CN105183731B - Recommendation information generation method, device and system - Google Patents
Recommendation information generation method, device and system Download PDFInfo
- Publication number
- CN105183731B CN105183731B CN201410244317.XA CN201410244317A CN105183731B CN 105183731 B CN105183731 B CN 105183731B CN 201410244317 A CN201410244317 A CN 201410244317A CN 105183731 B CN105183731 B CN 105183731B
- Authority
- CN
- China
- Prior art keywords
- recommendation
- value
- determining
- information
- factor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a recommendation information generation method, a recommendation information generation device and a recommendation information generation system. That is to say, in the recommendation information generation method provided in the embodiment of the present application, the target recommendation value is a recommendation value that integrates the original recommendation value and the evaluation text information, and since the evaluation text information is a factor often considered by a user, in the embodiment of the present application, the effective information amount included in the target recommendation value is increased, so that the recommendation value better meets the user requirement, and thus the accuracy of the recommendation information is improved.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method, an apparatus, and a system for generating recommendation information.
Background
With the continuous development of the internet, users are more and more used to select target objects, such as videos, audios and the like, according to the recommendation information of each object in the internet.
At present, recommendation information is mainly generated by a recommendation system according to a recommendation value of an object. Namely, the recommendation system recommends the recommendation value of each object to the user, and the user selects the target object according to the recommendation value.
The inventor researches and discovers that at present, the recommended value of the object is obtained by the following modes: and collecting the recommendation values of the object after the user experiences the object, summing the recommendation values and taking the average value as the final recommendation value of the object after collecting the recommendation values of a plurality of users to the object. And on the basis, generating recommendation information of the object to the user according to the last recommendation value of the object so that the user can select the target object.
It can be seen that, at present, recommendation information can only be generated singly according to the dimension of the user recommendation value, that is, the generation dimension of the recommendation information is single, so that the precision of the recommendation information is low.
Disclosure of Invention
The invention aims to provide a recommendation information generation method, a recommendation information generation device and a recommendation information generation system, so as to improve the precision of recommendation information.
In order to achieve the purpose, the invention provides the following technical scheme:
a recommendation information generation method includes:
acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects;
determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and generating first recommendation information of the object according to the target recommendation value.
A recommendation information generating apparatus comprising:
the acquisition module is used for acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects;
the first determining module is used for determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
the second determining module is used for determining the value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
the third determination module is used for determining the target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and the first generation module is used for generating first recommendation information of the object according to the target recommendation value.
A recommendation information generating system comprising:
the acquisition server is used for acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects;
the recommendation value determining server is used for determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value; determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information; determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and the recommendation information generation server is used for generating first recommendation information of the object according to the target recommendation value.
According to the scheme, the recommendation information generation method, the recommendation information generation device and the recommendation information generation system provided by the application determine the target recommendation value of the object from at least two dimensions (including the original recommendation value corresponding to the object and the evaluation text information corresponding to the object), and then generate recommendation information according to the target recommendation value. That is to say, in the recommendation information generation method provided in the embodiment of the present application, the target recommendation value is a recommendation value that integrates the original recommendation value and the evaluation text information, and since the evaluation text information is a factor often considered by a user, in the embodiment of the present application, the effective information amount included in the target recommendation value is increased, so that the recommendation value better meets the user requirement, and thus the accuracy of the recommendation information is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an implementation of a recommendation information generation method according to an embodiment of the present application;
fig. 2 is a flowchart illustrating an implementation of a step of determining a value of a second recommendation factor corresponding to evaluation text information according to the evaluation text information according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a recommendation information generation apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a second determining module provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of a third determining module provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an obtaining module according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a first determining module according to an embodiment of the present disclosure;
fig. 8 is another schematic structural diagram of a recommendation information generation apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a recommendation information generation apparatus according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a recommendation information generation apparatus according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of a recommendation information generation apparatus according to an embodiment of the present application;
fig. 12 is a schematic structural diagram of a recommendation information generation system according to an embodiment of the present application;
fig. 13 is a schematic structural diagram of an information processing system according to an embodiment of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be practiced otherwise than as specifically illustrated.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of an implementation of a recommendation information generation method according to an embodiment of the present application, where the implementation of the recommendation information generation method may include:
step S11: acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects;
the object may be a video, audio or book or other item to be recommended, such as an electronic product or the like.
The original recommendation value corresponding to the object is a recommendation value obtained by collecting recommendation values of a plurality of users to the object, summing the recommendation values and then taking a mean value.
The evaluation text information corresponding to the object refers to evaluation information of the object by the user.
In the embodiment of the application, recommendation factor information can be acquired from a source website. The source website can be a community website, or an e-commerce website, etc.
Step S12: determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
when the recommendation factor information is obtained from a source website, the value of the first recommendation factor may be the original recommendation value obtained.
Step S13: determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
in the embodiment of the application, the evaluation text information is used as a basis for determining the value of the second recommendation factor.
The execution sequence of steps S12 and S13 is not specifically limited, and step S12 may be executed first, and then step S13 may be executed; step S13 may be executed first, and then step S14 may be executed; alternatively, step S13 is executed in synchronization with step S14.
Step S14: determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
the weight of each recommendation factor can be preset, and can also be selected by the user according to the requirement of the user.
The sum of the weights of the recommendation factors is 1.
Step S15: and generating first recommendation information of the object according to the target recommendation value.
According to the recommendation information generation method provided by the embodiment of the application, the target recommendation value of the object is determined from at least two dimensions (including the original recommendation value corresponding to the object and the evaluation text information corresponding to the object), and then recommendation information is generated according to the target recommendation value. That is to say, in the recommendation information generation method provided in the embodiment of the present application, the target recommendation value is a recommendation value that integrates the original recommendation value and the evaluation text information, and since the evaluation text information is a factor often considered by a user, in the embodiment of the present application, the effective information amount included in the target recommendation value is increased, so that the recommendation value better meets the user requirement, and thus the accuracy of the recommendation information is improved.
In the foregoing embodiment, an implementation flowchart of the step of determining the value of the second recommendation factor corresponding to the evaluation text information according to the evaluation text information is shown in fig. 2, and may include:
step S21: extracting emotion words in the evaluation text information, wherein the emotion words at least comprise positive emotion words and negative emotion words;
the positive emotion words may be: words expressing the positive emotion of the human being such as like, happy, satisfied, good, fine, comfortable and clear;
the negative emotion words may be: the words which express negative emotions of people such as unpleasant, boring, hurting, bad, dislike, fuzzy and bad words.
The extracted emotion words can comprise positive emotion words and negative emotion words, and also comprise: neutral words, i.e., words without emotional coloration, such as: red, etc. represent words of color, quality, feel, etc.
Step S22: determining the proportion of the positive emotion words in the emotion words;
after extracting the emotional words, determining the proportion of the positive emotional words in the emotional words according to the number of the positive emotional words and the total number of the emotional words.
Step S23: and determining the value of the second recommendation factor according to the proportion.
Specifically, the value of the proportion of the positive emotion words can be mapped into the value range which is the same as the first recommendation factor according to a first preset rule, that is, the value range of the second recommendation factor is the same as the value range of the first recommendation factor.
In the foregoing embodiment, preferably, the determining the target recommendation value of the object according to the predetermined weight of each recommendation factor and the value of each recommendation factor may include:
determining a target recommendation value for the object according to a recommendation model, which may be:
wherein S is a target recommendation value of the object; a. theiIs the ith recommendation factor; w is aiIs the weight corresponding to the ith recommendation factor; n is the number of the recommendation factors.
For example, when the recommendation factor information includes only the original recommendation value and the evaluation text information corresponding to the object,
the target recommendation S for the object is:
S＝A1×w1+A2×w2
wherein A is1The value of the first recommendation factor is obtained; w is a1A weight of the first recommendation factor; a. the2The value of the second recommendation factor is obtained; w is a2Is the weight of the second recommendation factor.
In the embodiment of the application, the recommendation factor information can be acquired from one source website, and also can be acquired from two or more source websites, that is, the recommendation factor information can be acquired from at least two source websites.
When obtaining recommendation factor information from at least two source websites, the determining, according to the original recommendation value, a value of a first recommendation factor corresponding to the original recommendation value may include:
the value of the first recommendation factor is the average of the obtained at least two original recommendation values, i.e. the average of all the obtained original recommendation values.
In the foregoing embodiment, preferably, the recommendation factor information may further include:
the number of objects selected;
in this embodiment of the application, the number of selected objects may be the playing amount of the objects, that is, the playing times. For example, when the object is video or audio, the number of objects selected may be the amount of play of the object.
The number of objects selected may also be other quantity values, such as reading quantity data, sales quantity data, etc. of the objects (e.g., when the objects are electronic books).
Before determining the target recommendation value of the object according to the predetermined weight of each recommendation factor and the value of each recommendation factor, the method further comprises the following steps:
determining a value of a third recommendation factor corresponding to the number of objects selected.
Specifically, the selected number of the objects may be mapped into a value range that is the same as the first recommendation factor according to a second preset rule, that is, the value range of the third recommendation factor is also the same as the value range of the first recommendation factor.
After determining the value of the third recommendation factor, determining the target recommendation value of the object according to the predetermined weight of each recommendation factor and the value of each recommendation factor may include:
S＝A1×w1+A2×w2+A3×w3
wherein S is a target recommendation value of the object; a. the1The value of the first recommendation factor is obtained; w is a1A weight of the first recommendation factor; a. the2The value of the second recommendation factor is obtained; w is a2Is the weight of the second recommendation factor; a. the3The value of the third recommendation factor is obtained; w is a3Is the weight of the third recommendation factor.
The above embodiment, preferably, may further include:
counting the selected number of the objects according to time, and determining the variation trend of the selected number of the objects;
for example, the selected number of objects per day may be counted over a time period of one day, thereby forming a trend of the selected number of objects from day to day.
And generating second recommendation information of the object according to the target recommendation value and the change trend of the selected number of the objects.
In the embodiment of the application, the recommendation information not only comprises the target recommendation value of the object, but also comprises the variation trend of the selected number of the objects, so that the content of the recommendation information is enriched, and the guidance of the recommendation information to the user is improved.
The above embodiment, preferably, may further include:
extracting words in the evaluation text information;
forming a word belonging to the similar meaning word into a similar meaning word set;
that is, in the embodiments of the present application, words belonging to synonyms are grouped into one group, and in the embodiments of the present application, synonyms may be classified as synonyms.
Determining a preset number of synonym sets with the maximum number of words;
after grouping the words, all the sets of near-synonyms may be sorted (ascending or descending) by the number of words in each set of near-synonyms, and then, the sets of near-synonyms with the largest number of words are determined.
For example, assume that there are 10 synonym sets U1～U10The 10 synonym sets are ordered according to the order of the number of words from large to small as: u shape1>U2>U5>U9＝U3>U7>U4>U6>U8＝U10If the number of the determined synonym set is 4, that is, four synonym sets with the largest number of words are determined, then the determined synonym set with the largest number of four words may be U1,U2,U5,U9The following steps can be also adopted: u shape1,U2,U5,U3。
Taking the word with the most frequent occurrence in each similar meaning word set in the determined similar meaning word sets as a recommended word;
and generating third recommendation information of the object according to the target recommendation value and the recommendation word.
In the embodiment of the application, the recommendation information not only comprises the target recommendation value of the object, but also comprises the recommendation words for describing the object, so that the content of the recommendation information is enriched, and the guidance of the recommendation information to the user is improved.
In another embodiment provided by the embodiment of the present application, fourth recommendation information of the object may be further generated according to the target recommendation value, a variation trend of the number of selected objects, and the recommended word.
In the embodiment of the application, the recommendation information not only comprises the target recommendation value of the object, but also comprises the change trend of the selected number of the objects and the recommendation words for describing the objects, so that the content of the recommendation information is further enriched, and the guidance of the recommendation information to the user is improved.
Furthermore, the value range of the target recommendation value can be segmented, and the corresponding relation between each segmented range and the preset vocabulary is established according to a third preset rule, so that when the recommendation information is generated, the recommendation information comprises the target recommendation value and the vocabulary corresponding to the range to which the target value belongs, the content of the recommendation information is further enriched, and the guidance of the recommendation information to the user is improved.
It should be noted that the recommendation information generation method provided in the embodiment of the present application may be executed according to a preset time period;
the recommendation information generation method provided by the embodiment of the present application may also be executed when it is detected that the trigger condition is satisfied, for example, the recommendation information generation method provided by the embodiment of the present application may be executed when the object is retrieved according to the identification of the object input by the user.
Corresponding to the method embodiment, an embodiment of the present application further provides a recommendation information generating apparatus, and a schematic structural diagram of the recommendation information generating apparatus provided in the embodiment of the present application is shown in fig. 3, and the recommendation information generating apparatus may include:
an acquisition module 31, a first determination module 32, a second determination module 33, a third determination module 34 and a first generation module 35; wherein the content of the first and second substances,
the obtaining module 31 is configured to obtain recommendation factor information from a network according to the identification identifier of the object, where the recommendation factor information includes: original recommendation values and evaluation text information corresponding to the objects;
the first determining module 32 is configured to determine, according to the original recommendation value, a value of a first recommendation factor corresponding to the original recommendation value;
the second determining module 33 is configured to determine, according to the evaluation text information, a value of a second recommendation factor corresponding to the evaluation text information;
the third determining module 34 is configured to determine a target recommendation value of the object according to the predetermined weight of each recommendation factor and the value of each recommendation factor;
the first generating module 35 is configured to generate first recommendation information of the subject according to the target recommendation value.
According to the recommendation information generation device provided by the embodiment of the application, the target recommendation value of the object is determined from at least two dimensions (including the original recommendation value corresponding to the object and the evaluation text information corresponding to the object), and then recommendation information is generated according to the target recommendation value. That is to say, with the recommendation information generation apparatus provided in the embodiment of the present application, the target recommendation value is a recommendation value that integrates the original recommendation value and the evaluation text information, and since the evaluation text information is a factor that is often considered by a user, in the embodiment of the present application, the effective information amount included in the target recommendation value is increased, so that the recommendation value better meets the user requirement, and the precision of the recommendation information is improved.
In the foregoing embodiment, preferably, a schematic structural diagram of the second determining module 33 is shown in fig. 4, and may include:
an extraction unit 41, a first determination unit 42, a second determination unit 43; wherein the content of the first and second substances,
the extracting unit 41 is configured to extract emotion words in the evaluation text information, where the emotion words at least include positive emotion words and negative emotion words;
the first determining unit 42 is configured to determine a proportion of the positive emotion words in the emotion words;
the second determining unit 43 is configured to determine a value of the second recommendation factor according to the ratio.
In the foregoing embodiment, preferably, a schematic structural diagram of the third determining module 34 is shown in fig. 5, and may include:
a third determining unit 51, configured to determine a target recommendation value of the object according to a recommendation model, where the recommendation model is:
wherein S is a target recommendation value of the object; a. theiIs the ith recommendation factor; w is aiIs the weight corresponding to the ith recommendation factor; n is the number of the recommendation factors.
In the foregoing embodiment, preferably, a schematic structural diagram of the obtaining module 31 is shown in fig. 6, and may include:
an obtaining unit 61, configured to obtain recommendation factor information from at least two source websites of an object according to an identification of the object, where the recommendation factor information includes: the original recommendation value and the evaluation text information corresponding to the object.
In the foregoing embodiment, preferably, a schematic structural diagram of the first determining module 32 is shown in fig. 7, and may include:
a calculating unit 71, configured to calculate an average value of the obtained at least two original recommendation values, where the average value of the at least two original recommendation values is the value of the first recommendation factor.
In the foregoing embodiment, preferably, the recommendation factor information acquired by the acquiring module 31 may further include: the number of objects selected; correspondingly, another schematic structural diagram of the recommendation information generation apparatus provided in the embodiment of the present application is shown in fig. 8, and may further include:
a fourth determining module 81, connected to the obtaining module 31 and the third determining module 34, respectively, for determining a value of the third recommendation factor corresponding to the selected number of the objects.
On the basis of the embodiment shown in fig. 8, a schematic structural diagram of a recommendation information generation apparatus provided in the embodiment of the present application is shown in fig. 9, and may further include:
a statistics module 91 and a second generation module 92; wherein the content of the first and second substances,
the counting module 91 is configured to count the number of the selected objects according to time, and determine a variation trend of the number of the selected objects;
the second generating module 92 is configured to generate second recommendation information of the object according to the target recommendation value and a trend of change of the selected number of the objects.
Fig. 10 shows another schematic structural diagram of the recommendation information generation apparatus according to the embodiment of the present application, which may further include:
an extraction module 101, a set construction module 102, a fifth determination module 103, a sixth determination module 104 and a third generation module 105; wherein the content of the first and second substances,
the extraction module 101 is configured to extract words in the evaluation text information;
the set constructing module 102 is used for constructing words belonging to the similar meaning words into a similar meaning word set;
the fifth determining module 103 is configured to determine a preset number of synonym sets with a maximum number of words;
the sixth determining module 104 is configured to use, as a recommended word, a word with the highest frequency of occurrence in each determined near-meaning word set;
the third generating module 105 is configured to generate third recommendation information of the object according to the target recommendation value and the recommended word.
Fig. 11 shows another schematic structural diagram of the recommendation information generation apparatus according to an embodiment of the present application, which may include:
at least one processor 111 and a memory 112 coupled to the at least one processor; wherein the content of the first and second substances,
the at least one processor 111 is configured to:
acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects;
determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
determining a target recommendation value of the object according to the weight of each preset recommendation factor and the value of each recommendation factor;
and generating first recommendation information of the object according to the target recommendation value.
Specifically, the method disclosed in the embodiment of the present application may be applied to the processor 111, or implemented by the processor 111. The processor 111 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 111. For performing the methods disclosed in the embodiments of the present application, the processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor, decoder, etc. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor. The software module can be located in a storage medium mature in the field, such as a Random Access Memory (RAM), a Flash Memory, a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an electrically erasable and programmable Memory (EEPROM), a register, and the like. The storage medium is located in the memory 112, and the processor reads the information in the memory 112 and completes the steps of the method in combination with the hardware.
An exemplary structure diagram of the recommendation information generation system provided in the embodiment of the present application is shown in fig. 12, and may include:
the obtaining server 121 is configured to obtain recommendation factor information from a network according to the identification of the object, where the recommendation factor information includes: original recommendation values and evaluation text information corresponding to the objects;
a recommendation value determination server 122, configured to determine, according to the original recommendation value, a value of a first recommendation factor corresponding to the original recommendation value; determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information; determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and the recommendation information generation server 123 is configured to generate first recommendation information of the object according to the target recommendation value.
In the embodiment of the application, different functions are realized through different servers, so that recommendation information is generated.
Based on the embodiment shown in fig. 12, an embodiment of the present application further provides an information processing system, and a schematic structural diagram of the information processing system provided in the embodiment of the present application is shown in fig. 13, and the information processing system may include:
a computer terminal 131, a WEB server 132, an acquisition server 133, a recommendation value determination server 134, and a recommendation information generation server 135; wherein the content of the first and second substances,
the computer terminal 131 can receive the identification of the object input by the user, and send the identification of the object input by the user to the WEB server, and the WEB server searches the object according to the identification of the object;
the obtaining server 133 is configured to obtain recommendation factor information from a network according to the identification identifier of the object, where the recommendation factor information includes: original recommendation values and evaluation text information corresponding to the objects;
a recommendation value determination server 134, configured to determine, according to the original recommendation value, a value of a first recommendation factor corresponding to the original recommendation value; determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information; determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and a recommendation information generation server 135, configured to generate first recommendation information of the object according to the target recommendation value.
After finding the object, the WEB server 132 may request the recommendation information generation server 135 for the generation information of the object;
the WEB server 132 may also send an instruction to the recommendation information generation server 135 to instruct the recommendation information generation system configured by the acquisition server 133, the recommendation value determination server 134, and the recommendation information generation server 135 to generate recommendation information of the searched object after the object is found.
After finding the object, the WEB server 132 obtains recommendation information of the object, and feeds back the found object and the recommendation information of the object to the computer terminal 131.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. 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.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (15)
1. A recommendation information generation method, comprising:
acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects, and the number of the selected objects;
determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
determining a value of a third recommendation factor corresponding to the number of the selected objects according to the number of the selected objects;
determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and generating recommendation information of the object according to the target recommendation value, wherein the recommendation information comprises the target recommendation value, the variation trend of the selected number of the objects, and recommendation words describing the object in the evaluation text information.
2. The method of claim 1, wherein the determining a value of a second recommendation factor corresponding to the evaluation text information from the evaluation text information comprises:
extracting emotion words in the evaluation text information, wherein the emotion words at least comprise positive emotion words and negative emotion words;
determining the proportion of the positive emotion words in the emotion words;
and determining the value of the second recommendation factor according to the proportion.
3. The method of claim 1, wherein determining the target recommendation value for the subject based on the predetermined weight for each recommendation factor and the value of each recommendation factor comprises:
determining a target recommendation value of the object according to a recommendation model, wherein the recommendation model is as follows:
wherein S is a target recommendation value of the object; a. theiIs the ith recommendation factor; w is aiIs the weight corresponding to the ith recommendation factor; n is the number of the recommendation factors.
4. The method according to any one of claims 1-3, wherein the obtaining recommendation factor information from the network according to the identification of the object comprises:
and acquiring recommendation factor information from at least two source websites of the object according to the identification mark of the object.
5. The method of claim 4, wherein determining the value of the first recommendation factor corresponding to the original recommendation value from the original recommendation value comprises:
the value of the first recommendation factor is an average value of the obtained at least two original recommendation values.
6. The method of claim 1, further comprising:
counting the selected number of the objects according to time, and determining the variation trend of the selected number of the objects;
and generating second recommendation information of the object according to the target recommendation value and the change trend of the selected number of the objects.
7. The method of any one of claims 1-3, further comprising:
extracting words in the evaluation text information;
forming a word belonging to the similar meaning word into a similar meaning word set;
determining a preset number of synonym sets with the maximum number of words;
taking the word with the most frequent occurrence in each similar meaning word set in the determined similar meaning word sets as a recommended word;
and generating third recommendation information of the object according to the target recommendation value and the recommendation word.
8. A recommendation information generation apparatus, characterized by comprising:
the acquisition module is used for acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects, and the number of the selected objects;
the first determining module is used for determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value;
the second determining module is used for determining the value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information;
a fourth determining module, configured to determine, according to the number of selected objects, a value of a third recommendation factor corresponding to the number of selected objects;
the third determination module is used for determining the target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and the first generation module is used for generating recommendation information of the object according to the target recommendation value, wherein the recommendation information comprises the target recommendation value, the change trend of the selected number of the objects, and recommendation words describing the object in the evaluation text information.
9. The apparatus of claim 8, wherein the second determining module comprises:
the extracting unit is used for extracting emotion words in the evaluation text information, wherein the emotion words at least comprise positive emotion words and negative emotion words;
the first determining unit is used for determining the proportion of the positive emotion words in the emotion words;
and the second determining unit is used for determining the value of the second recommendation factor according to the proportion.
10. The apparatus of claim 8, wherein the third determining module comprises:
a third determining unit, configured to determine a target recommendation value of the object according to a recommendation model, where the recommendation model is:
wherein S is a target recommendation value of the object; a. theiIs the ith recommendation factor; w is aiIs the weight corresponding to the ith recommendation factor; n is the number of the recommendation factors.
11. The apparatus according to any one of claims 8-10, wherein the obtaining module comprises:
the acquisition unit is used for acquiring recommendation factor information from at least two source websites of the object according to the identification mark of the object, wherein the recommendation factor information comprises: the original recommendation value and the evaluation text information corresponding to the object.
12. The apparatus of claim 11, wherein the first determining module comprises:
and the calculating unit is used for calculating the average value of the obtained at least two original recommendation values, and the average value of the at least two original recommendation values is the value of the first recommendation factor.
13. The apparatus of claim 8, further comprising:
the counting module is used for counting the selected number of the objects according to time and determining the change trend of the selected number of the objects;
and the second generation module is used for generating second recommendation information of the object according to the target recommendation value and the change trend of the selected number of the objects.
14. The apparatus of any one of claims 8-10, further comprising:
the extraction module is used for extracting words in the evaluation text information;
the collection construction module is used for constructing words belonging to the similar meaning words into a similar meaning word collection;
the fifth determining module is used for determining a preset number of synonym sets with the maximum number of words;
a sixth determining module, configured to use a word with the highest frequency of occurrence in each of the determined near-meaning word sets as a recommended word;
and the third generation module is used for generating third recommendation information of the object according to the target recommendation value and the recommendation word.
15. A recommendation information generation system, comprising:
the acquisition server is used for acquiring recommendation factor information from a network according to the identification mark of the object, wherein the recommendation factor information comprises: original recommendation values and evaluation text information corresponding to the objects, and the number of the selected objects;
the recommendation value determining server is used for determining the value of a first recommendation factor corresponding to the original recommendation value according to the original recommendation value; determining a value of a second recommendation factor corresponding to the evaluation text information according to the evaluation text information; determining a value of a third recommendation factor corresponding to the number of the selected objects according to the number of the selected objects; determining a target recommendation value of the object according to the preset weight of each recommendation factor and the value of each recommendation factor;
and the recommendation information generation server is used for generating recommendation information of the object according to the target recommendation value, wherein the recommendation information comprises the target recommendation value, the variation trend of the selected number of the objects, and recommendation words describing the object in the evaluation text information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410244317.XA CN105183731B (en) | 2014-06-04 | 2014-06-04 | Recommendation information generation method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410244317.XA CN105183731B (en) | 2014-06-04 | 2014-06-04 | Recommendation information generation method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105183731A CN105183731A (en) | 2015-12-23 |
| CN105183731B true CN105183731B (en) | 2020-01-21 |
Family
ID=54905820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410244317.XA Active CN105183731B (en) | 2014-06-04 | 2014-06-04 | Recommendation information generation method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105183731B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105763952A (en) * | 2016-01-29 | 2016-07-13 | 浪潮软件集团有限公司 | Information prompting method and device |
| CN105843909A (en) * | 2016-03-24 | 2016-08-10 | 上海诺亚投资管理有限公司 | Financial information pushing method and apparatus |
| CN106528596A (en) * | 2016-09-23 | 2017-03-22 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN107093094A (en) * | 2016-11-25 | 2017-08-25 | 口碑控股有限公司 | The dissemination method and device of a kind of evaluation information |
| CN107948748B (en) * | 2017-11-30 | 2021-08-17 | 奇酷互联网络科技（深圳）有限公司 | Method, device, mobile terminal and computer storage medium for recommending videos |
| CN108595580B (en) * | 2018-04-17 | 2022-08-09 | 创新先进技术有限公司 | News recommendation method, device, server and storage medium |
| CN108549641B (en) * | 2018-04-26 | 2022-09-20 | 中国联合网络通信集团有限公司 | Song evaluation method, device, equipment and storage medium |
| CN108734549B (en) * | 2018-04-27 | 2021-12-21 | 达而观信息科技（上海）有限公司 | Item recommendation method and device |
| CN108960958B (en) * | 2018-04-27 | 2022-03-22 | 达而观信息科技（上海）有限公司 | Item recommendation method and device |
| CN108734548B (en) * | 2018-04-27 | 2021-12-17 | 达而观信息科技（上海）有限公司 | Item recommendation method and device |
| CN108763318B (en) * | 2018-04-27 | 2022-04-19 | 达而观信息科技（上海）有限公司 | Item recommendation method and device |
| CN110866768B (en) * | 2018-08-27 | 2024-04-16 | 阿里巴巴集团控股有限公司 | Evaluation method and device |
| CN110147500B (en) * | 2019-05-21 | 2021-11-16 | 北京奇艺世纪科技有限公司 | Information recommendation method and device |
| CN110598016B (en) * | 2019-09-11 | 2021-08-17 | 腾讯科技（深圳）有限公司 | Method, device, equipment and medium for recommending multimedia information |
| CN113468394A (en) * | 2021-07-06 | 2021-10-01 | 北京有竹居网络技术有限公司 | Data processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020308A (en) * | 2013-01-07 | 2013-04-03 | 北京趣拿软件科技有限公司 | Method and device for recommending travel strategy project |
| CN103235818A (en) * | 2013-04-27 | 2013-08-07 | 北京百度网讯科技有限公司 | Information push method and device based on webpage emotion tendentiousness |
| CN103279460A (en) * | 2013-05-24 | 2013-09-04 | 北京尚友通达信息技术有限公司 | Method for analyzing and processing online shopping comments |
| CN103678329A (en) * | 2012-09-04 | 2014-03-26 | 中兴通讯股份有限公司 | Recommendation method and device |
-
2014
- 2014-06-04 CN CN201410244317.XA patent/CN105183731B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678329A (en) * | 2012-09-04 | 2014-03-26 | 中兴通讯股份有限公司 | Recommendation method and device |
| CN103020308A (en) * | 2013-01-07 | 2013-04-03 | 北京趣拿软件科技有限公司 | Method and device for recommending travel strategy project |
| CN103235818A (en) * | 2013-04-27 | 2013-08-07 | 北京百度网讯科技有限公司 | Information push method and device based on webpage emotion tendentiousness |
| CN103279460A (en) * | 2013-05-24 | 2013-09-04 | 北京尚友通达信息技术有限公司 | Method for analyzing and processing online shopping comments |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105183731A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105183731B (en) | Recommendation information generation method, device and system | |
| CN106897284B (en) | Recommendation method and device for electronic books | |
| CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
| US10846332B2 (en) | Playlist list determining method and device, electronic apparatus, and storage medium | |
| CN103577593B (en) | A kind of video aggregation method and system based on microblog hot topic | |
| CN105095470B (en) | Data recommendation method and device for application program | |
| CN110896488B (en) | Recommendation method for live broadcast room and related equipment | |
| KR101491628B1 (en) | Method, apparatus and system for extracting keyword affecting for mood change of the public using blog | |
| CN109710841A (en) | Comment on recommended method and device | |
| CN104111939B (en) | A kind of book recommendation method and device | |
| CN105095179B (en) | The method and device that user's evaluation is handled | |
| CN106815266B (en) | Referee document retrieval method and device | |
| CN110046251A (en) | Community content methods of risk assessment and device | |
| CN104199838B (en) | A kind of user model constructing method based on label disambiguation | |
| CN105512300B (en) | information filtering method and system | |
| CN106202050B (en) | Theme information acquisition method and device and electronic equipment | |
| KR101976056B1 (en) | System and method for recommendation | |
| CN106919603B (en) | Method and device for calculating word segmentation weight in query word mode | |
| CN115474093B (en) | Method and device for calculating importance of video elements, storage medium and electronic equipment | |
| CN104462448B (en) | A kind of packet name classification method and device | |
| KR101573449B1 (en) | Method and apparatus for generating an opportunity map of mobile application | |
| CN110168315B (en) | Foot step counting method, device and equipment based on acceleration information | |
| CN113139102A (en) | Data processing method, data processing device, nonvolatile storage medium and processor | |
| CN113886585A (en) | Item recommendation method, computer device and computer-readable storage medium | |
| CN106383910B (en) | Method for determining search term weight, and method and device for pushing network resources |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |