Information query method, device and electronic equipment

Abstract

The embodiment of the present application discloses an information query method, device and electronic device, the method comprising: receiving a query request; determining query word information and target physical store information associated with the query request; predicting related categories based on the relevance information between the business object category and the query word under the condition of the target physical store; and sorting the business objects in the returned query results based on the related categories and the corresponding relevance information. Through the embodiment of the present application, the quality of the query results can be improved, and the query result page can be made into a "thousands of stores with thousands of faces".

Description

Technical Field

[0001] The present application relates to the field of information query technology, and in particular to an information query method, device and electronic equipment. Background Art

[0002] Under the "new retail" model, merchants can open physical stores offline and corresponding "cloud stores" online. Consumers can go directly to offline physical stores to purchase goods, or place orders in online "cloud stores", and then merchants provide door-to-door delivery services from offline physical stores (because offline physical stores are usually located near the location of consumer users, they can provide fast delivery services such as "half-hour delivery"), or users can choose to pick up the goods in the store after placing an order online, etc. This combination of online and offline methods can provide users with more complete services.

[0003] Among them, consumer users can browse the commodity object information provided by a specific "cloud store" through the associated client. During the browsing process, the user may enter a specific query word through the query entrance to search, and the client can display a list of commodity objects related to the query word in the cloud store.

[0004] Among them, the number of commodity objects displayed in the commodity object list may be relatively large, and in the case of display on the mobile terminal, due to the limited display area, the number of commodity objects displayed in each screen is very limited. Therefore, it may be necessary to display through multiple screens, and users need to slide the screen to browse the commodity object information that is relatively late. It can be seen that commodity objects that can be displayed on the first screen or the first few screens are more likely to attract the attention of users, while commodity object information displayed further back may be ignored due to the longer user operation path, and cannot get effective exposure opportunities.

[0005] It can be seen that in the process of providing query results, the ranking of specific query results is very important, which may directly affect the actual transaction results, or the transaction volume of a certain store, etc. Therefore, under the "new retail" model, how to improve the quality of query results has become a technical problem that needs to be solved by technical personnel in this field. Summary of the invention

[0006] The present application provides an information query method, device and electronic device, which can improve the quality of query results and realize the "thousands of stores with thousands of faces" of query result pages.

[0007] This application provides the following solutions:

[0008] An information query method, comprising:

[0009] receiving query requests;

[0010] Determining query word information and target physical store information associated with the query request;

[0011] According to the relevance information between the business object category and the query term under the condition of the target physical store, predict the related category;

[0012] The business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance information.

[0013] An information query method, comprising:

[0014] receiving query requests;

[0015] Submitting the query request to a server so that the server can determine query term information and target physical store information associated with the query request, predicting related categories based on relevance information between business object categories and the query term under the target physical store condition, and sorting business objects in the returned query results based on the related categories and corresponding relevance information;

[0016] Receive the query result information returned by the server and display it.

[0017] A method for generating a prediction database, comprising:

[0018] Providing dimension candidates for classifying physical stores by type;

[0019] Determining the physical store type information to be configured according to the information on at least one selected dimension;

[0020] Determine a query word to be configured, and categories and relevance information related to the query word in a first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0021] Receiving a relevance change value for a target category through the operation option;

[0022] The physical store type, the query term, and the relevance change value of the target category are submitted to the server so that the server can save them in the second prediction database.

[0023] An information query device, comprising:

[0024] A request receiving unit, used for receiving a query request;

[0025] An information determination unit, used to determine query word information and target physical store information associated with the query request;

[0026] A category prediction unit, configured to predict related categories based on the relevance information between the business object category and the query term under the target physical store condition;

[0027] The sorting unit is used to sort the business objects in the returned query results according to the relevant categories and the corresponding relevance information.

[0028] An information query device, comprising:

[0029] A request receiving unit, used for receiving a query request;

[0030] A request submission unit, used to submit the query request to the server, so that the server determines the query term information and the target physical store information associated with the query request, performs related category prediction based on the relevance information between the business object category and the query term under the target physical store condition, and sorts the business objects in the returned query results based on the related categories and the corresponding relevance information;

[0031] The query result receiving unit is used to receive the query result information returned by the server and display it.

[0032] A device for generating a prediction database, comprising:

[0033] A candidate item providing unit, used for providing dimension candidates for classifying physical stores into types;

[0034] A physical store type determination unit, configured to determine the physical store type information to be configured according to the information on at least one selected dimension;

[0035] A query word determination unit, used to determine the query word to be configured, and the categories and relevance information related to the query word in the first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0036] a change value receiving unit, configured to receive a relevance change value for a target category through the operation option;

[0037] The submitting unit is used to submit the relevance change value of the physical store type, the query term and the target category to the server so that the server can save it in the second prediction database.

[0038] An electronic device, comprising:

[0039] one or more processors; and

[0040] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0041] receiving query requests;

[0042] Determining query word information and target physical store information associated with the query request;

[0043] According to the relevance information between the business object category and the query term under the condition of the target physical store, predict the related category;

[0044] The business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance information.

[0045] An electronic device, comprising:

[0046] one or more processors; and

[0047] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0048] receiving query requests;

[0049] Submitting the query request to a server so that the server can determine query term information and target physical store information associated with the query request, predicting related categories based on relevance information between business object categories and the query term under the target physical store condition, and sorting business objects in the returned query results based on the related categories and corresponding relevance information;

[0050] Receive the query result information returned by the server and display it.

[0051] An electronic device, comprising:

[0052] one or more processors; and

[0053] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0054] Providing dimension candidates for classifying physical stores by type;

[0055] Determining the physical store type information to be configured according to the information on at least one selected dimension;

[0056] Determine a query word to be configured, and categories and relevance information related to the query word in a first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0057] Receiving a relevance change value for a target category through the operation option;

[0058] The physical store type, the query term, and the relevance change value of the target category are submitted to the server so that the server can save them in the second prediction database.

[0059] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0060] Through the embodiments of the present application, for the received query request, not only the query word associated with the specific query request can be determined, but also the physical store information associated with the query request can be determined. Then, under the condition of the specific physical store information, the business object category specifically related to the query word and the relevance between each business object category and the query word can be determined. In this way, when providing specific query results, the business objects can be sorted according to the category to which the business objects in the specific query results belong, and the corresponding relevance information under the above conditions. In this way, the displayed query result information can be made more in line with the actual operating conditions of the specific store, improve the quality of the query results, and realize the "thousands of stores with thousands of faces" of the query result page.

[0061] In an optional implementation, in addition to considering the physical store conditions, the population label conditions to which the request initiator user belongs can also be considered, so that while achieving "a thousand stores with a thousand faces" can also be achieved "a thousand people with a thousand faces".

[0062] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0065] Figure 2 is a flow chart of the first method provided in an embodiment of the present application;

[0066] Figure 3is a schematic diagram of the fusion of the first and second prediction databases provided in an embodiment of the present application;

[0067] Figure 4-1 , 4-2 is a schematic diagram of a query result page provided in an embodiment of the present application;

[0068] Figure 5 is a flow chart of the second method provided in an embodiment of the present application;

[0069] Figure 6 is a flowchart of the third method provided in an embodiment of the present application;

[0070] Figure 7 is a schematic diagram of a first device provided in an embodiment of the present application;

[0071] Figure 8 is a schematic diagram of a second device provided in an embodiment of the present application;

[0072] Fig. 9 is a schematic diagram of a third device provided in an embodiment of the present application;

[0073] Fig.10 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0075] In order to facilitate understanding of the technical solution provided by the embodiment of the present application, the following first introduces the processing solution in the prior art after receiving a query request. In the prior art, after receiving a query request, a list of business objects matching the query term can be determined, and then a specific query result page is generated, and the details of the specific business object list are displayed on the page. Among them, since the business object list usually includes multiple business objects matching the query term, in order to sort these business objects, a certain sorting strategy can be used, for example, it can include sorting by sales volume, or sorting by price, etc. Another specific sorting strategy is to sort according to the relevance between the category to which the business object belongs and the query term.

[0076] The categories mentioned here may generally refer to multiple subcategories under a certain upper-level category, and the upper-level category may be a category corresponding to a specific query term. For example, assuming the query term is "milk", the categories related to the query term may generally include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc. These categories are all subcategories under the "milk" category in the category system of the specific commodity object information service system.

[0077] In order to determine the relevance between the categories related to a specific query term and the query term, a prediction database can be created first, which stores various possible query terms, business object categories related to the query terms, and the relevance information between each specific category and the query term. Among them, the possible query terms can be determined based on the category name of a specific level of category. For example, for the possible query term "milk", the relevant categories include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., with relevances of 3, 3, 2, 2, etc.

[0078] In this way, after receiving a specific query request, the query term included therein can be determined first, and then the relevant categories and the relevance between each category and the query term can be determined by querying the prediction database. Next, this relevance information can be used to sort the specific business objects included in the specific query result. Specifically, after knowing the relevance between the specific category and the query term, and the business object information included in the specific query result, the category to which the specific business object belongs can be determined, and then the business objects in the business object list are sorted according to the relevance between the category to which the business object belongs and the query term. For example, the query term in a query request is "milk", and the specific query result includes business objects in multiple specific subcategories under the milk category. Since the relevance between the specific category and the query term is determined, the business objects can be sorted according to these relevances. For example, the business objects belonging to the "domestic fresh milk" category are displayed online, followed by the business objects of the "imported fresh milk" category, and the business objects of the "children's milk" category, and so on.

[0079] It can be seen that the relevance between specific related categories and query terms can affect the ranking of specific business objects in the query results, and the ranking results determine which business objects are displayed first and which are displayed later. The online display and the later display directly affect the effective exposure rate and transaction volume of the specific business objects, etc. Therefore, under this ranking strategy, the relevance information between related categories and query terms is particularly important.

[0080] In the solutions of the prior art, the specific prediction databases are universal, that is, no matter what specific scenario, as long as the query terms used are the same, the relevant categories provided and their relevance to the query terms are the same. However, in the "new retail" scenario, before the user initiates a query request, a target physical store that can provide services to the user has usually been located. For example, when a user is using an App that supports the "new retail" scenario, the client determines that the user's location is within the 5-kilometer service coverage of a physical store A, and can automatically display information related to the physical store A to the user, including information about the business objects that the store can provide, and information about related services, etc. On this basis, the user may initiate a query request related to the physical store, and the specific query result is usually also a list of business objects in the business objects associated with the physical store that match the query terms.

[0081] On the other hand, in the same system supporting the "new retail" scenario, the number of physical stores involved may be relatively large, and different physical stores, even different physical stores opened by the same company in different cities, regions, etc., may have great differences in actual business conditions. In addition, in the commodity object information service system under the "new retail" scenario, the store manager and other operators of specific physical stores may be given a lot of autonomy, including the business object categories sold in the specific store, the specific marketing strategies adopted, etc., which can be freely formulated by the operators of specific physical stores according to the actual business conditions of the store, etc., and the platform can support personalized sales or marketing plans for various different physical stores.

[0082] In this context, if different users use the same query words to initiate query requests, different physical stores may want to display different business objects to users first. For example, different physical stores usually need to adopt different sales strategies according to different store opening cycles. Among them, for physical stores with a store opening cycle of 0 to 3 months, since they are in the store's new customer acquisition period, their goal is more to obtain more users. Therefore, some new products, hot products, and other business objects that are easy to attract traffic or new users are usually the objects that such physical stores need to display first. For physical stores with a store opening cycle of 3 to 6 months, since they are in the store's growth period, standard products may be the objects that such physical stores need to display to users first. Furthermore, for physical stores with a store opening cycle of more than 6 months, since they are in the store's mature period, some business objects with higher profit points may need to be provided to users first, etc. It can be seen that for the above different types of physical stores, due to different specific operating conditions, the required sales targets may be different. In view of this situation, if the category relevance is determined only based on the query words and the query results are sorted, it will not be able to meet the personalized needs of various physical stores.

[0083] To this end, in an embodiment of the present application, since the query request initiated by the user is related to a certain target physical store, when determining the correlation between the specific business object category and the query term, it can be determined under the condition of the specific target physical store information. In other words, for different target physical stores, the correlation between the same query term and the related categories may be different. This meets the personalized information display needs of different physical stores. In addition, in an optional implementation, in addition to considering the factors of the physical store, the factors of the specific request initiator user can also be considered, including the user group label to which the user belongs, for example, office workers, students, mothers, etc., and multiple factors such as query terms, physical stores, and group labels can be combined to jointly determine the correlation between the query term and the related categories, and then sort the query results.

[0084] There are many ways to determine the categories and category relevance related to the query terms under the conditions of a specific physical store. For example, a personalized prediction database can be created for each physical store. In this personalized database, the relevance information of the query terms and related categories customized by each physical store can be saved. Alternatively, in order to reduce the number of personalized prediction databases, physical stores can be classified from one or more dimensions, and then the same personalized prediction database can be provided for the same type of physical store.

[0085] Alternatively, a public first prediction database may be provided, in which the differences between different physical stores are not considered, and the relevant categories corresponding to the specific query terms and the relevance of each relevant category are stored; a second prediction database may also be provided, in which only the categories that need to be changed and the relevance change values ​​are stored based on the first prediction database. In this way, the amount of data in the personalized prediction database can be greatly reduced.

[0086] From the perspective of the specific technical architecture, see Figure 1 , the embodiment of the present application can first provide a client, through which the consumer user can access the page associated with the specific physical store, and can also initiate a specific query request. In addition, it can also include a front-end server, that is, a server program for interacting with the client associated with the consumer user, and the server can determine the specific query result after receiving the specific query request, and can also determine the category and category relevance related to the specific query word. Among them, under the aforementioned implementation scheme of querying through the first prediction database and the second prediction database, the embodiment of the present application can also provide a configuration client for the physical store side, which can be installed in the terminal device associated with the user such as the physical store operator or the store manager, and can configure the category and relevance change value corresponding to the specific physical store or a certain physical store type, and can also provide a configuration server, and the specific configuration information can be submitted to the server, and a specific second prediction database is created. In this way, after receiving the specific query request, the front-end server can query from the first prediction database and the second prediction database at the same time, and combine the query results of the two to determine the category and relevance information related to the query word under the specific physical store condition.

[0087] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0088] Embodiment 1

[0089] First, this embodiment 1 provides an information query method from the perspective of the aforementioned front-end server. For details, see Figure 1 , the method may specifically include:

[0090] S201: receiving a query request;

[0091] The specific query request may be initiated when the user uses an associated client, which may be a client related to the "new retail" scenario. Before the user initiates a specific query request, the associated physical store may be determined first. For example, the physical store closest to the user's location, or a physical store within a certain range from the user's location, etc. In this way, the specific query request may be regarded as a query request associated with the target physical store.

[0092] S202: Determine query word information and target physical store information associated with the query request;

[0093] After receiving a specific query request, in an embodiment of the present application, the query term information carried in the query request can be first determined. The query term information can usually be input by the user, or selected from the recommended candidate terms. When the query request is submitted, the query term information will be carried in the request. In addition, in an embodiment of the present application, the target physical store associated with the query request can also be determined. As mentioned above, since the target physical store associated with the user can be determined before the query request is initiated, the physical store associated with the query request can be determined based on the information.

[0094] S203: Predicting related categories based on the relevance information between the business object category and the query term under the target physical store condition;

[0095] In order to determine the categories and category relevance related to the query words under the conditions of a specific physical store, there can be multiple ways. For example, in one implementation, a personalized prediction database can be created for each different physical store, and in this personalized database, the relevance information of the query words and related categories customized by each different physical store can be saved respectively. In this way, after receiving a specific query request, the personalized database corresponding to the specific physical store can be queried to determine the categories related to the specific query words under the conditions of the physical store, and their respective relevance. That is to say, in this way, each physical store can correspond to its own prediction database, and each database can save the relevance information between its own query words and categories. In this way, the relevance information corresponding to the category related to the query word can be determined according to the prediction database corresponding to the target physical store. Among them, for this implementation, when creating prediction databases for each different physical store, it can also refer to the existing data of other physical stores as experience information for creation. Specifically, the experience information can be obtained according to the prediction database information associated with the physical store with the same or similar attributes as the target physical store, and the prediction database corresponding to the target physical store can be created based on the experience information. After establishing a specific prediction database, in the actual process of using the database for prediction, statistics can be collected on the hits of the query results to the user's needs, and the prediction database corresponding to the target physical store can be updated according to the statistical results. In this way, the prediction database can be gradually made more consistent with the actual situation of the associated target physical store, highlighting the personalized characteristics.

[0096] Alternatively, in another implementation, in order to reduce the number of personalized prediction databases, physical stores can also be classified from one or more dimensions, and then the same personalized prediction database is provided for the same type of physical store. Among them, when classifying physical stores, they can be divided from multiple dimensions. For example, specific dimensions may include the store opening cycle mentioned above, or may also include geographical location, subsidiaries, distribution channels, and so on. When defining a physical store type, multiple dimensions can also be freely combined. For example, the store opening cycle and geographical location can be combined to define three types of physical stores with store opening cycles of 0 to 3 months, 3 to 6 months, and more than 6 months within a certain area, and so on.

[0097] In addition, considering that there are still some commonalities between different physical stores in terms of the relevance between query words and related categories, but there may be some differences in individual categories. Therefore, in order to further reduce the workload of operators and the amount of data in the personalized prediction database that needs to be maintained, a common first prediction database can be provided first, in which the differences between different physical stores can be ignored, and the relevant categories corresponding to the specific query words and the relevance of each relevant category can be saved; in addition, a second prediction database can be provided, which can include multiple data entries, each physical store type can correspond to one or more data entries in the database, and each data entry can record the categories that need to be changed in the relevance of the physical store type in the relevant categories corresponding to a certain query word, and the relevance change value (that is, the relevance after the change). In this way, in the second prediction database, it is only necessary to save the categories that need to be changed and the relevance change value based on the first prediction database, and for a certain query word, if there is no relevance change value for a certain related category in the second prediction database, the relevance between the category and the query word in the first prediction database can be used. In this way, the amount of data in the personalized prediction database can be greatly reduced. In addition, for operators, since they only need to configure the relevance change values ​​of specific categories that require special attention and query terms, instead of configuring the relevance of each related category under the same query term separately, their workload can be reduced and efficiency can be improved.

[0098] For example, in a specific implementation, the information stored in the first prediction database may be as shown in Table 1:

[0099] Table 1

[0100]

[0101] In the second prediction database, only the relevance of the categories that need to be changed based on the first prediction database needs to be saved for the specific physical store type. For example, in one implementation, the information saved in the second prediction database can be as shown in Table 2:

[0102] Table 2

[0103]

[0104] In this way, after receiving a specific query request, the information in the above two prediction databases can be combined to obtain the categories related to the query word under the condition of a specific physical store, as well as the correlation information between the specific categories. For example, if a query word is "milk", then by first querying the first prediction database, it can be known that the categories related to the query word include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., and the correlations are 3, 3, 2, 2, and so on. In addition, assuming that the type of the target store associated with the current query request is "a physical store with a store opening cycle of 0 to 3 months", it can be learned by querying the second prediction database that under the condition of the physical store, in the category corresponding to the query word, the correlation of "imported fresh milk" should be 2, and the correlation of children's milk should be 3. Finally, by combining the query results in the above two prediction databases, it can be determined that under the condition of the current physical store, the categories related to the query word "milk" include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., and the correlations are 3, 2, 3, 2, and so on. That is to say, under the condition of the physical store, the relevance of "imported fresh milk" and "children's milk" is changed to make it more consistent with the actual business conditions of the physical store, etc. In this way, when providing specific query results, the business objects in the query results can be sorted according to the size of the above relevance.

[0105] Of course, if the query word in another query request is also "milk", but the corresponding physical store type is "a branch of a physical store A in Shanghai", then by querying the second prediction database, it can be known that the relevance of "imported fresh milk" needs to be changed to 2. Then, by combining the query results of the two prediction databases, it is finally determined that under the physical store condition, the categories related to the query word "milk" include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., and the relevances are 3, 2, 2, 2, etc. In other words, compared with the previous physical store type, under the condition of this physical store type, the relevance of "children's milk" and the query word "milk" has not changed. Therefore, like other categories such as "domestic fresh milk" and "organic milk", the relevance information in the first prediction database can be used.

[0106] In addition, in the specific implementation, regarding the correlation between specific query terms and categories, in addition to considering the correlation with the actual operating conditions of specific physical stores, the correlation with user needs can also be considered. In other words, for different users, when using a certain query term to query, the information they expect to obtain may also be different. For this reason, in an embodiment of the present application, information related to specific user population labels and the like can also be reflected in the above-mentioned prediction database. In this way, after receiving a specific query request, in addition to determining the physical store information, the population label information to which the user belongs can also be determined, and a more accurate determination of the category relevance can be made.

[0107] Specifically, in the above-mentioned method of predicting through the first prediction database and the second prediction database, information related to the user population label can also be added to the second prediction database in advance. That is, under the same physical store type condition, the relevance change value between the specific category and the query term can also be set for different population labels. For example, it can be specifically shown in Table 3:

[0108] Table 3

[0109]

[0110]

[0111] In this way, after receiving a specific query request, if the associated query word is "milk", the physical store type is "a branch of a physical store A in Shanghai", and the group label of the request initiator user is "mom", then Figure 3 As shown, by querying the second prediction database, it can be known that the relevance of the related category "children's milk" has changed to 3. Then, based on the query results of the first prediction database, it can be known that under the conditions of the current physical store type and the user's population label, the categories related to the specific query terms include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., with relevances of 3, 3, 3, 2, etc., respectively. In other words, for the current physical store type and the user population label "mom", the relevance of "children's milk" is improved, so that business objects belonging to the "children's milk" category can be displayed with higher priority. The relevance of other categories can use the relevance information in the first prediction database.

[0112] In another query request, assuming that the query word is still "milk", the physical store type is still "a branch of a physical store A in Shanghai", but the population label of the request initiator user is "white-collar worker". By querying the second prediction database, it can be known that the relevance of the related category "domestic fresh milk" is 2, and the relevance of "organic milk" is 3. Then, based on the query results of the first prediction database, it can be known that under the conditions of the current physical store type and the population label to which the user belongs, the categories related to the specific query word include "domestic fresh milk", "imported fresh milk", "children's milk", "organic milk", etc., and the relevances are 2, 3, 2, and 3 respectively. In other words, for the current physical store type and the user population label of "white-collar worker", the relevance of "domestic fresh milk" is reduced, and the relevance of "organic milk" is increased, so that when providing query results, the business objects belonging to "imported fresh milk" and "organic milk" are displayed first, while "domestic fresh milk" and "children's milk" may not meet the current operating conditions of the physical store and the needs of the current users, so they can be displayed in a relatively backward position.

[0113] That is to say, in the above case, when determining the relevance between the category and the query term, the input information may include three aspects of information, namely, the query term, the type of physical store, and the user population label. Then, by querying the first prediction database and the second prediction database, the categories specifically related to the query term under the above-mentioned physical store type and user population label conditions, as well as their respective relevance, can be predicted. Subsequent use of this relevance information under specific conditions to provide query results can achieve "thousands of stores, thousands of faces" and "thousands of people, thousands of faces", that is, in the case of different physical store types and different user populations, even if the same query term is used for querying, the relevance of specific related categories may be different, which in turn affects the ranking results of business objects in the specific query results.

[0114] It should be noted that in the example shown in Table 2 above, the "crowd tag" field corresponding to some physical store types may be empty, that is, for this type of store, the influence of the crowd factor may not be considered. In addition, the crowd tag to which the specific request initiator user belongs can be obtained based on a separately saved user tag library, etc. The information in the tag library can be created based on the user's historical behavior records, or the user's personal profile and other information, which will not be described in detail here.

[0115] S204: Sort the business objects in the returned query results according to the relevant categories and the corresponding relevance information.

[0116] After determining the relevance of a specific category to the query term, physical store, user group, etc., the business objects in the query results can be sorted according to this relevance information. Specifically, first determine the category to which the business object in the specific query result belongs, and then determine the display priority of the specific business object according to the category relevance information. The higher the category relevance, the higher the display priority of the corresponding business object, and the easier it is to appear on the first screen or in a relatively front position for display.

[0117] For example, when the query word is "milk", the physical store type is "a physical store A branch in Shanghai", and the user to whom the request originates belongs is labeled "mom", the most relevant categories are "children's milk", "domestic fresh milk", and "imported fresh milk", and "children's milk" is predicted by the second prediction database, so the business objects of this category can be displayed first. Figure 4-1 As shown in 41 and 42 in the figure, two business objects specifically belonging to "children's milk" are displayed in the first resource position on the first screen. When the query word is "milk", the physical store type is "a physical store A branch in Shanghai", and the group label of the request initiator user is "white-collar worker", the most relevant related categories are "imported fresh milk" and "organic milk". Therefore, Figure 4-2 As shown in 43 and 44, business objects belonging to these two categories can be displayed preferentially, and so on.

[0118] In addition, in the specific implementation, the category system in the system usually has a hierarchical feature. For example, a certain category may include multiple subcategories. Therefore, when the business objects in the query results are sorted according to the determined related categories and the corresponding relevance information, the business objects under the subcategories associated with the related categories can also be sorted according to the sorting information corresponding to the related categories. For example, when the query word is "milk", the related categories include "organic milk", and its ranking is relatively high, and the "organic milk" category also includes subcategories such as "imported organic milk" and "domestic organic milk", then the business objects under these related subcategories can also have a relatively high ranking, and so on.

[0119] In summary, through the embodiments of the present application, for the received query request, not only the query word associated with the specific query request can be determined, but also the physical store information associated with the query request can be determined. Then, under the condition of the specific physical store information, the business object category specifically related to the query word and the relevance between each business object category and the query word can be determined. In this way, when providing specific query results, the business objects can be sorted according to the category to which the business objects in the specific query results belong, and the corresponding relevance information under the above conditions. In this way, the displayed query result information can be made more in line with the actual operating conditions of the specific store, realizing the "thousands of stores with thousands of faces" of the query result page.

[0120] In an optional implementation, in addition to considering the physical store conditions, the population label conditions to which the request initiator user belongs can also be considered, so that while achieving "a thousand stores with a thousand faces" can also be achieved "a thousand people with a thousand faces".

[0121] Embodiment 2

[0122] The second embodiment corresponds to the first embodiment and provides an information query method from the perspective of the client provided to the consumer user. Figure 5 , the method may specifically include:

[0123] S501: receiving a query request;

[0124] S502: Submitting the query request to the server so that the server determines the query term information and the target physical store information associated with the query request, performs related category prediction based on the relevance information between the business object category and the query term under the target physical store condition, and sorts the business objects in the returned query results based on the related categories and the corresponding relevance information;

[0125] S503: Receive the query result information returned by the server and display it.

[0126] For the undescribed parts in the second embodiment, please refer to the description in the first embodiment, which will not be repeated here.

[0127] Embodiment 3

[0128] As described in the aforementioned embodiment one, in one implementation method, category prediction can be performed by combining a first prediction database with a second prediction database. In this way, the information in the first prediction database can be unchanged or in a relatively stable state, and the data in the second prediction database can be configured by a specific physical store operator or store manager, and as the physical store's operating conditions and other information change, the specific configuration information may change. To this end, in order to make it more convenient for operators or store managers to configure the data in the second prediction database, a tool can also be provided to users such as operators or store managers, so that operators or store managers can submit category change value configuration information for specific physical store types through the tool. For details, see Figure 6 , Embodiment 3 of the present application provides a method for generating a prediction database, which method may specifically include:

[0129] S601: providing dimension candidates for classifying physical stores into different types;

[0130] In specific implementation, when the operator or store manager is configuring, they usually need to specify the specific type of physical store for which the configuration information needs to be submitted. To this end, the tool can first provide dimension candidates for classifying physical stores into types. Through the candidate, the user can select the specific dimension and the value under the dimension. Among them, there can be multiple specific optional dimensions, and the user can freely combine multiple dimensions when making a selection.

[0131] S602: Determine the type information of the physical store to be configured according to the information on the selected at least one dimension;

[0132] S603: Determine the query word to be configured, and the categories and relevance information related to the query word in the first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0133] The specific query term information that needs to be configured can be input by the user, or can be selected from a number of optional query terms. After determining the query term to be configured, the type and relevance information related to the query term in the first prediction database can be displayed, and operation options for changing the relevance of some or all of the categories can be provided. In other words, since the data in the second prediction database is a change operation performed on some categories based on the first prediction database, the data in the first prediction database can be listed first, and users can select the categories that need to be changed and the corresponding relevance change values ​​based on their own operational needs.

[0134] S604: receiving a relevance change value for a target category through the operation option;

[0135] S605: Submitting the physical store type, the query term, and the relevance change value of the target category to the server so that the server saves them into the second prediction database.

[0136] After receiving the specific change value, the relevance change value of the physical store type, the query word, and the target category can be submitted to the server to be saved in the second prediction database. After receiving the query request associated with the physical store type and the query word, the relevance information between the business object category and the query word under the target physical store type condition can be determined by combining the query results in the first prediction database and the second prediction database.

[0137] In addition, operation options for configuring user population information can also be provided; after receiving the configuration results of the target user population information, the physical store type, user population information, query terms and relevance change values ​​of the target category can be submitted to the server so that the server can save them in the second prediction database.

[0138] Corresponding to the first embodiment, the present application embodiment also provides an information query device, see Figure 7 , the device may include:

[0139] A request receiving unit 701, configured to receive a query request;

[0140] An information determination unit 702, configured to determine query word information and target physical store information associated with the query request;

[0141] Category prediction unit 703, used to predict related categories according to the relevance information between the business object category and the query term under the condition of the target physical store;

[0142] The sorting unit 704 is used to sort the business objects in the returned query results according to the relevant categories and the corresponding relevance information.

[0143] In specific implementation, the information determination unit may be specifically used for:

[0144] The target physical store information associated with the request is determined based on the geographical location information of the request sender and the service coverage information associated with the physical store.

[0145] The category prediction unit may specifically include:

[0146] A store type determination subunit, used to determine the target physical store type according to the information of the target store;

[0147] The prediction subunit is used to predict related categories according to the relevance information between the business object category and the query term under the condition of the target physical store type.

[0148] The prediction subunit may be specifically used for:

[0149] The relevance information corresponding to the categories related to the query term is determined by querying the prediction database corresponding to the target physical store type; the prediction database includes the categories and relevance information related to the specific query term under the condition of the specific physical store type.

[0150] Alternatively, in another manner, the prediction subunit may specifically include:

[0151] A first query subunit, configured to obtain categories and relevance information related to the query term by querying the first prediction database;

[0152] A second query subunit is configured to obtain, by querying the second prediction database, relevance change values ​​of at least some of the relevant categories corresponding to the query term under the target physical store type condition;

[0153] The comprehensive determination subunit is used to determine the relevance information between the business object category and the query term under the condition of the target physical store type by comprehensively analyzing the query results in the first prediction database and the second prediction database.

[0154] The physical store types include: physical store types divided based on the dimension of the physical store's opening cycle.

[0155] Alternatively, the physical store types include: physical store types divided based on the geographical location, subsidiary or distribution channel dimensions of the physical store.

[0156] Alternatively, the physical store types include: physical store types divided by combining multiple dimensions.

[0157] In another embodiment, the category prediction unit may be specifically used for:

[0158] According to the prediction database corresponding to the target physical store, the relevance information corresponding to the category related to the query word is determined; the prediction database includes the category and relevance information related to the specific query word under the condition of the specific physical store.

[0159] The prediction database corresponding to the target physical store is created in the following way:

[0160] The empirical information is obtained based on the prediction database information associated with the physical store having the same or similar attributes as the target physical store, and a prediction database corresponding to the target physical store is created based on the empirical information.

[0161] The device may also include:

[0162] The data updating unit is used to collect statistics on the matching of the query results with the user's needs, and update the prediction database corresponding to the target physical store according to the statistical results.

[0163] In addition, the device may also include:

[0164] A user group information determination unit, used to determine the user group information to which the user associated with the query request belongs;

[0165] The category prediction unit can be specifically used for:

[0166] According to the relevance information between the business object category and the query term under the conditions of the target physical store and the user population, relevant category prediction is performed.

[0167] Wherein, the related category is associated with a plurality of subcategories;

[0168] The sorting unit may also be used to:

[0169] According to the relevant categories and corresponding relevance information, the sorting information of the business objects under the relevant categories and their subcategories in the query results is determined.

[0170] Corresponding to the second embodiment, the present application embodiment also provides an information query device, see Figure 8 , the device may include:

[0171] A request receiving unit 801, configured to receive a query request;

[0172] The request submission unit 802 is used to submit the query request to the server so that the server determines the query term information and the target physical store information associated with the query request, performs related category prediction based on the relevance information between the business object category and the query term under the target physical store condition, and sorts the business objects in the returned query results based on the related categories and the corresponding relevance information;

[0173] The query result receiving unit 803 is used to receive the query result information returned by the server and display it.

[0174] Corresponding to the third embodiment, the present application embodiment also provides a device for generating a prediction database, see Fig. 9 , the device may include:

[0175] A candidate item providing unit 901 is used to provide dimension candidates for classifying physical stores into types;

[0176] A physical store type determination unit 902, configured to determine the physical store type information to be configured according to the information on at least one selected dimension;

[0177] A query word determination unit 903 is used to determine a query word to be configured, and categories and relevance information related to the query word in the first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0178] A change value receiving unit 904, configured to receive a relevance change value for a target category through the operation option;

[0179] The submitting unit 905 is used to submit the physical store type, the query term and the relevance change value of the target category to the server so that the server saves it in the second prediction database.

[0180] In a specific implementation, the device may further include:

[0181] A relevance determination unit is used to determine, after receiving a query request associated with the physical store type and the query term, the relevance information between the business object category and the query term under the target physical store type condition by integrating the query results in the first prediction database and the second prediction database.

[0182] In addition, the device may also include:

[0183] An operation option providing unit, used to provide operation options for configuring user population information;

[0184] The submitting unit is specifically used to submit the physical store type, user population information, query terms and the relevance change value of the target category to the server after receiving the configuration result of the target user population information, so that the server saves it into the second prediction database.

[0185] In addition, an embodiment of the present application further provides an electronic device, including:

[0186] one or more processors; and

[0187] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0188] receiving query requests;

[0189] Determining query word information and target physical store information associated with the query request;

[0190] According to the relevance information between the business object category and the query term under the condition of the target physical store, predict the related category;

[0191] The business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance information.

[0192] An electronic device, comprising:

[0193] one or more processors; and

[0194] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0195] receiving query requests;

[0196] Submitting the query request to a server so that the server can determine query term information and target physical store information associated with the query request, predicting related categories based on relevance information between business object categories and the query term under the target physical store condition, and sorting business objects in the returned query results based on the related categories and corresponding relevance information;

[0197] Receive the query result information returned by the server and display it.

[0198] and another electronic device comprising:

[0199] one or more processors; and

[0200] A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0201] Providing dimension candidates for classifying physical stores by type;

[0202] Determining the physical store type information to be configured according to the information on at least one selected dimension;

[0203] Determine a query word to be configured, and categories and relevance information related to the query word in a first prediction database, and provide an operation option for performing a change operation on the relevance of the categories related to the query word;

[0204] Receiving a relevance change value for a target category through the operation option;

[0205] The physical store type, the query term, and the relevance change value of the target category are submitted to the server so that the server can save them in the second prediction database.

[0206] in, Fig.10 The architecture of an electronic device is exemplarily shown. For example, device 1000 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, etc.

[0207] Reference Fig.10 , device 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input / output (I / O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0208] The processing component 1002 generally controls the overall operation of the device 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 1002 may include one or more modules to facilitate the interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate the interaction between the multimedia component 1008 and the processing component 1002.

[0209] The memory 1004 is configured to store various types of data to support the operation of the device 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0210] The power supply component 1006 provides power to the various components of the device 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1000.

[0211] The multimedia component 1008 includes a screen that provides an output interface between the device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and / or a rear camera. When the device 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0212] The audio component 1010 is configured to output and / or input audio signals. For example, the audio component 1010 includes a microphone (MIC), and when the device 1000 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1004 or sent via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

[0213] I / O interface 1012 provides an interface between processing component 1002 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0214] The sensor assembly 1014 includes one or more sensors for providing various aspects of status assessment for the device 1000. For example, the sensor assembly 1014 can detect the open / closed state of the device 1000, the relative positioning of components, such as the display and keypad of the device 1000, and the sensor assembly 1014 can also detect the position change of the device 1000 or a component of the device 1000, the presence or absence of user contact with the device 1000, the orientation or acceleration / deceleration of the device 1000, and the temperature change of the device 1000. The sensor assembly 1014 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1014 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0215] The communication component 1016 is configured to facilitate wired or wireless communication between the device 1000 and other devices. The device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0216] In an exemplary embodiment, the device 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0217] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, and the above instructions can be executed by the processor 1020 of the device 1000 to complete the method provided by the technical solution of the present disclosure. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0218] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0219] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0220] The above is a detailed introduction to the information query method, device and electronic device provided by the present application. The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. An information query method, characterized in that: include: receiving a query request; Determine target query word information and target physical store information associated with the query request; Obtaining personalized relevance information of the target physical store, the relevance information including: relevance information between a plurality of business object categories and a query word when the target physical store is used as a condition, the plurality of business object categories being a plurality of subcategories under a category corresponding to the query word, so as to predict, from the plurality of business object categories, relevant categories and their relevances related to the target query word when the target physical store is used as a condition; The business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance.

2. The method according to claim 1, characterized in that: The target physical store information associated with the query request is determined in the following manner: The target physical store information associated with the request is determined based on the geographical location information of the request sender and the service coverage information associated with the physical store.

3. The method according to claim 1, characterized in that The obtaining of the personalized customization relevance information of the target physical store includes: Determine the type of the target physical store according to the information of the target physical store; According to the personalized relevance information of the target physical store type, the personalized relevance information of the target physical store type is determined; the personalized relevance information of the target physical store type includes: under the condition of the same target physical store type, the relevance information between multiple business object categories and query terms.

4. The method according to claim 3, characterized in that Also includes: The personalized relevance information of the target physical store type is obtained in the following way: By querying the prediction database corresponding to the target physical store type, the personalized customization relevance information of the target physical store type is determined; the prediction database includes the relevance information between multiple business object categories and query terms under the condition of the same physical store type.

5. The method according to claim 3, characterized in that: Also includes: The personalized relevance information of the target physical store type includes: Obtaining multiple business object categories and their relevances related to the query term by querying a first prediction database; By querying a second prediction database, obtaining, under the condition that the target physical store type is used as a condition, relevance change values ​​of at least some of the relevant categories corresponding to the query term; By integrating the query results in the first prediction database and the second prediction database, the correlation information between the multiple business object categories and the query words is determined under the condition of the target physical store type.

6. The method according to claim 3, characterized in that The physical store types include: physical store types divided based on the dimension of the physical store's opening cycle.

7. The method according to claim 3, characterized in that The physical store types include: physical store types divided based on the geographical location, subsidiary or distribution channel dimensions of the physical store.

8. The method according to claim 3, characterized in that The physical store types include: physical store types divided by combining multiple dimensions.

9. The method according to claim 1, characterized in that: The obtaining of the personalized customization relevance information of the target physical store includes: According to the personalized prediction database corresponding to the target physical store, the personalized customized relevance information of the target physical store is determined; the personalized prediction database includes categories and relevances related to the specific query word under the condition of a specific physical store.

10. The method according to claim 9, characterized in that The personalized prediction database corresponding to the target physical store is created in the following way: Experience information is obtained based on prediction database information associated with physical stores having the same or similar attributes as the target physical store, and a personalized prediction database corresponding to the target physical store is created based on the experience information.

11. The method according to claim 10, characterized in that Also includes: By collecting statistics on the matching of the query results with the user's needs, the prediction database corresponding to the target physical store is updated according to the statistical results.

12. The method according to any one of claims 1 to 11, characterized in that: Also includes: Determine user group information to which the user associated with the query request belongs; Make predictions for related categories, including: According to the relevance information between the business object category and the query term under the conditions of the target physical store and the user population, relevant category prediction is performed.

13. The method according to any one of claims 1 to 11, characterized in that The related category is associated with multiple subcategories; When the business objects in the returned query results are sorted, the method further includes: According to the relevant categories and corresponding relevance information, the sorting information of the business objects under the relevant categories and their subcategories in the query results is determined.

14. An information query method, characterized in that: include: receiving a query request; Submit the query request to a server so that the server determines query term information and target physical store information associated with the query request, and obtains personalized relevance information of the target physical store, wherein the relevance information includes: relevance information between multiple business object categories and the query term when the target physical store is used as a condition, wherein the multiple business object categories are multiple subcategories under the category corresponding to the query term, so as to predict relevant categories and their relevances related to the target query term when the target physical store is used as a condition from the multiple business object categories, and sort the business objects in the returned query results according to the relevant categories and the corresponding relevances; Receive the query result information returned by the server and display it.

15. A method for generating a prediction database, characterized in that: include: Providing dimension candidates for classifying physical stores by type; Determining the physical store type information to be configured according to the information on at least one selected dimension; Determining a query word to be configured, and a plurality of business object categories and relevance information thereof related to the query word in a first prediction database, and providing an operation option for performing a change operation on the relevance of the business object categories related to the query word; Receiving a relevance change value for a target category through the operation option; Submitting the physical store type, the query term, and the relevance change value of the target category to the server so that the server saves it in the second prediction database; So that after receiving a query request associated with the physical store type and the query term, the correlation information between multiple business object categories and the query term under the condition of the target physical store is determined by integrating the query results in the first prediction database and the second prediction database, and the relevant categories and their relevance related to the target query term under the condition of the target physical store are predicted from the multiple business object categories, and the business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance.

16. The method according to claim 15, characterized in that Also includes: Providing operation options for configuring user population information; After receiving the configuration result of the target user population information, the physical store type, user population information, query term and relevance change value of the target category are submitted to the server so that the server can save them in the second prediction database.

17. An information query device, characterized in that: include: A request receiving unit, used for receiving a query request; An information determination unit, used to determine target query word information and target physical store information associated with the query request; a category prediction unit, configured to obtain personalized customized relevance information of the target physical store, the relevance information comprising: relevance information between a plurality of business object categories and a query word when the target physical store is used as a condition, the plurality of business object categories being a plurality of subcategories under a category corresponding to the query word, so as to predict, from the plurality of business object categories, relevant categories and their relevances related to the target query word when the target physical store is used as a condition; The sorting unit is used to sort the business objects in the returned query results according to the relevant categories and the corresponding relevance.

18. An information query device, characterized in that: include: A request receiving unit, used for receiving a query request; a request submission unit, configured to submit the query request to a server, so that the server can determine query term information and target physical store information associated with the query request, and obtain personalized relevance information of the target physical store, wherein the relevance information includes: relevance information between a plurality of business object categories and the query term under the condition that the target physical store is used as a condition, wherein the plurality of business object categories are a plurality of subcategories under the category corresponding to the query term, so as to predict relevant categories and their relevances related to the target query term under the condition that the target physical store is used as a condition from the plurality of business object categories, and sort the business objects in the returned query results according to the relevant categories and the corresponding relevances; The query result receiving unit is used to receive the query result information returned by the server and display it.

19. A device for generating a prediction database, characterized in that: include: A candidate item providing unit, used for providing dimension candidates for classifying physical stores into types; A physical store type determination unit, configured to determine the physical store type information to be configured according to the information on at least one selected dimension; A query word determination unit, used to determine a query word to be configured, and a plurality of business object categories and relevance information related to the query word in a first prediction database, and provide an operation option for performing a change operation on the relevance of the business object categories related to the query word; a change value receiving unit, configured to receive a relevance change value for a target category through the operation option; A submitting unit, configured to submit the physical store type, the query term, and the relevance change value of the target category to a server so that the server saves the relevance change value to a second prediction database; So that after receiving a query request associated with the physical store type and the query term, the correlation information between multiple business object categories and the query term under the condition of the target physical store is determined by integrating the query results in the first prediction database and the second prediction database, and the relevant categories and their relevance related to the target query term under the condition of the target physical store are predicted from the multiple business object categories, and the business objects in the returned query results are sorted according to the relevant categories and the corresponding relevance.

20. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method as claimed in any one of claims 1 to 17.

Images