CN112528144A - Search recommendation method and device, intelligent device, electronic device and storage medium - Google Patents

Abstract

The application discloses a search recommendation method and device, an intelligent device, an electronic device and a storage medium, which can be applied to artificial intelligence, cloud computing, big data, computer data, intelligent search, information flow and a knowledge graph. The specific implementation scheme is as follows: acquiring a search task of a user, determining a search target object according to the search task, determining a category of the search target object, determining an association category having an association relationship with the category, and generating and outputting recommendation information according to the search target object and the association category, wherein the recommendation information comprises: the target object and the object belonging to the associated category are searched, and the object belonging to the associated category is recommended in combination, so that the problem of large limitation of search recommendation in the related technology is solved, the technical effects of flexibility, diversity, richness and reliability of search recommendation are improved, and the search experience of a user is enhanced.

Description

Search and recommend methods, devices, smart devices, electronic devices and storage media

technical field

This application relates to computer and data processing technologies, and in particular to a search recommendation method, device, smart device, electronic device and storage medium, which can be applied to artificial intelligence, cloud computing, big data, computer data, intelligent search, information flow, and Knowledge Graph.

Background technique

With the development of Internet technology and the increase in the amount of information, how to improve the comprehensiveness of recommended information for users has become an urgent problem to be solved.

In the prior art, a commonly used method is: determine an object with a high similarity to the search target object, and generate and output recommendation information according to the search target object and the determined object with a high similarity, for example, search The target object is a mobile phone of model XX, and the determined object with high similarity can be a mobile phone of model YY that is similar in appearance to the mobile phone of model XX, and the recommendation information is generated and output according to the mobile phone of model XX and the mobile phone of model YY.

However, generating recommendation information through similarity has relatively large limitations and cannot meet the broader needs of users.

SUMMARY OF THE INVENTION

The present application provides a search recommendation method, apparatus, smart device, electronic device and storage medium for improving the comprehensiveness of recommendation.

According to the first aspect of the present application, a search recommendation method is provided, including:

Obtain the search task of the user, and determine the search target object according to the search task;

Determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category;

According to the search target object and the associated category, recommendation information is generated and output; wherein, the recommendation information includes: the search target object and objects belonging to the associated category.

Through the search recommendation method provided by the embodiment of the present application, the technical effect of improving the style and flexibility of the recommendation is achieved.

According to a second aspect of the present application, a search recommendation device is provided, comprising:

The first acquisition module is used to acquire the search task of the user, and determine the search target object according to the search task;

a first determining module, configured to determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category;

a generating module, configured to generate recommendation information according to the search target object and the association category; wherein the recommendation information includes: the search target object and objects belonging to the association category;

An output module, configured to output the recommended information.

According to a third aspect of the present application, an electronic device is provided, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present application, a smart device is provided, comprising:

an exporter, at least one processor, and a memory communicatively coupled to the at least one processor; wherein the exporter is coupled to the at least one processor;

the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the first aspect;

The outputter is used for outputting the recommendation information.

According to a fifth aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect.

According to a sixth aspect of the present application, there is provided a computer program product, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

It should be understood that the content described in this section is not intended to identify key or critical features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the present application will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

1 is a schematic diagram of an application scenario according to an embodiment of the present application;

2 is a schematic diagram according to an embodiment of the present application;

3 is a schematic diagram according to another embodiment of the present application;

4 is a schematic diagram of a visualization chart according to an embodiment of the present application;

5 is a schematic diagram of a visualization chart according to another embodiment of the present application;

6 is a schematic diagram of a visualization chart according to another embodiment of the present application;

7 is a schematic diagram according to another embodiment of the present application;

8 is a schematic diagram according to another embodiment of the present application;

9 is a schematic diagram according to another embodiment of the present application;

10 is a schematic diagram according to another embodiment of the present application;

FIG. 11 is a schematic diagram according to yet another embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

In an example, the search recommendation method provided by the embodiment of the present application can be applied to an application scenario of item recommendation (eg, product recommendation). For example, the server recommends furniture, electrical appliances, and books to the user.

In another example, the search recommendation method provided by the embodiment of the present application may be applied to an application scenario of information recommendation (eg, news recommendation). For example, the server recommends the latest news, weather information, and road condition information to the user.

In another example, the search recommendation method provided by the embodiment of the present application can be applied to an application scenario of human-computer interaction. For example, based on the interaction information initiated by the user, the server recommends topics and related content related to the interaction information to the interaction robot.

It is worth noting that the above examples are only used to illustrate the applicable application scenarios of the search recommendation method of the embodiment of the present application, and should not be understood as a limitation of the application scenario of the search recommendation method of the embodiment of the present application.

In order to deepen the reader's understanding of the application scenario of the search recommendation method of the embodiment of the present application, item recommendation (such as product recommendation) is now taken as an example, and the present application is described with reference to FIG. The application scenarios of the search recommendation method of the embodiment are described in detail as follows.

In the application scenario shown in FIG. 1 , when the user 101 has a search demand, such as a demand for purchasing commodities, a search request may be sent to the server 103 based on the user terminal 102 .

For example, as shown in FIG. 1 , the user 101 may input “XX air conditioner” on the display interface of the user terminal 102 , and send a search request to the server 103 through the virtual button “Search” on the display interface of the user terminal 102 .

The server 103 receives the search request sent by the user terminal 102 for searching for "XX air conditioner", and generates and feeds back recommendation information including "XX air conditioner" to the user terminal 102 .

The user terminal 102 may display recommendation information including "XX air conditioner".

In the related art, in order to improve the user's shopping experience, the server 103 may determine a "YY air conditioner" with a high similarity to "XX air conditioner", generate and feed back recommendation information including "XX air conditioner" and "YY air conditioner" to the user terminal 102 .

Among them, the higher similarity can be represented, the performance similarity is higher, and the appearance similarity is higher.

That is to say, in the related art, while recommending the commodity searched by the user to the user, the server may also recommend commodities related to the commodity searched by the user to the user.

However, using the similarity recommendation method to recommend products to users may result in a technical problem that the recommendation has greater limitations and cannot meet the broader needs of users. flexibility and comprehensiveness.

Through creative work, the inventor of the present application has obtained the inventive concept of the present application: determine the category of the object to be recommended (such as an item, etc.) Objects, and associated categories generate recommendation information, so as to achieve flexible and comprehensive technical effects of recommendation.

The technical solutions of the present application and how the technical solutions of the present application solve the above-mentioned technical problems will be described in detail below with specific examples. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

The present application provides a search recommendation method, device, intelligent device, electronic device and storage medium, which are applied to artificial intelligence, cloud computing, big data, computer vision, intelligent search, and knowledge graph in the field of computer and data processing technology, to The technical effect of achieving the flexibility and comprehensiveness of search recommendation.

FIG. 2 is a schematic diagram according to an embodiment of the present application. As shown in FIG. 2 , the search recommendation method in the embodiment of the present application may include:

S201: Acquire a user's search task, and determine a search target object according to the search task.

Exemplarily, the execution body of this embodiment may search for a recommendation device, and the search and recommendation device may be a server (including a cloud server and a local server), a computer, a terminal device, a processor, a chip, and the like.

For example, when the search recommendation method of this embodiment is applied to the application scenario shown in FIG. 1 , the search recommendation apparatus may be a server as shown in FIG. 1 .

In one example, the search task may be actively triggered by the user. For example, when a user has a search requirement, a search task initiated by the user equipment (such as a mobile terminal, etc.) to the search recommendation apparatus is used.

In this embodiment, the search target object may be the object searched by the user this time.

For example, in combination with the application scenario shown in FIG. 1 , when the user initiates a search task of "XX air conditioner" to the search recommendation device based on the user equipment, the search recommendation device determines "XX air conditioner" as the search target object.

In another example, the search task may be generated by the search recommendation apparatus based on the user's historical search records. For example, the search recommendation device generates search tasks based on time intervals and based on the user's historical search records.

In this embodiment, the search target object may be the object searched by the user's history.

For example, if a user searches for "XX air conditioner" in a recent period (such as within a week), but has not placed an order for purchase, the search recommendation device can actively generate a search task, generate and send recommendation information to the user equipment.

And on the basis that the search recommendation device actively generates the search task, the search recommendation device can generate and send recommendation information to the user equipment when the relevant information of the search target object changes, such as price information.

It should be understood that the above examples are only used to illustrate some situations of triggering a search task, and should not be construed as a limitation on the triggering of the search task and the search task.

S202: Determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category.

It is worth noting that the categories in this embodiment may be categories determined based on industry classification standards, such as home improvement as one category and automobiles as another category; it may also be set based on requirements, historical records, and experience, such as doors and windows is one category, appliances are another.

However, in this embodiment, when the category is a category based on an industry classification standard, the flexibility and comprehensiveness of the search recommendation method in this embodiment can be relatively high.

Combining the above example and the application scenario shown in FIG. 1 , if the search target object shown is "XX air conditioner", it can be determined that the category of the search target object is home decoration.

Correspondingly, after the belonging category is determined, it is possible to continue to determine the associated category that has an associated relationship with the belonging category. That is, there is an association between the owning category and related categories, such as home improvement and automobiles.

S203: Generate and output recommendation information according to the search target object and the associated category.

The recommendation information includes: the search target object and the objects belonging to the associated category.

In this embodiment, the recommendation information may include contents of two dimensions, the contents of one dimension are the search target objects, and the contents of the other dimension are the objects belonging to the associated category.

In combination with the above example, if the search target object is "XX air conditioner" and the associated category is automobile, the recommended information includes: "XX air conditioner" and objects belonging to automobiles (such as "XX automobile").

Exemplarily, the search recommendation apparatus may output recommendation information through an interactive interface. For example, in combination with the application scenario shown in FIG. 1 , the search and recommendation apparatus may send recommendation information to a user terminal, and output the recommendation information through an interactive interface (ie, a display interface) of the user terminal.

It is worth noting that, in this embodiment, the feature of determining the category of the search target object and determining the associated category that has an associated relationship with the category is introduced. The recommendation information of the objects of the associated category can be implemented, so that the recommendation information can include more recommendation elements, thereby achieving the technical effects of comprehensiveness, flexibility, and reliability of the recommendation.

FIG. 3 is a schematic diagram according to another embodiment of the present application. As shown in FIG. 3 , the search recommendation method in the embodiment of the present application may include:

S301: For each category of text data, perform object extraction processing on each category of text data, and construct a visual chart including various categories based on the objects obtained through the object extraction processing.

Exemplarily, text data may be obtained based on categories, and the text data of each category may include: the content of the text, the title of the text, a comment about the object in the text, and a description about the object in the text, and the like.

Object extraction processing can be implemented based on technologies such as named entity recognition, such as nouns, place names, institution names, commodity label names, etc., which can be used as object words for object things, such as the brand name of the car in the car, the names of major tourist attractions, and the department name, etc.

In this embodiment, different objects may constitute a visual chart, and each category in the visual chart may include multiple different objects. That is, the visualization chart includes multiple categories, and each category includes multiple different objects.

In some embodiments, the objects of the visualization chart have an belonging relationship with the categories of the visualization chart, that is, the objects of the visualization chart belong to the category of the visualization chart, and the belonging relationship can be characterized based on the second edge connection relationship.

FIG. 4 is a schematic diagram of a visualization chart according to an embodiment of the present application. As shown in FIG. 4 , the visualization chart may include two categories, namely home improvement and automobile, and “XX air conditioner” and “frameless wooden doors and windows” are the visualization charts , and they all belong to the home improvement category; "A car" and "B car" are also objects of the visualization chart, and both belong to the car category.

FIG. 5 is a schematic diagram of a visualization chart according to another embodiment of the present application. As shown in FIG. 5 , on the basis of the visualization chart shown in FIG. 4 , in some embodiments, for each category, each category can be determined subcategories below. For example, the sub-categories under the home improvement category include: doors, windows and home appliances; the sub-categories under the automobile category include: fuel vehicles and new energy vehicles.

And as shown in Figure 5, the sub-category doors and windows can include: "frameless wooden doors and windows" objects and "framed wooden doors and windows" objects; sub-category home appliances can include: "XX air conditioner" objects and "XX refrigerator objects"; The category of fuel vehicles can include: "C car" and "D car"; the sub-category of new energy vehicles can include "A car" and "B car".

Similarly, sub-categories can be determined based on industry standards, or based on requirements, historical records, and experiments.

S302: Determine the co-occurrence frequency of each category based on the acquired historical search records.

Among them, the co-occurrence frequency represents the frequency of occurrence of different categories in adjacent search records in historical search records.

Exemplarily, the historical search records may be historical search records within a preset time period, such as historical search records within half a year.

Frequency can represent, in historical search records, the number of times that different categories appear repeatedly in adjacent search records.

For example, the object "XX air conditioner" belongs to the home improvement category, and "A car" belongs to the automobile category. In the historical search records of half a year, the number of adjacent search records for "XX air conditioner" and "A car" is n (n is an integer greater than or equal to 1) times, the co-occurrence frequency of the home improvement category and the automobile category is n times.

S303: Determine the first edge connection relationship of each category according to the co-occurrence frequency, and update the visualization chart based on the first connection relationship of each category.

Among them, the first edge connection relationship represents the association relationship.

Exemplarily, in this embodiment, it can be understood that whether there is an association relationship between two categories can be determined based on the co-occurrence frequency, and when there is an association relationship between the two categories, it can be connected based on the first edge in the visual graph. relationship is represented.

Combining the above example, if it is determined based on the co-occurrence frequency that there is an association between the home improvement category and the automobile category, as shown in FIG. On the basis shown, in the visual chart, add the first edge connection relationship between the home improvement category and the car category,

It should be understood that, the above example is only taken as an example of two categories to illustrate, and should not be construed as a limitation on the number of categories.

It is worth noting that, in this embodiment, by determining the association relationship between categories based on the co-occurrence frequency, the accuracy and reliability of the determined association relationship between When the visual chart of the association relationship determines the recommended information, the content dimension of the recommended information is increased, the technical effect of the flexibility, comprehensiveness, and reliability of the recommendation is improved, and the user experience is enhanced.

S304: Acquire the search task of the user, and determine the search target object according to the search task.

Exemplarily, for the description of S304, reference may be made to S201, which will not be repeated this time.

S305: Determine, according to the visual chart, the category to which the search target object has a second edge connection relationship.

Combining the above examples, it can be seen that there is a second edge connection relationship between the object of the visualization chart and the category of the visualization chart, and the second edge connection relationship represents the belonging relationship between the object and the category. In this embodiment, when the search recommendation device is based on the search When the task determines the search target object, the category to which the search target object has a second edge connection relationship can be determined from the visual chart based on the search target object.

For example, in combination with the visual chart shown in FIG. 6 , if the search target object is "XX air conditioner", then "XX air conditioner" can be a home improvement category. And as shown in FIG. 6 , the search recommendation device may determine the home electronics category to which it belongs based on “XX air conditioner”, and determine the home improvement category to which it belongs based on the home electronics category.

It is worth noting that, in this embodiment, by determining the category that has a second edge connection relationship with the search target object from the visual chart, the technical effect of determining the category to which the search target object belongs can be improved and the technical effect of reliability can be improved.

S306: Determine an association category that has a first edge connection relationship with the category to which it belongs, according to the visual chart.

Combining the above examples, it can be seen that the categories of the visual chart have a first edge connection relationship between the categories, and the first edge connection relationship represents the association relationship between the categories and the categories. In this embodiment, when the search recommendation device determines based on the visual chart When searching for the category to which the target object belongs, it can be determined from the visual chart based on the category to which it belongs, the associated category that has a first edge connection relationship with the category to which it belongs, that is, the associated category that has an associated relationship with the category to be determined from the visual chart.

For example, with reference to the visual chart shown in FIG. 6 , if the category is home decoration, the search recommendation device may determine that the associated category is automobile based on the first edge connection relationship between the home decoration category and the automobile category.

In the same way, by determining from the visual chart, the association category that has the first edge connection relationship with the category to which it belongs can improve the technical effect of determining the efficiency and reliability of the association category. The recommendation information is the technical effect of the flexibility and comprehensiveness of user recommendation.

S307: Determine an object that has a second edge connection relationship with the associated category according to the visual chart.

Combining the above example and Fig. 6, if the association class is car, the object with the second edge connection relationship with the car can be one of "A car", "B car", "C car", and "D car" or more.

S308: Generate and output recommendation information according to the object that has a second edge connection relationship with the association category and the search target object.

The recommendation information includes: the search target object and the objects belonging to the associated category.

Combining the above example and Figure 6, if the objects with the second edge connection relationship with the associated category are "A car", "B car", "C car", and "D car", the search target object is "XX air conditioner", The recommended information may include: "XX air conditioner" and "A car", may also include: "XX air conditioner" and "B car", or may include: "XX air conditioner", "A car", "B car", "C car", etc.

It is worth noting that, in this embodiment, by determining an object that has a second edge connection relationship with the associated category, and generating and outputting recommendation information based on the object and the search target object, the content dimension of the recommendation information can be increased, thereby increasing the content dimension of the recommendation information. It can meet the user's relatively broad search needs, and by making recommendations for users based on related categories, the recommended information can be highly matched with the user's search needs, so that the technical effect of the reliability and accuracy of the recommendation is high.

FIG. 7 is a schematic diagram according to another embodiment of the present application. As shown in FIG. 7 , the search recommendation method in the embodiment of the present application may include:

S701: Obtain historical search records, determine co-occurrence frequencies of various categories based on the historical search records, and construct a mapping relationship based on the co-occurrence frequencies.

Among them, the co-occurrence frequency represents the frequency of occurrence of different categories in adjacent search records in historical search records. The mapping relationship represents the association between categories.

Exemplarily, for the description of the co-occurrence frequency, reference may be made to the description of the co-occurrence frequency in the above example, which will not be repeated here.

In this embodiment, a mapping relationship for representing the association relationship between categories may be constructed based on the co-occurrence frequency. In some embodiments, the mapping relationship can be represented by a linked list.

It is worth noting that, in this embodiment, by determining the co-occurrence frequency based on the historical search records, and constructing the mapping relationship based on the co-occurrence frequency, the mapping relationship can more accurately express the association relationship between the categories, so that the The technical effect of improving the accuracy and reliability of the recommended information when the mapping relationship is used to determine the recommended information.

In some embodiments, constructing the mapping relationship based on the co-occurrence frequency may include the following steps:

Step 1: Determine the correlation probability between categories according to the co-occurrence frequency.

Among them, the correlation probability represents the probability of continuing to search for the second category after the first category is searched in the historical search records.

That is to say, in this embodiment, the categories with the associated relationship have directivity.

Combining the above example and Figure 6, the co-occurrence frequency of the home improvement category and the car category is n times. In the historical search records, after searching for the home improvement category, the number of times to continue searching for the automobile category is m times, then the number of times between the home improvement category and the automobile category is m. Correlation probability=m/n, correspondingly, the correlation probability between the automobile category and the home improvement category=(n-m)/n.

Step 2: Build a mapping relationship according to the association probability.

After determining the relevance probability, the search recommendation apparatus may construct a mapping relationship based on the relevance probability. For example, a correlation probability threshold may be preset, and if the determined correlation probability between categories is greater than the correlation probability threshold, a mapping relationship between categories is constructed.

Specifically, in combination with the above example, if m/n is greater than the correlation probability threshold, a mapping relationship including the correlation between the home improvement category and the car category is constructed, and in the mapping relationship, there is a directivity between the home improvement category and the automobile category , that is, when it is determined that the attribution category is home improvement, it can be determined that the category associated with the home improvement category is the automobile category.

Illustratively, the relevance probability threshold may be set based on requirements, history, and experimentation, among others.

It is worth noting that, in this embodiment, by determining the association relationship between categories based on the association probability, the reliability and accuracy of the determined association relationship can be improved, so that the association relationship is highly suitable for the user's search needs, thereby The technical effect of realizing the object in the information recommended for the user is the object that meets the user's search requirements, thereby improving the flexibility and reliability of the recommendation.

S702: Acquire a search task of the user, and determine a search target object according to the search task.

Exemplarily, for the description of S702, reference may be made to S101, which will not be repeated this time.

S703: Based on the mapping relationship, determine an association category that has an association relationship with the category to which it belongs.

It is worth noting that there is an association relationship between different categories, and by determining an association category whose category has an association relationship based on the mapping relationship, the technical effect of determining the efficiency of the association category can be improved.

S704: Acquire a secondary search record based on the search target object.

Among them, the secondary search record represents that after searching the search target object, the record of the object is continued to be searched.

Similarly, the secondary search records are search records within a preset time period, such as search records within a month, which may be specifically set based on requirements, historical records, and experiments, which are not limited in this embodiment.

S705: Based on the associated category, select objects belonging to the associated category from the secondary search records.

For example, if the search target object is "XX air conditioner", the category it belongs to is home improvement, and the associated category with the home improvement category is automobile, the secondary search records include "XX mattress", "XX tile", and "A car" ”, etc., the search recommendation device may determine “A car” as an object belonging to the associated category.

In some embodiments, the search recommendation apparatus may select objects belonging to the associated category from the secondary search records based on the visual chart as shown in FIG. 6 .

It is worth noting that, in this embodiment, by selecting objects belonging to the associated category from the secondary search records, it is possible to improve the accuracy and reliability of the recommended information when the recommendation information is generated based on the objects belonging to the associated category. It has the technical effect of making the recommended information highly fit to the user's search needs.

In some embodiments, S705 may include the following steps:

Step 1: From the secondary search records, select the object with the most searches belonging to the associated category.

Step 2: Determine the object with the most searches as the object belonging to the associated category.

Combining the above example, if the associated category is automobile, and the secondary search records include "A car", "B car", and "C car" belonging to the car category, the search recommendation device can determine "A car", "C car" The number of searches for "B car" and "C car", for example, "A car" is searched for a times, "B car" is searched for b times, and "C car" is searched for c times, and it is determined that a The largest of , b, and c is a, and the object that can be selected by the search recommendation device is "A car".

Correspondingly, when the search recommending device determines that the most frequently searched times belonging to the associated category are a, then "A car" may be determined as an object belonging to the associated category.

It is worth noting that, in this embodiment, by determining the object belonging to the association category with the most searches as the object belonging to the association category, the height between the object belonging to the association category and the search target object can be improved. Relevance, so that the generated recommendation information is highly related to the user's search needs, which improves the technical effect of the accuracy and reliability of the recommendation.

It is worth noting that the method for determining the object belonging to the associated category can also be: the object with the most purchases belongs to the associated category; it can also be the object with the most transaction volume belonging to the associated category; it can also be the object with the most evaluation. The preferred objects belonging to the association category, etc., are not limited in this embodiment.

S706: Generate and output recommendation information based on the search target object and the objects belonging to the associated category.

Combining the above examples, the search recommendation may generate output recommendation information based on the search target object "XX air conditioner" and the object "A car" belonging to the associated category.

It is worth noting that, in the related art, the recommendation information output by the search recommendation device only includes the search target object "XX air conditioner", or other air conditioners with similar functions (or similar appearances) to the search target object "XX air conditioner", while in In this embodiment, the recommendation information further includes the object "A car" belonging to the associated category, so that the limitation of recommendation in the related art can be avoided, and the flexibility and comprehensive technical effect of the recommendation can be improved.

FIG. 8 is a schematic diagram according to another embodiment of the present application. As shown in FIG. 8 , the search recommendation apparatus 800 in the embodiment of the present application may include:

The first obtaining module 801 is configured to obtain a user's search task, and determine a search target object according to the search task.

The first determining module 802 is configured to determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category.

The generating module 803 is configured to generate recommendation information according to the search target object and the association category; wherein the recommendation information includes: the search target object and objects belonging to the association category.

The output module 804 is configured to output the recommendation information.

In some embodiments, an association relationship exists between different categories; the first determining module 802 is configured to, based on a preset mapping relationship, determine an association category that has an association relationship with the category to which it belongs, wherein the The mapping relationship represents the association between categories.

FIG. 9 is a schematic diagram according to another embodiment of the present application. As shown in FIG. 9 , on the basis of the embodiment shown in FIG. 8 , the search recommendation apparatus in the embodiment of the present application may include:

The second obtaining module 805 is used for obtaining historical search records.

The second determining module 806 is configured to determine the co-occurrence frequencies of various categories based on the historical search records; wherein, the co-occurrence frequencies represent, in the historical search records, the frequency of occurrence of different categories in adjacent search records .

The first building module 807 is configured to build the mapping relationship based on the co-occurrence frequency.

In some embodiments, the first construction module 806 is configured to determine the correlation probability between the categories according to the co-occurrence frequency, and construct the mapping relationship according to the correlation probability; wherein, the The probability representation of the relevance, in the historical search record, after the first category is searched, the probability of continuing to search for the second category.

In some embodiments, different categories constitute a visual chart, and different categories in the visual chart have a first edge connection relationship, and the first edge connection relationship represents an association relationship; the first determination module 802 uses and determining, according to the visual graph, the association category that has a first edge connection relationship with the category to which it belongs.

FIG. 10 is a schematic diagram according to another embodiment of the present application. As shown in FIG. 10 , on the basis of the embodiment shown in FIG. 9 , the search recommendation apparatus in the embodiment of the present application may include:

The extraction module 808 is configured to perform object extraction processing on the text data of each category with respect to the text data of each category;

The second construction module 809 is configured to construct a visual chart including various categories based on the objects obtained by the object extraction process;

The third determining module 810 is configured to determine the co-occurrence frequency of each category based on the acquired historical search records, and determine the first edge connection relationship of each category according to the co-occurrence frequency; wherein, the co-occurrence frequency Frequency representation, in the historical search records, the frequency of occurrence of different categories in adjacent search records;

The updating module 811 is configured to update the visualization chart based on the first connection relationship of each category.

In some embodiments, different objects constitute a visual chart, and there are multiple different objects under categories in the visual chart, and a second edge connection relationship exists between the objects of the visual chart and the categories of the visual chart, The second edge connection relationship represents the belonging relationship between the object and the category; the first determining module 802 is configured to, according to the visual chart, determine the belonging relationship with the search target object that has a second edge connection relationship category.

In some embodiments, the generating module 803 is configured to, according to the visual chart, determine the objects that have a second edge connection relationship with the association category, and, according to the objects that have a second edge connection relationship with the association category , and the search target object to generate the recommendation information.

In some embodiments, the generating module 803 is configured to obtain a secondary search record based on the search target object; wherein, the secondary search record represents that after searching for the search target object, continue searching for an object and based on the association category, select objects belonging to the association category from the secondary search records, and generate the object based on the search target object and the objects belonging to the association category Recommended information.

In some embodiments, the generating module 803 is configured to, from the secondary search records, select the object with the most searches belonging to the associated category, and determine the object with the most searches as belonging to the associated category An object of the associated class.

According to an embodiment of the present application, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect above, for example, implements FIG. 2 , FIG. 3 , and The training method of the expression prediction model shown in any embodiment in FIG. 7

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

FIG. 11 is a schematic diagram according to still another embodiment of the present application. As shown in FIG. 11 , the electronic device 1100 includes a computing unit 1101 , which can be loaded according to a computer program stored in a read only memory (ROM) 1102 or from a storage unit 1108 into a computer program in random access memory (RAM) 1103 to perform various appropriate actions and processes. In the RAM 1103, various programs and data necessary for the operation of the device 1100 can also be stored. The computing unit 1101 , the ROM 1102 , and the RAM 1103 are connected to each other through a bus 1104 . An input/output (I/O) interface 1105 is also connected to the bus 1104 .

Various components in the device 1100 are connected to the I/O interface 1105, including: an input unit 1106, such as a keyboard, mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a magnetic disk, an optical disk, etc. ; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 1101 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 1101 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 executes the various methods and processes described above, such as a search recommendation method. For example, in some embodiments, the search recommendation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1108 . In some embodiments, part or all of the computer program may be loaded and/or installed on device 1100 via ROM 1102 and/or communication unit 1109 . When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the search recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the search recommendation method by any other suitable means (eg, by means of firmware).

Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Blockchain-based Service Networks (BSNs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the problems existing in traditional physical host and virtual private server (VPS, Virtual Private Server) services. The management is difficult and the business expansion is weak. The server can also be a distributed system server, or a server combined with a blockchain

According to another aspect of the embodiments of the present application, the embodiments of the present application further provide a smart device, including:

an exporter, at least one processor, and a memory communicatively coupled to the at least one processor; wherein the exporter is coupled to the at least one processor;

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform as described in any of the above embodiments the method described;

The outputter is used for outputting the recommendation information.

In some embodiments, the smart device further includes: a receiver;

The receiver is used for receiving a search request, and the search request is used for requesting to search for the search target object;

Alternatively, the receiver is used to receive a click request, and the click request is used to request to open an application.

In some embodiments, the receiver is any of the following: a microphone, a smart screen, and a user interface.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be performed in parallel, sequentially or in different orders, and as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (26)

1. A search recommendation method, comprising: Obtain the search task of the user, and determine the search target object according to the search task; Determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category; According to the search target object and the associated category, recommendation information is generated and output; wherein, the recommendation information includes: the search target object and objects belonging to the associated category. 2. The method according to claim 1, wherein an association relationship exists between different categories; determining an association category that has an association relationship with the belonging category, comprising: Based on a preset mapping relationship, an association category having an association relationship with the belonging category is determined, wherein the mapping relationship represents an association relationship between categories. 3. The method according to claim 2, before determining an association category having an association relationship with the belonging category based on a preset mapping relationship, the method further comprises: Obtain historical search records, determine co-occurrence frequencies of various categories based on the historical search records, and construct the mapping relationship based on the co-occurrence frequencies; wherein, the co-occurrence frequency representations, in the historical search records, are different How often the category appears in adjacent search records. 4. The method according to claim 3, wherein constructing the mapping relationship based on the co-occurrence frequency comprises: The correlation probability between the categories is determined according to the co-occurrence frequency, and the mapping relationship is constructed according to the correlation probability; wherein, the correlation probability represents, in the historical search record, the first After the category has been searched, continue searching for the probability of the second category. 5. The method according to claim 1, wherein different categories constitute a visual chart, and different categories in the visual chart have a first edge connection relationship, and the first edge connection relationship represents an association relationship; determining Associated categories that have an associated relationship with the category to which they belong, including: According to the visual chart, determine the association category that has a first edge connection relationship with the category to which it belongs. 6. The method according to claim 5, before determining, according to the visual chart, the association category that has a first edge connection relationship with the category to which it belongs, the method further comprises: For each category of text data, perform object extraction processing on each category of text data, and construct visual charts including various categories based on the objects obtained by the object extraction processing; Based on the acquired historical search records, the co-occurrence frequency of each category is determined, the first edge connection relationship of each category is determined according to the co-occurrence frequency, and the first edge connection relationship of each category is updated based on the A visualization chart; wherein the co-occurrence frequency represents, in the historical search records, the frequency of occurrence of different categories in adjacent search records. 7. The method according to any one of claims 1 to 6, wherein different objects constitute a visual chart, and there are multiple different objects under categories in the visual chart, and the objects of the visual chart are the same as the ones in the visual chart. The categories of the visual chart have a second edge connection relationship, and the second edge connection relationship represents the belonging relationship between the object and the category; determining the category to which the search target object belongs, including: According to the visual graph, the category to which the search target object has a second edge connection relationship is determined. 8. The method according to claim 7, wherein generating and outputting recommendation information according to the search target object and the associated category, comprising: According to the visual graph, determine the object that has a second edge connection relationship with the association category; The recommendation information is generated and output according to the object that has a second edge connection relationship with the association category and the search target object. 9. The method according to any one of claims 1 to 6, wherein, according to the search target object and the association category, generating and outputting recommendation information, comprising: Acquiring a secondary search record based on the search target object; wherein, the secondary search record represents that after the search target object is searched, the record of the object is continued to be searched; Selecting objects belonging to the associated category from the secondary search records based on the associated category, and generating and outputting the recommendation information based on the search target object and the objects belonging to the associated category . 10. The method of claim 9, wherein, based on the association category, selecting objects belonging to the association category from the secondary search records comprises: From the secondary search records, the object with the most searches belonging to the associated category is selected, and the object with the most searches is determined as the object belonging to the associated category. 11. A search recommendation device, comprising: The first acquisition module is used to acquire the search task of the user, and determine the search target object according to the search task; a first determining module, configured to determine the category to which the search target object belongs, and determine the associated category that has an associated relationship with the category; a generating module, configured to generate recommendation information according to the search target object and the association category; wherein the recommendation information includes: the search target object and objects belonging to the association category; An output module, configured to output the recommended information. 12 . The apparatus according to claim 11 , wherein an association relationship exists between different categories; the first determining module is configured to, based on a preset mapping relationship, determine an association that has an association relationship with the category to which it belongs. 13 . categories, wherein the mapping relationship represents an association relationship between categories. 13. The apparatus of claim 12, further comprising: The second acquisition module is used to acquire historical search records; The second determining module is configured to determine the co-occurrence frequencies of various categories based on the historical search records; wherein, the co-occurrence frequencies represent the frequencies of occurrences of different categories in adjacent search records in the historical search records; The first building module is configured to build the mapping relationship based on the co-occurrence frequency. 14. The apparatus according to claim 13, wherein the first building module is configured to determine the correlation probability between the categories according to the co-occurrence frequency, and construct the correlation probability according to the correlation probability A mapping relationship; wherein the correlation probability represents, in the historical search record, the probability of continuing to search for the second category after the first category is searched. 15. The apparatus according to claim 11, wherein different categories constitute a visual chart, and different categories in the visual chart have a first edge connection relationship, and the first edge connection relationship represents an association relationship; the The first determining module is configured to, according to the visual chart, determine the association category that has a first edge connection relationship with the category to which it belongs. 16. The apparatus of claim 15, further comprising: The extraction module is used to perform object extraction processing on the text data of each category according to the text data of each category; The second building module is used to construct a visual chart including various categories based on the object obtained by the object extraction process; The third determining module is configured to determine the co-occurrence frequency of each category based on the acquired historical search records, and determine the first edge connection relationship of each category according to the co-occurrence frequency; wherein the co-occurrence frequency Characterization, in the historical search records, the frequency of different categories appearing in adjacent search records; An update module, configured to update the visualization chart based on the first connection relationship of each category. 17. The device according to any one of claims 11 to 16, wherein different objects constitute a visual chart, and there are multiple different objects under categories in the visual chart, and the objects of the visual chart are the same as those of the visual chart. The categories of the visual chart have a second edge connection relationship, and the second edge connection relationship represents the belonging relationship between the object and the category; the first determination module is used for, according to the visual chart, determine and the search The target object has the category of the second edge connection relationship. 18. The apparatus according to claim 17, wherein the generating module is configured to, according to the visual graph, determine an object that has a second edge connection relationship with the association category, and according to the object that has a first edge connection with the association category The object of the two-sided connection relationship and the search target object generate the recommendation information. 19. The apparatus according to any one of claims 11 to 16, wherein the generating module is used to obtain a secondary search record based on the search target object; wherein, the secondary search record is characterized in After searching for the search target object, continue to search the records of the object, and based on the associated category, select objects belonging to the associated category from the secondary search records, and based on the search target object and the The recommendation information is generated for the objects belonging to the association category. 20. The apparatus according to claim 19, wherein the generating module is configured to, from the secondary search records, select the object with the most searches belonging to the associated category, and select the object with the most searches Objects identified as belonging to the association class. 21. An electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-10 Methods. 22. A smart device comprising: an exporter, at least one processor, and a memory communicatively coupled to the at least one processor; wherein the exporter is coupled to the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-10 Methods; The outputter is used for outputting the recommendation information. 23. The smart device of claim 22, further comprising: a receiver; The receiver is used for receiving a search request, and the search request is used for requesting to search for the search target object; Alternatively, the receiver is used to receive a click request, and the click request is used to request to open an application. 24. The smart device of claim 23, wherein the receiver is any one of the following: a microphone, a smart screen, and a user interface. 25. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any of claims 1-10. 26. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-10.

Images