CN109739972A - A kind of novel recommended method and equipment - Google Patents
A kind of novel recommended method and equipment Download PDFInfo
- Publication number
- CN109739972A CN109739972A CN201811614711.2A CN201811614711A CN109739972A CN 109739972 A CN109739972 A CN 109739972A CN 201811614711 A CN201811614711 A CN 201811614711A CN 109739972 A CN109739972 A CN 109739972A
- Authority
- CN
- China
- Prior art keywords
- novel
- mode
- user
- reading
- recalls
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The purpose of the application is to provide a kind of novel recommended method and equipment, the application is when user triggers and reads first object novel, in response to the reading instruction to first object novel, mode is recalled according at least one and its recalls a Weight Acquisition at least second target novel;An at least second target novel is ranked up, and an at least second target novel is sent to user equipment according to ranking results, while so that the text information of the first object novel is presented to the user by the user equipment, it can also recommend an at least second target novel to the user, so that user can also look at an at least second target novel when reading first object novel, to increase user to the reading interest of the second target novel, to which interest when user reads first object novel not only can be improved, enthusiasm and in all experiencing, user can also be increased to the user's viscosity for reading novel.
Description
Technical field
This application involves computer field more particularly to a kind of novel recommended methods and equipment.
Background technique
Currently, all kinds of electronic equipments constantly penetrates into the every aspect of people's life.Wherein, light due to carrying
Property, more and more users like through electronic equipment (such as mobile phone, PAD etc.) read books.But Most users read novel
With randomness and lack patience, this just makes reading novel become to have a glance at, and leading to user, not only reading interest declines, and may be used also
It can be lost a part and read user.
Summary of the invention
The purpose of the application is to provide a kind of novel recommended method and equipment, to improve product when user reads novel
Polarity, Experience Degree and user's viscosity.
According to the one aspect of the application, a kind of novel recommended method is provided, wherein the described method includes:
It reads and instructs in response to first object novel, mode is recalled based at least one and its recalls weight, obtain at least
One the second target novel;
An at least second target novel is ranked up, and will at least second mesh according to ranking results
Mark novel is sent to user equipment.
Further, in above-mentioned novel recommended method, described read in response to first object novel is instructed, and is based at least one
Kind recalls mode and its recalls weight, before an acquisition at least second target novel, further includes:
Default at least one recalls mode, and that recalls mode described in determining every kind recalls weight.
Further, in above-mentioned novel recommended method, determine every kind described in the mode of recalling recall weight, comprising:
According to the history reading information for the user for reading the first object novel, at least one recall mode into
Row right assessment, obtain every kind described in recall the corresponding recommendation weight of mode.
Further, it in above-mentioned novel recommended method, reads and instructs in response to first object novel, called together based at least one
It the mode of returning and its recalls weight, obtains an at least second target novel, comprising:
It reads and instructs in response to first object novel, it is corresponding to determine that at least one every kind recalled in mode recalls mode
Novel to be recommended;
Based on recalling the corresponding novel to be recommended of mode described at least one every kind recalled in mode and described call together
Weight is returned, determine and obtains an at least second target novel.
Further, it in above-mentioned novel recommended method, reads and instructs in response to first object novel, determine that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the initial label reading of user and novel label are based on, in novel data
It is recalled in library, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode.
Further, it in above-mentioned novel recommended method, reads and instructs in response to first object novel, determine that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the determining user with the reading first object novel, which exists, to be associated with
The good friend user of system;
History reading information based on the good friend user carries out collaborative filtering in novel database, determines at least one
It plants every kind recalled in mode and recalls the corresponding novel to be recommended of mode.
Further, it in above-mentioned novel recommended method, reads and instructs in response to first object novel, determine that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the history based on the user for reading the first object novel reads letter
Breath is recalled in novel database, and it is corresponding to be recommended small to determine that at least one every kind recalled in mode recalls mode
It says.
Further, in above-mentioned novel recommended method, an at least second target novel is ranked up, and according to
An at least second target novel is sent to user equipment by ranking results, comprising:
An at least second target novel is ranked up based on machine learning algorithm;
An at least second target novel is sequentially sent to the user equipment according to ranking results.
According to the another aspect of the application, a kind of computer-readable medium is additionally provided, is stored thereon with computer-readable
Instruction when the computer-readable instruction can be executed by processor, makes the processor realize such as above-mentioned novel recommended method.
According to the another aspect of the application, a kind of equipment is additionally provided, wherein the equipment includes:
One or more processors;
Computer-readable medium, for storing one or more computer-readable instructions,
When one or more of computer-readable instructions are executed by one or more of processors, so that one
Or multiple processors realize such as above-mentioned novel recommended method.
Compared with prior art, the application is when user triggers and reads first object novel, in response to small to first object
The reading instruction said, recalls mode according at least one and its recalls a Weight Acquisition at least second target novel;To described
At least a second target novel is ranked up, and an at least second target novel is sent to use according to ranking results
Family equipment can also be to while so that the text information of the first object novel is presented to the user by the user equipment
The user recommends an at least second target novel, so that user can also look at least when reading first object novel
One the second target novel is read with increasing user to the reading interest of the second target novel so that user not only can be improved
Interest, enthusiasm and in all experiencing when reading first object novel, can also increase user to the user's viscosity for reading novel.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows a kind of flow diagram of novel recommended method according to the application one aspect;
Fig. 2 shows recommend block schematic illustration in a kind of novel recommended method according to the application one aspect.
The same or similar appended drawing reference represents the same or similar component in attached drawing.
Specific embodiment
The application is described in further detail with reference to the accompanying drawing.
In a typical configuration of this application, terminal, the equipment of service network and trusted party include one or more
Processor (CPU), input/output interface, network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or
Any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, computer
Readable medium does not include non-temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
As shown in Figure 1, a kind of process of novel recommended method of the application one aspect illustrates the first object novel phase
During associated second target novel.This method comprises: step S11, step S12, step S13, step S14, step
S21, step S22, step S23 and step S24, specifically comprise the following steps:
In actual application scenarios, user is reading the first object novel when reading novel, for the ease of user
When can also recognize the related information of the first object novel, to improve the enthusiasm that user reads the first object novel,
Step S11 reads in response to first object novel and instructs, recalls mode based at least one and its recall weight, obtains at least
One the second target novel;Here, the mode of recalling includes but is not limited to: recalling mode, based on cooperateing with based on content
Filter recalls mode, mode is recalled in the combination based on content and collaborative filtering and recalls mode based on what user's history was read,
In, the mode of recalling based on collaborative filtering can be described based on content and collaborative filtering using linear (line) algorithm
The combination mode of recalling can use context-aware internet startup disk (Context-Aware Network Embedding, CANE)
Algorithm etc..
Step S12 is ranked up an at least second target novel, and according to ranking results at least one by described in
Portion's the second target novel is sent to user equipment, realizes the sequence at least one the second target novel of acquisition, and according to
Second target novel is sent to the user equipment by ranking results.
Above-mentioned steps S11 and step S12 is not only realized when user reads first object novel, and triggering obtains at least
The operation of one the second target novel, also will acquire after at least a second target novel is ranked up, according to ranking results
An at least second target novel is sent to the corresponding user equipment of user for reading the first object novel, so that institute
While stating user equipment and be presented to the user the text information of the first object novel, can also recommend to the user to
A few second target novel, so as to can also look at least second target when reading first object novel small by user
It says, to increase user to the reading interest of the second target novel, so that user, which not only can be improved, reads first object novel
When interest, enthusiasm and in all experiencing, user can also be increased to the user's viscosity for reading novel.
In the present embodiment, the step S11 reads in response to first object novel and instructs, and recalls mode based at least one
And its weight is recalled, before an acquisition at least second target novel, further includes:
Default at least one recalls mode, and that recalls mode described in determining every kind recalls weight, here, this recalls weight
Being used to indicate the novel to be recommended recalled based on the mode of recalling can determine as the accounting of the second target novel.
For example, for the ease of user corresponding second target novel can be recommended to user when reading novel, it is simultaneously
Agree with the novel that user is usually read convenient for the second target novel of recommendation and can be preset in advance before the step S11
It is one or more to recall mode, the mode of recalling can be based on content recall mode, based on collaborative filtering recall mode,
Combination based on content and collaborative filtering recalls mode and recalls one of mode or a variety of based on user's history reading, with
The subsequent degrees of association based on one or more second target novels for recalling mode determination are improved, which is second mesh
Mark the relevance and compatible degree between novel and first object novel;Preset it is one or more recall mode after, in order to just
It can be determined as the second mesh in fictitious specific how many novel to be recommended to be recommended that clearly every kind of mode of recalling is recalled
Novel is marked, also need to recall mode described in determining every kind recalls weight, to be determined that every kind of mode of recalling corresponds to institute subsequent
After the novel to be recommended recalled, the weight of recalling that can recall mode based on every kind filters out every kind to recall mode corresponding wait push away
The second target novel and quantity can be determined as by recommending novel.
Then above-described embodiment of the application, the mode of recalling described in every kind of determination in the step S11 are recalled weight, are wrapped
It includes:
According to the history reading information for the user for reading the first object novel, at least one recall mode into
Row right assessment, obtain every kind described in recall the corresponding recommendation weight of mode.Here, the history reading information of the user includes
But be not limited to: user's amount of reading, reading type, reading time section, reading depth and reading rate etc. are able to reflect user's history
The relevant information of reading.
For example, in the increase for the amount of reading for reading novel with user, the type and reading of the novel that user needs to read
Preference also can be with change, then the step S11 can in real time or periodically obtain the user's for reading the first object novel
History reading information, and the history reading information of the user according to acquisition, weigh at least one mode of recalling
Reevaluating, obtain every kind described in recall the corresponding recommendation weight of mode, for example, if the preset mode of recalling includes based on content
Recall mode, based on collaborative filtering recall mode and based on user's history read recall mode, when going through from the user
It can be seen that the amount of reading of user is very big and user is mainly partial to read by this based on user's history reading in history reading information
The novel recalled of the mode of recalling and from novel content of text information of reading of user etc. it can be seen that user is also biased to
In the novel that the mode of recalling based on content of reading is recalled, then in the history reading information according to the user to the user
The reading preference for reading the novel that the mode of recalling described at least one every kind recalled in mode is recalled carries out weight and comments
After estimating, obtain above-mentioned three kinds and recall in mode to recall mode, recalling mode and be based on based on collaborative filtering based on content
The weight of recalling for recalling mode that user's history is read is respectively as follows: 35%, 5% and 60%, so that subsequent recall weight according to this
Small the second target novel for determining to send to user equipment that is right to be recommended recalled from the corresponding mode of recalling, realization pair
The calculating and determination of every kind of weight for recalling mode.
In the present embodiment, the step S11 reads in response to first object novel and instructs, and recalls mode based at least one
And its weight is recalled, obtain an at least second target novel, comprising:
It reads and instructs in response to first object novel, it is corresponding to determine that at least one every kind recalled in mode recalls mode
Novel to be recommended;
Based on recalling the corresponding novel to be recommended of mode described at least one every kind recalled in mode and described call together
Weight is returned, determine and obtains an at least second target novel.
For example, being respectively as follows: the side of recalling based on content if preset at least one, which recalls mode, recalls mode including 4 kinds
Formula, recalling mode, mode is recalled in the combination based on content and collaborative filtering and being based on user's history based on collaborative filtering are read
Recall mode, meanwhile, if based on content recall mode, based on collaborative filtering recall mode, based on content with cooperateed with
The combination of filter recall mode and based on user's history read recall mode recall weight be respectively as follows: 20%, 10%, 25% and
45%, then when user reads the first object novel, reads and instruct in response to first object novel, if recalling based on content
The quantity for the novel to be recommended that mode is recalled is 10, the novel to be recommended that the mode of recalling based on collaborative filtering is recalled
Quantity is 20, and the quantity for the novel to be recommended that the combination mode of recalling based on content and collaborative filtering is recalled is 8 and base
In the quantity of novel to be recommended that the mode of recalling that user's history is read is recalled be 40;Then, it is recalled respectively according to every kind
The corresponding novel to be recommended of mode can be used as the quantity of the second target novel, wherein based on content to recall mode corresponding
It says for 10 fictitious 2 and is confirmed as the second target novel, mode is corresponding 20 small is right for recalling based on collaborative filtering
2 say and be confirmed as the second target novel, recall mode corresponding 8 fictitious 2 based on content and collaborative filtering
It says and is confirmed as the second target novel, and recall mode corresponding 40 fictitious 18 based on what user's history was read and say quilt
It is determined as the second target novel, and then determines based on recalling the second target novel that mode determines in above-mentioned 4 there is 2+2+2+18=
24, and this 24 the second target novels are obtained, it realizes and mode is recalled according at least one and its recalls weight, to determine simultaneously
Obtain an at least second target novel.
Then above-described embodiment of the application, reading in the step S11 in response to first object novel instruct, determine
At least one every kind recalled in mode recalls the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the initial label reading of user and novel label are based on, in novel data
It is recalled in library, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode.Here, the use
When the initial label reading in family includes but is not limited to that user initially reads novel, the initial reading being arranged to novel application program is marked
Label, such as war label reading, history label reading and swordsman's label reading, so as to novel application program is subsequent can be to user
Recommend novel corresponding with the initial label reading;The novel label is used to indicate the user and adds in history reading process
The label or user's future of the label reading added or the novel types of user concern want the label for the novel types read
Deng.For example, reading and instructing in response to first object novel, can be said according to user's initial log in user when reading novel
Novel label that the initial label reading of the user being arranged when novel application program and user add in history reading process, user
The novel label of novel types of interest and user's future want the label for the novel types read when usually reading, in novel
It is recalled in database, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode, realize
The corresponding determination with recommendation novel of mode is recalled to every kind.
Then above-described embodiment of the application, reading in the step S11 in response to first object novel instruct, determine
At least one every kind recalled in mode recalls the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the determining user with the reading first object novel, which exists, to be associated with
The good friend user of system;Here, the good friend user be used to indicate with read the first object novel user there are incidence relations
User, the incidence relation is either the good friend user that friend relation is also possible to the user recommends the reading of the user
User.
History reading information based on the good friend user carries out collaborative filtering in novel database, determines at least one
It plants every kind recalled in mode and recalls the corresponding novel to be recommended of mode.
For example, reading and instructing in response to first object novel in user when reading novel, the first mesh is read according to current
There are the good friend users of incidence relation with the user for the user's lookup for marking novel, and the good friend is obtained after finding the good friend user
The history reading information of user;Then, it according to the history reading information of the good friend user, is cooperateed in novel database
Filtering, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode, realizes and has according to user
There is the history reading information of the good friend user of friend relation to recall novel to be recommended, so as to subsequent according to the novel to be recommended
Determine the second target novel for sending to user equipment, so that user is while reading first object novel, it can be timely
Solve that there are the second target novels that the good friend of friend relation may read with it, so that improving user reads the same of interest
When, so that user is understood the novel that its good friend user read to excite user to read the interest of the second target novel, into one
Step improves user's reading experience degree and user's viscosity.
Then above-described embodiment of the application, reading in the step S11 in response to first object novel instruct, determine
At least one every kind recalled in mode recalls the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the history based on the user for reading the first object novel reads letter
Breath is recalled in novel database, and it is corresponding to be recommended small to determine that at least one every kind recalled in mode recalls mode
It says.
For example, the continuous promotion of the amount of reading with the user for reading the first object novel, it can going through from user
Information of the user in history reading process is well understood in history reading information, which includes but is not limited to that the user goes through
Amount of reading, reading novel length, reading novel types, reading novel frequency and reading novel style that history is read etc..In user
When reading first object novel, reads and instruct in response to first object novel, obtain the history reading information of the user;It
Afterwards, in order to more precisely compute and determine that every kind is recalled the corresponding novel to be recommended of mode, the step S11 is according to the user's
History reading information is recalled in novel database, and it is corresponding to determine that at least one every kind recalled in mode recalls mode
Novel to be recommended, realizes the history reading information by user to determine that every kind is recalled the corresponding novel to be recommended of mode, with
Continue after an action of the bowels and determine that the second target novel sent to user equipment more meets the reading requirement of user according to the novel to be recommended,
To meet user while reading first object novel, it can recognize that the second target interested to the user is small in time
It says, so that save user searches the energy for needing the novel read after reading first object novel, not only increases user
Reading experience degree, also enhance user read novel when user's viscosity.
Then above-described embodiment of the application, the step S12 are ranked up an at least second target novel,
And an at least second target novel is sent to user equipment according to ranking results, comprising:
An at least second target novel is ranked up based on machine learning algorithm;It will be described according to ranking results
At least a second target novel is sequentially sent to the user equipment.Here, the machine learning algorithm includes but is not limited to:
Linear regression algorithm (Linear Regression, LR), XGBoost enhancing algorithm and LightGBM gradient lifting scheme algorithm
Deng.
For example, when user reads first object novel, it is determined that need at least second mesh pushed to the user
After marking novel, in order to avoid disposably push to user push caused by a determining at least second target novel effect compared with
Difference and user can not disposably receive many push novels when reading, and the application is determining an at least second target novel
Afterwards, if at least second target novel of the determination is 8 the second target novels, be respectively as follows: novel 1, novel 2, novel 3,
Novel 4, novel 5, novel 6, novel 7 and novel 8 are then ranked up according to 8 novels of machine learning algorithm doubling, are sorted
As a result are as follows: novel 6, novel 2, novel 4, novel 8, novel 1, novel 7, novel 3 and novel 5, later, according to this 8 novels
Ranking results are as follows: novel 6, novel 2, novel 4, novel 8, novel 1, novel 7, novel 3 and novel 5 by 8 novels sequentially
It is sent to the user equipment, for example, first sending novel 6 to the user equipment, then sends novel to the user equipment
2 ... ..., novel 5 finally is sent to the user equipment, so that user equipment is during user reads novel, with readding
When reading the different content of text information of the novel, Xiang Suoshu user recommends the second different target novels, has reached in user
During reading novel, the purpose of the second different target novels is sequentially pushed to user, further improves user's reading
Interest, enthusiasm and user's viscosity during novel.
As shown in Fig. 2, the pre-set mode of recalling includes but is not limited in one practical application scene of the application: being based on
What content was recalled recalls mode, recalls mode, based on content and collaborative filtering (relationship) based on what collaborative filtering (relationship) was recalled
Recall recall mode and user's history based on user's real reading situation reads recalling in mode of carrying out that supplement recalls
It is one or more, preset for carrying out carrying out weight to every kind of mode of recalling after at least one that novel is recalled recalls mode
Assessment, obtain every kind recall mode recall weight.Wherein, based on content recall the corresponding novel to be recommended of mode according to
The initial label reading in family and novel label recall it is determining, based on collaborative filtering (relationship) recall to recall mode corresponding
Novel to be recommended recall using linear regression scheduling algorithm determining, is called together based on what content and collaborative filtering (relationship) were recalled
Return the corresponding novel to be recommended of mode using context-aware internet startup disk algorithm: CANE recall it is determining, in order to protect
Demonstrate,prove novel to be recommended comprehensive recalled and accurate fixed, also according to user's real reading situation user's history reading information into
Capable supplement calls back determination and recalls the corresponding novel to be recommended of mode based on what user's history was read;Then, it is recalled according to every kind
Mode recall weight carry out equal proportion extract it is corresponding recall the corresponding novel to be recommended of mode and be determined as the second target novel, and
The corresponding novel moderate proportions to be recommended of mode are recalled by every kind to put forward to be determined as the second target novel to merge, and are obtained most
At least second target novel sent to user equipment is needed afterwards;Later, machine learning algorithm is used, for example, linear return
Reduction method (Linear Regression, LR), XGBoost enhancing algorithm and LightGBM gradient lifting scheme algorithm etc. are to true
At least second target novel made is ranked up, and at least a second target novel will sequentially be sent out according to ranking results
User is given to set so that user equipment with read the first object novel different content of text information when, to institute
It states user and recommends the second different target novels, reached during user reads novel, sequentially pushed to user different
The second target novel purpose, further improve user read novel during interest, enthusiasm and user's viscosity.
According to the another aspect of the application, a kind of computer-readable medium is additionally provided, is stored thereon with computer-readable
Instruction when the computer-readable instruction can be executed by processor, makes the processor realize such as above-mentioned novel recommended method.
According to the another aspect of the application, a kind of equipment is additionally provided, wherein the equipment includes:
One or more processors;
Computer-readable medium, for storing one or more computer-readable instructions,
When one or more of computer-readable instructions are executed by one or more of processors, so that one
Or multiple processors realize such as above-mentioned novel recommended method.
Here, the detailed content of each embodiment in the equipment recommended for novel, for details, reference can be made to above-mentioned small
The corresponding part of recommended method embodiment is said, here, repeating no more.
In conclusion the application user trigger read first object novel when, in response to being read to first object novel
Reading instruction recalls mode according at least one and its recalls a Weight Acquisition at least second target novel;To described at least one
Portion's the second target novel is ranked up, and an at least second target novel is sent to user according to ranking results and is set
It is standby, it, can also be to described while so that the text information of the first object novel is presented to the user by the user equipment
User recommends an at least second target novel, so that user can also look at least one when reading first object novel
Second target novel, to increase user to the reading interest of the second target novel, so that user, which not only can be improved, reads the
Interest, enthusiasm when one target novel and in all experiencing, can also increase user to the user's viscosity for reading novel.
It should be noted that the application can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, the software program of the application can be executed to implement the above steps or functions by processor.Similarly, the application
Software program (including relevant data structure) can be stored in computer readable recording medium, for example, RAM memory,
Magnetic or optical driver or floppy disc and similar devices.In addition, hardware can be used to realize in some steps or function of the application, example
Such as, as the circuit cooperated with processor thereby executing each step or function.
In addition, a part of the application can be applied to computer program product, such as computer program instructions, when its quilt
When computer executes, by the operation of the computer, it can call or provide according to the present processes and/or technical solution.
And the program instruction of the present processes is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal-bearing mediums and transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, including a device according to one embodiment of the application, which includes using
Memory in storage computer program instructions and processor for executing program instructions, wherein when the computer program refers to
When enabling by processor execution, method and/or skill of the device operation based on aforementioned multiple embodiments according to the application are triggered
Art scheme.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case where without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and scope of the present application is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the application.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.That states in device claim is multiple
Unit or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to table
Show title, and does not indicate any particular order.
Claims (10)
1. a kind of novel recommended method, wherein the described method includes:
It reads and instructs in response to first object novel, mode is recalled based at least one and its recalls weight, obtain at least one
Second target novel;
An at least second target novel is ranked up, and according to ranking results that at least second target is small
It says and is sent to user equipment.
2. being based at least one according to the method described in claim 1, wherein, described read in response to first object novel instructs
Kind recalls mode and its recalls weight, before an acquisition at least second target novel, further includes:
Default at least one recalls mode, and that recalls mode described in determining every kind recalls weight.
3. according to the method described in claim 2, wherein it is determined that the mode of recalling described in every kind recalls weight, comprising:
According to the history reading information for the user for reading the first object novel, at least one mode of recalling is weighed
Reevaluating, obtain every kind described in recall the corresponding recommendation weight of mode.
4. according to the method described in claim 3, wherein, reading and instructing in response to first object novel, called together based at least one
It the mode of returning and its recalls weight, obtains an at least second target novel, comprising:
It reads and instructs in response to first object novel, it is corresponding wait push away to determine that at least one every kind recalled in mode recalls mode
Recommend novel;
Based on recalling the corresponding novel to be recommended of mode and the power of recalling described at least one every kind recalled in mode
Weight determines and obtains an at least second target novel.
5. according to the method described in claim 4, wherein, reading and instructing in response to first object novel, determine that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the initial label reading of user and novel label are based on, in novel database
It is recalled, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode.
6. according to the method described in claim 5, wherein, reading and instructing in response to first object novel, determine that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, determine that there are incidence relations with the user of the reading first object novel
Good friend user;
History reading information based on the good friend user, carries out collaborative filtering in novel database, determines that at least one is called together
Every kind in the mode of returning is recalled the corresponding novel to be recommended of mode.
7. method according to claim 5 or 6, wherein read and instruct in response to first object novel, determine at least one
It recalls every kind in mode and recalls the corresponding novel to be recommended of mode, comprising:
It reads and instructs in response to first object novel, the history reading information based on the user for reading the first object novel exists
It is recalled in novel database, determines that at least one every kind recalled in mode recalls the corresponding novel to be recommended of mode.
8. according to the method described in claim 7, wherein, be ranked up to an at least second target novel, and according to
An at least second target novel is sent to user equipment by ranking results, comprising:
An at least second target novel is ranked up based on machine learning algorithm;
An at least second target novel is sequentially sent to the user equipment according to ranking results.
9. a kind of computer-readable medium, is stored thereon with computer-readable instruction, the computer-readable instruction can be processed
When device executes, the processor is made to realize such as method described in any item of the claim 1 to 8.
10. a kind of equipment, wherein the equipment includes:
One or more processors;
Computer-readable medium, for storing one or more computer-readable instructions,
When one or more of computer-readable instructions are executed by one or more of processors, so that one or more
A processor realizes such as method described in any item of the claim 1 to 8.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811614711.2A CN109739972A (en) | 2018-12-27 | 2018-12-27 | A kind of novel recommended method and equipment |
PCT/CN2019/123979 WO2020135001A1 (en) | 2018-12-27 | 2019-12-09 | Novel recommendation method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811614711.2A CN109739972A (en) | 2018-12-27 | 2018-12-27 | A kind of novel recommended method and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109739972A true CN109739972A (en) | 2019-05-10 |
Family
ID=66361472
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811614711.2A Pending CN109739972A (en) | 2018-12-27 | 2018-12-27 | A kind of novel recommended method and equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109739972A (en) |
WO (1) | WO2020135001A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110502299A (en) * | 2019-08-12 | 2019-11-26 | 南京大众书网图书文化有限公司 | It is a kind of for providing the method and apparatus of novel information |
WO2020135001A1 (en) * | 2018-12-27 | 2020-07-02 | 上海连尚网络科技有限公司 | Novel recommendation method and apparatus |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
US20150379612A1 (en) * | 2009-03-31 | 2015-12-31 | Richrelevance, Inc. | Multi-strategy generation of product recommendations |
CN105488662A (en) * | 2016-01-07 | 2016-04-13 | 北京歌利沃夫企业管理有限公司 | Bi-directional recommendation-based online recruitment system |
US20160188734A1 (en) * | 2014-12-30 | 2016-06-30 | Socialtopias, Llc | Method and apparatus for programmatically synthesizing multiple sources of data for providing a recommendation |
CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
CN106897284A (en) * | 2015-12-17 | 2017-06-27 | 腾讯科技(深圳)有限公司 | The recommendation method and device of e-book |
CN106997347A (en) * | 2016-01-22 | 2017-08-01 | 华为技术有限公司 | Information recommendation method and server |
CN107656938A (en) * | 2016-07-26 | 2018-02-02 | 北京搜狗科技发展有限公司 | It is a kind of to recommend method and apparatus, a kind of device for being used to recommend |
CN107949843A (en) * | 2015-09-04 | 2018-04-20 | 株式会社东芝 | Item recommendation system, item recommendation method and program |
CN108509534A (en) * | 2018-03-15 | 2018-09-07 | 华南理工大学 | Individualized music commending system based on deep learning and its implementation |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106682012B (en) * | 2015-11-06 | 2020-12-01 | 阿里巴巴集团控股有限公司 | Commodity object information searching method and device |
US10860646B2 (en) * | 2016-08-18 | 2020-12-08 | Spotify Ab | Systems, methods, and computer-readable products for track selection |
CN106611050B (en) * | 2016-12-22 | 2018-08-03 | 掌阅科技股份有限公司 | E-book recommends method, apparatus and server |
CN109739972A (en) * | 2018-12-27 | 2019-05-10 | 上海连尚网络科技有限公司 | A kind of novel recommended method and equipment |
-
2018
- 2018-12-27 CN CN201811614711.2A patent/CN109739972A/en active Pending
-
2019
- 2019-12-09 WO PCT/CN2019/123979 patent/WO2020135001A1/en active Application Filing
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150379612A1 (en) * | 2009-03-31 | 2015-12-31 | Richrelevance, Inc. | Multi-strategy generation of product recommendations |
CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
US20160188734A1 (en) * | 2014-12-30 | 2016-06-30 | Socialtopias, Llc | Method and apparatus for programmatically synthesizing multiple sources of data for providing a recommendation |
CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
CN107949843A (en) * | 2015-09-04 | 2018-04-20 | 株式会社东芝 | Item recommendation system, item recommendation method and program |
CN106897284A (en) * | 2015-12-17 | 2017-06-27 | 腾讯科技(深圳)有限公司 | The recommendation method and device of e-book |
CN105488662A (en) * | 2016-01-07 | 2016-04-13 | 北京歌利沃夫企业管理有限公司 | Bi-directional recommendation-based online recruitment system |
CN106997347A (en) * | 2016-01-22 | 2017-08-01 | 华为技术有限公司 | Information recommendation method and server |
CN107656938A (en) * | 2016-07-26 | 2018-02-02 | 北京搜狗科技发展有限公司 | It is a kind of to recommend method and apparatus, a kind of device for being used to recommend |
CN108509534A (en) * | 2018-03-15 | 2018-09-07 | 华南理工大学 | Individualized music commending system based on deep learning and its implementation |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020135001A1 (en) * | 2018-12-27 | 2020-07-02 | 上海连尚网络科技有限公司 | Novel recommendation method and apparatus |
CN110502299A (en) * | 2019-08-12 | 2019-11-26 | 南京大众书网图书文化有限公司 | It is a kind of for providing the method and apparatus of novel information |
CN110502299B (en) * | 2019-08-12 | 2021-05-14 | 南京大众书网图书文化有限公司 | Method and equipment for providing novel information |
Also Published As
Publication number | Publication date |
---|---|
WO2020135001A1 (en) | 2020-07-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108595642A (en) | The method and apparatus of information in a kind of search for application | |
US8751472B2 (en) | User behavior model for contextual personalized recommendation | |
US10229160B2 (en) | Search results based on a search history | |
CN109522488A (en) | A kind of information recommendation method and equipment | |
US20140324414A1 (en) | Method and apparatus for displaying emoticon | |
US9264502B2 (en) | Download resource recommendation method, system and storage medium | |
CN108549569A (en) | The method and apparatus of information in a kind of search for application | |
CN107231485B (en) | Method and device for establishing event reminding | |
CN102831170A (en) | Pushing method and device of event information | |
US7797314B2 (en) | Adaptive searching | |
CN107832332A (en) | The method, apparatus and electronic equipment for recommending word are generated in navigating search frame | |
US9621507B2 (en) | Control method and apparatus for data display | |
US8082291B2 (en) | Identifying relevant data from unstructured feeds | |
CN109739972A (en) | A kind of novel recommended method and equipment | |
WO2009133232A1 (en) | Method, apparatus, and computer program product for providing usage analysis | |
CN106354841B (en) | Method and device for testing recommendation algorithm | |
US8825698B1 (en) | Showing prominent users for information retrieval requests | |
CN103078782A (en) | Friend note recommendation note implementation method and system | |
CN113950678A (en) | Application pushing method and related device | |
CN113220557A (en) | Cold-start recommendation model evaluation method, system, computer device and storage medium | |
CN111143695B (en) | Searching method, searching device, server and storage medium | |
CN111045031B (en) | SBAS message automatic arranging method and device and storage medium | |
CN104111926A (en) | Generation method and generation device for attention recommending list of address book | |
EP3318021B1 (en) | Managing and indexing communication data, and recommending communication type | |
CN103853711A (en) | Text information processing method and device |
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 |