CN114048374A - Method and device for determining object to be recommended - Google Patents
Method and device for determining object to be recommended Download PDFInfo
- Publication number
- CN114048374A CN114048374A CN202111264790.0A CN202111264790A CN114048374A CN 114048374 A CN114048374 A CN 114048374A CN 202111264790 A CN202111264790 A CN 202111264790A CN 114048374 A CN114048374 A CN 114048374A
- Authority
- CN
- China
- Prior art keywords
- information
- recommended
- determining
- pool
- objects
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000002372 labelling Methods 0.000 claims abstract description 43
- 238000013136 deep learning model Methods 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 3
- 240000005020 Acaciella glauca Species 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000003499 redwood Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
-
- 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
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for determining an object to be recommended, wherein the method comprises the following steps: acquiring object statistical information and an information pool, wherein the object statistical information comprises a plurality of objects; performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool; determining the relevance between each object based on the labeled information pool; and generating a recommendation library based on the labeled information pool and the association degree, wherein the recommendation library comprises objects to be recommended corresponding to each object. All objects are marked in massive news information, and the association degree between each object is determined, so that the most relevant target object is determined according to the preset object and recommended to a user, the accuracy and comprehensiveness of user query and retrieval are effectively improved, and the user experience is improved.
Description
Technical Field
The present invention relates to the field of information management technologies, and in particular, to a method for determining an object to be recommended, a device for determining an object to be recommended, and a computer-readable storage medium.
Background
With the development of the internet, the demand of users for information query is increasing, and more scenes are needed for the users to query information. In the existing query method, a user first determines some keywords, and then directly searches the keywords through a search engine or a search platform to obtain the content of a desired query.
However, in the actual application process, the user has a more comprehensive and more accurate query demand, for example, in the process of querying the investment institutions, when the user directly queries the corresponding investment institutions through keywords, the user also has a demand of querying information of similar investment institutions or related investment institutions, while on the one hand, the prior art only pushes the investment institutions directly queried by the user, so that the limitation is large; on the other hand, under the condition of huge information amount on the internet at present, a user cannot accurately acquire investment institutions similar to or related to the retrieved investment institutions, so that the existing information query method cannot meet the actual requirements of the user.
Disclosure of Invention
In order to solve the technical problems in the prior art, embodiments of the present invention provide a method and an apparatus for determining an object to be recommended, in which all objects are labeled in massive news information and the association degree between each object is determined, so that a recommended object with a high association degree with an input object is provided for a user, the accuracy and comprehensiveness of user query and retrieval are effectively improved, and user experience is improved.
In order to achieve the above object, an embodiment of the present invention provides a method for determining an object to be recommended, where the method for determining includes: acquiring object statistical information and an information pool, wherein the object statistical information comprises a plurality of objects; performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool; determining the relevance between each object based on the labeled information pool; and generating a recommendation library based on the labeled information pool and the association degree, wherein the recommendation library comprises objects to be recommended corresponding to each object.
Preferably, the determination method further comprises: acquiring an input object; determining at least one first object to be recommended corresponding to the input object from the plurality of objects based on the association degree, and recommending the first object to be recommended.
Preferably, the determination method further comprises: acquiring a preset keyword; screening the information pool based on the preset keywords to obtain a screened information pool; and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
Preferably, the performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool includes: acquiring a preset deep learning model, wherein the preset deep learning model is generated based on the object statistical information training; and carrying out object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
Preferably, the determining the relevance between each object based on the tagged information pool includes: traversing each information in the labeled information pool in sequence; extracting all objects in the current information, and storing the common occurrence times of each object in the current information; and determining the correlation degree between each object based on the common occurrence times of all the objects in each information message.
Preferably, the determining, from the recommendation library, at least one first object to be recommended corresponding to the input object based on the association degree includes: acquiring a preset recommended quantity; sorting the relevance; and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
Preferably, the determination method further comprises: taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object; determining at least one second object to be recommended contained in all the first recommended objects; screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended; and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
Correspondingly, an embodiment of the present invention further provides a device for determining an object to be recommended, where the device includes: the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring object statistical information and an information pool, and the object statistical information comprises a plurality of objects; the labeling unit is used for performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool; the relevancy determining unit is used for determining the relevancy between each object based on the labeled information pool; and the recommendation library generating unit is used for generating a recommendation library based on the labeled information pool and the association degree, and the recommendation library comprises the objects to be recommended corresponding to each object.
Preferably, the determining device further comprises a recommending unit, and the recommending unit is configured to: acquiring an input object; determining at least one first object to be recommended corresponding to the input object from the recommendation library based on the association degree, and recommending the first object to be recommended.
Preferably, the determination apparatus further comprises a screening unit configured to: acquiring a preset keyword; screening the information pool based on the preset keywords to obtain a screened information pool; and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
Preferably, the labeling unit includes: the model acquisition module is used for acquiring a preset deep learning model, and the preset deep learning model is generated based on the object statistical information training; and the labeling module is used for performing object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
Preferably, the association degree determining unit includes: the traversing module is used for sequentially traversing each information in the labeled information pool; the frequency determining module is used for extracting all objects in the current information and storing the common occurrence frequency of each object in the current information; and the association degree determining module is used for determining the association degree between each object based on the common occurrence times of all the objects in each information message.
Preferably, the determining, from the recommendation library, at least one first object to be recommended corresponding to the input object based on the association degree includes: acquiring a preset recommended quantity; sorting the relevance; and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
Preferably, the determining apparatus further comprises a secondary recommending unit, and the secondary recommending unit is configured to: taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object; determining at least one second object to be recommended contained in all the first recommended objects; screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended; and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method provided by the embodiment of the present invention.
Through the technical scheme provided by the invention, the invention at least has the following technical effects:
by collecting news information and marking all objects, in the process of retrieval and query of subsequent users, the most relevant target object can be automatically determined according to the object detected and queried by the user and recommended to the user, so that the comprehensiveness and accuracy of user query and retrieval are effectively expanded, the user is assisted to know the relevant information of the queried investment institution in more detail, and the user experience is improved.
Meanwhile, the deep learning model trained on the basis of the object is adopted for automatic labeling, so that the accuracy and comprehensiveness of the labeled object can be effectively improved, and an accurate data basis is provided for the subsequent recommendation of the target object.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a flowchart of a specific implementation of a method for determining an object to be recommended according to an embodiment of the present invention;
fig. 2 is a flowchart of a specific implementation of determining a degree of association between objects in the method for determining an object to be recommended according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for determining an object to be recommended according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The terms "system" and "network" in embodiments of the present invention may be used interchangeably. The "plurality" means two or more, and in view of this, the "plurality" may also be understood as "at least two" in the embodiments of the present invention. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" generally indicates that the preceding and following related objects are in an "or" relationship, unless otherwise specified. In addition, it should be understood that the terms first, second, etc. in the description of the embodiments of the invention are used for distinguishing between the descriptions and are not intended to indicate or imply relative importance or order to be construed.
Referring to fig. 1, an embodiment of the present invention provides a method for determining an object to be recommended, where the method includes:
s10), acquiring object statistical information and an information pool, wherein the object statistical information comprises a plurality of objects;
s20) carrying out object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool;
s30) determining the relevance between each object based on the labeled information pool;
s40) generating a recommendation library based on the labeled information pool and the correlation degree, wherein the recommendation library comprises objects to be recommended corresponding to each object.
In one possible embodiment, in order to provide a user with an accurate recommended object, a recommendation library capable of accurately recommending an object is first established. Specifically, first, an object statistical information and an information pool are obtained, for example, in the embodiment of the present invention, the object is an investment organization, the object statistical information is investment organization statistical information stored in an enterprise database, the investment organization statistical information includes a plurality of investment organization information, each investment organization information includes information such as a name, business information, and fund information of a corresponding investment organization, and the information pool may be news information collected from the internet, for example, the information pool is established after news information within half a year of the current time is collected.
Then, object labeling is performed on each information in the information pool according to the object statistical information, and the labeled information pool is obtained, for example, the name of each object can be used as a keyword, object labeling is performed on each information in the information pool in a keyword matching mode to obtain the labeled information pool, at this time, the association degree between each object is determined based on the labeled information pool, and at this time, a recommendation library can be established based on the labeled information pool and the association degree between each object.
In the embodiment of the invention, the association degree of each object is determined according to a large amount of news information, and the recommendation library for recommending the objects is further established, so that accurate recommendation can be carried out based on the basis of big data in the subsequent object recommendation process instead of simply carrying out recommendation according to a temporary retrieval result or a retrieval result of a search engine, and the recommendation accuracy can be effectively improved.
After the creation of the recommendation library is completed, accurate recommendation service can be provided for the user. In the embodiment of the present invention, the determining method further includes: acquiring an input object; determining at least one first object to be recommended corresponding to the input object from the plurality of objects based on the association degree, and recommending the first object to be recommended.
For example, in one possible embodiment, after creating the recommendation library of the objects, an input object input by the user is first obtained, for example, the input object is an object desired to be searched by the user or an object desired to be subjected to related information acquisition, and then at least one object to be recommended that can be recommended is further determined from the recommendation library according to the degree of association between each object, for example, at least one object most related to the input object is recommended as the first object to be recommended.
In the embodiment of the invention, the association degree between each investment institution is automatically analyzed according to massive investment institution information and news information, when a user inquires a certain investment institution, the investment institution to be recommended, which is relatively associated with the investment institution, can be quickly and accurately found out, and the investment institution to be recommended is recommended to the user, so that the search surface of the user is effectively expanded on the basis of effectively improving the recommendation accuracy.
As is readily known to those skilled in the art, in the information era, the daily news information amount is very large, and therefore, if all the news information is traversed during each annotation process of the investment institution, the calculation amount is greatly increased, and the calculation efficiency is reduced.
Therefore, in order to solve the above technical problem, in an embodiment of the present invention, the determining method further includes: acquiring a preset keyword; screening the information pool based on the preset keywords to obtain a screened information pool; and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
In a possible implementation manner, before labeling each object in the news information, a preset keyword is obtained first, for example, the preset keyword may include but is not limited to keywords such as "investment", "financing", and the like, so as to filter the news information, so as to only retain the news information including the keyword, and on this basis, the object labeling is performed on each information in the screened information pool, thereby greatly reducing the amount of calculation in the labeling process, accelerating the labeling speed, and improving the labeling efficiency.
However, the above method is labeled by means of keywords, although the labeling speed is fast, the labeling accuracy and recall thereof cannot meet the actual requirements of the user, for example, in an embodiment, the keywords set by the user are redwood capital, however, the investment institution names appearing in some news are redwood investment fund, for such news, although both refer to the same investment institution, there is a certain missing label through the labeling manner of the keywords, and the actual requirements cannot be met.
In order to solve the above technical problem, in an embodiment of the present invention, the performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool includes: acquiring a preset deep learning model, wherein the preset deep learning model is generated based on the object statistical information training; and carrying out object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
In a possible implementation manner, in order to improve the accuracy of labeling the target, a deep learning model may be trained in advance, for example, in an embodiment of the present invention, an initial deep learning model is trained according to the object statistical information, and the preset deep learning model is obtained, and the preset deep learning model can effectively identify a same investment organization with similar expression.
In the embodiment of the invention, in the process of marking the investment institutions in the news information, automatic marking is carried out based on the preset deep learning model, so that the same investment institutions with similar expressions or the investment institutions which may be the investment institutions but are not recorded in the investment statistical information can be effectively identified, the marking accuracy and comprehensiveness are effectively improved, and more accurate and comprehensive associated investment institutions are provided for users in the subsequent recommendation process.
Referring to fig. 2, in the embodiment of the present invention, the determining the association degree between each object based on the tagged information pool includes:
s31) traversing each information in the labeled information pool in turn;
s32) extracting all objects in the current information and storing the common occurrence times of each object in the current information;
s33) determining a degree of association between each object based on the number of common occurrences of all objects in each information message.
In one possible implementation, after the annotated information pool is obtained, the association degree between each object is further analyzed and determined. For example, in the embodiment of the present invention, each piece of information in the post-annotation information pool is traversed sequentially, for example, the current post-annotation information pool includes 6 pieces of information, the first piece of information is analyzed first, all objects in the first piece of information are extracted first, for example, in an embodiment, the first piece of information includes A, B, C, D four investment institutions, and the four investment institutions and the common occurrence time thereof are stored, for example, in the embodiment of the present invention, after traversing the first piece of information, the investment institutions and the common occurrence times of the investment institutions with the investment institution a are: b (1), C (1) and D (1), corresponding to the investment institutions and their frequency, which co-occur with the investment institution B: the statistics of the investment institutions and the times of the investment institutions which appear together with the investment institutions C and D are the same as those of the investment institutions A (1 time), C (1 time) and D (1 time), and are not described in detail herein.
Then, the object in the second information is further extracted, for example, in the second information, which includes A, C, D, E, the investment institutions co-occurring with the investment institution a are determined and the number of the investment institutions is: b (1), C (2), D (2) and E (1), respectively, the investment entity co-occurrence with the C, D, E investment entity and its number can be determined. The association degree between each object can be determined according to the common occurrence frequency of all the objects in each information in the labeled information pool, for example, the common occurrence frequency of every two objects is used as the association degree between the two objects, and at the moment, the labeled information and the association degree between each object are stored to establish a recommendation library.
Further, in this embodiment of the present invention, the determining, from the recommendation library, at least one first object to be recommended corresponding to the input object based on the association degree includes: acquiring a preset recommended quantity; sorting the relevance; and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
After the object statistics library is established, accurate object recommendation can be performed in response to input of a user. In a possible embodiment, after determining that an input object (e.g., an input investment institution) of the user is obtained, a preset recommendation number is obtained first, for example, a recommendation number (e.g., 3) for each search of the user may be preset, then 3 investment institutions most relevant to the input investment institution are obtained according to the relevance, for example, by ranking the relevance, and according to the ranking result of the relevance, 3 investment institutions with the highest relevance to the input investment institution are determined from the obtained multiple investment institutions as first investment institutions to be recommended and are recommended to the user as final recommendation results.
In the embodiment of the invention, the association degrees of all investment institutions are analyzed and determined according to the news information, so that the most relevant or similar relevant investment institutions can be determined and recommended to the user according to the retrieval investment institutions of the user in the subsequent retrieval process of the user, thereby effectively improving the comprehensive and accurate expansion of the user retrieval and improving the retrieval experience of the user.
Further, in the embodiment of the present invention, in order to provide a more comprehensive and accurate object recommendation for a user, the determining method further includes: taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object; determining at least one second object to be recommended contained in all the first recommended objects; screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended; and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
In a possible implementation, after determining a plurality of first to-be-recommended investment institutions corresponding to the investment institutions input by the user, further taking each first to-be-recommended investment institution as a new input object, and obtaining at least one second to-be-recommended object of each new input object, for example, in an embodiment, the user inputs investment institution a, when the first to-be-recommended investment institution of the investment institution a is determined to be investment institution B, C, when it is further determined that its associated investment institution includes investment institutions A, C and D based on investment institution B, when the associated investment institution of investment institution C includes investment institution A, B, D, when all the second to-be-recommended investment institutions (A, B, C, D) are screened according to the first to-be-recommended investment institution (B, C) associated with investment institution a, and obtaining the corresponding screened second object to be recommended, for example, in the embodiment of the present invention, the second object to be recommended is the investment organization D, and at this time, the investment organization D is used as a second object to be recommended of the investment organization a, and the second object to be recommended may be recommended to the user immediately or may be recommended to the user after a delay.
In the embodiment of the invention, the secondary recommendation object of the input object is determined according to the further association object of the input object, so that the condition of missing recommendation of the input object is further effectively reduced, meanwhile, on the basis of ensuring the recommendation accuracy, the recommendation comprehensiveness of the relevant objects of the input object is effectively expanded, and the user experience is improved.
The following describes an apparatus for determining an object to be recommended according to an embodiment of the present invention with reference to the drawings.
Referring to fig. 3, based on the same inventive concept, an embodiment of the present invention provides an apparatus for determining an object to be recommended, where the apparatus includes: the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring object statistical information and an information pool, and the object statistical information comprises a plurality of objects; the labeling unit is used for performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool; the relevancy determining unit is used for determining the relevancy between each object based on the labeled information pool; and the recommendation library generating unit is used for generating a recommendation library based on the labeled information pool and the association degree, and the recommendation library comprises the objects to be recommended corresponding to each object.
In an embodiment of the present invention, the determining apparatus further includes a recommending unit, and the recommending unit is configured to: acquiring an input object; determining at least one first object to be recommended corresponding to the input object from the recommendation library based on the association degree, and recommending the first object to be recommended.
In an embodiment of the present invention, the determining apparatus further includes a screening unit, and the screening unit is configured to: acquiring a preset keyword; screening the information pool based on the preset keywords to obtain a screened information pool; and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
In an embodiment of the present invention, the labeling unit includes: the model acquisition module is used for acquiring a preset deep learning model, and the preset deep learning model is generated based on the object statistical information training; and the labeling module is used for performing object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
In an embodiment of the present invention, the association degree determining unit includes: the traversing module is used for sequentially traversing each information in the labeled information pool; the frequency determining module is used for extracting all objects in the current information and storing the common occurrence frequency of each object in the current information; and the association degree determining module is used for determining the association degree between each object based on the common occurrence times of all the objects in each information message.
In an embodiment of the present invention, the determining, from the recommendation library, at least one first object to be recommended corresponding to the input object based on the association degree includes: acquiring a preset recommended quantity; sorting the relevance; and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
In an embodiment of the present invention, the determining apparatus further includes a secondary recommending unit, and the secondary recommending unit is configured to: taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object; determining at least one second object to be recommended contained in all the first recommended objects; screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended; and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
Further, the embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the method according to the embodiment of the present invention.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention do not describe every possible combination.
Those skilled in the art will understand that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (15)
1. A method for determining an object to be recommended is characterized by comprising the following steps:
acquiring object statistical information and an information pool, wherein the object statistical information comprises a plurality of objects;
performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool;
determining the relevance between each object based on the labeled information pool;
and generating a recommendation library based on the labeled information pool and the association degree, wherein the recommendation library comprises objects to be recommended corresponding to each object.
2. The determination method according to claim 1, characterized in that the determination method further comprises:
acquiring an input object;
determining at least one first object to be recommended corresponding to the input object from the recommendation library based on the association degree, and recommending the first object to be recommended.
3. The determination method according to claim 1, characterized in that the determination method further comprises:
acquiring a preset keyword;
screening the information pool based on the preset keywords to obtain a screened information pool;
and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
4. The method of claim 1, wherein the performing object labeling on each information item in the information pool based on the object statistic information to obtain a labeled information pool comprises:
acquiring a preset deep learning model, wherein the preset deep learning model is generated based on the object statistical information training;
and carrying out object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
5. The method of claim 2, wherein determining the relevance between each object based on the tagged pool of information comprises:
traversing each information in the labeled information pool in sequence;
extracting all objects in the current information, and storing the common occurrence times of each object in the current information;
and determining the correlation degree between each object based on the common occurrence times of all the objects in each information message.
6. The determination method according to claim 5, wherein the determining at least one first object to be recommended corresponding to the input object from the recommendation library based on the association degree comprises:
acquiring a preset recommended quantity;
sorting the relevance;
and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
7. The determination method according to claim 6, characterized in that the determination method further comprises:
taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object;
determining at least one second object to be recommended contained in all the first recommended objects;
screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended;
and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
8. An apparatus for determining an object to be recommended, the apparatus comprising:
the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring object statistical information and an information pool, and the object statistical information comprises a plurality of objects;
the labeling unit is used for performing object labeling on each information in the information pool based on the object statistical information to obtain a labeled information pool;
the relevancy determining unit is used for determining the relevancy between each object based on the labeled information pool;
and the recommendation library generating unit is used for generating a recommendation library based on the labeled information pool and the association degree, and the recommendation library comprises the objects to be recommended corresponding to each object.
9. The apparatus according to claim 8, wherein the apparatus further comprises a recommending unit configured to:
acquiring an input object;
determining at least one first object to be recommended corresponding to the input object from the recommendation library based on the association degree, and recommending the first object to be recommended.
10. The apparatus according to claim 8, characterized in that the apparatus further comprises a screening unit configured to:
acquiring a preset keyword;
screening the information pool based on the preset keywords to obtain a screened information pool;
and carrying out object labeling on each information in the screened information pool based on the object statistical information to obtain a labeled information pool.
11. The apparatus according to claim 8, wherein the labeling unit includes:
the model acquisition module is used for acquiring a preset deep learning model, and the preset deep learning model is generated based on the object statistical information training;
and the labeling module is used for performing object labeling on each information in the information pool based on the preset deep learning model to obtain the labeled information pool.
12. The apparatus according to claim 9, wherein the association degree determining unit includes:
the traversing module is used for sequentially traversing each information in the labeled information pool;
the frequency determining module is used for extracting all objects in the current information and storing the common occurrence frequency of each object in the current information;
and the association degree determining module is used for determining the association degree between each object based on the common occurrence times of all the objects in each information message.
13. The apparatus according to claim 12, wherein the determining, from the recommendation library, at least one first object to be recommended corresponding to the input object based on the association degree includes:
acquiring a preset recommended quantity;
sorting the relevance;
and determining the number of objects corresponding to the preset recommendation number with the highest relevance to the input object from the recommendation library as the first object to be recommended based on the relevance ranking.
14. The apparatus according to claim 13, wherein the apparatus further comprises a secondary recommendation unit configured to:
taking the first object to be recommended as a new input object, and determining at least one second object to be recommended corresponding to the new input object;
determining at least one second object to be recommended contained in all the first recommended objects;
screening the at least one second object to be recommended based on the at least one first recommended object to obtain a screened second object to be recommended;
and taking the screened second object to be recommended as a secondary object to be recommended of the input object.
15. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264790.0A CN114048374A (en) | 2021-10-28 | 2021-10-28 | Method and device for determining object to be recommended |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264790.0A CN114048374A (en) | 2021-10-28 | 2021-10-28 | Method and device for determining object to be recommended |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114048374A true CN114048374A (en) | 2022-02-15 |
Family
ID=80206400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111264790.0A Pending CN114048374A (en) | 2021-10-28 | 2021-10-28 | Method and device for determining object to be recommended |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114048374A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2147315A2 (en) * | 2007-04-18 | 2010-01-27 | Tethys Bioscience, Inc. | Diabetes-related biomarkers and methods of use thereof |
| CN103294778A (en) * | 2013-05-13 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Method and system for pushing messages |
| CN106776881A (en) * | 2016-11-28 | 2017-05-31 | 中国科学院软件研究所 | A kind of realm information commending system and method based on microblog |
| CN109949090A (en) * | 2019-03-18 | 2019-06-28 | 深圳市小满科技有限公司 | Lead referral method, apparatus, electronic equipment and medium |
| CN111723293A (en) * | 2020-06-24 | 2020-09-29 | 上海风秩科技有限公司 | Article content recommendation method and device, electronic equipment and storage medium |
| CN112148889A (en) * | 2020-09-23 | 2020-12-29 | 平安直通咨询有限公司上海分公司 | Recommendation list generation method and device |
-
2021
- 2021-10-28 CN CN202111264790.0A patent/CN114048374A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2147315A2 (en) * | 2007-04-18 | 2010-01-27 | Tethys Bioscience, Inc. | Diabetes-related biomarkers and methods of use thereof |
| CN103294778A (en) * | 2013-05-13 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Method and system for pushing messages |
| CN106776881A (en) * | 2016-11-28 | 2017-05-31 | 中国科学院软件研究所 | A kind of realm information commending system and method based on microblog |
| CN109949090A (en) * | 2019-03-18 | 2019-06-28 | 深圳市小满科技有限公司 | Lead referral method, apparatus, electronic equipment and medium |
| CN111723293A (en) * | 2020-06-24 | 2020-09-29 | 上海风秩科技有限公司 | Article content recommendation method and device, electronic equipment and storage medium |
| CN112148889A (en) * | 2020-09-23 | 2020-12-29 | 平安直通咨询有限公司上海分公司 | Recommendation list generation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7636714B1 (en) | Determining query term synonyms within query context | |
| CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
| US20040249808A1 (en) | Query expansion using query logs | |
| CN110795627B (en) | Information recommendation method and device and electronic equipment | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN108241613A (en) | A kind of method and apparatus for extracting keyword | |
| CN103425687A (en) | Retrieval method and system based on queries | |
| CN108304444A (en) | Information query method and device | |
| CN103136228A (en) | Image search method and image search device | |
| CN111008265A (en) | Enterprise information searching method and device | |
| US9971782B2 (en) | Document tagging and retrieval using entity specifiers | |
| CN104657376A (en) | Searching method and searching device for video programs based on program relationship | |
| CN107943937B (en) | Debtor asset monitoring method and system based on judicial public information analysis | |
| JP2013174988A (en) | Similar document retrieval support apparatus and similar document retrieval support program | |
| CN107590233A (en) | A kind of file management method and device | |
| JP7256357B2 (en) | Information processing device, control method, program | |
| CN111259171A (en) | Method and server for searching multimedia resources based on word segmentation index | |
| CN107577667B (en) | Entity word processing method and device | |
| CN114048374A (en) | Method and device for determining object to be recommended | |
| CN115328945A (en) | Data asset retrieval method, electronic device and computer-readable storage medium | |
| JP2010286888A (en) | Information collection system, information collection method, and program therefor | |
| CN115146030A (en) | Official document writing method and system based on knowledge graph | |
| CN111666749A (en) | Hot article identification method | |
| CN111538902B (en) | Information pushing method and device, storage medium and electronic equipment | |
| Dorosz et al. | Latent semantic analysis evaluation of conceptual dependency driven focused crawling |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230731 Address after: Room 404-405, 504, Building B-17-1, Big data Industrial Park, Kecheng Street, Yannan High tech Zone, Yancheng, Jiangsu Province, 224000 Applicant after: Yancheng Tianyanchawei Technology Co.,Ltd. Address before: 224000 room 501-503, building b-17-1, Xuehai road big data Industrial Park, Kecheng street, Yannan high tech Zone, Yancheng City, Jiangsu Province Applicant before: Yancheng Jindi Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right |