Data search method and device, equipment, medium and product

Abstract

The invention relates to the technical field of computers, and discloses a data search method and device, equipment, a medium and a product. The method comprises the following steps: acquiring current search data and reference data corresponding to the current search data; determining a target search demand corresponding to the current search data based on the search demand corresponding to the reference data; and displaying a search result corresponding to the target search demand on a search result page. By implementing the technical scheme of the invention, accurate pre-judgment of the search demand of the user can be realized, so that the search result meeting the search demand of the user can be accurately obtained, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to data search methods, devices, equipment, media and products. Background Art

[0002] With the development and popularization of the Internet, users are increasingly inclined to search for life service-related products in their daily lives. Many words used in searches often have multiple meanings. When search terms have multiple meanings, the search results given in the industry usually obtain personalized content based on the user's historical search characteristics. If there is no personalized reference, the mainstream consumption of the search term is referenced. However, when a certain type of demand suddenly breaks out and there is no corresponding historical search feature for this type of demand, the current search mechanism is difficult to predict the user's search needs, resulting in difficulty in giving corresponding search results. Summary of the invention

[0003] In view of this, the present disclosure provides a data search method, apparatus, device, medium and product to solve the problem that it is difficult to predict user search needs and the search results are difficult to meet the user search needs.

[0004] In a first aspect, the present disclosure provides a method for displaying search results, comprising:

[0005] Obtain the current search data and the reference data corresponding to the current search data;

[0006] Based on the search requirements corresponding to the reference data, determine the target search requirements corresponding to the current search data;

[0007] The search results corresponding to the target search requirements are displayed on the search results page.

[0008] In a second aspect, the present disclosure provides a device for displaying search results, including:

[0009] An acquisition module is used to acquire the current search data and the reference data corresponding to the current search data;

[0010] A search requirement determination module, used to determine the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data;

[0011] The display module is used to display the search results corresponding to the target search requirements on the search results page.

[0012] In a third aspect, the present disclosure provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the data search method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0013] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the data search method of the first aspect or any corresponding embodiment thereof.

[0014] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the data search method of the first aspect or any corresponding embodiment thereof.

[0015] The data search method, device, equipment, medium and product provided in this embodiment obtains reference data corresponding to the current search data, and determines the target search demand of the current search data according to the search demand corresponding to the reference data, thereby expanding the source of determining the target search demand corresponding to the current search data. The data search is performed according to the target search demand, and the obtained search results are displayed on the search results page. Therefore, when a certain type of demand suddenly breaks out, the actual search demand of the user is determined in combination with the introduced reference data. Even if there is no previous behavior data of the user, the user's search demand can be accurately predicted, so that the search results that meet the user's search needs can be accurately obtained, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a schematic diagram of searching for related technologies in an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of a search interface and a banner display of a related technology in an embodiment of the present disclosure;

[0019] Figure 3 is a flowchart of a data search method according to an embodiment of the present disclosure;

[0020] Figure 4 is a schematic diagram of inputting current search data through a search box according to an embodiment of the present disclosure;

[0021] Figure 5 is a schematic diagram of determining the current search data through a channel page according to an embodiment of the present disclosure;

[0022] Figure 6 is a flowchart of another data search method according to an embodiment of the present disclosure;

[0023] Figure 7 is a flowchart of another data search method according to an embodiment of the present disclosure;

[0024] Figure 8 is a structural block diagram of a data search device according to an embodiment of the present disclosure;

[0025] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] With the development and popularization of the Internet, users are increasingly inclined to search for life service-related products in their daily lives. Figure 1 As shown, during the search process, the user enters the search term, and the search engine gives the search results based on the consumption of other users. Furthermore, the user determines whether the search results given by the search engine meet the search requirements. If they meet the search requirements, the presentation of the search results is updated with reference to this consumption.

[0033] Specifically, many words used in search often have multiple meanings. When search terms have multiple meanings, the search results given usually obtain personalized content based on the user's historical search features. If there is no personalized reference, the mainstream consumption of the search term is referenced. However, when a certain type of demand suddenly breaks out and there is no corresponding historical search feature for this type of demand, the current search mechanism is difficult to predict the user's search needs, resulting in difficulty in giving corresponding search results.

[0034] For example, when a sudden hot topic such as the release of the movie "XXX" appears, and the movie name overlaps with other life service-related names, the current search mechanism is difficult to make an accurate prediction. When the user's actual demand is XXX movie tickets, with XXX as the search term, the APP's search results are as follows: Figure 2 As shown on the left, the search results are displayed based on other users' historical consumption, all of which are stores and related products that provide leisure and entertainment projects with the same name as XXX, which is seriously inconsistent with the actual search needs of users.

[0035] In view of the above situation, the related technology usually adopts the method of manually setting a banner after users or other channels complain or feedback to meet the relevant search needs, such as Figure 2 As shown on the right. However, in actual application, if such situations occur frequently, they rely on manual discovery and operation, which may cause problems such as difficulty in finding problems, long cycle, and waste of labor costs.

[0036] Therefore, how to automatically provide search results that meet users' search needs when users have no previous behavior has become an important challenge and urgent need currently faced.

[0037] In view of this, the present disclosure provides a data search method, which obtains reference data corresponding to the current search data when performing data search, determines the target search demand of the current search data according to the search demand corresponding to the reference data, and then performs data search according to the target search demand, and displays the search results on the search results page. Therefore, when a certain type of demand suddenly breaks out, the source of determining the search demand is expanded by introducing reference data, which facilitates the rapid acquisition of the user's actual search demand, realizes the accurate prediction of the user's search demand, and can accurately obtain the search results that meet the user's search demand, which helps to improve the user experience.

[0038] According to an embodiment of the present disclosure, a data search method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] In this embodiment, a data search method is provided, which can be used in electronic devices, such as mobile phones, tablet computers, computers, etc. Figure 3 is a flow chart of a data search method according to an embodiment of the present disclosure. Figure 3 As shown, the process includes the following steps:

[0040] Step S101, obtaining the current search data and the reference data corresponding to the current search data.

[0041] The current search data is the data that needs to be searched in a targeted manner at present. Specifically, the current search data may include search terms, search images, search videos, etc.

[0042] In some examples, the user may input a search term into the search box according to his / her search requirements, and accordingly, the search box may respond to the user's input operation and obtain the corresponding search term, such as Figure 4 The search term input method is not limited to manual, specified term control, voice-to-text, or input based on historical search records.

[0043] In some examples, the search terms can be obtained from the channel page of the application, such as Figure 5 As shown, multiple search terms are displayed in advance in the channel page, and the user can select the desired search term from them.

[0044] In some examples, the search image or search video may be uploaded locally from the electronic device, or may be scanned by the user using a scanning function of the electronic device.

[0045] Reference data is data related to the current search data, and may include historical search data, search data generated at the current location of the electronic device, and rewritten data generated during the search process.

[0046] The reference data can be combined to further clarify the content of the search data. Specifically, an application is deployed in the electronic device, and the search data entered when the search is initiated through the application is stored in the database of the application. Whenever the user initiates a search request, the electronic device can access the database to obtain reference data related to the user's search data.

[0047] Step S102: determining the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data.

[0048] Search requirements are used to characterize the content to be searched in the reference data, and target search requirements are used to characterize the content to be actually searched in the current search data.

[0049] Specifically, a trained search demand determination model is pre-deployed in the electronic device, and the search demand determination model is used to understand and predict the user's search intention. The search demand determination model can be obtained based on neural network training, machine learning algorithm training, or deep learning algorithm training. There is no specific limitation on the training method of the search demand model here, as long as the determination of search intent can be achieved.

[0050] As mentioned above, the reference data contains a variety of content, and accordingly, there can be multiple search demand determination models, that is, different types of reference data correspond to corresponding search demand determination models. Specifically, the search demand determination model can determine the main focus and search needs of the reference data by analyzing the keywords contained in the reference data, wherein the keyword analysis can include semantic understanding of the keywords, word frequency statistics, context analysis, etc. The search demand determination model can also determine the corresponding search needs in combination with the user's historical behavior, etc. In addition, considering the impact of contextual information on search needs, such as geographic location, time, device type, etc., the search demand determination model can adjust the search needs according to the contextual information. Of course, the search demand determination model can also combine multimodal information (such as images, audio, video, etc.) to infer the search needs corresponding to the reference data.

[0051] Combined with the search requirements corresponding to the reference data, the current search data is analyzed to understand the search intent of the current search data as accurately as possible, determine the target search requirements corresponding to the current search data, and thus determine the actual content of the current search data.

[0052] Step S103: displaying search results corresponding to the target search requirement on the search results page.

[0053] After the target search demand is determined, the target search demand is sent to the corresponding data source for data search to obtain the initial search results. The initial search is screened in combination with the current search data, and irrelevant results are removed to obtain the final search results, which are then displayed on the search results page of the application. Specifically, the search results can be displayed in the form of a video, a list, a map interface, or other forms. The display form of the search results is not specifically limited here.

[0054] The data search method provided in this embodiment obtains reference data corresponding to the current search data, and determines the target search demand of the current search data according to the search demand corresponding to the reference data, thereby expanding the source of determining the target search demand corresponding to the current search data. The data search is performed according to the target search demand, and the obtained search results are displayed on the search results page. Therefore, when a certain type of demand suddenly breaks out, the actual search demand of the user is determined in combination with the introduced reference data. Even if there is no previous behavior data of the user, the user's search demand can be accurately predicted, so that the search results that meet the user's search demand can be accurately obtained, thereby improving the user experience.

[0055] In this embodiment, a data search method is provided, which can be used in electronic devices, such as mobile phones, tablet computers, computers, etc. Figure 6 is a flow chart of a data search method according to an embodiment of the present disclosure. Figure 6 As shown, the process includes the following steps:

[0056] Step S201, obtaining the current search data and the reference data corresponding to the current search data. For detailed description, please refer to the relevant description of the corresponding steps in the above embodiment, which will not be repeated here.

[0057] Step S202: determining the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data.

[0058] Specifically, the reference data includes consumption data and rewriting data. The consumption data refers to the mass consumption data generated at the user's location, that is, the search consumption data that is the same or similar to the current search data, such as clicks, views, etc.; the rewriting data is used to represent the modified consumption data, specifically the mass consumption data generated at the user's location before and after the rewriting, that is, the rewriting of the search data generated before and after the search, such as the rewriting of search terms and word frequency, etc.

[0059] Accordingly, the above step S202 includes:

[0060] Step S2021, based on the analysis result of the consumption data, determine the first search demand corresponding to the consumption data.

[0061] The first search demand represents the search demand of the general public in the region. Specifically, the consumption data is analyzed by a search demand determination model corresponding to the consumption data deployed in the electronic device to determine the consumption content contained in the consumption data, and the first search demand is determined in combination with the type of the consumption content.

[0062] In some optional implementations, the above step S2021 may include:

[0063] Step a1: determine at least one type of search content corresponding to the consumption data.

[0064] Step a2: determining a first search demand corresponding to the consumption data according to a search proportion of at least one type of search content in the consumption data.

[0065] The search content indicates the content that the user actually wants to search for. The consumption data includes various types of search content. By classifying the content included in the consumption data, the various types of search content corresponding to the consumption data can be determined.

[0066] The search ratio indicates the proportion of each type of search content in the consumption data. Specifically, different types of search content have corresponding search ratios in the consumption data. Combined with the search ratio of the search content in the consumption data, the corresponding first search demand is determined, and the first search demand is used to represent the public demand in the region.

[0067] In a specific example, the consumption data corresponds to a corresponding search demand determination model, and the acquired consumption data is input into the search demand determination model, and the consumption data is analyzed by the search demand model to determine the proportion of each search content in the consumption data. The first search demand corresponding to the consumption data is determined based on the proportion. Specifically, if the difference in search proportions of different search data is within a preset value (for example, 5%, 10%, 15%, etc., which is not specifically limited here), the search demand is determined based on different search contents, otherwise, the search demand is determined based on the search content with a larger search proportion.

[0068] Assuming the preset value is 10%, taking "XXX" as an example, if 20% of users consume leisure and entertainment videos with the same name as XXX, and 30% consume XXX movie ticket purchase-related content, and the difference between the proportions of these two types of needs is within the preset value, then it is determined that the first search demand contains two different types of needs at the same time. If 1% of users consume leisure and entertainment videos with the same name as XXX, and 30% consume XXX movie ticket purchase-related content, although there are two different types of needs, the proportion of these two different types of search content is too different, then it is determined that the first search demand is XXX movie ticket purchase.

[0069] In the above implementation, the search contents contained in the consumption data are classified to determine the search proportions of each type of search contents, and the search needs corresponding to the consumption data are determined based on the search proportions. Thus, by referring to the mass consumption data, the data source for search demand judgment is expanded.

[0070] Step S2022: Determine a second search requirement corresponding to the rewritten data based on the analysis result of the rewritten data.

[0071] The second search demand represents the search demand of the general public in the region before and after the rewriting. Specifically, the consumption data before and after the rewriting are analyzed by a search demand determination model corresponding to the rewriting data deployed in the electronic device to determine the consumption content contained in the consumption data before and after the rewriting, and the second search demand is determined in combination with the consumption content before and after the rewriting.

[0072] In a specific example, the consumption data before and after the rewriting is input into the corresponding search demand determination model, and the consumption data before and after the rewriting is analyzed by the search demand model to determine the rewritten search demand. For example, when searching for the keyword "XXX", most users rewrite the search term from "XXX" to "XXX movie ticket group purchase", so it can be determined that the rewritten search demand (i.e., the second search demand) is XXX movie tickets.

[0073] Step S2023: determining a target search requirement based on the first search requirement and the second search requirement.

[0074] The second search demand is introduced on the basis of the first search demand. The public search demand in the current area can be determined by combining the first search demand and the second search demand. Then the target search demand corresponding to the current search data can be determined according to the public search demand.

[0075] In some optional implementations, the above method further includes: determining a rewriting rate corresponding to the rewritten data, and accordingly, the target search requirement is determined based on the first search requirement, the second search requirement and the rewriting rate.

[0076] The rewrite rate indicates the rewrite ratio of search data, that is, the proportion of search data that has been rewritten. For rewritten consumption data, there is a corresponding rewrite mark or rewrite record. After obtaining the consumption data, it is detected whether the consumption data has been rewritten. If it has been rewritten, the search data before the rewrite is obtained. At the same time, the rewritten data is counted, and the proportion of the rewritten data in the total consumption data is calculated to obtain the rewrite rate corresponding to the rewritten data.

[0077] The rewriting rate is compared with the preset rewriting rate to determine whether the rewriting rate exceeds the preset rewriting rate. The preset rewriting rate is a pre-set rewriting rate for determining the content contained in the target search requirement. Specifically, when the rewriting rate exceeds the preset rewriting rate, it means that the rewriting rate is high, and the target search requirement is determined based on the first search requirement and the second search requirement; when the rewriting rate does not exceed the rewriting rate, it means that the rewriting rate is low, and the target search requirement is determined based on the first search requirement.

[0078] In the above implementation, the target search demand of this search is determined by combining the first search demand corresponding to the regional mass consumption data, the second search demand corresponding to the rewritten data, and the rewriting rate, thereby enabling a comprehensive judgment of the target search demand and facilitating accurate prediction of the target search demand.

[0079] Specifically, the reference data also includes previous behavior data, which is used to characterize historical consumption data, that is, historical search data generated by the user before the current search. Specifically, the previous behavior data may include video data browsed before the current search, recently used search terms, and historical preference data, etc.

[0080] Accordingly, the above step S202 further includes:

[0081] Step S2024: based on the analysis result of the previous behavior data, determine the third search requirement corresponding to the previous behavior data.

[0082] The third search demand represents the personalized demand of the user. Specifically, the search demand determination model corresponding to the previous behavior data deployed in the electronic device analyzes the previous behavior data, determines the search content contained in the previous behavior data, and determines the third search demand in combination with the search content.

[0083] Step S2025, determining a target search requirement based on the first search requirement, the second search requirement, and the third search requirement.

[0084] Since the third search demand is a personalized demand determined based on the user's previous behavior data, that is, the third search demand represents the content actually required to be searched for the current search data, the target search demand can be predicted in combination with the first search demand, the second search demand and the third search demand to obtain the target search demand.

[0085] In a specific example, the obtained previous behavior data is input into the corresponding search demand determination model, and the previous behavior data is analyzed through the search demand model to determine the personalized demand corresponding to the previous behavior data. For example, when searching for the search term "XXX", if the user has browsed a store exploration video of a leisure and entertainment merchant with the same name as XXX in the local area before the current search, the store exploration video is the previous behavior data generated by the user. At this time, the third search demand can be determined for the previous behavior data as: to find a store and related products of leisure and entertainment projects with the same name as XXX.

[0086] Step S203: Display the search results corresponding to the target search requirement on the search results page. For detailed description, please refer to the relevant description of the corresponding steps in the above embodiment, which will not be repeated here.

[0087] The data search method provided in this embodiment introduces the public's rewritten data on the basis of regional public consumption data, expanding the data source for determining the target search demand. At the same time, the rewritten data is used to determine the public's rewritten needs, and the target search needs are comprehensively judged according to the first search demand corresponding to the public consumption data and the second search demand corresponding to the rewritten data, so as to determine a more accurate target search demand. When there is previous behavior data, the first search demand, the second search demand, and the third search demand are comprehensively judged as the target search demand, thereby determining the search demand that meets the user. Furthermore, relevant hot content can be introduced according to the target search demand, so as to quickly obtain the user's consumption posterior data on the results related to the new demand, which solves the problem of long-term and continuous misjudgment of user demand after the demand outbreak.

[0088] In this embodiment, a data search method is provided, which can be used in electronic devices such as mobile phones, tablet computers, computers, etc. Figure 7 is a flowchart of a method for displaying search results according to an embodiment of the present disclosure, such as Figure 7 As shown, the process includes the following steps:

[0089] Step S301, obtaining the current search data and the reference data corresponding to the current search data. For detailed description, please refer to the relevant description of the corresponding steps in the above embodiment, which will not be repeated here.

[0090] Step S302: based on the search requirements corresponding to the reference data, determine the target search requirements corresponding to the current search data. For detailed description, please refer to the relevant description of the corresponding steps in the above embodiment, which will not be repeated here.

[0091] Step S303: display the search results corresponding to the target search requirement on the search results page.

[0092] Specifically, the above step S303 includes:

[0093] Step S3031, determine the search results according to the target search requirements and the current search data.

[0094] The database of the application is screened according to the target search requirements to obtain relevant content corresponding to the target search requirements, and then the current search data is matched with the relevant content corresponding to the target search requirements to find relevant search results containing the current search data.

[0095] Step S3032: Based on the relevance of the search results to the current search data, the search results are displayed on a search results page.

[0096] The relevance is used to characterize the relevance between the search results and the current search data. The higher the relevance, the more consistent the search results are with the current search data. The order of the search results is determined according to the relevance between the search results and the current search data, and the search results are displayed on the search results page according to the order.

[0097] In some optional implementations, the above step S3032 includes:

[0098] Step c1, obtaining attribute data corresponding to the search results, wherein the attribute data includes basic data, performance data and categories.

[0099] Step c2, determining a first correlation between the current search data and basic data, and a second correlation between the target search demand and the corresponding category.

[0100] Step c3, determining the ranking of the search results according to the first relevance, the second relevance and the performance data.

[0101] Step c4, displaying the search results on the search results page in order.

[0102] Attribute data is used to characterize the attributes of search results, including basic data, performance data, and categories. Basic data is used to characterize the basic attribute information of search results, such as the name and evaluation of the search results; performance data is used to characterize the performance attributes of search results, such as ratings, click-through rates, conversion rates, etc.; and categories are used to characterize the categories or classifications to which search results belong, such as entertainment, food, movies, etc.

[0103] After the search results are obtained, the search results are parsed to extract the attribute data contained in the search results. For each search result, the first correlation between the current search data and the basic data is determined by text matching, semantic understanding, keyword matching, etc. At the same time, the category to which the current search data belongs is analyzed, and the category to which the search results belong is matched with the category to which the target search demand belongs to perform correlation matching to determine the second correlation between the target search demand and the category to which it belongs.

[0104] The first relevance, second relevance and performance data corresponding to each search result are fused using weighted average, linear combination or other algorithms to obtain the fusion result corresponding to each search result. Based on the fusion result, the relevance between each search result and the current search data is determined, and the search results are sorted according to the relevance. The higher the relevance, the higher the search result ranking. Then, the search results are displayed on the search results page according to the determined ranking. This achieves accurate display of search results and improves the user's search experience.

[0105] The data search method provided in this embodiment performs data search according to the target search requirements and the current search data to obtain corresponding search results, and displays the final search results on the search results page based on the relevance between the search results and the current search data, so as to facilitate users to consume search data according to the target search requirements.

[0106] As one or more specific application embodiments of the embodiments of the present disclosure, the data search process is as follows:

[0107] Step 1: Users can Figure 4 The search word "XXX" is manually entered into the search box shown, and the application can obtain the current search data entered by the user, that is, the search word "XXX".

[0108] Step 2, obtain whether there is previous behavior data before the user enters "XXX", if so, obtain the previous behavior data, otherwise go to step 4.

[0109] Step 3: Determine the personalized needs corresponding to the user's previous behavior data based on the relevant model corresponding to the deployed previous behavior data. For example, if the user browsed a store exploration video of a leisure and entertainment merchant with the same name as XXX in the user's location before the current search, the personalized needs are determined to be to find a store and related products of leisure and entertainment projects with the same name as XXX.

[0110] Step 4, obtain the public consumption data of the user's location. The location is not limited to the user's city, but may also be a province, country, etc. The consumption data is the consumption of the same search term or similar search terms, such as clicks, transactions, etc.

[0111] Step 5: Determine the mass demand corresponding to the mass consumption data based on the relevant model corresponding to the deployed mass consumption data. For example, if 20% of users consume videos related to leisure and entertainment with the same name as XXX, and 30% consume content related to the purchase of XXX movie tickets, it is considered that there are two different types of mass demand at the same time.

[0112] Step 6, obtain the public's rewriting data before and after, that is, the search terms and word frequencies before and after the current search.

[0113] Step 7: Determine the public demand corresponding to the public rewritten data before and after the rewritten data according to the relevant model corresponding to the deployed rewritten data. For example, 80% of the search terms of users with related searches are rewritten from "XXX" to "XXX movie ticket group purchase", and the public demand after the rewrite is XXX movie tickets.

[0114] Step 8, according to the personalized needs, public needs, public needs before and after rewriting, rewriting rate, etc. given by different models, the target search needs corresponding to this search are determined. For example, personalized needs cannot be determined, public needs point to shops and related products of leisure and entertainment projects with the same name as XXX, and 50% of users have rewritten and the public needs after rewriting are XXX movie tickets. Table 1 shows some examples, but they are not exhaustive, and the benchmark values ​​for judging the higher and lower rewriting rates can be determined according to actual needs.

[0115] Table 1 Example of target search requirements

[0116]

[0117] Step 9: Obtain relevant search results in different forms such as video / POI according to the determined target search requirements and the search terms input by the user.

[0118] Step 10: Obtain basic information and performance data of the search results according to the obtained relevant search results. Taking POI as an example, the basic information may be name, evaluation, etc.; the performance data may be rating, click volume, conversion rate, etc.

[0119] Step 11, sorting is performed based on the relevance between the search term and the basic data of the relevant search results, the relevance between the target search demand and the category to which the relevant search results belong, the performance data of the relevant search results, etc., and the target search results are displayed on the search aggregation page based on the sorting.

[0120] In this way, sudden hot spots such as the release of the movie "XXX" appear, and the movie name overlaps with other life service-related names. When the user's actual demand is XXX movie tickets, using XXX as the search term, it can be judged based on other users' rewritten data that the user's demand may be a store and related products of leisure and entertainment projects with the same name as XXX, or XXX movie tickets, and the search results corresponding to the two types of needs are given. This avoids the problem that such situations previously relied on manual discovery and operation, which often could not be solved or were solved with great delay when such situations occurred frequently.

[0121] In the present embodiment, a data search device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0122] This embodiment provides a data search device, such as Figure 8 As shown, including:

[0123] The acquisition module 401 is used to acquire the current search data and the reference data corresponding to the current search data.

[0124] The search requirement determination module 402 is used to determine the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data.

[0125] The display module 403 is used to display the search results corresponding to the target search requirements on the search results page.

[0126] In some optional implementations, the reference data includes consumption data and rewritten data, and the rewritten data is used to represent the modified consumption data. Accordingly, the search demand determination module 402 includes:

[0127] The first search requirement determining unit is used to determine a first search requirement corresponding to the consumption data based on an analysis result of the consumption data.

[0128] The second search requirement determining unit is used to determine a second search requirement corresponding to the rewritten data based on the analysis result of the rewritten data.

[0129] The target determination unit is used to determine a target search requirement based on the first search requirement and the second search requirement.

[0130] In some optional implementations, the search requirement determination module 402 further includes:

[0131] The rewriting determination unit is used to determine the rewriting rate corresponding to the rewriting data. Accordingly, the target search requirement is determined based on the first search requirement, the second search requirement and the rewriting rate.

[0132] In some optional implementations, the first search requirement determining unit includes:

[0133] The search content determination subunit is used to determine at least one type of search content corresponding to the consumption data.

[0134] The demand determination subunit is used to determine a first search demand corresponding to the consumption data according to a search proportion of at least one type of search content in the consumption data.

[0135] In some optional implementations, the reference data also includes previous behavior data, which is used to characterize historical consumption data. Accordingly, the search demand determination module 402 includes:

[0136] The third search requirement determining unit is used to determine a third search requirement corresponding to the preceding behavior data based on the analysis result of the preceding behavior data.

[0137] The third target determination unit is used to determine a target search requirement based on the first search requirement, the second search requirement and the third search requirement.

[0138] In some optional implementations, the display module 403 includes:

[0139] The search result determination unit is used to determine the search result according to the target search requirement and the current search data.

[0140] The display unit is used to display the search results on the search results page based on the relevance of the search results to the current search data.

[0141] In some optional embodiments, the display unit includes:

[0142] The attribute acquisition subunit is used to obtain the attribute data corresponding to the search results. The attribute data includes basic data, performance data and the category to which it belongs.

[0143] The relevance determination subunit is used to determine the first relevance between the current search data and the basic data, and the second relevance between the target search demand and the category to which it belongs.

[0144] The ranking determination subunit is used to determine the ranking of the search results according to the first relevance, the second relevance and the performance data.

[0145] The sorting display subunit is used to display the search results on the search result page in sort order.

[0146] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0147] The data search device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0148] The data search device provided in this embodiment obtains reference data corresponding to the current search data, and determines the target search demand of the current search data according to the search demand corresponding to the reference data, thereby expanding the source of determining the target search demand corresponding to the current search data. The data search is performed according to the target search demand, and the obtained search results are displayed on the search results page. Therefore, when a certain type of demand suddenly breaks out, the actual search demand of the user is determined in combination with the introduced reference data. Even if there is no previous behavior data of the user, the user's search demand can be accurately predicted, so that the search results that meet the user's search demand can be accurately obtained, thereby improving the user experience.

[0149] The present disclosure also provides an electronic device having the above Figure 8 The data search device shown.

[0150] See also Fig. 9 , Fig. 9 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present disclosure, such as Fig. 9 As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 10 is taken as an example.

[0151] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0152] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0153] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0154] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0155] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0156] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0157] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0158] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0159] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A data search method, characterized in that: The method comprises: Obtaining the current search data and reference data corresponding to the current search data; Based on the search requirements corresponding to the reference data, determining the target search requirements corresponding to the current search data; The search results corresponding to the target search requirements are displayed on the search results page.

2. The method according to claim 1, characterized in that The reference data includes consumption data and rewritten data, and the rewritten data is used to represent the modified consumption data; the step of determining the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data includes: Determining a first search requirement corresponding to the consumption data based on an analysis result of the consumption data; Determining a second search requirement corresponding to the rewritten data based on an analysis result of the rewritten data; The target search requirement is determined based on the first search requirement and the second search requirement.

3. The method according to claim 2, characterized in that The method further comprises: A rewriting rate corresponding to the rewriting data is determined, wherein the target search requirement is determined based on the first search requirement, the second search requirement and the rewriting rate.

4. The method according to claim 2 or 3, characterized in that: The determining, based on the analysis result of the consumption data, a first search requirement corresponding to the consumption data includes: determining at least one type of search content corresponding to the consumption data; A first search demand corresponding to the consumption data is determined according to a search proportion of the at least one type of search content in the consumption data.

5. The method according to claim 2, characterized in that: The reference data also includes preceding behavior data, and the preceding behavior data is used to characterize consumption data generated historically; the determining the target search demand corresponding to the current search data based on the search demand corresponding to the reference data includes: Determining a third search requirement corresponding to the preceding behavior data based on an analysis result of the preceding behavior data; The target search requirement is determined based on the first search requirement, the second search requirement, and the third search requirement.

6. The method according to claim 1, characterized in that The displaying of search results corresponding to the target search requirement on the search results page includes: Determine search results according to the target search requirements and the current search data; Based on the relevance of the search results to the current search data, the search results are displayed on the search results page.

7. The method according to claim 6, characterized in that The step of displaying the search results on the search results page based on the relevance between the search results and the current search data includes: Acquire attribute data corresponding to the search result, wherein the attribute data includes basic data, performance data and category; Determine a first correlation between the current search data and the basic data, and a second correlation between the target search demand and the category to which it belongs; Determining the ranking of the search results according to the first relevance, the second relevance, and the performance data; The search results are displayed on the search result page according to the order.

8. A data search device, characterized in that: The device comprises: An acquisition module, used to acquire the current search data and reference data corresponding to the current search data; A search requirement determination module, used to determine the target search requirement corresponding to the current search data based on the search requirement corresponding to the reference data; The display module is used to display the search results corresponding to the target search requirements on the search results page.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the data search method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the data search method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the data search method according to any one of claims 1 to 7.

Images