CN111914165B - Target object recommendation method, device, equipment and storage medium - Google Patents
Target object recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111914165B CN111914165B CN202010609231.8A CN202010609231A CN111914165B CN 111914165 B CN111914165 B CN 111914165B CN 202010609231 A CN202010609231 A CN 202010609231A CN 111914165 B CN111914165 B CN 111914165B
- Authority
- CN
- China
- Prior art keywords
- target
- attribute
- target object
- weight
- requester
- 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.)
- Active
Links
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)
Abstract
The application discloses a target object recommending method, a target object recommending device, target object recommending equipment and a storage medium. The method comprises the following steps: responding to an acquisition request of a requester, and sending a first target list containing target objects; determining behavior preference of the requester according to the operation type of the requester for the target object in the first target list; and recommending a second target list containing target objects based on the result of the behavior preference correction to the acquisition request. According to the technical scheme, even if the acquisition request filled by the requester is not very accurate, the actual demand of the requester can be determined according to the actual operation type of the acquisition requester on each target object, so that the target objects meeting the demand of the requester can be more accurately recommended for the requester, and the recommendation efficiency and the recommendation accuracy are improved.
Description
Technical Field
The embodiment of the application relates to the technical field of Internet, in particular to a target object recommending method, device, equipment and storage medium.
Background
With the development of internet technology, the manner in which users obtain services has changed greatly. Many businesses have developed web products that offer various services, such as APPs that offer home services, APPs that offer shipping services, and so forth.
When using these products, the user can select a service provider according to his own needs, and the service provider can be understood as a service person, such as a cleaning agent or a driver, which provides services for the user. In the following, a user recruits a cleaner as an example, and in order to recruit the cleaner, the user usually performs screening and recruitment of the cleaner by filling in recruitment information or setting screening conditions. If meeting the conditions of a certain cleaning agent, the user can send out the offer information to the cleaning agent, and if the cleaning agent accepts the offer, recruitment is completed. In practical application, recruitment information provided by a user or set screening conditions are relatively solidified and cannot represent the current real recruitment requirement of the user, so that recommended cleaning staff cannot necessarily meet the recruitment requirement of the user.
Disclosure of Invention
The embodiment of the application provides a target object recommending method, device, equipment and storage medium, which are used for recommending a proper target object for a requester.
In a first aspect, an embodiment of the present application provides a target object recommendation method, where the method includes:
responding to an acquisition request of a requester, and sending a first target list containing target objects;
determining behavior preference of the requester according to the operation type of the requester for the target object in the first target list;
correcting the acquisition request based on the behavior preference;
and recommending a second target list containing target objects according to the corrected result.
In a second aspect, an embodiment of the present application provides a target object recommendation apparatus, including:
the sending module is used for responding to the acquisition request of the requester and sending a first target list containing target objects;
a determining module, configured to determine a behavior preference of the requester according to an operation type of the requester for a target object in the first target list;
the correction module is used for correcting the acquisition request based on the behavior preference;
and the recommending module is used for recommending a second target list containing the target objects according to the corrected result.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, and a memory, where the memory is configured to store one or more computer instructions, and the one or more computer instructions implement the target object recommendation method according to the first aspect when executed by the processor.
In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program causes a client to implement the target object recommendation method according to the first aspect when executed.
In the embodiment of the application, after receiving the acquisition request of the requester, the server side recommends a first target list containing a plurality of target objects for the requester according to the information carried by the acquisition request. After the requester receives the first target list, the requester performs related operations on the target objects in the first target list, and further, the behavior preference of the requester can be determined according to the operation types of the requester on each target object. And correcting the acquisition request by using the behavior preference, and recommending a second target list containing target objects according to the corrected result. According to the technical scheme, even if the acquisition request filled by the requester is not very accurate, the actual demand of the requester can be determined according to the actual operation type of the acquisition requester on each target object, so that the target objects meeting the demand of the requester can be more accurately recommended for the requester, and the recommendation efficiency and the recommendation accuracy are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a target object recommending method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a display effect of a request operation type according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a target object recommendation device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application 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, the "plurality" generally includes at least two.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product 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 product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or system comprising such elements.
In embodiments of the present application, the requestor may be a service requestor or a service provider, and the target object with respect to which it is to be a service provider or a service requestor, respectively. For example, the requesting party is a recruiter, and the corresponding target object may be a cleaner, a nurse, a jiffy, and so forth. In practical applications, the basic information registration is performed in advance, whether it is a requesting party or a target object, for example, the recruiter registers the recruitment requirement, and the job seeker fills in the job seeker requirement and the basic personal information. Some of the information is merely representative of the idea or standpoint of the recruiter or job seeker when filling in the information, and over time, the actual recruitment demand may change, but the requesting party is unaware of the need to modify the original registration information, which may result in the target object recommended for the requesting party not conforming to the current latest recruitment demand of the recruiter.
Fig. 1 is a flow chart of a target object recommending method provided by an embodiment of the present application, which is applied to a server, as shown in fig. 1, and the method includes the following steps:
101: in response to a request for retrieval by a requestor, a first target list containing target objects is sent.
102: and determining the behavior preference of the requester according to the operation type of the requester for the target objects in the first target list.
103: and correcting the acquisition request based on the behavior preference.
104: and recommending a second target list containing target objects according to the corrected result.
For ease of understanding, in the following embodiments, a recruiter will be taken as an example, and a job seeker (e.g., a cleaner, a member of the evening, etc.) will be taken as a target object.
The requesting party selects or fills in an acquisition request through the client, wherein the acquisition request contains a limiting condition of a target object which the requesting party wants to acquire, for example, the acquisition request can contain target attributes of age, household registration, expected salary, working age, working content and the like, and the target attributes are used as screening conditions of the target object. After receiving the request from the requesting party, the server searches the storage unit (such as a database) for storing the target objects according to the relevant screening conditions provided by the requesting party for the target objects meeting the limiting conditions, and then generates a first target list containing the target objects. In practical applications, the first target list can only display a limited number of target objects at a time on the client of the requesting party, and is usually ordered according to the relevance of the target objects to the constraint, or according to the score of the target objects. If the requester wants to browse more target objects, more target objects can be obtained through page turning operation.
In practical applications, the requestor may browse the expanded first target list, view the expanded target object, and perform related operation processing on the target object, and specifically, the operation processing may be classified into various operation types, for example, an offer operation, a focus operation, a browse operation, and so on. It is readily appreciated that the requestor may employ different types of operations on the target object, and may characterize different degrees of interest of the requestor in the target object. In other words, the offer operation represents the highest attention, the attention operation represents the next highest attention, and the browse operation represents the weakest attention. These operations represent the current actual behavior of the requester, and these behavior rules may be used to characterize the behavior preference of the user, that is, a certain class of the current behavior of the requester or a target object with a certain target attribute, for example, 3 consecutive target objects sent by the requester, where all the target attributes "native" are shanxi, and indicate that the behavior preference of the requester is the target attribute of native shanxi.
When browsing the target object, the requester can open and view the interested target object, for example, open the relevant information of the target object through clicking operation, and the requester can intuitively see all the information of the target object. In addition, if the requester can execute the behavior characterizing different attention degrees of the requester on the target object through the operation modes related to the attention operation or the collection operation and the like.
For another example, when the requester browses the target objects, it finds that a certain pushed target object is a target object required by the requester, and the requester may perform an offer operation on the target object, in other words, the requester sends out a recruitment invitation.
It should be noted that, since the types of operations sent by the requesting party to the target objects are different, a distinction is made in the background, so that the target objects can also see the respective target objects having different attention degrees. For example, fig. 2 is a schematic diagram of a display effect of a type of operation of a requester according to an embodiment of the present application. As can be seen from fig. 2, assuming that the requestor sends out an offer operation to a certain target object, in the job-seeking information acquired by the target object, the requestor sending out the offer operation will be preferentially recommended to the target object; second, the requestor performing the attention operation is sent to the target object. In practical applications, the attention degree of the requester may be directly displayed on the client of the target object, for example, the issuing of the offer operation is represented by a handshake icon, the attention operation is represented by a five-pointed star icon, and so on. Furthermore, the target object can make corresponding feedback according to different attention degrees, and feedback information generated by different feedback modes is not completely the same. For example, the target user makes two different feedback to two requesters simultaneously, the first feedback mode is to accept the offer of the requester, and the second feedback mode is to take the attention mode as feedback to a requester after seeing the attention operation of the requester. Further, after receiving different feedback information of the target objects, each requester sorts each target object in the current target object list.
In order to accurately distinguish the attention degree of the requesting party to the target object, the weight value marking can be carried out on the target attribute of the target object according to the operation type of the requesting party to the target object. Further, according to the comparison result of the weight values, the target attribute with the large weight value is used as the behavior preference of the requester.
Specifically, when the requesting party performs related operations (such as browsing operations, attention operations, offer operations, etc.) on each target object in the first target list through the client, the server side also obtains the operation type of each target object by the requesting party. The method that the requester performs the operation type may be triggered by the operation control (for example, focus control) according to the requester, that is, each operation type corresponds to one operation control or one operation gesture, and the service side can simply and clearly obtain the operation type performed by the requester at the client side.
The target object may include various target attributes. For example, assuming that the target object is a nurse, the corresponding target attribute may be a post type, home, age, expected salary, business age, etc.; for another example, the target object is a driver, and the corresponding target attribute may be driving book type, native, age, desired salary, driving age, and so forth. Generally, the same category of target objects has the same type of target attribute, for example, two target objects which are also careers, and the target attributes are the post type, the native place, the age, the expected salary, the business age and the like, but the values or contents corresponding to the specific native place, the age and the like may be different.
From the foregoing, it is clear that the types of operations made by the requesters are different, and that the degrees of attention of the requesters to the target objects are different. The higher the degree of attention, the greater the corresponding marked weight value. Specifically, if the operation type is an offer operation, determining a weight value of target data contained in the target object as a first weight value; if the operation type is concerned operation, determining that the weight value of the target data contained in the target object is a second weight value; if the operation type is browsing operation, determining that the weight value of the target data contained in the target object is a third weight value; wherein the first weight value is greater than the second weight value and greater than the third weight value.
After the weight values of the target attributes marked in the plurality of target objects are obtained, the weight values of the target attributes are subjected to comprehensive weight processing, so that the corresponding values of the target attributes or the concerned degree of the content can be known; in other words, the larger the attribute value of a certain target attribute or the weight integrated value of the content, the more important the target attribute having the content or the attribute value is to the requesting party. The weight integrated value calculation formula is as follows:
for example, take the example of calculating native comprehensive weights: suppose the offer weight is 3, the attention weight is 2, and the browsing weight is 1. In the obtained statistical list, the offer list contains 3 Shanxes and 1 Shandong, and the attention list is as follows: the browsed list is statistically 0 for 3 shanks.
According to the calculation formula, the native is the comprehensive weight value of Shanxi:
the weight value of the combination of the Mithrough and the Shandong:
and then comparing the weight comprehensive values corresponding to different attribute values or contents in the same category of target attributes. When the target attribute types are more, the weight comprehensive values corresponding to different attribute values of the same category of target attribute can be ranked (when the target attribute type is realized, for example, the target attribute type can be realized by a quick ranking method), the size relation of the weight comprehensive values corresponding to different attribute values can be known, and the attribute value or the content with the largest weight comprehensive value corresponding to each target attribute can be determined.
As can be seen from comparing the above weight integrated values, the shanxi weight is greater than the shandong weight, in other words, the attribute of the target object that the requester focuses on is the target object of native cross. Further, the target attribute having the aforementioned attribute value or content may be regarded as the behavior preference of the requester. The acquired behavior preferences can more truly reflect the current demand conditions (such as recruitment demands or job-seeking demands) of the requesting party, and can be used for correcting the target attributes (such as manually filled recruitment conditions) filled by the requesting party before.
In practical applications, when a requester initiates an acquisition request to a server, the requester typically sets a target attribute as a filtering condition. The screening condition can be set in various ways, for example, the target attribute for screening can be set by filling recruitment information by the requester, or the target attribute and attribute value for screening can be set by the requester through a screening control. Of course, if the requester considers that a certain target attribute is not concerned, the target attribute and the attribute value may be selectively set.
After the requester finishes setting each target attribute, each target attribute is given a certain initial weight, for example, the default initial weight is 2. The request party transmits the weight value given by the client to the server, so that the server can acquire the carried target attribute and the corresponding initial weight value from the acquisition request sent by the request party, and the weight correction processing is carried out on the initial weight value and the weight comprehensive value corresponding to the target attribute.
If the attribute values corresponding to the same category target attribute are the same, the initial weight and the weight comprehensive value of the attribute value are obtained. If the attribute values corresponding to the same category of target attributes are different, comparing the initial value of the attribute value with the magnitude of the weight integrated value, and taking the attribute value with the large weight value as the new attribute value of the modified target attribute. It should be explained here that the larger the weight value, the more representative of the current requester requirement, and therefore, the weight value needs to be compared here to determine the target attribute and its attribute value for screening the second target list.
After the correction of the acquisition request is completed, the second target list may be rescreened according to the latest obtained target attribute. The first target list may also be rescreened to obtain the second target list according to the latest obtained target attribute after the correction of the acquisition request is completed. As can be seen from the foregoing, the behavior preference of the requester can more truly reflect the target object required by the current requester, so that the initial acquisition request is corrected by using the behavior preference, so as to obtain the second target list which can better meet the latest requirement or the current requirement of the requester, and thus, the recommendation success rate of the target object can be improved.
Furthermore, as can be seen from the foregoing, different operation types of the requesting party can be visually presented to the target object, and then the target object can make corresponding feedback or response after seeing different attention degrees of the requesting party. The feedback information of the target object can be an offer, attention, browsing and the like, and different feedback information can be realized by different feedback modes. Similarly, different feedback modes are used for representing different interestingness of the target object to the requester; for example, if the feedback mode of the target object is that an offer is received, the feedback mode indicates that the interest of the target object to the requester is highest; the feedback mode of the target object is concerned, which means that the target object has a certain interest degree to the requesting party, namely the interest degree is general; the feedback mode of the target object is browsing, which indicates that the target object has weaker interest level to the requester. Similarly, different interestingness corresponds to an interest score, and the higher the interestingness is, the larger the corresponding interest score is. That is, the interest score of the accepted offer is the largest, the feedback information is the interest score of the interest, and the lowest is the interest score of the browse.
After the second target list containing the latest target objects is obtained by screening with the corrected acquisition request, further screening can be performed according to the interest scores or the target objects in the second target list can be ordered by using the interest scores.
In this embodiment, the second target list is obtained by screening according to the obtaining request and the behavior preference of the requester provided by the requester, and the interest degree of the target object to the requester can be comprehensively considered as a screening condition or a sorting condition for producing the second target list, so that the target object in the second target list can more conform to the expectation of the requester and also conform to the expectation of the target object, and the matching success rate is improved. Different from the traditional commodity recommendation mode, in order to enable the recommendation pairing success rate to be higher, the requirements of a requester are considered, the actual requirements of a target object are considered, so that the requester is matched with the target object more, and the recommendation efficiency and the recommendation matching rate can be effectively improved.
Fig. 3 is a schematic structural diagram of a target object recommendation device according to an embodiment of the present application, where the device may be applied to a server, and may include: the system comprises a sending module 31, a determining module 32, a correcting module 33 and a recommending module 34.
A sending module 31, configured to send a first target list including target objects in response to an acquisition request of a requester;
a determining module 32, configured to determine a behavior preference of the requester according to an operation type of the requester for the target objects in the first target list;
a correction module 33, configured to correct the acquisition request based on the behavior preference;
and a recommending module 34, configured to recommend a second target list containing target objects according to the corrected result.
Optionally, the determining module 32 is further configured to obtain an operation type of the requesting party for each of the target objects in the first target list; marking the weight value of the target attribute contained in each target object according to the operation type; and determining the target attribute with a large weight value as the behavior preference according to the weight value comparison result.
Optionally, the method further comprises: if the operation type is an offer operation, determining that the weight value of the target data contained in the target object is a first weight value; if the operation type is concerned operation, determining that the weight value of the target data contained in the target object is a second weight value; if the operation type is browsing operation, determining that the weight value of the target data contained in the target object is a third weight value;
wherein the first weight value is greater than the second weight value and greater than the third weight value.
Optionally, the determining module 32 is further configured to determine a weight integrated value of the target attribute, where the plurality of attribute values are labeled respectively; and determining a target attribute with a large weight integrated value as the behavior preference according to the result of comparing the sizes of the weight integrated values.
Optionally, a correction module 33 is configured to obtain a target attribute carried in the obtaining request and an initial weight corresponding to the target attribute; and carrying out weighted correction processing on the initial weight value and the weight comprehensive value corresponding to the target attribute.
Optionally, a recommendation module 34, configured to obtain feedback information of the target object for the operation type; according to the feedback information of the target object, determining the interest degree of the target object to the requester; sorting the target objects according to the interest level of the target objects on the requester; and generating a second target list of the target objects ordered from big to small according to the interestingness.
Optionally, the sending module 31 is configured to obtain a target object screening condition included in the obtaining request; and determining the target object meeting the target object screening condition, and sending a first target list containing the target object.
The apparatus shown in fig. 3 may perform the steps related to the server in fig. 1, and the detailed implementation process and technical effects are referred to the description in the foregoing embodiments, which are not repeated herein.
In one possible design, the structure of the target object recommendation apparatus shown in fig. 3 may be implemented as an electronic device, as shown in fig. 4, where the electronic device may include: the system comprises a processor 41 and a memory 42, wherein the memory 42 is used for storing one or more computer instructions, and the one or more computer instructions realize the steps executed by the server in the previous embodiments when being executed by the processor 41.
Optionally, a communication interface 43 may be included in the electronic device for communicating with other devices.
In addition, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program makes a server execute the target object recommendation method in each embodiment.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by adding necessary general purpose hardware platforms, or may be implemented by a combination of hardware and software. Based on such understanding, the foregoing aspects, in essence and portions contributing to the art, may be embodied in the form of a computer program product, which may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable resource updating apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable resource updating apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable resource updating device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable resource updating apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (9)
1. A target object recommendation method, which is applied to a server, the method comprising:
responding to an acquisition request of a requester, and sending a first target list containing target objects;
determining behavior preference of the requester according to the operation type of the requester for the target object in the first target list;
correcting the acquisition request based on the behavior preference; the method specifically comprises the following steps: acquiring a target attribute carried in the acquisition request and an initial weight corresponding to the target attribute; performing weighted correction processing on the initial weight and the weight comprehensive value corresponding to the target attribute;
the weight comprehensive value is obtained by comprehensively weight processing the weight value of the target attribute after the weight value of the target attribute marked in a plurality of target objects is obtained;
screening out the target attribute and the attribute value corresponding to the target attribute for constructing the second target list based on the comparison result of the initial weight and the weight comprehensive value corresponding to the attribute value of the target attribute;
recommending a second target list containing target objects according to the corrected result, wherein the second target list specifically comprises: after finishing the correction of the acquisition request, rescreening according to the latest obtained target attribute to obtain a second target list; or after finishing the correction of the acquisition request, rescreening the first target list according to the latest obtained target attribute to obtain a second target list.
2. The method of claim 1, wherein the determining the behavior preference of the requestor according to the type of operation of the requestor for the target object in the first target list comprises:
acquiring the operation type of the requester for each target object in the first target list;
marking the weight value of the target attribute contained in each target object according to the operation type;
and determining the target attribute with a large weight value as the behavior preference according to the weight value comparison result.
3. The method according to claim 2, wherein the marking the weight value of the target attribute included in each of the target objects according to the operation type includes:
if the operation type is an offer operation, determining that the weight value of the target data contained in the target object is a first weight value;
if the operation type is concerned operation, determining that the weight value of the target data contained in the target object is a second weight value;
if the operation type is browsing operation, determining that the weight value of the target data contained in the target object is a third weight value;
wherein the first weight value is greater than the second weight value and greater than the third weight value.
4. A method according to claim 3, wherein said determining the target attribute with a large weight value as the behavior preference according to the weight value comparison result comprises:
determining weight comprehensive values of the target attribute, corresponding to the plurality of attribute values, which are marked respectively;
and determining a target attribute with a large weight integrated value as the behavior preference according to the result of comparing the sizes of the weight integrated values.
5. The method of claim 1, wherein the recommendation comprises a second target list of target objects, comprising:
acquiring feedback information of the target object aiming at the operation type;
according to the feedback information of the target object, determining the interest degree of the target object to the requester;
sorting the target objects according to the interest level of the target objects on the requester;
and generating a second target list of the target objects ordered from big to small according to the interestingness.
6. The method of claim 1, wherein the sending the first target list including the target object in response to the request for the target object from the requestor comprises:
acquiring a target object screening condition contained in the acquisition request;
and determining the target object meeting the target object screening condition, and sending a first target list containing the target object.
7. A target object recommendation device, the device comprising:
the sending module is used for responding to the acquisition request of the requester and sending a first target list containing target objects;
a determining module, configured to determine a behavior preference of the requester according to an operation type of the requester for a target object in the first target list;
the correction module is used for correcting the acquisition request based on the behavior preference; the method specifically comprises the following steps: acquiring a target attribute carried in the acquisition request and an initial weight corresponding to the target attribute; performing weighted correction processing on the initial weight and the weight comprehensive value corresponding to the target attribute;
the weight comprehensive value is obtained by comprehensively weight processing the weight value of the target attribute after the weight value of the target attribute marked in a plurality of target objects is obtained;
screening out the target attribute and the attribute value corresponding to the target attribute for constructing the second target list based on the comparison result of the initial weight and the weight comprehensive value corresponding to the attribute value of the target attribute;
the recommending module is configured to recommend a second target list including target objects according to the corrected result, and specifically includes: after finishing the correction of the acquisition request, rescreening according to the latest obtained target attribute to obtain a second target list; or after finishing the correction of the acquisition request, rescreening the first target list according to the latest obtained target attribute to obtain a second target list.
8. A computer storage medium storing a computer program which, when executed by a client, implements the target object recommendation method as claimed in claims 1 to 6.
9. An electronic device, comprising: a processor, a memory for storing one or more computer instructions, wherein the one or more computer instructions when executed by the processor implement the target object recommendation method of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609231.8A CN111914165B (en) | 2020-06-29 | 2020-06-29 | Target object recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609231.8A CN111914165B (en) | 2020-06-29 | 2020-06-29 | Target object recommendation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111914165A CN111914165A (en) | 2020-11-10 |
| CN111914165B true CN111914165B (en) | 2023-10-20 |
Family
ID=73226244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010609231.8A Active CN111914165B (en) | 2020-06-29 | 2020-06-29 | Target object recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914165B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468354A (en) * | 2021-07-23 | 2021-10-01 | 建信金融科技有限责任公司 | Method and device for recommending chart, electronic equipment and computer readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709758A (en) * | 2016-12-19 | 2017-05-24 | 浙江网新恒天软件有限公司 | Intelligent recommendation and distribution solution for service class commodities in electronic commerce products |
| CN108319646A (en) * | 2017-12-26 | 2018-07-24 | 金瓜子科技发展（北京）有限公司 | Vehicle source searching method and device based on user's history behavior |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
| CN109726267A (en) * | 2018-12-28 | 2019-05-07 | 苏州思必驰信息科技有限公司 | Story recommended method and device for Story machine |
| CN109767318A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Loan product recommended method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7634472B2 (en) * | 2003-12-01 | 2009-12-15 | Yahoo! Inc. | Click-through re-ranking of images and other data |
| US20160335372A1 (en) * | 2015-05-15 | 2016-11-17 | Sap Se | Systems and methods for search with priorities by assigning weights to query terms |
-
2020
- 2020-06-29 CN CN202010609231.8A patent/CN111914165B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709758A (en) * | 2016-12-19 | 2017-05-24 | 浙江网新恒天软件有限公司 | Intelligent recommendation and distribution solution for service class commodities in electronic commerce products |
| CN108319646A (en) * | 2017-12-26 | 2018-07-24 | 金瓜子科技发展（北京）有限公司 | Vehicle source searching method and device based on user's history behavior |
| CN109767318A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Loan product recommended method, device, equipment and storage medium |
| CN109726267A (en) * | 2018-12-28 | 2019-05-07 | 苏州思必驰信息科技有限公司 | Story recommended method and device for Story machine |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
Non-Patent Citations (2)
| Title |
|---|
| Alistair Moffat等.Incorporating User Expectations and Behavior into the Measurement of Search Effectiveness.ACM Transactions on Information Systems.2017,第35卷(第3期),1-38. * |
| 曹晓龙等.基于TF-IQF模型和图聚类的个性化搜索研究.计算机工程与科学.2011,第33卷(第12期),116-120. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111914165A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9589025B2 (en) | Correlated information recommendation | |
| US8914382B2 (en) | System and method for generation of a dynamic social page | |
| US9569499B2 (en) | Method and apparatus for recommending content on the internet by evaluating users having similar preference tendencies | |
| US20160224683A1 (en) | Blending of content item types in a social network | |
| CN105677765B (en) | Recommend the method and system of desired functional sequence to user | |
| US9760610B2 (en) | Personalized search using searcher features | |
| US20120124126A1 (en) | Contextual and task focused computing | |
| RU2757546C2 (en) | Method and system for creating personalized user parameter of interest for identifying personalized target content element | |
| US8972418B2 (en) | Dynamic generation of relevant items | |
| EP2778970A1 (en) | Facet group ranking for search results | |
| JP2018156429A (en) | Information processing device, information processing method, and program | |
| US20210109989A1 (en) | Systems and methods for automatically generating and optimizing web pages | |
| KR20210008862A (en) | Action indicator for the search action output element | |
| JP6203304B2 (en) | Information processing apparatus, information processing method, and information processing program | |
| US20180107720A1 (en) | Dynamic assignment of search parameters to search phrases | |
| US20180144305A1 (en) | Personalized contextual recommendation of member profiles | |
| US20090125503A1 (en) | Web page categorization using graph-based term selection | |
| CN111914165B (en) | Target object recommendation method, device, equipment and storage medium | |
| US8825698B1 (en) | Showing prominent users for information retrieval requests | |
| US9183299B2 (en) | Search engine for ranking a set of pages returned as search results from a search query | |
| JP6056327B2 (en) | Electronic commerce server device | |
| WO2016018467A1 (en) | Behavior influenced search ranking | |
| US9817905B2 (en) | Profile personalization based on viewer of profile | |
| JP2022544830A (en) | Multi-provider search response validation and integration | |
| US10747821B2 (en) | Optimized digital component analysis system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |