CN113158037A - Object-oriented information recommendation method and device - Google Patents
Object-oriented information recommendation method and device Download PDFInfo
- Publication number
- CN113158037A CN113158037A CN202110352211.1A CN202110352211A CN113158037A CN 113158037 A CN113158037 A CN 113158037A CN 202110352211 A CN202110352211 A CN 202110352211A CN 113158037 A CN113158037 A CN 113158037A
- Authority
- CN
- China
- Prior art keywords
- recommendation information
- target object
- target
- similar
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The specification discloses an object-oriented information recommendation method and device. An object-oriented information recommendation method is applied to a server and comprises the following steps: when determining recommendation information of a target object, determining an object portrait of the target object; judging whether similar objects of the target object are stored or not; under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects; and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to an object-oriented information recommendation method and apparatus.
Background
With the development of technology, more and more scenes of information recommendation exist in life, such as recommending interesting products for users, recommending matching policies for enterprises and the like. Based on this, how to recommend information to a required object becomes a key point of attention in the industry.
Disclosure of Invention
In view of the above, the present specification provides an object-oriented information recommendation method and apparatus.
Specifically, the description is realized by the following technical scheme:
an object-oriented information recommendation method is applied to a server and comprises the following steps:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
An object-oriented information recommendation device is applied to a server and comprises the following components:
a portrait determination unit that determines an object portrait of a target object when recommendation information of the target object is determined;
a judging unit that judges whether or not a similar object of the target object is stored;
an acquisition unit that acquires, in a case where a similar object of the target object is stored, history recommendation information of the similar object;
an information determination unit that determines target recommendation information recommended to the target object based on the history recommendation information and the object portrait.
An object-oriented information recommendation apparatus comprising:
a processor;
a memory for storing machine executable instructions;
wherein, by reading and executing machine-executable instructions stored by the memory that correspond to object-oriented information recommendation logic, the processor is caused to:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
One embodiment of the specification realizes that when the server side determines the recommendation information of the target object, the server side can determine the object portrait of the target object, judge whether similar objects of the target object are stored or not, if yes, obtain historical recommendation information of the target object, and determine the target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
By adopting the method, when information is recommended for the target object, the object portrait can be constructed through the attribute of the target object for recommendation, and the historical recommendation information of similar objects can be combined for recommendation, so that on one hand, richer recommendation information can be obtained for recommendation, and the user experience is improved. On the other hand, for target objects with less data, such as cold-start users and inactive users, similar objects can be fully utilized for recommendation, and the technical problems that recommendation cannot be performed and the recommendation accuracy is low in the related technology are solved.
Drawings
FIG. 1 is a flowchart illustrating an object-oriented information recommendation method according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating another object-oriented information recommendation method according to an exemplary embodiment of the present disclosure;
FIG. 3 is a schematic view of a page shown in an exemplary embodiment of the present description;
FIG. 4 is a flow chart diagram illustrating a method for determining similar objects in an exemplary embodiment of the present description;
FIG. 5 is a diagram of a hardware configuration of a server in which an object-oriented information recommendation device is located according to an exemplary embodiment of the present disclosure;
fig. 6 is a block diagram of an object-oriented information recommendation apparatus according to an exemplary embodiment of the present specification.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the appended claims.
The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
With the development of technology, more and more scenes of information recommendation exist in life, such as recommending interesting products for users, recommending matching policies for enterprises and the like. In the related art, when information is recommended for a certain object, the attributes and features of the object are usually analyzed to find information matching the needs of the object for recommendation. However, some objects may have less attributes and features, such as cold-start users and inactive users, and thus may not be able to accurately recommend information to the objects.
The specification provides an object-oriented information recommendation method, which can recommend information to a required object. Even if objects with few attributes and characteristics are subjected to reasonable and accurate recommendation, the user experience is greatly improved.
Referring to fig. 1, fig. 1 is a flowchart illustrating an object-oriented information recommendation method according to an exemplary embodiment of the present disclosure.
The method may be applied to an electronic device having a memory, a processor, such as a server or a cluster of servers. The method may comprise the steps of:
106, acquiring historical recommendation information of the similar object under the condition that the similar object of the target object is stored;
and step 108, determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
The above steps are explained below.
First, the target object and the recommendation information in the present embodiment are described, the target object may be any entity, such as a user, an enterprise, an organization, a social group, and the like, and the recommendation information may be a commodity, product information, news, a policy, and the like, which is not limited in particular.
In this embodiment, when determining the recommendation information of the target object, the server may first determine the object portrait of the target object. For example, when the target object is an enterprise, the object representation may be an enterprise representation, and the server may obtain information about the type, size, business product, partners, etc. of the enterprise and construct the enterprise representation based on the information. The method for constructing an enterprise portrait may refer to related technologies, and this embodiment will not be described herein.
Here, the server may directly obtain the stored object representation, or may generate the object representation when it is necessary to specify the recommendation information of the target object, which is not particularly limited.
In this embodiment, the server may further determine whether a similar object of the target object is stored, where the similar object refers to an object having a higher similarity with the target object in some dimensions. For example, when the target object is a business, the similar object may be a similar business that is close in size and business to the business. For another example, when the target object is a user, the similar object may also be a user close to the user's preference, or may also be a user close to the user's address location, a friend of the user, and so on, which are not examples herein. In this embodiment, the similar object may be determined by the server based on its own data, or may be obtained by analyzing data on the internet acquired by a web crawler, or may be manually set by the user, which is not particularly limited.
In this embodiment, in the case that a similar object exists, the server may obtain historical recommendation information of the similar object, and then determine target recommendation information recommended to the target object according to the historical recommendation information and the object image of the target object. For example, a plurality of pieces of recommendation information can be determined according to the object portrait, a plurality of pieces of recommendation information can be determined according to historical recommendation information of similar enterprises, and then the two pieces of recommendation information are integrated to determine target recommendation information. Specific methods will be described in the following examples.
As can be seen from the above description, in an embodiment of the present specification, when determining recommendation information of a target object, a server may determine an object representation of the target object, determine whether similar objects of the target object are stored, if yes, obtain historical recommendation information of the target object, and determine the target recommendation information recommended to the target object based on the historical recommendation information and the object representation.
By adopting the method, when information is recommended for the target object, the object portrait can be constructed through the attribute of the target object for recommendation, and the historical recommendation information of similar objects can be combined for recommendation, so that on one hand, richer recommendation information can be obtained for recommendation, and the user experience is improved. On the other hand, for target objects with less data, such as cold-start users and inactive users, similar objects can be fully utilized for recommendation, and the technical problems that recommendation cannot be performed and the recommendation accuracy is low in the related technology are solved.
The following describes an embodiment of another object-oriented information recommendation method provided in this specification.
Referring to fig. 2, fig. 2 is a flowchart illustrating another object-oriented information recommendation method according to an exemplary embodiment of the present disclosure.
The method may be applied to an electronic device having a memory and a processor, such as a server or a server cluster, and may include the steps of:
in step 202, when the recommendation information of the target object is determined, the object portrait of the target object is determined.
In this step, the timing of determining the recommendation information of the target object may be various.
For example, it may be determined that the timing for determining the recommendation information of the target object is reached when a recommendation information acquisition request initiated by the target object is received. For example, when the target object is an enterprise, an employee or a person in charge of the enterprise may click a corresponding button or control on a client, such as a page of application software or an applet, to initiate the recommendation information acquisition request.
For another example, the present embodiment may recommend information according to a similar object of the target object, and if the similar object is changed and updated, the corresponding recommendation information is also updated, so that when it is monitored that the target object sets the similar object, it may be determined that the time for determining the recommendation information of the target object is reached. The setting process of the similar objects will be explained in the subsequent steps.
For another example, the recommendation information may be updated periodically, and the update period may be preset. The timing of determining the recommendation information may also be when the periodic update timing of the recommendation information is reached.
For another example, the recommendation information may also be updated and published in real time, such as news, policies, products published by enterprises, and the like, and when it is monitored that the recommendation information is published, it may be determined that the time for determining the recommendation information is reached.
In this step, when the recommendation information of the target object is determined, the portrait of the target object may be determined. For constructing the object image, reference may be made to the foregoing embodiments, which are not described herein again.
In this embodiment, whether or not the similar object of the target object is stored may be determined. The determination process of the similar objects will be described in detail in the following embodiments.
and step 208, determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
In this embodiment, if the similar object of the target object is stored, the historical recommendation information of the similar object in a preset time period, such as the last month and the last week, may be obtained. All recommendation information recommended to the similar objects in a preset time period can be acquired, and only part of recommendation information can be acquired, for example, recommendation information with high browsing volume and recommendation information with high adoption rate can be acquired. Target recommendation information recommended to the target object is then determined based on the historical recommendation information and the object representation.
In one example, a first set of recommendation information may be determined based on a representation of a target object, a second set of recommendation information may be determined based on historical recommendation information for similar objects, and target recommendation information recommended to the target object may then be determined based on the first set of recommendation information and the second set of recommendation information.
Wherein the first set of recommendation information may be determined by the following method. Some key features representing the target user can be determined according to the representation of the target object, for example, when the target object is an enterprise, the key features can be medium and small enterprises, the scale of 100-plus 500 persons and the high and new technology industry, recommendation information meeting the requirements of the enterprise can be matched from the existing recommendation information set according to the features, for example, when the recommendation information is a policy, a policy facing the medium and small enterprises and a policy related to the high and new technology industry can be determined, and the sets can be used as a first recommendation information set. Of course, the above examples are merely exemplary, and other methods may be used to obtain the first recommendation information set.
And then, a union set of the first recommendation information set and the second recommendation information set can be selected, so that the duplicate removal effect is achieved, and the duplicate removed recommendation information is the target recommendation information. Or an intersection set can be taken for the first recommendation information set and the second recommendation information set, and the recommendation information obtained by taking the intersection set is taken as the target recommendation information, so that the recommendation degree and the accuracy of the obtained target recommendation information are higher.
In another example, after obtaining the second recommendation information set according to the historical recommendation information of the similar object, the second recommendation information set may be filtered based on the representation of the target object. For example, when the object portrait is the user portrait, the interest preference and the characteristics of the user can be analyzed according to the portrait of the target object, and then recommendation information which does not accord with the interest preference of the user is filtered from the second recommendation information set based on the information, so that the recommendation information which accords with the requirements of the user better is recommended to the user.
And step 210, if not, acquiring the object portrait as the target object to determine target recommendation information.
In this embodiment, if the similar object of the target object is not stored, the recommendation information may be determined according to the object image of the target object, and specific reference may be made to the foregoing embodiment.
Of course, in addition to the above example, if the target object has a similar object and no information is recommended for the similar object, that is, no history recommendation information exists for the similar object, the recommendation information may be determined based on the object representation of the target object.
In this embodiment, after the target recommendation information is determined, different operations may be performed according to different timings of determining the target recommendation information. For example, when the update time of the target recommendation information is reached or when it is monitored that the similar object of the target object is updated in the above example, the target recommendation information may be stored. For another example, when the recommendation information acquisition request initiated by the target object is received, the target recommendation information may be sent to the target object.
And 212, sequencing the target recommendation information according to a preset sequencing rule.
In this embodiment, after the target recommendation information is determined, the target recommendation information may be sorted, and the method is used to send the sorted recommendation information to the target object after receiving a recommendation information acquisition request initiated by the target object. The sorting method can be various:
for example, historical browsing data of the target recommendation information may be acquired, and sorted according to the browsing amount from high to low.
For another example, historical adoption data of the target recommendation information may be acquired and sorted in order from high to low according to the adoption rate. For example, if the target recommendation information is a policy for medium-sized and small enterprises, the declaration conditions of the policies can be obtained, and the policies are sorted from high declaration rate to low declaration rate. For another example, the target recommendation information may also be products, and may be sorted from high to low according to the purchase rate of the products.
For another example, when the target recommendation information is obtained from the historical recommendation information of the similar objects, the similar objects corresponding to the target recommendation information may also be obtained, and then the similar objects are sorted in the order of high similarity to low similarity between the target object and the similar objects.
It should be noted that, in this embodiment, the sorting process in step 212 may be executed by the server, that is, the server may sort the target recommendation information, so as to send a sorting result to the client for displaying after receiving a request from the client in the following. Step 212 may also be performed by the client, that is, after receiving the request sent by the client, the server may send the target recommendation information that is not sorted to the client, and the client may sort and then display the target recommendation information, which is not limited in this embodiment.
In this embodiment, the target object may initiate a recommendation information acquisition request, for example, a corresponding button or control may be clicked on a client page to initiate the acquisition request, or it may also be determined that the target object initiates the acquisition request after monitoring that the target object opens a specific page, for example, after opening an information recommendation page.
After receiving the request, the server acquires recommendation information of the target object, and then can send the target recommendation information and the corresponding similar object to the client, and the client can display the information on a page for reference and reference of the target object.
After the server side obtains the recommendation information of the target object, whether the aging duration of each recommendation information is reached can be judged, if yes, the recommendation information can be deleted, and the recommendation information is not sent to the client side. The aging duration may be a default value, or may be set according to a specific service, for example, when the recommendation information is a policy, and the policy may have a limitation on declaration time, the aging duration may be set based on the declaration time.
The client presentation method may refer to fig. 3, and fig. 3 is a schematic page diagram shown in an exemplary embodiment of the present specification. As shown in fig. 3, there are 3 pieces of recommendation information, which are "information 1", "information 2", and "information 3", respectively, and a similar object corresponding to the piece of recommendation information is labeled at the lower right corner of the area where each piece of recommendation information is located, where the similar object corresponding to "information 1" is "similar object 1", and the similar object corresponding to "information 2" is "similar object 2". When the user browses the page, the reason for recommending the information can be clearly known, and the user experience can be improved.
Of course, the page shown in fig. 3 is only an exemplary illustration, and other display methods may be adopted in practical applications.
In this embodiment, after the target recommendation information and the similar object corresponding to the target recommendation information are displayed on the client page, the user may also initiate a viewing request for any recommendation information, for example, the user may click on the recommendation information to initiate the request. After receiving the request, the server may present a detailed page of the recommendation information to the user, for example, when the recommendation information is a policy, the server may jump to a page that issues the policy, and the user may view the detailed information on the page and may also perform operations such as declaration.
As can be seen from the above description, in an embodiment of the present specification, historical recommendation information of similar objects of a target object may be obtained, and recommendation information recommended to the target object is determined based on the historical recommendation information and an object image of the target object, so that technical problems of incapability of recommendation and inaccurate recommendation caused by less data of the target object in the related art are solved. And richer information can be recommended to the target object, so that the user experience is improved.
In addition, when the recommendation information is displayed for the target object, the recommendation information can be displayed, and similar objects corresponding to the recommendation information can also be displayed, so that the target object can be helped to know the reason for recommending the information, and the user experience can also be improved.
A method for determining similar objects to a target object provided in the present specification is described below.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for determining a similar object according to an exemplary embodiment of the present disclosure, where the method includes the following steps:
In this embodiment, the target object may initiate a similar object setting request.
For example, when the target object is an enterprise, an employee or a person in charge of the enterprise may initiate a similar object setting request through a client, such as application software or an applet, for example, a corresponding button on a client page may be clicked to initiate a request, and then the client sends the request to a server for processing.
Of course, besides the target object actively initiating the similar object setting request, the server may also actively push the reminding information of the similar object to the target object.
Taking the target object as an enterprise as an example, after the server detects a login request of an enterprise account, whether the enterprise has a similar enterprise can be judged, and if the enterprise has the similar enterprise, the enterprise is not required to be reminded to set the similar enterprise; if not, whether the basic information of the enterprise is sufficient can be further judged.
The basic information may be information for knowing the target object, for example, when the target object is a user, the basic information may be identity information, professional information, hobbies and interests, behavior data, and the like of the user, and the user may be recommended according to the basic information. The basic information may be information of the enterprise held by the server itself, or information of the enterprise obtained by the server from the internet, and the server may determine whether the basic information is sufficient, for example, may determine whether the basic information exists in all specified dimensions, and whether the number of the basic information meets the requirements, and if these conditions satisfy the requirement that the basic information is sufficient, the enterprise may not be prompted to set a similar enterprise. Of course, the above example is merely an exemplary description, and the term "basic information is sufficient" in this embodiment means that if more accurate recommendation information can be obtained for a target object based on the basic information, the basic information is considered to be sufficient.
If the basic information is not sufficient, the server side can send a similar object setting reminder to the enterprise to extract the set similar object, and can also output a reminder such as 'set similar object, let us know you better', 'set similar object, recommend more accurate information for you', and the like. After receiving the reminder, the enterprise may click a corresponding button on the client page to initiate a similar object setup request.
In this embodiment, after receiving the request, the server may determine a plurality of candidate objects according to the target object, where the candidate objects are some objects similar to the target object determined by the server.
In one example, the server may obtain several attribute features of the target object, which may be multidimensional. For example, when the target object is an enterprise, the attribute characteristics of the service dimension, such as the service type and the service mode, may be obtained, and the attribute characteristics of the product dimension, such as the product type, the product function, and the product sales amount, may also be obtained.
The server can compare the attribute features of the target object with the attribute features of the existing object, and determine the objects with similar attribute features as candidate objects.
Still taking the above example as an example, assume that the target object is business a, there are 3 existing businesses B, C, D, and their respective attribute characteristics in the product dimension can be seen in table 1 below:
TABLE 1
Then, each attribute feature of the target object may be respectively compared with corresponding attribute features of other existing objects, and the comparison result may refer to table 2 below:
| type of product | Product function | Product audience | |
| Enterprise B | Uniformity | Uniformity | Uniformity |
| Enterprise C | Inconsistency | Uniformity | Inconsistency |
| Enterprise D | Inconsistency | Inconsistency | Inconsistency |
TABLE 2
Then for each business, the "consistent" attribute may be assigned a score of 1, and the "inconsistent" attribute may be assigned a score of 0, resulting in a score of 2 for business B, a score of 1 for business C, and a score of 0 for business D, and finding that the score of business B is the highest, i.e., business B is closest to business a, may take business B as a candidate. Of course, several top-scoring businesses may be candidates, such as business B and business C.
It should be noted that the above example is merely an exemplary illustration, and in practical applications, other methods may be adopted to determine the candidate enterprises, for example, various situations such as "consistent", "more consistent", "completely inconsistent", and the like may also be set; for another example, different weights may be set for each attribute, for example, the weight value of the attribute of "product type" may be greater than the weight value of "product audience". In addition, in addition to the above comparison from only one dimension of attributes, the comparison may also be performed from multiple dimensions of attributes, and this embodiment is not an example.
In another example, the server may also determine the candidate objects of the target object through the trained model. For example, still taking the target object as an enterprise as an example, the features of each dimension such as the area, industry, business scope, personnel scale, registered fund, product information and the like of the enterprise can be extracted, the features are converted into vectors, the vectors are utilized to train the model, the model can perform similarity calculation on the vectors corresponding to any two enterprises, and then a plurality of enterprises with the highest similarity with the target enterprise are found and serve as candidate enterprises to be output. After the model is trained, target enterprises to be predicted can be input into the model, the model can recall a batch of enterprises and characteristics thereof according to preset conditions, and similarity is calculated based on the characteristics of the target enterprises and the characteristics of the enterprises, so that candidate enterprises are predicted. Of course, the above examples are merely exemplary, and other methods may be used to train the model in practical applications, and the present embodiment is not limited thereto.
In another example, the server may also construct a knowledge graph containing a large number of objects in advance to determine candidate objects based on the knowledge graph.
For example, the entities in the knowledge graph may be various objects, such as various enterprises in the above example, the connection edges between the entities represent the association relationships between the enterprises, such as business cooperation relationships, parent-subsidiary relationships, equity relationships, etc., and each entity may also have its own entity attribute, which may also be the region to which the enterprise belongs, industry, business scope, personnel size, registered funds, product information, etc. In determining the candidate object of the target object, an entity similar to the target object may be searched in the knowledge graph as the candidate object, for example, an object having a specified association relationship with the target object (i.e., having a specified type of continuous edge) may be found in the knowledge graph as the candidate object. Or the objects with similar circles of communication and similar entity attributes can be found in the knowledge graph as candidate objects.
Of course, the above examples are merely exemplary illustrations, and in practical applications, other methods may be used to obtain the candidate object.
In this embodiment, after the server determines the candidate objects, the server may send the candidate objects to the target object, for example, to a client where the target object logs in, the client may display the candidate objects, and then the target object may select a similar object from the candidate objects.
In one example, the client may present introduction information such as names, addresses, business contents, and the like of the candidate objects to help the target object select an object that is considered to be similar from the candidate objects.
In another example, the client may also present the reason why the candidate object is similar to the target object.
For example, for the above example of determining the candidate object based on the attribute feature of the target object, similar attribute features may be displayed, which is helpful for the target object to better select a similar object.
For another example, for the above example of determining the candidate object based on the model, since the model may be a model without interpretability, the reason why the candidate object is similar to the target object may not be directly known from the output result of the model. Other methods can be adopted for analysis, for example, the candidate object obtained by model prediction can be compared with the target object, similar features between the candidate object and the target object can be analyzed, and the features can be displayed on the client page.
In this embodiment, the target object may select an object considered similar to the target object from the candidate objects, and after receiving the similar object set by the user, the server may establish and store a mapping relationship between the similar object and the target object.
Of course, in addition to the above example, the target object may consider that none of the candidate objects calculated by the client is similar to itself, and then the target object may also customize the similar object, for example, manually input the name of the similar object and submit the name to the server.
As can be seen from the above description, in an embodiment of the present specification, the server may receive a similar object setting request from a target object, determine several candidate objects based on the target object, and send the candidate objects to the target object, the target object may select a similar object from the candidate objects and send the similar object to the server, and the server may store an association relationship between the target object and the similar object.
By adopting the method, some candidate objects can be automatically determined, so that the target object can conveniently select similar objects, the server can be further facilitated to determine recommendation information for the target object based on the similar objects, the accuracy of the recommendation information is improved, and the user experience is improved.
Corresponding to the embodiments of the object-oriented information recommendation method, the present specification also provides embodiments of an object-oriented information recommendation apparatus.
The embodiment of the object-oriented information recommendation device can be applied to the server. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the server where the device is located. In terms of hardware, as shown in fig. 5, a hardware structure diagram of a server in which the object-oriented information recommendation device is located in this specification is shown, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 5, the server in which the device is located in the embodiment may also include other hardware according to the actual function of the server, which is not described again.
Fig. 6 is a block diagram of an object-oriented information recommendation apparatus according to an exemplary embodiment of the present specification.
Referring to fig. 6, the object-oriented information recommendation apparatus may be applied to the server shown in fig. 5, and includes: the portrait determining unit 610, the judging unit 620, the acquiring unit 630, the information determining unit 640, the responding unit 650, the sending unit 660, the reminding unit 670, the detecting unit 680 and the sorting unit 690.
Wherein, the portrait determining unit 610 determines an object portrait of a target object when determining recommendation information of the target object;
a judging unit 620 that judges whether a similar object of the target object is stored;
an acquisition unit 630, in a case where a similar object of the target object is stored, acquiring history recommendation information of the similar object;
an information determination unit 640 determines target recommendation information recommended to the target object based on the history recommendation information and the object representation.
Optionally, the information determining unit 640:
determining a first recommendation information set according to the portrait of the target object;
determining a second recommendation information set according to the historical recommendation information of the similar objects;
determining the target recommendation information based on the first recommendation information set and the second recommendation information set.
Optionally, the information determining unit 640:
determining a second recommendation information set according to the historical recommendation information of the similar objects;
filtering the second set of recommendation information based on the representation of the target object;
and determining the target recommendation information based on the second recommendation information set obtained by filtering.
Optionally, the process of determining similar objects includes:
receiving a similar object setting request from a target object, determining a plurality of candidate objects based on the target object, and sending the candidate objects to the target object;
receiving the similar object determined by the target object from the candidate objects.
Optionally, the apparatus further comprises:
the detecting unit 680, after detecting the login request of the target object, determines whether a similar object of the target object is stored;
and if not, the reminding unit 670 sends a similar object setting reminder to the target object, wherein the similar object setting request is sent by the target object based on the reminder.
Optionally, the determining a plurality of candidate objects based on the target object includes:
acquiring a plurality of attribute characteristics of a target object;
and determining a plurality of candidate objects with the similarity meeting the requirement with the target object according to the attribute characteristics.
Optionally, the method further includes:
a response unit 650 that acquires target recommendation information of a target object in response to a recommendation information acquisition request from the target object;
the sending unit 660 sends the target recommendation information to the target object.
Optionally, when the target recommendation information is history recommendation information of similar objects of the target object, the sending unit 660:
and sending the target recommendation information and the similar object corresponding to the target object recommendation information to the target object.
Optionally, the method further includes:
the sorting unit 690 sorts the target recommendation information according to a preset sorting rule;
the transmitting unit 660:
and sending the target recommendation information and the sequencing result thereof to the target object.
Optionally, the sorting unit 690:
sorting is performed by one or more of the following methods:
sequencing the historical browsing data of the recommended information according to similar objects;
sorting the historical adoption data of the recommendation information according to similar objects;
and sequencing according to the similarity between the target object and the similar object corresponding to the recommendation information.
Optionally, the timing for determining the recommendation information of the target object includes one or more of the following:
receiving a recommendation information acquisition request from a target object;
receiving a similar object set by a target object;
the update time of the recommendation information is reached;
and monitoring the release of the recommendation information.
Optionally, the information determining unit 640 further:
and under the condition that the similar object of the target object is not stored, determining target recommendation information for the target object according to the portrait of the target object.
Optionally, the object is an enterprise, and the recommendation information is a policy.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
Corresponding to the foregoing embodiment of the object-oriented information recommendation method, the present specification further provides an object-oriented information recommendation apparatus, including: a processor and a memory for storing machine executable instructions. Wherein the processor and the memory are typically interconnected by means of an internal bus. In other possible implementations, the device may also include an external interface to enable communication with other devices or components.
In this embodiment, the processor is caused to:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
Optionally, in determining target recommendation information recommended to the target object based on the historical recommendation information and the object representation, the processor is caused to:
determining a first recommendation information set according to the portrait of the target object;
determining a second recommendation information set according to the historical recommendation information of the similar objects;
determining the target recommendation information based on the first recommendation information set and the second recommendation information set.
Optionally, in determining target recommendation information recommended to the target object based on the historical recommendation information and the object representation, the processor is caused to:
determining a second recommendation information set according to the historical recommendation information of the similar objects;
filtering the second set of recommendation information based on the representation of the target object;
and determining the target recommendation information based on the second recommendation information set obtained by filtering.
Optionally, during the determination of similar objects, the processor is caused to:
receiving a similar object setting request from a target object, determining a plurality of candidate objects based on the target object, and sending the candidate objects to the target object;
receiving the similar object determined by the target object from the candidate objects.
Optionally, the processor is further caused to:
after a login request of a target object is detected, judging whether a similar object of the target object is stored or not;
if not, sending a similar object setting prompt to the target object, wherein the similar object setting request is sent by the target object based on the prompt.
Optionally, in determining a number of candidate objects based on the target object, the processor is caused to:
acquiring a plurality of attribute characteristics of a target object;
and determining a plurality of candidate objects with the similarity meeting the requirement with the target object according to the attribute characteristics.
Optionally, the processor is further caused to:
in response to a recommendation information acquisition request from a target object, acquiring target recommendation information of the target object;
and sending the target recommendation information to the target object.
Optionally, when the target recommendation information is historical recommendation information of similar objects of the target object, the processor is caused to:
and sending the target recommendation information and the similar object corresponding to the target object recommendation information to the target object.
Optionally, the processor is further caused to:
sequencing the target recommendation information according to a preset sequencing rule;
the sending the target recommendation information to the target object includes:
and sending the target recommendation information and the sequencing result thereof to the target object.
Optionally, when the target recommendation information is sorted according to a preset sorting rule, the processor is caused to:
sorting is performed by one or more of the following methods:
sequencing the historical browsing data of the recommended information according to similar objects;
sorting the historical adoption data of the recommendation information according to similar objects;
and sequencing according to the similarity between the target object and the similar object corresponding to the recommendation information.
Optionally, the timing for determining the recommendation information of the target object includes one or more of the following:
receiving a recommendation information acquisition request from a target object;
receiving a similar object set by a target object;
the update time of the recommendation information is reached;
and monitoring the release of the recommendation information.
Optionally, the processor is further caused to:
and under the condition that the similar object of the target object is not stored, determining target recommendation information for the target object according to the portrait of the target object.
Optionally, the object is an enterprise, and the recommendation information is a policy.
In correspondence with the foregoing object-oriented information recommendation method embodiments, the present specification also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
Optionally, the determining target recommendation information recommended to the target object based on the historical recommendation information and the object representation includes:
determining a first recommendation information set according to the portrait of the target object;
determining a second recommendation information set according to the historical recommendation information of the similar objects;
determining the target recommendation information based on the first recommendation information set and the second recommendation information set.
Optionally, the determining target recommendation information recommended to the target object based on the historical recommendation information and the object representation includes:
determining a second recommendation information set according to the historical recommendation information of the similar objects;
filtering the second set of recommendation information based on the representation of the target object;
and determining the target recommendation information based on the second recommendation information set obtained by filtering.
Optionally, the process of determining similar objects includes:
receiving a similar object setting request from a target object, determining a plurality of candidate objects based on the target object, and sending the candidate objects to the target object;
receiving the similar object determined by the target object from the candidate objects.
Optionally, the method further includes:
after a login request of a target object is detected, judging whether a similar object of the target object is stored or not;
if not, sending a similar object setting prompt to the target object, wherein the similar object setting request is sent by the target object based on the prompt.
Optionally, the determining a plurality of candidate objects based on the target object includes:
acquiring a plurality of attribute characteristics of a target object;
and determining a plurality of candidate objects with the similarity meeting the requirement with the target object according to the attribute characteristics.
Optionally, the method further includes:
in response to a recommendation information acquisition request from a target object, acquiring target recommendation information of the target object;
and sending the target recommendation information to the target object.
Optionally, when the target recommendation information is historical recommendation information of similar objects of the target object, the sending the target recommendation information to the target object includes:
and sending the target recommendation information and the similar object corresponding to the target object recommendation information to the target object.
Optionally, the method further includes:
sequencing the target recommendation information according to a preset sequencing rule;
the sending the target recommendation information to the target object includes:
and sending the target recommendation information and the sequencing result thereof to the target object.
Optionally, the sorting the target recommendation information according to a preset sorting rule includes:
sorting is performed by one or more of the following methods:
sequencing the historical browsing data of the recommended information according to similar objects;
sorting the historical adoption data of the recommendation information according to similar objects;
and sequencing according to the similarity between the target object and the similar object corresponding to the recommendation information.
Optionally, the timing for determining the recommendation information of the target object includes one or more of the following:
receiving a recommendation information acquisition request from a target object;
receiving a similar object set by a target object;
the update time of the recommendation information is reached;
and monitoring the release of the recommendation information.
Optionally, the method further includes:
and under the condition that the similar object of the target object is not stored, determining target recommendation information for the target object according to the portrait of the target object.
Optionally, the object is an enterprise, and the recommendation information is a policy.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (25)
1. An object-oriented information recommendation method is applied to a server and comprises the following steps:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
2. The method of claim 1, wherein determining target recommendation information to recommend to the target object based on the historical recommendation information and the object representation comprises:
determining a first recommendation information set according to the portrait of the target object;
determining a second recommendation information set according to the historical recommendation information of the similar objects;
determining the target recommendation information based on the first recommendation information set and the second recommendation information set.
3. The method of claim 1, wherein determining target recommendation information to recommend to the target object based on the historical recommendation information and the object representation comprises:
determining a second recommendation information set according to the historical recommendation information of the similar objects;
filtering the second set of recommendation information based on the representation of the target object;
and determining the target recommendation information based on the second recommendation information set obtained by filtering.
4. The method of claim 1, wherein the process of determining the similar objects comprises:
receiving a similar object setting request from a target object, determining a plurality of candidate objects based on the target object, and sending the candidate objects to the target object;
receiving the similar object determined by the target object from the candidate objects.
5. The method of claim 4, further comprising:
after a login request of a target object is detected, judging whether a similar object of the target object is stored or not;
if not, sending a similar object setting prompt to the target object, wherein the similar object setting request is sent by the target object based on the prompt.
6. The method of claim 4, the determining a number of candidate objects based on the target object, comprising:
acquiring a plurality of attribute characteristics of a target object;
and determining a plurality of candidate objects with the similarity meeting the requirement with the target object according to the attribute characteristics.
7. The method of claim 1, further comprising:
in response to a recommendation information acquisition request from a target object, acquiring target recommendation information of the target object;
and sending the target recommendation information to the target object.
8. The method of claim 7, when the target recommendation information is historical recommendation information of similar objects of the target object, the sending the target recommendation information to the target object comprises:
and sending the target recommendation information and the similar object corresponding to the target object recommendation information to the target object.
9. The method of claim 7, further comprising:
sequencing the target recommendation information according to a preset sequencing rule;
the sending the target recommendation information to the target object includes:
and sending the target recommendation information and the sequencing result thereof to the target object.
10. The method of claim 9, wherein the sorting the target recommendation information according to a preset sorting rule comprises:
sorting is performed by one or more of the following methods:
sequencing the historical browsing data of the recommended information according to similar objects;
sorting the historical adoption data of the recommendation information according to similar objects;
and sequencing according to the similarity between the target object and the similar object corresponding to the recommendation information.
11. The method of claim 1, wherein the timing of the recommendation of the target object comprises one or more of the following:
receiving a recommendation information acquisition request from a target object;
receiving a similar object set by a target object;
the update time of the recommendation information is reached;
and monitoring the release of the recommendation information.
12. The method of claim 1, further comprising:
and under the condition that the similar object of the target object is not stored, determining target recommendation information for the target object according to the portrait of the target object.
13. The method of any of claims 1-12, wherein the object is a business and the recommendation information is a policy.
14. An object-oriented information recommendation device is applied to a server and comprises the following components:
a portrait determination unit that determines an object portrait of a target object when recommendation information of the target object is determined;
a judging unit that judges whether or not a similar object of the target object is stored;
an acquisition unit that acquires, in a case where a similar object of the target object is stored, history recommendation information of the similar object;
an information determination unit that determines target recommendation information recommended to the target object based on the history recommendation information and the object portrait.
15. The apparatus of claim 14, the information determination unit to:
determining a first recommendation information set according to the portrait of the target object;
determining a second recommendation information set according to the historical recommendation information of the similar objects;
determining the target recommendation information based on the first recommendation information set and the second recommendation information set.
16. The apparatus of claim 14, the information determination unit to:
determining a second recommendation information set according to the historical recommendation information of the similar objects;
filtering the second set of recommendation information based on the representation of the target object;
and determining the target recommendation information based on the second recommendation information set obtained by filtering.
17. The apparatus of claim 14, the process of determining similar objects comprising:
receiving a similar object setting request from a target object, determining a plurality of candidate objects based on the target object, and sending the candidate objects to the target object;
receiving the similar object determined by the target object from the candidate objects.
18. The apparatus of claim 17, further comprising:
the detection unit is used for judging whether similar objects of the target object are stored or not after the login request of the target object is detected;
and if not, sending a similar object setting prompt to the target object, wherein the similar object setting request is sent by the target object based on the prompt.
19. The apparatus of claim 17, the determining a number of candidate objects based on the target object, comprising:
acquiring a plurality of attribute characteristics of a target object;
and determining a plurality of candidate objects with the similarity meeting the requirement with the target object according to the attribute characteristics.
20. The apparatus of claim 14, further comprising:
the response unit is used for responding to a recommendation information acquisition request from a target object and acquiring the target recommendation information of the target object;
and the sending unit is used for sending the target recommendation information to the target object.
21. The apparatus according to claim 20, wherein when the target recommendation information is history recommendation information of similar objects to the target object, the transmission unit:
and sending the target recommendation information and the similar object corresponding to the target object recommendation information to the target object.
22. The apparatus of claim 20, further comprising:
the sorting unit sorts the target recommendation information according to a preset sorting rule;
the transmission unit:
and sending the target recommendation information and the sequencing result thereof to the target object.
23. The apparatus of claim 14, wherein the timing for determining the recommendation information of the target object comprises one or more of the following:
receiving a recommendation information acquisition request from a target object;
receiving a similar object set by a target object;
the update time of the recommendation information is reached;
and monitoring the release of the recommendation information.
24. The apparatus according to any one of claims 14-23, wherein the object is a business and the recommendation information is a policy.
25. An object-oriented information recommendation apparatus comprising:
a processor;
a memory for storing machine executable instructions;
wherein, by reading and executing machine-executable instructions stored by the memory that correspond to object-oriented information recommendation logic, the processor is caused to:
when determining recommendation information of a target object, determining an object portrait of the target object;
judging whether similar objects of the target object are stored or not;
under the condition that similar objects of the target object are stored, acquiring historical recommendation information of the similar objects;
and determining target recommendation information recommended to the target object based on the historical recommendation information and the object portrait.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110352211.1A CN113158037A (en) | 2021-03-31 | 2021-03-31 | Object-oriented information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110352211.1A CN113158037A (en) | 2021-03-31 | 2021-03-31 | Object-oriented information recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113158037A true CN113158037A (en) | 2021-07-23 |
Family
ID=76886335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110352211.1A Pending CN113158037A (en) | 2021-03-31 | 2021-03-31 | Object-oriented information recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158037A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297515A (en) * | 2022-03-10 | 2022-04-08 | 成都明途科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140143233A1 (en) * | 2012-11-20 | 2014-05-22 | Alibaba Group Holding Limited | Method and system for recommending target object information |
| CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
| CN110909176A (en) * | 2019-11-20 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Data recommendation method and device, computer equipment and storage medium |
| CN111695023A (en) * | 2019-03-11 | 2020-09-22 | 北京京东尚科信息技术有限公司 | Information recommendation method and device, storage medium and equipment |
| CN111861760A (en) * | 2020-06-22 | 2020-10-30 | 中国平安财产保险股份有限公司 | Product recommendation method, device, equipment and storage medium |
-
2021
- 2021-03-31 CN CN202110352211.1A patent/CN113158037A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140143233A1 (en) * | 2012-11-20 | 2014-05-22 | Alibaba Group Holding Limited | Method and system for recommending target object information |
| CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
| CN111695023A (en) * | 2019-03-11 | 2020-09-22 | 北京京东尚科信息技术有限公司 | Information recommendation method and device, storage medium and equipment |
| CN110909176A (en) * | 2019-11-20 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Data recommendation method and device, computer equipment and storage medium |
| CN111861760A (en) * | 2020-06-22 | 2020-10-30 | 中国平安财产保险股份有限公司 | Product recommendation method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 郑树泉: "《工业智能技术与应用》", 31 January 2019 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297515A (en) * | 2022-03-10 | 2022-04-08 | 成都明途科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11301729B2 (en) | Systems and methods for inferential sharing of photos | |
| US11250487B2 (en) | Computer vision and image characteristic search | |
| CN109086394B (en) | Search ranking method and device, computer equipment and storage medium | |
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| US8997117B1 (en) | System and method for creating personal connection alerts | |
| US9218568B2 (en) | Disambiguating data using contextual and historical information | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| CN106874314B (en) | Information recommendation method and device | |
| CN110503506B (en) | Item recommendation method, device and medium based on grading data | |
| US10931620B2 (en) | Calculating efficient messaging parameters | |
| US8949237B2 (en) | Detecting overlapping clusters | |
| CN107918618B (en) | Data processing method and device | |
| CN112667825B (en) | Intelligent recommendation method, device, equipment and storage medium based on knowledge graph | |
| CN110647683B (en) | Information recommendation method and device | |
| EP3739470A1 (en) | Method and apparatus for performing categorised matching of videos, and selection engine | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN113158037A (en) | Object-oriented information recommendation method and device | |
| CN111506733B (en) | Object portrait generation method and device, computer equipment and storage medium | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN110659406A (en) | Searching method and device | |
| CN109934689B (en) | Target object ranking interpretation method and device, electronic equipment and readable storage medium | |
| CN113822566A (en) | Business assessment processing method and device, computer equipment and storage medium | |
| CN106484710B (en) | Dynamic data processing method and device and information display method and device | |
| US11956400B2 (en) | Systems and methods for measuring document legibility | |
| CN117874328A (en) | Service information recommendation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |
|
| RJ01 | Rejection of invention patent application after publication |