A search platform evaluation method and device

Abstract

The embodiment of the present invention provides a method and device for evaluating a search platform, and relates to the field of data processing technology. The method includes: obtaining a first data set based on user data of a search platform to be evaluated within a first preset time period, the first data set including: multiple search keywords and a recall set of each search keyword, the recall set of any search keyword including the recall results extracted by each user from the response content of the search keyword; obtaining the entropy value of the first data set based on the recall set of each search keyword in the first data set; judging whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set; if so, determining whether to perform personalized transformation on the search platform to be evaluated based on the entropy value of the first data set. The embodiment of the present invention is used to effectively evaluate whether it is necessary to perform personalized transformation on the search platform.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an evaluation method and device for a search platform. Background Art

[0002] With the rapid development of computer technology and network technology, the amount of information has exploded, and it has become increasingly difficult to filter out effective information from massive amounts of information for distribution to users. In this context, personalized information recommendation has emerged. Due to its high efficiency, personalized information recommendation has become the mainstream way of information distribution.

[0003] With the booming development of recommendation systems, search platforms have also shown a trend of personalization, especially in the fields of e-commerce and advertising. Personalized technical transformation can improve users' search efficiency and enhance users' experience. However, personalized technical transformation requires investment in servers, manpower and other costs. Therefore, before personalizing the search platform, it is necessary to evaluate whether it is necessary to personalize the search platform. For example: in an e-commerce shopping platform, if different users search for products based on the same search keyword, most of the users ultimately purchase the same product. At this time, even if personalized transformation is performed, since most of the users ultimately purchase the same product, when different users search for products based on the search keyword, the product display pages of most users will be the same, and the benefits of personalized transformation are low, so there is no need to perform personalized transformation; if different users search for products based on the same search keyword, most of the users ultimately purchase different products, then after personalized transformation, when different users search for products based on the search keyword, different product display pages can be displayed for the products that different users ultimately purchase, so as to improve the efficiency of users finding the products they want to purchase. The benefits of personalized transformation are high, so it is necessary to perform personalized transformation. However, there is currently no solution that can effectively evaluate whether it is necessary to personalize the search platform. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a search platform evaluation method and device for effectively evaluating whether it is necessary to perform personalized transformation on the search platform.

[0005] In order to achieve the above purpose, the embodiment of the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for evaluating a search platform, comprising:

[0007] Acquire a first data set according to user data of the search platform to be evaluated within a first preset time period, wherein the first data set includes: a plurality of search keywords and a recall set of each search keyword, wherein the recall set of any search keyword includes recall results extracted by each user from the response content of the search keyword;

[0008] Obtaining an entropy value of the first data set according to a recall set of each search keyword in the first data set;

[0009] Determining whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set;

[0010] If so, it is determined whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set.

[0011] As an optional implementation of the embodiment of the present invention, obtaining the entropy value of the first data set according to the recalled set of each search keyword in the first data set includes:

[0012] Obtaining an entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set;

[0013] The entropy value of the first data set is obtained according to the entropy values ​​of each recalled set in the first data set.

[0014] As an optional implementation of the embodiment of the present invention, obtaining the entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set includes:

[0015] According to the number of recall results in each recall set in the first data set, obtaining the distribution probability of each recall result in the recall set to which it belongs;

[0016] According to the distribution probability of each recall result in the recall set to which it belongs, the entropy value of each recall set in the first data set is obtained.

[0017] As an optional implementation of the embodiment of the present invention, obtaining the entropy value of each recall set in the first data set according to the distribution probability of each recall result in the recall set to which it belongs includes:

[0018] According to the distribution probability of each recall result in the recall set to which it belongs, obtain the first calculated value corresponding to each recall result, wherein the first calculated value corresponding to any recall result is the logarithm of the distribution probability of the recall result in the recall set to which it belongs with base 2;

[0019] According to the distribution probability of each recall result in the recall set to which it belongs and the first calculated value, obtain the second calculated value corresponding to each recall result, the second calculated value corresponding to any recall result is the inverse of the product of the distribution probability of the recall result in the recall set to which it belongs and the first calculated value;

[0020] The second calculated values ​​corresponding to the respective recall results in the respective recall sets are summed to obtain the entropy values ​​of the respective recall sets in the first data set.

[0021] As an optional implementation of the embodiment of the present invention, obtaining the entropy value of the first data set according to the entropy values ​​of each recall set in the first data set includes:

[0022] Obtaining the number of recall results in each recall set in the first data set;

[0023] The entropy value of each recall set in the first data set is weightedly summed according to the number of recall results to obtain the entropy value of the first data set.

[0024] As an optional implementation of the embodiment of the present invention, the determining whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set includes:

[0025] Determining whether the entropy value of the first data set is greater than a preset threshold;

[0026] If yes, determine to perform personalized transformation on the search platform to be evaluated;

[0027] If not, it is determined that the search platform to be evaluated will not be personalized.

[0028] As an optional implementation of the embodiment of the present invention, when it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, the method includes:

[0029] Acquire a second data set according to user data of the search platform to be evaluated within a second preset time period, where the second preset time period is greater than the first preset time period;

[0030] Obtaining an entropy value of the second data set;

[0031] It is determined whether the entropy value of the user data of the search platform to be evaluated has reached a stable state according to the entropy value of the second data set.

[0032] As an optional implementation of the embodiment of the present invention, the determining, based on the entropy value of the first data set, whether the entropy value of the user data of the search platform to be evaluated has reached a stable state includes:

[0033] Obtaining a difference between an entropy value of the first data set and an entropy value of a third data set; the third data set is a data set obtained based on user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period;

[0034] If the difference is less than or equal to the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state;

[0035] If the difference is greater than the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0036] As an optional implementation of the embodiment of the present invention, the determining, based on the entropy value of the first data set, whether the entropy value of the user data of the search platform to be evaluated has reached a stable state includes:

[0037] Determine whether the entropy value of the first data set is less than the entropy value of a third data set; the third data set is a data set obtained according to user data of the search platform to be evaluated within a third preset time length, and the first preset time length is greater than the third preset time length;

[0038] If so, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state;

[0039] If not, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0040] As an optional implementation of the embodiment of the present invention, the step of obtaining a first data set according to user data of the search platform to be evaluated within a first preset time period includes:

[0041] Obtaining all search keywords and a recall set of each search keyword of the search platform to be evaluated within the first preset time period;

[0042] Sorting the search keywords in descending order according to the number of recall results in the recall set to obtain a sorting result;

[0043] The first data set is generated according to a first preset ratio of search keywords in the sorted results and a recalled set of the first preset ratio of search keywords in the sorted results.

[0044] In a second aspect, an embodiment of the present invention provides an evaluation device for a search platform, including:

[0045] A data acquisition unit, configured to acquire a first data set according to user data of the search platform to be evaluated within a first preset time period, wherein the first data set includes: a plurality of search keywords and a recall set of each search keyword, wherein the recall set of any search keyword includes a recall result extracted by each user from a response content of the search keyword;

[0046] an entropy value acquisition unit, configured to acquire an entropy value of the first data set according to a recall set of each search keyword in the first data set;

[0047] A processing unit, configured to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set;

[0048] An evaluation unit is used to determine whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set when the entropy value of the user data of the search platform to be evaluated reaches a stable state.

[0049] As an optional implementation of an embodiment of the present invention, the entropy value acquisition unit is specifically used to obtain the entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set; and obtain the entropy value of the first data set according to the entropy value of each recall set in the first data set.

[0050] As an optional implementation manner of an embodiment of the present invention, the entropy value acquisition unit is specifically used to obtain the distribution probability of each recall result in the recall set to which it belongs according to the number of recall results in each recall set in the first data set; and obtain the entropy value of each recall set in the first data set according to the distribution probability of each recall result in the recall set to which it belongs.

[0051] As an optional implementation manner of an embodiment of the present invention, the entropy value acquisition unit is specifically used to obtain a first calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs, and the first calculated value corresponding to any recall result is the logarithm of the distribution probability of the recall result in the recall set to which it belongs with base 2; obtain a second calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs and the first calculated value, and the second calculated value corresponding to any recall result is the inverse of the product of the distribution probability of the recall result in the recall set to which it belongs and the first calculated value; sum the second calculated values ​​corresponding to each recall result in each recall set to obtain the entropy value of each recall set in the first data set.

[0052] As an optional implementation of an embodiment of the present invention, the entropy value acquisition unit is specifically used to obtain the number of recall results in each recall set in the first data set; perform weighted summation of the entropy values ​​of each recall set in the first data set according to the number of recall results to obtain the entropy value of the first data set.

[0053] As an optional implementation of an embodiment of the present invention, the evaluation unit is specifically used to determine whether the entropy value of the first data set is greater than a preset threshold; if so, determine to perform personalized transformation on the search platform to be evaluated; if not, determine not to perform personalized transformation on the search platform to be evaluated.

[0054] As an optional implementation of the embodiment of the present invention, the data acquisition unit is further used to acquire a second data set based on the user data of the search platform to be evaluated within a second preset time length when it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, and the second preset time length is greater than the first preset time length;

[0055] The entropy value acquisition unit is further used to acquire the entropy value of the second data set;

[0056] The processing unit is further used to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state according to the entropy value of the second data set.

[0057] As an optional implementation manner of an embodiment of the present invention, the processing unit is specifically used to obtain the difference between the entropy value of the first data set and the entropy value of the third data set; the third data set is a data set obtained based on the user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period; if the difference is less than or equal to a threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state; if the difference is greater than the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0058] As an optional implementation of an embodiment of the present invention, the processing unit is specifically used to determine whether the entropy value of the first data set is less than the entropy value of a third data set; the third data set is a data set obtained based on the user data of the search platform to be evaluated within a third preset time length, and the first preset time length is greater than the third preset time length; if so, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state; if not, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0059] As an optional implementation manner of the present invention, the data acquisition unit is specifically used to obtain all search keywords of the search platform to be evaluated within the first preset time length and a recall set of each search keyword; sort the search keywords in descending order according to the number of recall results in the recall set to obtain the sorting result; generate the first data set according to the search keywords with a previous preset proportion in the sorting result and the recall set of the search keywords with a previous preset proportion in the sorting result.

[0060] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the search platform evaluation method described in any of the above-mentioned embodiments when executing the computer program.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which, when the computer program is executed by a computing device, enables the computing device to implement the search platform evaluation method described in any of the above-mentioned embodiments.

[0062] In a fifth aspect, an embodiment of the present invention provides a computer program product. When the computer program product is run on a computer, the computer implements the search platform evaluation method described in any of the above embodiments.

[0063] The evaluation method of the search platform provided by the embodiment of the present invention, when evaluating whether it is necessary to perform personalized transformation on the search platform to be evaluated, first obtains a first data set including multiple search keywords and a recall set of each search keyword according to the user data of the search platform to be evaluated within a first preset time, then obtains the entropy value of the first data set according to the recall set of each search keyword in the first data set, and then judges whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set, and when it is determined whether the entropy value of the user data of the search platform to be evaluated has reached a stable state, determines whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set. Since the entropy value of the first data set can effectively characterize the degree of confusion of the user data of the search platform to be evaluated within the first preset time, and the degree of confusion of the user data of the search platform to be evaluated is the main basis for measuring the benefits of personalized transformation, when the degree of confusion of the user data of the search platform to be evaluated reaches a stable state, it can be effectively determined whether it is necessary to perform personalized transformation on the search platform to be evaluated according to the degree of confusion of the user data. That is, the embodiment of the present invention can effectively evaluate whether it is necessary to perform personalized transformation on the search platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0066] Figure 1 One of the step flow charts of the evaluation method of the search platform provided by the embodiment of the present invention;

[0067] Figure 2 A second flowchart of the method for evaluating a search platform provided by an embodiment of the present invention;

[0068] Figure 3 A schematic diagram of the structure of an evaluation device for a search platform provided by an embodiment of the present invention;

[0069] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the scheme of the present invention will be further described below. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present invention, rather than all of the embodiments.

[0072] It should be noted that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" are not intended to limit the quantity and execution order. For example, the first brightness data and the second brightness data are only intended to distinguish different brightness data, rather than to limit the order of the brightness data.

[0073] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. In addition, in the description of the embodiments of the present invention, unless otherwise specified, the meaning of "multiple" refers to two or more.

[0074] The embodiment of the present invention provides a method for evaluating a search platform, referring to Figure 1 As shown, the evaluation method of the search platform includes the following steps S11 to S14:

[0075] S11. Acquire a first data set according to user data of the search platform to be evaluated within a first preset time period.

[0076] The first data set includes: multiple search keywords and a recall set of each search keyword, and the recall set of any search keyword includes the recall results extracted by each user from the response content of the search keyword.

[0077] The first preset time length in the embodiment of the present invention can be set according to the number of active users of the search platform to be evaluated. If the number of active users of the search platform to be evaluated is large, a large amount of user data can be generated in a short time, and the first preset time length can be set shorter. If the number of active users of the search platform to be evaluated is small, it takes a longer time to accumulate sufficient user data, and the first preset time length can be set longer.

[0078] In the embodiment of the present invention, the recalled set of search keywords may be the response content of the search keyword that receives the specified user operation.

[0079] For example: the search platform to be evaluated is a video playback platform that supports the search function and the designated user operation is the user's playback operation. Within the first preset time period, user A, user B, user C, and user D respectively searched for videos on the video playback platform by searching for the keyword "funny video", and the response content returned by the video playback platform all included: video 1, video 2, ... video n, and user A entered a play operation for video 2 in the response content, user B entered a play operation for video 1 in the response content, user C entered a play operation for video 4 in the response content, and user D entered a play operation for video 2 in the response content. Then the recall set of the search keyword "funny video" is {video 1, video 2, video 2, video 4}.

[0080] Another example: the search platform to be evaluated is an e-commerce shopping platform that supports the search function and the designated user operation is the user's payment operation. Within the first preset time period, user A, user B, user C, and user D respectively searched for products on the e-commerce shopping platform by searching for the keyword "mobile phone", and the response content returned by the e-commerce shopping platform all included: mobile phone 1, mobile phone 2, ... mobile phone n, and user A entered a payment operation for mobile phone 1, user B entered a payment operation for mobile phone 1, user C entered a payment operation for mobile phone 3, and user D entered a payment operation for any product in the response content, then the recall set of the search keyword "mobile phone" is {mobile phone 1, mobile phone 1, mobile phone 3}.

[0081] S12. Obtain an entropy value of the first data set according to a recall set of each search keyword in the first data set.

[0082] As an optional implementation of the embodiment of the present invention, the above step S12 (obtaining the entropy value of the first data set according to the recalled set of each search keyword in the first data set) includes the following steps a and b:

[0083] Step a: Obtain the entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set.

[0084] Continuing from the above example, the recall set for the search keyword “funny video” is {video 1, video 2, video 2, video 4}, so the number of recall results in the recall set for the search keyword “funny video” is 4; the recall set for the search keyword “mobile phone” is {mobile phone 1, mobile phone 1, mobile phone 3}, so the number of recall results in the recall set for the search keyword “mobile phone” is 3.

[0085] Optionally, the above step a (obtaining the entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set) includes the following steps a1 and a2:

[0086] Step a1: According to the number of recall results in each recall set in the first data set, obtain the distribution probability of each recall result in the recall set to which it belongs.

[0087] As described in the above example, the recall set for the search keyword "funny video" is {video 1, video 2, video 2, video 4}, and the number of recall results in the recall set for the search keyword "funny video" is 4, so the distribution probability of the recall result "video 1" in the recall set is 0.25, the distribution probability of the recall result "video 2" in the recall set is 0.5, and the distribution probability of the recall result "video 4" in the recall set is 0.25. The recall set for the search keyword "mobile phone" is {mobile phone 1, mobile phone 1, mobile phone 3}, and the number of recall results in the recall set for the search keyword "mobile phone" is 3, so the distribution probability of the recall result "mobile phone 1" in the recall set is 2 / 3, and the distribution probability of the recall result "mobile phone 3" in the recall set is 1 / 3.

[0088] Step a2: Obtain the entropy value of each recall set in the first data set according to the distribution probability of each recall result in the recall set to which it belongs.

[0089] Step b: obtaining the entropy value of the first data set according to the entropy values ​​of each recall set in the first data set.

[0090] That is, the entropy value of each recall set in the first data set is first obtained, and then the entropy value of the first data set is obtained according to the entropy value of each recall set in the first data set.

[0091] S13: judging whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set.

[0092] As an optional implementation of the embodiment of the present invention, the above step S13 (determining whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set) includes the following steps 1 to 4:

[0093] Step 1: Obtain a difference between an entropy value of the first data set and an entropy value of a third data set.

[0094] The third data set is a data set obtained based on user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period.

[0095] Step 2: Determine whether the difference is greater than a threshold difference.

[0096] In the above step 2, if the difference is less than or equal to the threshold difference, then execute the following step 3, and if the difference is greater than the threshold difference, then execute the following step 4.

[0097] Step 3: Determine whether the entropy value of the user data of the search platform to be evaluated reaches a stable state.

[0098] Step 4: Determine that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0099] As an optional implementation of the embodiment of the present invention, the above step S13 (determining whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set) includes the following steps I to III:

[0100] Step I: determine whether the entropy value of the first data set is less than the entropy value of the third data set.

[0101] The third data set is a data set obtained based on user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period.

[0102] In the above step I, if the entropy value of the first data set is less than the entropy value of the third data set, execute the following step II, and if the entropy value of the first data set is greater than or equal to the entropy value of the third data set, execute the following step III.

[0103] Step II: Determine that the entropy value of the user data of the search platform to be evaluated reaches a stable state.

[0104] Step III: Determine that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0105] Exemplarily, the time length can be preset as the step length, and a data set is gradually obtained based on the user data of the search platform to be evaluated in a longer period of time, and the entropy value of the data set obtained this time and the entropy value of the data set obtained last time are calculated to determine that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, until it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state. For example: with a step length of 1 day, a data set can be obtained based on the user data of the search platform to be evaluated in the last 1 day and the last 2 days, and the entropy value of the data set obtained based on the user data of the search platform to be evaluated in the last 1 day and the entropy value of the data set obtained based on the user data of the search platform to be evaluated in the last 2 days is determined to have not reached a stable state. If it has not reached a stable state, the entropy value of the data set obtained based on the user data of the search platform to be evaluated in the last 3 days is obtained, and the entropy value of the data set obtained based on the user data of the search platform to be evaluated in the last 2 days and the entropy value of the data set obtained based on the user data of the search platform to be evaluated in the last 3 days is determined to have not reached a stable state, and so on, until it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state. .

[0106] It should be noted that, in addition to the above embodiments, in the embodiments of the present invention, other methods may be used to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state. For example, when the entropy value of the user data of the search platform to be evaluated begins to decrease for the first time after being smoothed, it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state.

[0107] In the above step S13, if it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state, the following step S14 is executed.

[0108] S14: Determine whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set.

[0109] Specifically, before the search platform to be evaluated is personalized, when different users search based on the same search keyword, the response content fed back by the search platform to be evaluated is the same. After the personalized transformation, when different users search based on the same search keyword, the search platform to be evaluated will feed back different response content to different users based on user preferences, user historical data, etc.

[0110] The evaluation method of the search platform provided by the embodiment of the present invention, when evaluating whether it is necessary to perform personalized transformation on the search platform to be evaluated, first obtains a first data set including multiple search keywords and a recall set of each search keyword according to the user data of the search platform to be evaluated within a first preset time, then obtains the entropy value of the first data set according to the recall set of each search keyword in the first data set, and then judges whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set, and when it is determined whether the entropy value of the user data of the search platform to be evaluated has reached a stable state, determines whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set. Since the entropy value of the first data set can effectively characterize the degree of confusion of the user data of the search platform to be evaluated within the first preset time, and the degree of confusion of the user data of the search platform to be evaluated is the main basis for measuring the benefits of personalized transformation, when the degree of confusion of the user data of the search platform to be evaluated reaches a stable state, it can be effectively determined whether it is necessary to perform personalized transformation on the search platform to be evaluated according to the degree of confusion of the user data. That is, the embodiment of the present invention can effectively evaluate whether it is necessary to perform personalized transformation on the search platform.

[0111] As an extension and refinement of the above embodiment, the embodiment of the present invention provides another evaluation method for a search platform, referring to Figure 2 As shown, the evaluation method of the search platform includes the following steps S201 to S213:

[0112] S201: Obtain all search keywords and a recall set of each search keyword of the search platform to be evaluated within the first preset time period.

[0113] That is, the search keywords used by each user of the search platform to be evaluated when searching and the recall set of each search keyword are obtained.

[0114] S202: Sort the search keywords in descending order according to the number of recall results in the recall set to obtain a sorting result.

[0115] That is, the search keywords are sorted in descending order according to the number of recalled results from large to small.

[0116] S203: Generate the first data set according to the search keywords with a previous preset ratio in the sorted results and a recalled set of the search keywords with a previous preset ratio in the sorted results.

[0117] Exemplarily, the preset ratio may be 30%, 40%, 50%, etc., which is not limited in the embodiment of the present invention.

[0118] In practice, since the long-tail search keywords of the search platform often occupy a large number and a small frequency, it is likely that the user data of the search platform is difficult to accumulate to a stable entropy value. In order to solve the above problem, the above embodiment only selects the search keywords with the largest preset proportion of the number of recall results, so the above embodiment can reduce the deviation of the entropy value of the user data of the search platform.

[0119] S204. Obtain, according to the number of recall results in each recall set in the first data set, a distribution probability of each recall result in the recall set to which it belongs.

[0120] S205. Obtain a first calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs.

[0121] The first calculated value corresponding to any recall result is the logarithm of the distribution probability of the recall result in the recall set to which it belongs, with base 2.

[0122] Assume that the distribution probability of the recall result x is P(x), and the first calculated value corresponding to the recall result x is A(x), then:

[0123] A(x)=log2P(x)

[0124] S206. Obtain a second calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs and the first calculated value.

[0125] The second calculated value corresponding to any recall result is the inverse of the product of the distribution probability of the recall result in the recall set to which it belongs and the first calculated value.

[0126] Assume that the first calculated value corresponding to the recall result x is B(x), then:

[0127] B(x)=-P(x)*A(x)=-P(x)log2 P(x)

[0128] S207: summing up the second calculated values ​​corresponding to the respective recall results in the respective recall sets to obtain the entropy values ​​of the respective recall sets in the first data set.

[0129] Assume that the recall set S includes n recall results, and the entropy value of the recall set S is ε(s), then:

[0130]

[0131] S208: Obtain the number of recall results in each recall set in the first data set.

[0132] S209 . Perform a weighted summation of the entropy values ​​of each recall set in the first data set according to the number of recall results to obtain the entropy value of the first data set.

[0133] For example, the first data set includes recall set 1, recall set 2, and recall set 3, and the entropy value of recall set 1 is ε(1) and the number of recall results is a1, the entropy value of recall set 2 is ε(2) and the number of recall results is a2, and the entropy value of recall set 3 is ε(3) and the number of recall results is a3. Then the entropy value ε of the first data set can be calculated as follows:

[0134]

[0135] S210: Determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set.

[0136] In the above step S210, if it is determined based on the entropy value of the first data set that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, then a second data set is obtained based on the user data of the search platform to be evaluated within a second preset time length, and the second preset time length is greater than the first preset time length; the entropy value of the second data set is obtained; and based on the entropy value of the second data set, it is determined whether the entropy value of the user data of the search platform to be evaluated has reached a stable state.

[0137] That is, Figure 2As shown, the first preset time length in the above embodiment is replaced with a second preset time length that is greater than the first preset time length, and the above steps S201 to S210 are re-executed until it is determined that the entropy value of the user data of the search platform to be evaluated reaches a stable state.

[0138] In the above step S210, if it is determined according to the entropy value of the first data set that the entropy value of the user data of the search platform to be evaluated has reached a stable state, the following step S211 is executed.

[0139] S211. Determine whether the entropy value of the first data set is greater than a preset threshold.

[0140] The embodiment of the present invention does not limit the specific size of the preset threshold, and it can be set according to actual needs in actual use.

[0141] In the above step S211, if it is determined that the entropy value of the first data set is greater than the preset threshold, the following step S212 is executed, and if it is determined that the entropy value of the first data set is less than or equal to the preset threshold, the following step S213 is executed.

[0142] S212: Determine to perform personalized transformation on the search platform to be evaluated.

[0143] S213: Determine not to perform personalized transformation on the search platform to be evaluated.

[0144] For example, with a step length of 10 days, data sets are gradually obtained based on user data of the search platform 1 in a longer period of time, and the entropy values ​​of each data set are shown in Table 1 below:

[0145] Table 1

[0146]

[0147] It can be seen from Table 1 that after obtaining the entropy value of the data set 9, it can be determined that the entropy value of the user data of the search platform 1 has reached a stable state and is stable at 8.0.

[0148] Exemplarily, with a step length of 1 day, data sets are gradually obtained based on user data of the search platform 2 in a longer period of time, and the entropy values ​​of each data set are shown in the following Table 2:

[0149] Table 2

[0150]

[0151] It can be seen from Table 2 that after obtaining the entropy value of the data set 7, it can be determined that the entropy value of the user data of the search platform 2 has reached a stable state and is stable at 3.00.

[0152] Furthermore, by comparing Table 1 and Table 2, it can be seen that when the entropy value of the user data of search platform 1 reaches a stable state, the entropy value is 8.0, and when the entropy value of the user data of search platform 2 reaches a stable state, the entropy value is 3.00. It can be seen that the benefit of personalizing the search platform 1 is greater than the benefit of personalizing the search platform 2.

[0153] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present invention further provides an evaluation device for a search platform. This embodiment corresponds to the above method embodiment. For ease of reading, this embodiment will no longer repeat the details of the above method embodiment one by one, but it should be clear that the evaluation device for the search platform in this embodiment can correspond to all the contents of the above method embodiment.

[0154] The embodiment of the present invention provides an evaluation device for a search platform. Figure 3 is a schematic diagram of the structure of the evaluation device of the search platform, such as Figure 3 As shown, the evaluation device 300 of the search platform includes:

[0155] The data acquisition unit 31 is used to acquire a first data set according to user data of the search platform to be evaluated within a first preset time period, wherein the first data set includes: a plurality of search keywords and a recall set of each search keyword, wherein the recall set of any search keyword includes the recall results extracted by each user from the response content of the search keyword;

[0156] An entropy value acquisition unit 32, configured to acquire an entropy value of the first data set according to a recall set of each search keyword in the first data set;

[0157] A processing unit 33 is used to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set;

[0158] The evaluation unit 34 is configured to determine whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set when the entropy value of the user data of the search platform to be evaluated reaches a stable state.

[0159] As an optional implementation of an embodiment of the present invention, the entropy value acquisition unit 32 is specifically used to obtain the entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set; and obtain the entropy value of the first data set according to the entropy value of each recall set in the first data set.

[0160] As an optional implementation of an embodiment of the present invention, the entropy value acquisition unit 32 is specifically used to obtain the distribution probability of each recall result in the recall set to which it belongs according to the number of recall results in each recall set in the first data set; and obtain the entropy value of each recall set in the first data set according to the distribution probability of each recall result in the recall set to which it belongs.

[0161] As an optional implementation manner of an embodiment of the present invention, the entropy value acquisition unit 32 is specifically used to obtain a first calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs, and the first calculated value corresponding to any recall result is the logarithm of the distribution probability of the recall result in the recall set to which it belongs with base 2; obtain a second calculated value corresponding to each recall result according to the distribution probability of each recall result in the recall set to which it belongs and the first calculated value, and the second calculated value corresponding to any recall result is the inverse of the product of the distribution probability of the recall result in the recall set to which it belongs and the first calculated value; sum the second calculated values ​​corresponding to each recall result in each recall set to obtain the entropy value of each recall set in the first data set.

[0162] As an optional implementation of an embodiment of the present invention, the entropy value acquisition unit 32 is specifically used to obtain the number of recall results in each recall set in the first data set; perform weighted summation of the entropy values ​​of each recall set in the first data set according to the number of recall results to obtain the entropy value of the first data set.

[0163] As an optional implementation of the embodiment of the present invention, the evaluation unit 34 is specifically used to determine whether the entropy value of the first data set is greater than a preset threshold; if so, determine to perform personalized transformation on the search platform to be evaluated; if not, determine not to perform personalized transformation on the search platform to be evaluated.

[0164] As an optional implementation of the embodiment of the present invention, the data acquisition unit 31 is further used to acquire a second data set based on the user data of the search platform to be evaluated within a second preset time length when it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, and the second preset time length is greater than the first preset time length;

[0165] The entropy value acquisition unit 32 is further used to acquire the entropy value of the second data set;

[0166] The processing unit 33 is further configured to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state according to the entropy value of the second data set.

[0167] As an optional implementation of an embodiment of the present invention, the processing unit 33 is specifically used to obtain the difference between the entropy value of the first data set and the entropy value of the third data set; the third data set is a data set obtained based on the user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period; if the difference is less than or equal to a threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state; if the difference is greater than the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0168] As an optional implementation of an embodiment of the present invention, the processing unit 33 is specifically used to determine whether the entropy value of the first data set is less than the entropy value of a third data set; the third data set is a data set obtained based on the user data of the search platform to be evaluated within a third preset time length, and the first preset time length is greater than the third preset time length; if so, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state; if not, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

[0169] As an optional implementation of the present invention, the data acquisition unit 31 is specifically used to obtain all search keywords of the search platform to be evaluated within the first preset time period and a recall set of each search keyword; sort the search keywords in descending order according to the number of recall results in the recall set to obtain the sorting result; generate the first data set according to the search keywords with a previous preset proportion in the sorting result and the recall set of the search keywords with a previous preset proportion in the sorting result.

[0170] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device. Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device provided in this embodiment includes: a memory 401 and a processor 402, wherein the memory 401 is used to store a computer program; and the processor 402 is used to execute the evaluation method of the search platform provided in the above embodiment when executing the computer program.

[0171] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computing device implements the search platform evaluation method provided in the above embodiment.

[0172] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product. When the computer program product is executed on a computer, the computing device implements the search platform evaluation method provided in the above embodiment.

[0173] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0174] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0175] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0176] Computer readable media include permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A search platform evaluation method, characterized in that: include: Acquire a first data set according to user data of the search platform to be evaluated within a first preset time period, wherein the first data set includes: a plurality of search keywords and a recall set of each search keyword, wherein the recall set of any search keyword includes recall results extracted by each user from the response content of the search keyword; Obtaining an entropy value of the first data set according to a recall set of each search keyword in the first data set; Determining whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set; If yes, determining whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set; The determining whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set includes: Determining whether the entropy value of the first data set is greater than a preset threshold; If yes, determine to perform personalized transformation on the search platform to be evaluated; If not, it is determined that the search platform to be evaluated will not be personalized.

2. The method according to claim 1, characterized in that The obtaining the entropy value of the first data set according to the recalled set of each search keyword in the first data set includes: Obtaining an entropy value of each recall set in the first data set according to the number of recall results in each recall set in the first data set; The entropy value of the first data set is obtained according to the entropy values ​​of each recalled set in the first data set.

3. The method according to claim 2, characterized in that The obtaining, according to the number of recall results in each recall set in the first data set, an entropy value of each recall set in the first data set includes: According to the number of recall results in each recall set in the first data set, obtaining the distribution probability of each recall result in the recall set to which it belongs; According to the distribution probability of each recall result in the recall set to which it belongs, the entropy value of each recall set in the first data set is obtained.

4. The method according to claim 3, characterized in that The obtaining, according to the distribution probability of each recall result in the recall set to which it belongs, the entropy value of each recall set in the first data set includes: According to the distribution probability of each recall result in the recall set to which it belongs, obtain the first calculated value corresponding to each recall result, wherein the first calculated value corresponding to any recall result is the logarithm of the distribution probability of the recall result in the recall set to which it belongs with base 2; According to the distribution probability of each recall result in the recall set to which it belongs and the first calculated value, obtain the second calculated value corresponding to each recall result, the second calculated value corresponding to any recall result is the inverse of the product of the distribution probability of the recall result in the recall set to which it belongs and the first calculated value; The second calculated values ​​corresponding to the respective recall results in the respective recall sets are summed to obtain the entropy values ​​of the respective recall sets in the first data set.

5. The method according to claim 2, characterized in that: The obtaining the entropy value of the first data set according to the entropy values ​​of each recalled set in the first data set includes: Obtaining the number of recall results in each recall set in the first data set; The entropy value of each recall set in the first data set is weightedly summed according to the number of recall results to obtain the entropy value of the first data set.

6. The method according to claim 1, characterized in that In the case where it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state, the method includes: Acquire a second data set according to user data of the search platform to be evaluated within a second preset time period, where the second preset time period is greater than the first preset time period; Obtaining an entropy value of the second data set; It is determined whether the entropy value of the user data of the search platform to be evaluated has reached a stable state according to the entropy value of the second data set.

7. The method according to claim 1, characterized in that: The determining, based on the entropy value of the first data set, whether the entropy value of the user data of the search platform to be evaluated has reached a stable state includes: Obtaining a difference between an entropy value of the first data set and an entropy value of a third data set; the third data set is a data set obtained based on user data of the search platform to be evaluated within a third preset time period, and the first preset time period is greater than the third preset time period; If the difference is less than or equal to the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has reached a stable state; If the difference is greater than the threshold difference, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

8. The method according to claim 1, characterized in that: The determining, based on the entropy value of the first data set, whether the entropy value of the user data of the search platform to be evaluated has reached a stable state includes: Determine whether the entropy value of the first data set is less than the entropy value of a third data set; the third data set is a data set obtained according to user data of the search platform to be evaluated within a third preset time length, and the first preset time length is greater than the third preset time length; If so, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state; If not, it is determined that the entropy value of the user data of the search platform to be evaluated has not reached a stable state.

9. The method according to any one of claims 1 to 8, characterized in that: The step of obtaining a first data set according to user data of the search platform to be evaluated within a first preset time period includes: Obtaining all search keywords and a recall set of each search keyword of the search platform to be evaluated within the first preset time period; Sorting the search keywords in descending order according to the number of recall results in the recall set to obtain a sorting result; The first data set is generated according to a first preset ratio of search keywords in the sorted results and a recalled set of the first preset ratio of search keywords in the sorted results.

10. An evaluation device for a search platform, characterized in that: include: A data acquisition unit, configured to acquire a first data set according to user data of the search platform to be evaluated within a first preset time period, wherein the first data set includes: a plurality of search keywords and a recall set of each search keyword, wherein the recall set of any search keyword includes a recall result extracted by each user from a response content of the search keyword; an entropy value acquisition unit, configured to acquire an entropy value of the first data set according to a recall set of each search keyword in the first data set; A processing unit, configured to determine whether the entropy value of the user data of the search platform to be evaluated has reached a stable state based on the entropy value of the first data set; An evaluation unit, configured to determine whether to perform personalized transformation on the search platform to be evaluated according to the entropy value of the first data set when the entropy value of the user data of the search platform to be evaluated reaches a stable state; The processing unit is specifically used to determine whether the entropy value of the first data set is greater than a preset threshold; if so, determine to perform personalized transformation on the search platform to be evaluated; if not, determine not to perform personalized transformation on the search platform to be evaluated.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the search platform evaluation method described in any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the search platform evaluation method according to any one of claims 1 to 9.

13. A computer program product, characterized in that When the computer program product runs on a computer, the computer is enabled to implement the search platform evaluation method according to any one of claims 1 to 9.

Images