatus, characterized in that the apparatus comprises:
the search segmentation acquisition module is used for acquiring at least one search segmentation included in the search terms;
a channel obtaining module, configured to obtain multiple channels corresponding to each search word;
the evaluation parameter acquisition module is used for acquiring a first channel evaluation parameter of each search word; the channel evaluation parameters comprise second channel evaluation parameters of each channel corresponding to the search participle;
and the distribution prediction module is used for performing distribution prediction on the channel on the search terms according to the first channel evaluation parameter.
10. The apparatus of claim 9, further comprising:
the segmentation record acquisition module is used for acquiring at least one search segmentation record included in the historical search terms;
the word segmentation record channel acquisition module is used for acquiring a plurality of channels corresponding to each search word segmentation record;
the click parameter acquisition module is used for acquiring a first click parameter of each search word segmentation record; the click parameters comprise second click parameters of each channel corresponding to the search participle records;
an evaluation parameter record obtaining module, configured to obtain, according to the first click parameter, a channel evaluation parameter record of each search word segmentation record; the channel evaluation parameter records comprise second channel evaluation parameters of each channel corresponding to the search word segmentation records;
the evaluation parameter obtaining module is configured to obtain a first channel evaluation parameter of each search word from the channel evaluation parameter record.
11. The apparatus of claim 10, wherein the evaluation parameter record obtaining module comprises:
the click probability obtaining sub-module is used for obtaining the first click probability of each search participle record according to the first click parameters; the first click probability comprises a second click probability of each channel corresponding to the search participle record; the first click parameters comprise click times and/or click rates;
and the evaluation parameter record acquisition submodule is used for acquiring the channel evaluation parameter record of each search participle record according to the first click probability.
12. The apparatus of claim 9, further comprising:
the judging module is used for judging whether the searching times of the searching words are larger than or equal to the preset times;
the search participle obtaining module is used for determining at least one search participle included in the search terms as the search terms under the condition that the search times of the search terms are greater than or equal to the preset times;
and under the condition that the searching times of the searching terms are smaller than the preset times, performing word segmentation processing on the searching terms to obtain the at least one searching word.
13. The apparatus of claim 12, wherein in the case that the number of searches of the search term is less than the preset number, the distribution prediction module comprises:
a target evaluation parameter obtaining sub-module, configured to obtain, according to the first channel evaluation parameter, a target channel evaluation parameter for which the search term belongs to each of the channels;
and the distribution prediction submodule is used for performing distribution prediction on the channels on the search terms according to the target channel evaluation parameters.
14. The apparatus of claim 13, wherein the target evaluation parameter acquisition sub-module comprises:
a weight obtaining unit, configured to calculate, according to the first channel evaluation parameter, a weight of each word segmentation according to the following formula:
wherein, wiRepresenting the weight of the ith search word; e.g. of the typemaxWhich represents a normalization parameter, is given by,
n represents the total number of channels; e.g. of the typeiThe entropy of the information representing the ith search term,
Pija channel evaluation parameter indicating that the ith search word belongs to the jth channel;
and the target evaluation parameter acquisition unit is used for acquiring the target channel evaluation parameters of each channel to which the search terms belong according to the weight.
15. The apparatus according to claim 14, wherein the target evaluation parameter acquisition unit includes:
a probability obtaining subunit, configured to obtain, according to the weight, a target click probability that the search term belongs to each channel;
and the target evaluation parameter acquisition subunit is used for acquiring the target channel evaluation parameter of each channel to which the search term belongs according to the target click probability.
16. The apparatus of claim 15, wherein the probability obtaining subunit is configured to obtain, according to the weight, a target click probability that the search term belongs to each of the channels according to the following formula:
wherein Q isjRepresenting the target click probability of the search term belonging to the jth channel; pijA second channel rating parameter indicating that the ith search term belongs to the jth channel; m represents the total number of search tokens; w is aiRepresenting the weight of the ith search term.
17. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the search processing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910245155.4A CN110110191B (en) | 2019-03-28 | 2019-03-28 | Search processing method and apparatus, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910245155.4A CN110110191B (en) | 2019-03-28 | 2019-03-28 | Search processing method and apparatus, and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110110191A CN110110191A (en) | 2019-08-09 |
| CN110110191B true CN110110191B (en) | 2021-05-25 |
Family
ID=67484835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910245155.4A Active CN110110191B (en) | 2019-03-28 | 2019-03-28 | Search processing method and apparatus, and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110191B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073684A (en) * | 2010-12-22 | 2011-05-25 | 百度在线网络技术（北京）有限公司 | Method and device for excavating search log and page search method and device |
| CN104166730A (en) * | 2014-08-28 | 2014-11-26 | 无锡天脉聚源传媒科技有限公司 | Method and device for displaying search result |
| CN105069062A (en) * | 2015-07-28 | 2015-11-18 | 无锡天脉聚源传媒科技有限公司 | Video information processing method and apparatus |
| CN105893533A (en) * | 2016-03-31 | 2016-08-24 | 北京奇艺世纪科技有限公司 | Text matching method and device |
| CN107920260A (en) * | 2016-10-10 | 2018-04-17 | 国家新闻出版广电总局广播科学研究院 | Digital cable customers behavior prediction method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160098735A1 (en) * | 2014-10-07 | 2016-04-07 | Adobe Systems Incorporated | Marketing channel attribution |
-
2019
- 2019-03-28 CN CN201910245155.4A patent/CN110110191B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073684A (en) * | 2010-12-22 | 2011-05-25 | 百度在线网络技术（北京）有限公司 | Method and device for excavating search log and page search method and device |
| CN104166730A (en) * | 2014-08-28 | 2014-11-26 | 无锡天脉聚源传媒科技有限公司 | Method and device for displaying search result |
| CN105069062A (en) * | 2015-07-28 | 2015-11-18 | 无锡天脉聚源传媒科技有限公司 | Video information processing method and apparatus |
| CN105893533A (en) * | 2016-03-31 | 2016-08-24 | 北京奇艺世纪科技有限公司 | Text matching method and device |
| CN107920260A (en) * | 2016-10-10 | 2018-04-17 | 国家新闻出版广电总局广播科学研究院 | Digital cable customers behavior prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110110191A (en) | 2019-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110149540B (en) | Recommendation processing method and device for multimedia resources, terminal and readable medium | |
| CN108829808B (en) | Page personalized sorting method and device and electronic equipment | |
| CN110475155B (en) | Live video hot state identification method, device, equipment and readable medium | |
| CN110727868B (en) | Object recommendation method, device and computer-readable storage medium | |
| CN111782947B (en) | Search content display method and device, electronic equipment and storage medium | |
| CN113688310B (en) | Content recommendation method, device, equipment and storage medium | |
| CN111489155B (en) | Data processing method and device for data processing | |
| US11818428B2 (en) | Identifying viewing characteristics of an audience of a content channel | |
| CN111522724B (en) | Method and device for determining abnormal account number, server and storage medium | |
| CN107153684A (en) | Display methods, device and the equipment of PUSH message | |
| CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
| CN107729491B (en) | Method, device and equipment for improving accuracy rate of question answer search | |
| CN106815284A (en) | The recommendation method and recommendation apparatus of news video | |
| CN109348262A (en) | A kind of calculation method, device, equipment and the storage medium of main broadcaster's similarity | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN103593382A (en) | Information processing apparatus, information processing method, and program | |
| CN110110191B (en) | Search processing method and apparatus, and computer-readable storage medium | |
| US9530024B2 (en) | Recommendation system for protecting user privacy | |
| CN115834959A (en) | Video recommendation information determination method and device, electronic equipment and medium | |
| CN107341172B (en) | Video profit calculation modeling device and method and video recommendation device and method | |
| US20150235129A1 (en) | Systems, methods and non-transitory computer readable storage media for tracking and evaluating predictions regarding relationships | |
| CN114880458A (en) | Book recommendation information generation method, device, equipment and medium | |
| CN114842382A (en) | Method, device, equipment and medium for generating semantic vector of video | |
| CN113515701A (en) | Information recommendation method and device | |
| CN110555131B (en) | Content recommendation method, content recommendation device and electronic 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 |