CN112328873A

CN112328873A - Information recommendation method, device, equipment and storage medium

Info

Publication number: CN112328873A
Application number: CN202011175330.6A
Authority: CN
Inventors: 耿贵宁; 唐会芳
Original assignee: Suzhou 360 Intelligent Security Technology Co Ltd
Current assignee: Suzhou 360 Intelligent Security Technology Co Ltd
Priority date: 2020-10-28
Filing date: 2020-10-28
Publication date: 2021-02-05

Abstract

The invention belongs to the technical field of data processing, and discloses an information recommendation method, an information recommendation device, information recommendation equipment and a storage medium, wherein the method determines service demand information according to an information query request of a user; determining a service object to be selected according to the service demand information, and searching service data corresponding to the service object to be selected; analyzing the service data to obtain a service analysis result of the service object to be selected; and determining a target recommendation object from the service objects to be selected according to the service analysis result, and displaying the target recommendation object. In the invention, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

Description

Information recommendation method, device, equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to an information recommendation method, apparatus, device, and storage medium.

Background

Data classification is a key part in data protection work, is an important basis of data hierarchical management, and is a premise for realizing centralized, specialized, standardized and safe data management. The data generated, collected, processed, used or managed is classified according to a standard data classification method, so that the data assets can be clearly clarified comprehensively, the standardized management of the data assets is realized, and the maintenance and the expansion of the data are facilitated. Due to the fact that various industries relate to various aspects of production and life, the business is complex and wide, the data volume is large, the data classification is difficult, the data classification efficiency is low, the difficulty is large, the labor investment is large, the cost is high, and the classification limitation is realized. At present, when service inquiry is carried out, the problem that the inquiry result is inaccurate due to the limitation of data classification exists, and meanwhile, the problem that the actual operation service is inconsistent with the inquiry result due to too large service classification range exists, so that the use experience of a user is greatly influenced.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide an information recommendation method, device, equipment and storage medium, and aims to solve the technical problems that the existing service query result is inaccurate and the actual operation service does not accord with the query result.

In order to achieve the above object, the present invention provides an information recommendation method, including the steps of:

when receiving an information query request of a user, determining service demand information according to the information query request;

determining a service object to be selected according to the service demand information, and searching service data corresponding to the service object to be selected;

analyzing the service data to obtain a service analysis result of the service object to be selected;

and determining a target recommendation object from the service objects to be selected according to the service analysis result, and displaying the target recommendation object.

Optionally, the step of determining a service object to be selected according to the service requirement information, and searching for service data corresponding to the service object to be selected includes:

determining a target recommendation strategy matched with the service demand information through a preset service configuration recommendation strategy;

determining a to-be-selected business object which has a correlation with the business demand information through the target recommendation strategy;

and searching the business data corresponding to the business object to be selected.

Optionally, the step of determining, by the target recommendation policy, a candidate service object having a correlation with the service demand information includes:

determining a recommended service object which has a correlation with the service demand information through the target recommendation strategy;

determining a recommendation sequence of the recommended service objects based on a historical recommendation result;

and determining the service objects to be selected from the recommended service objects according to the recommendation sequence.

Optionally, the step of searching for the service data corresponding to the service object to be selected includes:

crawling network data related to the business object to be selected;

obtaining target advertisement service data, target recruitment service data and target order service data from the network data;

and generating service data according to the target advertisement service data, the target recruitment service data and the target order service data.

Optionally, the step of obtaining target advertisement service data, target recruitment service data, and target order service data from the network data includes:

determining a target traffic volume according to the network data, and judging whether the target traffic volume reaches a preset traffic volume;

and when the target traffic reaches the preset traffic, searching corresponding target advertisement service data, target recruitment service data and target order service data in a first preset service data table through a precise searching mode.

Optionally, after the step of determining a target traffic volume according to the network data and determining whether the target traffic volume reaches a preset traffic volume, the method further includes:

and when the target traffic does not reach the preset traffic, searching corresponding target advertisement service data, target recruitment service data and target order service data in a second preset service data table through a sequential searching mode.

Optionally, before the step of obtaining the target advertisement service data, the target recruitment service data, and the target order service data from the network data, the method further includes:

determining a service keyword of the service object to be selected according to the network data, and formulating a service matching rule according to the service keyword;

obtaining log information matched with the service matching rule from historical network data, and determining a service object corresponding to the log information, network behavior time corresponding to the log information and service content corresponding to the log information according to the log information;

and constructing a first preset service data table and a second preset service data table according to the service object corresponding to the log information, the network behavior time and the service content.

Optionally, the step of analyzing the service data to obtain a service analysis result of the service object to be selected includes:

obtaining a characteristic weight value corresponding to the service data through a first preset model according to the service data;

obtaining a characteristic weight value corresponding to target characteristic information through a second preset model according to the characteristic weight value corresponding to the service data;

and obtaining a service analysis result of the service object to be selected through a third preset model according to a preset service recommendation threshold range and a characteristic weight value corresponding to the target characteristic information.

Optionally, the step of determining the service requirement information according to the information query request includes:

determining a corresponding keyword group and keyword information according to the information query request, wherein the keyword group comprises a plurality of keywords;

judging whether a keyword consistent with the keyword information exists in the keyword group according to preset keyword information;

if the keyword group has a keyword consistent with the keyword information, obtaining request address information of the information query request;

and calling a service interface corresponding to the request address information to obtain target return data, and determining service requirement information according to the target return data.

extracting a target keyword of the information query request;

matching a keyword set through a preset keyword set according to the target keywords;

and determining service demand information according to a response set corresponding to the keyword set.

Optionally, before the step of determining the service requirement information according to the response set corresponding to the keyword set, the method further includes:

judging whether the keyword set is a plurality of keyword sets;

and when the keyword set is not a plurality of keyword sets, executing the step of determining the service demand information according to the response set corresponding to the keyword set.

Optionally, after the step of determining whether the keyword set is a plurality of keyword sets, the method further includes:

when the keyword set is a plurality of keyword sets, determining a primary keyword set according to the weight of the keyword set;

determining a secondary keyword set according to the relevancy of a plurality of keyword sets and the primary keyword set;

and determining service demand information according to the response sets corresponding to the primary keyword set and the secondary keyword set.

In addition, to achieve the above object, the present invention also provides an information recommendation apparatus, including:

the determining module is used for determining service demand information according to an information query request when the information query request of a user is received;

the searching module is used for determining a service object to be selected according to the service demand information and searching service data corresponding to the service object to be selected;

the analysis module is used for analyzing the business data to obtain a business analysis result of the business object to be selected;

and the display module is used for determining a target recommendation object from the service objects to be selected according to the service analysis result and displaying the target recommendation object.

Optionally, the search module is further configured to determine a target recommendation policy matched with the service demand information through a preset service configuration recommendation policy;

the searching module is further used for determining a to-be-selected business object which has a correlation with the business requirement information through the target recommendation strategy;

the searching module is further configured to search for the service data corresponding to the service object to be selected.

Optionally, the search module is further configured to determine, through the target recommendation policy, a recommended service object having a correlation with the service demand information;

the searching module is further used for determining the recommending sequence of the recommended service object based on the historical recommending result;

the searching module is further configured to determine a service object to be selected from the recommended service objects according to the recommendation sequence.

Optionally, the searching module is further configured to crawl network data related to the to-be-selected business object;

the searching module is further used for obtaining target advertisement service data, target recruitment service data and target order service data from the network data;

the searching module is further configured to generate service data according to the target advertisement service data, the target recruitment service data, and the target order service data.

Optionally, the searching module is further configured to determine a target traffic volume according to the network data, and determine whether the target traffic volume reaches a preset traffic volume;

the searching module is further configured to search corresponding target advertisement service data, target recruitment service data and target order service data in a first preset service data table through a precise searching mode when the target service volume reaches the preset service volume.

Optionally, the searching module is further configured to search, in the second preset service data table, corresponding target advertisement service data, target recruitment service data, and target order service data through a sequential search mode when the target service volume does not reach the preset service volume.

In addition, to achieve the above object, the present invention also provides an information recommendation apparatus, including: the information recommendation system comprises a memory, a processor and an information recommendation program stored on the memory and capable of running on the processor, wherein the information recommendation program is configured with the steps of realizing the information recommendation method.

Furthermore, to achieve the above object, the present invention also provides a storage medium having an information recommendation program stored thereon, which when executed by a processor implements the steps of the information recommendation method as described above.

When receiving an information query request of a user, determining service demand information according to the information query request; determining a service object to be selected according to the service demand information, and searching service data corresponding to the service object to be selected; analyzing the service data to obtain a service analysis result of the service object to be selected; and determining a target recommendation object from the service objects to be selected according to the service analysis result, and displaying the target recommendation object. In the invention, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

Drawings

Fig. 1 is a schematic structural diagram of an information recommendation device of a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating a first embodiment of an information recommendation method according to the present invention;

FIG. 3 is a flowchart illustrating a second embodiment of an information recommendation method according to the present invention;

FIG. 4 is a diagram illustrating a default service classification table according to an embodiment of the present invention;

FIG. 5 is a flowchart illustrating a third embodiment of an information recommendation method according to the present invention;

fig. 6 is a block diagram of an information recommendation apparatus according to a first embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of an information recommendation device of a hardware operating environment according to an embodiment of the present invention.

As shown in fig. 1, the information recommendation apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.

Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the information recommendation device and may include more or less components than those shown, or some components in combination, or a different arrangement of components.

As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an information recommendation program.

In the information recommendation apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the information recommendation device of the present invention may be provided in the information recommendation device, which calls the information recommendation program stored in the memory 1005 through the processor 1001 and executes the information recommendation method provided by the embodiment of the present invention.

An embodiment of the present invention provides an information recommendation method, and referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of an information recommendation method according to the present invention.

In this embodiment, the information recommendation method includes the following steps:

step S10: when receiving an information query request of a user, determining service demand information according to the information query request.

It should be noted that the execution subject of this embodiment is the information recommendation device, and the information recommendation device may be an electronic device such as a personal computer or a server, which is not limited in this embodiment. When an information query request of a user is received, service requirement information is determined according to the information query request, and the manner of determining the service requirement information may be implemented in various manners, which is described below by taking a natural language processing manner as an example, and of course, may also be implemented in other manners, which is not limited in this embodiment.

Specifically, the process of determining the service requirement information according to the information query request may be: determining a corresponding keyword group and keyword information according to the information query request, wherein the keyword group comprises a plurality of keywords; judging whether a keyword consistent with the keyword information exists in the keyword group according to preset keyword information; if the keyword group has a keyword consistent with the keyword information, obtaining request address information of the information query request; and calling a service interface corresponding to the request address information to obtain target return data, and determining service requirement information according to the target return data. In this embodiment, a preset keyword database may be stored in the server, where the preset keyword database includes a plurality of preset keywords, and the information query request is subjected to keyword recognition through the preset keywords, that is, keywords corresponding to the preset keywords in the information query request are obtained, and keywords included in the information query request are obtained, so as to obtain a keyword group. If the keyword group has the keyword consistent with the keyword information, acquiring request address information corresponding to the information query request, so as to call a corresponding service interface according to the request address information, acquire corresponding data information, namely target return data, and determine service requirement information according to the target return data.

It is easy to understand that, the process of determining the service requirement information according to the information query request may further be: extracting a target keyword of the information query request; matching a keyword set through a preset keyword set according to the target keywords; and determining service demand information according to a response set corresponding to the keyword set. In the information query, the user terminal may send an information query request to the server, where the information query request generally includes at least one keyword describing a request target, and the server extracts the target keyword in the information query request after receiving the information query request.

It should be understood that there may be a plurality of matched keyword sets, and at this time, before determining the service demand information according to the response set corresponding to the keyword set, it is necessary to determine whether the keyword set is a plurality of keyword sets; when the keyword set is not a plurality of keyword sets, determining service demand information according to a response set corresponding to the keyword set; when the keyword set is a plurality of keyword sets, determining a main-level keyword set according to the weight of the keyword set; determining a secondary keyword set according to the relevancy of the plurality of keyword sets and the primary keyword set; and determining the service demand information according to the response sets corresponding to the primary keyword set and the secondary keyword set. In this embodiment, in the keyword sets, each keyword set is provided with a weight, the weight is used to describe the frequency of the keyword set being retrieved, the weight of the keyword set is defined by establishing an associated keyword set, a service requirement information feedback result is output according to the weight and the association degree in the information query request process, associated feedback is output as much as possible in a single information query request, the number of requests in the information query request and feedback processes is reduced, the efficiency of information query feedback is improved, and the user experience is enhanced.

Step S20: and determining a service object to be selected according to the service demand information, and searching service data corresponding to the service object to be selected.

It should be noted that, the process of determining the service object to be selected according to the service requirement information may be: determining a target recommendation strategy matched with the service demand information through a preset service configuration recommendation strategy; and determining the business object to be selected which has a correlation with the business demand information through the target recommendation strategy.

Specifically, a target recommendation strategy matched with the service requirement information of the user is selected from recommendation strategies configured for the service requirements in advance, namely preset service configuration recommendation strategies; the target recommendation strategy comprises various recommendation services which have binding relation with the service demand information, namely determining a to-be-selected service object which has a correlation relation with the service demand information; and determining the recommendation sequence of each recommended service, wherein the recommendation sequence of each service can be determined according to the historical recommendation result of each recommended service. Obtaining the historical recommendation result of each recommendation service, and determining the recommendation success rate of each recommendation service according to the historical recommendation result of each recommendation service; and determining the recommendation sequence of each recommended service according to the recommendation success rate of each recommended service, namely displaying the service objects to be selected to the user according to the recommendation sequence.

It should be noted that there may be a candidate service object with an expanded operation range in the candidate service objects, the actual operation service does not match the query result, and in order to avoid the actual operation service not matching the query result and further improve the query accuracy, in this embodiment, the service data corresponding to the candidate service object is searched to further analyze the actual operation service, determine a target recommendation object for the user, and display the target recommendation object.

It is easy to understand that the process of searching the service data corresponding to the service object to be selected may be: crawling network data related to the business object to be selected; obtaining target advertisement service data, target recruitment service data and target order service data from the network data; and generating service data according to the target advertisement service data, the target recruitment service data and the target order service data. In the embodiment, the actual advertisement service data, the recruitment service data and the order service data related to the to-be-selected service object can be obtained through network crawling, so that the actual operation service of the to-be-selected service object can be further analyzed conveniently. Other business information related to the business object to be selected can be obtained through network crawling, which is not limited in this embodiment.

Step S30: and analyzing the service data to obtain a service analysis result of the service object to be selected.

It is easy to understand that, according to the service data, a characteristic weight value corresponding to the service data is obtained through a first preset model; obtaining a characteristic weight value corresponding to target characteristic information through a second preset model according to the characteristic weight value corresponding to the service data; and obtaining a service analysis result of the service object to be selected through a third preset model according to a preset service recommendation threshold range and a characteristic weight value corresponding to the target characteristic information. The service data of the service object to be selected may also be analyzed in other manners, which is not limited in this embodiment.

Specifically, the first preset model may include a logistic regression model and a maximum entropy model, and the maximum entropy model calculates a feature weight value corresponding to each service feature information in each group of service data according to the logistic regression function. The second preset model may comprise a support vector machine model; and predicting the characteristic weight value corresponding to the target characteristic information through a support vector machine model according to the characteristic weight value corresponding to each service characteristic information. The third preset model may comprise a logistic regression model; substituting the characteristic weight value corresponding to the target characteristic information into the logistic regression model, predicting recommended target characteristic information according to a preset service recommendation threshold range, and taking the recommended target characteristic information as a service analysis result of the service object to be selected.

Step S40: and determining a target recommendation object from the service objects to be selected according to the service analysis result, and displaying the target recommendation object.

It is easy to understand that the recommended target feature information of each service object to be selected is obtained according to the service analysis result, a target recommended object is determined from the service objects to be selected according to the recommended target feature information, and the target recommended object is displayed. Meanwhile, the selected service object meeting the range of the recommended target characteristic information can be used as a target recommended object, and the target recommended object is the target object meeting the service requirements of the user, so that the information query request of the user can be accurately responded according to the target recommended object, and the user experience is improved.

The embodiment determines the service demand information according to the information query request when receiving the information query request of a user; determining a service object to be selected according to the service demand information, and searching service data corresponding to the service object to be selected; analyzing the service data to obtain a service analysis result of the service object to be selected; and determining a target recommendation object from the service objects to be selected according to the service analysis result, and displaying the target recommendation object. In the embodiment, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

Referring to fig. 3, fig. 3 is a flowchart illustrating an information recommendation method according to a second embodiment of the present invention. Based on the first embodiment, in step S20, the information recommendation method in this embodiment specifically includes:

step S201: and determining a target recommendation strategy matched with the service demand information through a preset service configuration recommendation strategy.

It should be noted that, in this embodiment, a target recommendation policy matched with the service demand information may be determined by presetting a service configuration recommendation policy; and determining the business object to be selected which has a correlation with the business demand information through the target recommendation strategy. The embodiment may also directly determine the candidate service object through the preset service classification table.

Specifically, a target recommendation strategy matched with the service requirement information of the user is selected from recommendation strategies configured for the service requirements in advance, namely preset service configuration recommendation strategies; the target recommendation strategy comprises various recommendation services which have binding relation with the service demand information, namely determining a to-be-selected service object which has a correlation relation with the service demand information; and determining the recommendation sequence of each recommended service, namely displaying the service objects to be selected to the user according to the recommendation sequence.

Specifically, the preset service classification table is directly determined that the service object to be selected needs to be established first, and the process of establishing the preset service classification table may be as follows: determining a service management subject according to a service line of a target vertical industry, and determining a service management range according to the service management subject; constructing a service mapping relation according to the service management main body and the service management range; determining a service management object according to the service mapping relation, and determining corresponding service data according to the service management object; classifying the service data according to a preset data classification mode to obtain a data first-class subclass; classifying the primary data subclasses according to a preset data classification mode to obtain secondary data subclasses; and constructing a preset service classification table of the target vertical industry according to the service line, the service management main body, the service management range, the first-level subclass of data and the second-level subclass of data.

Referring to fig. 4, fig. 4 is a schematic diagram of a preset service classification table according to an embodiment of the present invention; in this embodiment, tax is taken as an example for explanation, a tax service line is taken as a service primary subclass to be subdivided, a service secondary subclass is determined, and the name is: determining a primary subclass of a service, namely a basic service line, and determining all service management bodies under each service line; determining a management range corresponding to each business management main body, and determining a corresponding relation; naming mapping relationships are business level subclasses. Namely, the mapping relation between various service management bodies and the management range is named to obtain the name of the service secondary subclass. And defining the management range of each service level subclass. And determining a management object corresponding to the management range of the business second-class subclass, namely finding all data under the business second-class subclass. Subdividing each 'single-class service data sum' according to a preset data classification mode to obtain a data first-class subclass; the clearly divided primary subclasses of the data are further subdivided according to a preset data classification mode, and one or more secondary subsets of the data are generated after subdivision, wherein the preset data classification mode can comprise: and constructing a preset business classification table of the target vertical industry according to the business line, the business management main body, the business management range, the first-level subclass of data and the second-level subclass of data according to the data property, the importance degree, the management requirement and the use requirement. The preset business classification table further comprises company A, company B, company C, company D and the like which correspondingly process the business, so that the business object to be selected can be determined to be one or more of company A, company B, company C and company D through the preset business classification table.

Step S202: and determining the business object to be selected which has a correlation with the business demand information through the target recommendation strategy.

It is easy to understand that, a recommended service object which has a correlation with the service requirement information is determined through the target recommendation strategy; determining a recommendation sequence of the recommended service objects based on a historical recommendation result; and determining the service objects to be selected from the recommended service objects according to the recommendation sequence. The target recommendation strategy comprises various recommendation services which have binding relation with the service demand information, namely determining a to-be-selected service object which has a correlation relation with the service demand information; and determining the recommendation sequence of each recommended service, wherein the recommendation sequence of each service can be determined according to the historical recommendation result of each recommended service. Obtaining the historical recommendation result of each recommendation service, and determining the recommendation success rate of each recommendation service according to the historical recommendation result of each recommendation service; and determining the recommendation sequence of each recommended service according to the recommendation success rate of each recommended service, namely displaying the service objects to be selected to the user according to the recommendation sequence.

Step S203: and searching the business data corresponding to the business object to be selected.

It should be understood that the process of obtaining the targeted advertising service data, the targeted recruitment service data, and the targeted order service data from the network data may be: determining a target traffic volume according to the network data, and judging whether the target traffic volume reaches a preset traffic volume; when the target traffic volume reaches the preset traffic volume, searching corresponding target advertisement service data, target recruitment service data and target order service data in a first preset service data table through a precise searching mode; and when the target traffic does not reach the preset traffic, searching corresponding target advertisement service data, target recruitment service data and target order service data in a second preset service data table through a sequential searching mode. In this embodiment, the first preset service data table may be an HBase data table, the second preset service data table may be a MYSQL data table, when the traffic volume is small, the MYSQL database is used for query and matching, the query and matching efficiency is within an acceptable range, and the data is easier to modify. When the traffic is large, the HBase database is adopted for inquiring and matching, and efficient information inquiry and matching can be realized.

It is easy to understand that before obtaining the target advertisement service data, the target recruitment service data and the target order service data from the network data, the following steps may be further performed: determining a service keyword of the service object to be selected according to the network data, and formulating a service matching rule according to the service keyword; obtaining log information matched with the service matching rule from historical network data, and determining a service object corresponding to the log information, network behavior time corresponding to the log information and service content corresponding to the log information according to the log information; and constructing a first preset service data table and a second preset service data table according to the service object corresponding to the log information, the network behavior time and the service content. In this embodiment, the first preset service data table may be an HBase data table, and the second preset service data table may be an MYSQL data table, where the HBase data table has disadvantages in deleting and modifying data, and the MYSQL data table has disadvantages in query matching efficiency of information when the traffic is large, so that the effect is not ideal when any data table is used singly. The embodiment combines the advantages of the two databases to obtain the service data corresponding to the service object to be selected.

The embodiment determines a target recommendation strategy matched with the service demand information through a preset service configuration recommendation strategy; determining a to-be-selected business object which has a correlation with the business demand information through the target recommendation strategy; and searching the business data corresponding to the business object to be selected. In the embodiment, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

Referring to fig. 5, fig. 5 is a flowchart illustrating an information recommendation method according to a third embodiment of the present invention. Based on the first embodiment, in step S30, the information recommendation method in this embodiment specifically includes:

step S301: and obtaining a characteristic weight value corresponding to the service data through a first preset model according to the service data.

It is easy to understand that, according to the service data, a characteristic weight value corresponding to the service data is obtained through a first preset model; the first preset model may include a logistic regression model and a maximum entropy model, and the characteristic weight value corresponding to each service characteristic information in each group of service data is calculated through the maximum entropy model according to the logistic regression function.

Specifically, a set quantity group of service data is taken as a training sample, the set quantity group of service data is substituted into the logistic regression model to obtain a logistic regression function of the set quantity group of service data, and a characteristic weight value corresponding to the service data is obtained through the maximum entropy model according to the logistic regression function.

Step S302: and obtaining a characteristic weight value corresponding to the target characteristic information through a second preset model according to the characteristic weight value corresponding to the service data.

It should be noted that, a feature weight value corresponding to the target feature information is obtained through a second preset model according to the feature weight value corresponding to the service data; wherein the second preset model may comprise a support vector machine model; and predicting the characteristic weight value corresponding to the target characteristic information through a support vector machine model according to the characteristic weight value corresponding to each service characteristic information.

Specifically, m-3 sets of feature weight values can be selected from m sets of feature weight values to serve as training data of the support vector machine model, a plurality of support vector machine models trained on the basis of a plurality of kernel functions are constructed, the most appropriate support vector machine model is selected to conduct feature weight value parameter optimization on the m-3 sets of feature weight values, and training is conducted after the feature weight value parameters are optimized so as to predict the feature weight value corresponding to the target feature information.

Step S303: and obtaining a service analysis result of the service object to be selected through a third preset model according to a preset service recommendation threshold range and a characteristic weight value corresponding to the target characteristic information.

It should be understood that a service analysis result of the service object to be selected is obtained through a third preset model according to a preset service recommendation threshold range and a characteristic weight value corresponding to the target characteristic information; wherein the third predetermined model may include a logistic regression model; substituting the characteristic weight value corresponding to the target characteristic information into the logistic regression model, predicting recommended target characteristic information according to a preset service recommendation threshold range, taking the recommended target characteristic information as a service analysis result of the service object to be selected, and simultaneously taking the service object to be selected meeting the range of the recommended target characteristic information as a target recommendation object.

It is easy to understand that the business data of the selected business object may also be analyzed in other ways, which is not limited in this embodiment. And obtaining recommendation target characteristic information of each service object to be selected according to the service analysis result, determining a target recommendation object from the service objects to be selected according to the recommendation target characteristic information, and displaying the target recommendation object. Meanwhile, the selected service object meeting the range of the recommended target characteristic information can be used as a target recommended object, and the target recommended object is the target object meeting the service requirements of the user, so that the information query request of the user can be accurately responded according to the target recommended object, and the user experience is improved.

According to the embodiment, a characteristic weight value corresponding to the service data is obtained through a first preset model according to the service data; obtaining a characteristic weight value corresponding to target characteristic information through a second preset model according to the characteristic weight value corresponding to the service data; and obtaining a service analysis result of the service object to be selected through a third preset model according to a preset service recommendation threshold range and a characteristic weight value corresponding to the target characteristic information. In the embodiment, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

In addition, an embodiment of the present invention further provides a storage medium, where an information recommendation program is stored on the storage medium, and the information recommendation program is executed by a processor to perform the steps of the information recommendation method described above.

Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.

Referring to fig. 6, fig. 6 is a block diagram illustrating a first embodiment of an information recommendation device according to the present invention.

As shown in fig. 6, the information recommendation apparatus according to the embodiment of the present invention includes:

the determining module 10 is configured to determine service requirement information according to an information query request when the information query request of a user is received.

It should be noted that, when an information query request of a user is received, service requirement information is determined according to the information query request, and the manner of determining the service requirement information may be implemented in various manners, which is described below by taking a natural language processing manner as an example, and of course, may also be implemented in other manners, which is not limited in this embodiment.

And the searching module 20 is configured to determine a service object to be selected according to the service demand information, and search service data corresponding to the service object to be selected.

And the analysis module 30 is configured to analyze the service data to obtain a service analysis result of the service object to be selected.

And the display module 40 is configured to determine a target recommended object from the to-be-selected service objects according to the service analysis result, and display the target recommended object.

The information recommendation device of the embodiment includes: the determining module 10 is configured to determine service requirement information according to an information query request when the information query request of a user is received; the searching module 20 is configured to determine a service object to be selected according to the service demand information, and search service data corresponding to the service object to be selected; the analysis module 30 is configured to analyze the service data to obtain a service analysis result of the service object to be selected; and the display module 40 is configured to determine a target recommended object from the to-be-selected service objects according to the service analysis result, and display the target recommended object. In the embodiment, on the basis of determining the service object to be selected according to the service demand information, the actual service range is further analyzed through the service data of the service object to be selected, so that the final target recommendation object is determined, the inconsistency between the actual operation service and the query result is avoided, the query accuracy is further improved, and the technical problems that the existing service query result is inaccurate and the actual operation service and the query result are inconsistent are solved.

In an embodiment, the search module 20 is further configured to determine a target recommendation policy matched with the service demand information through a preset service configuration recommendation policy;

the searching module 20 is further configured to determine, through the target recommendation policy, a to-be-selected service object having a correlation with the service demand information;

the searching module 20 is further configured to search the service data corresponding to the service object to be selected.

In an embodiment, the search module 20 is further configured to determine, through the target recommendation policy, a recommended service object having a correlation with the service demand information;

the searching module 20 is further configured to determine a recommendation sequence of the recommended service object based on a historical recommendation result;

the searching module 20 is further configured to determine a service object to be selected from the recommended service objects according to the recommendation sequence.

In an embodiment, the search module 20 is further configured to crawl network data related to the to-be-selected business object;

the searching module 20 is further configured to obtain target advertisement service data, target recruitment service data, and target order service data from the network data;

the searching module 20 is further configured to generate service data according to the target advertisement service data, the target recruitment service data, and the target order service data.

In an embodiment, the searching module 20 is further configured to determine a target traffic volume according to the network data, and determine whether the target traffic volume reaches a preset traffic volume;

the searching module 20 is further configured to search, in a precise searching mode, corresponding target advertisement service data, target recruitment service data, and target order service data in a first preset service data table when the target service volume reaches the preset service volume.

In an embodiment, the searching module 20 is further configured to search, in a sequential search mode, corresponding target advertisement service data, target recruitment service data, and target order service data in a second preset service data table when the target service volume does not reach the preset service volume.

In an embodiment, the search module 20 is further configured to determine a service keyword of the service object to be selected according to the network data, and formulate a service matching rule according to the service keyword;

the searching module 20 is further configured to obtain log information matched with the service matching rule from historical network data, and determine a service object corresponding to the log information, network behavior time corresponding to the log information, and service content corresponding to the log information according to the log information;

the search module 20 is further configured to construct a first preset service data table and a second preset service data table according to the service object corresponding to the log information, the network behavior time, and the service content.

In an embodiment, the analysis module 30 is further configured to obtain a characteristic weight value corresponding to the service data through a first preset model according to the service data;

the analysis module 30 is further configured to obtain a feature weight value corresponding to the target feature information through a second preset model according to the feature weight value corresponding to the service data;

the analysis module 30 is further configured to obtain a service analysis result of the service object to be selected through a third preset model according to a preset service recommendation threshold range and a feature weight value corresponding to the target feature information.

In an embodiment, the determining module 10 is further configured to determine a corresponding keyword group and keyword information according to the information query request, where the keyword group includes a plurality of keywords;

the determining module 10 is further configured to determine whether a keyword consistent with the keyword information exists in the keyword group according to preset keyword information;

the determining module 10 is further configured to obtain request address information of the information query request if a keyword consistent with the keyword information exists in the keyword group;

the determining module 10 is further configured to call a service interface corresponding to the request address information to obtain target return data, and determine service requirement information according to the target return data.

In an embodiment, the determining module 10 is further configured to extract a target keyword of the information query request;

the determining module 10 is further configured to match a keyword set through a preset keyword set according to the target keyword;

the determining module 10 is further configured to determine service requirement information according to the response set corresponding to the keyword set.

In an embodiment, the determining module 10 is further configured to determine whether the keyword set is a plurality of keyword sets;

the determining module 10 is further configured to, when the keyword set is not a plurality of keyword sets, execute a step of determining service requirement information according to a response set corresponding to the keyword set.

In an embodiment, the determining module 10 is further configured to determine a primary keyword set according to weights of the keyword sets when the keyword sets are several keyword sets;

the determining module 10 is further configured to determine a secondary keyword set according to the relevancy between the plurality of keyword sets and the primary keyword set;

the determining module 10 is further configured to determine service demand information according to the response sets corresponding to the primary keyword set and the secondary keyword set.

Other embodiments or specific implementation manners of the information recommendation device of the present invention may refer to the above-mentioned embodiments of the information recommendation method, and are not described herein again.

It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.

It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.

In addition, the technical details that are not described in detail in this embodiment may refer to the information recommendation method provided in any embodiment of the present invention, and are not described herein again.

Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

The invention discloses A1 and an information recommendation method, which comprises the following steps:

A2, the information recommendation method as in a1, wherein the step of determining the service object to be selected according to the service requirement information and searching the service data corresponding to the service object to be selected includes:

A3, the information recommendation method as in a2, wherein the step of determining the business object to be selected having a correlation with the business requirement information through the target recommendation policy includes:

A4, the information recommendation method as in A3, wherein the step of searching the service data corresponding to the service object to be selected includes:

crawling network data related to the business object to be selected;

A5, the information recommendation method as in a4, wherein the step of obtaining target advertisement service data, target recruitment service data and target order service data from the network data comprises:

A6, the information recommendation method as in a5, further comprising, after the steps of determining a target traffic volume according to the network data and determining whether the target traffic volume reaches a preset traffic volume:

A7, the information recommendation method as in a6, wherein before the step of obtaining the target advertisement service data, the target recruitment service data and the target order service data from the network data, the information recommendation method further comprises:

A8, the information recommendation method as in a1, wherein the step of analyzing the service data to obtain a service analysis result of the service object to be selected includes:

The information recommendation method according to any one of a1 to A8, as recited in a9, wherein the step of determining the service requirement information according to the information query request includes:

The information recommendation method according to any one of a1 to A8, as recited in a10, wherein the step of determining the service requirement information according to the information query request includes:

extracting a target keyword of the information query request;

A11, the information recommendation method as in a10, wherein before the step of determining the service requirement information according to the response set corresponding to the keyword set, the method further comprises:

judging whether the keyword set is a plurality of keyword sets;

A12, the information recommendation method as in a11, further comprising, after the step of determining whether the keyword set is a plurality of keyword sets:

The invention also discloses B13 and an information recommendation device, wherein the information recommendation device comprises:

The information recommendation device of B14, as described in B13, the search module is further configured to determine a target recommendation policy matching the service demand information by a preset service configuration recommendation policy;

B15, the information recommendation device as described in B14, the search module further configured to determine, according to the target recommendation policy, a recommended business object having a correlation with the business requirement information;

B16, the information recommendation device as described in B15, the search module is further configured to crawl network data related to the business object to be selected;

The information recommendation device of B17, as described in B16, the search module is further configured to determine a target traffic volume according to the network data, and determine whether the target traffic volume reaches a preset traffic volume;

B18, the information recommendation device according to B17, wherein the searching module is further configured to search the corresponding target advertisement service data, target recruitment service data and target order service data in the second preset service data table through a sequential searching mode when the target service volume does not reach the preset service volume.

C19, an information recommendation apparatus, the information recommendation apparatus comprising: the information recommendation system comprises a memory, a processor and an information recommendation program stored on the memory and capable of running on the processor, wherein the information recommendation program is configured with the steps of realizing the information recommendation method.

D20, a storage medium having stored thereon an information recommendation program which when executed by a processor implements the steps of the information recommendation method as described above.

Claims

1. An information recommendation method, characterized in that the information recommendation method comprises the steps of:

2. The information recommendation method according to claim 1, wherein the step of determining the service object to be selected according to the service demand information and searching for the service data corresponding to the service object to be selected comprises:

3. The information recommendation method according to claim 2, wherein the step of determining the candidate service object having a correlation with the service requirement information through the target recommendation policy comprises:

4. The information recommendation method according to claim 3, wherein the step of searching for the service data corresponding to the service object to be selected comprises:

crawling network data related to the business object to be selected;

5. The information recommendation method of claim 4, wherein said step of obtaining targeted advertising service data, targeted recruitment service data, and targeted order service data from said network data comprises:

6. The information recommendation method of claim 5, wherein after the steps of determining a target traffic volume according to the network data and determining whether the target traffic volume reaches a preset traffic volume, further comprising:

7. The information recommendation method of claim 6, wherein said step of obtaining targeted advertising service data, targeted recruitment service data, and targeted order service data from said network data is preceded by the step of:

8. An information recommendation apparatus characterized by comprising:

9. An information recommendation apparatus characterized by comprising: a memory, a processor and an information recommendation program stored on the memory and executable on the processor, the information recommendation program being configured with steps to implement the information recommendation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that the storage medium has stored thereon an information recommendation program which, when executed by a processor, implements the steps of the information recommendation method according to any one of claims 1 to 7.