CN117992676A - Intelligent scientific and technological achievement recommendation method based on big data - Google Patents
Intelligent scientific and technological achievement recommendation method based on big data Download PDFInfo
- Publication number
- CN117992676A CN117992676A CN202410393742.9A CN202410393742A CN117992676A CN 117992676 A CN117992676 A CN 117992676A CN 202410393742 A CN202410393742 A CN 202410393742A CN 117992676 A CN117992676 A CN 117992676A
- Authority
- CN
- China
- Prior art keywords
- recommended
- preset
- recommendation
- attention
- field
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000007774 longterm Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 235000019633 pungent taste Nutrition 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of intelligent recommendation, in particular to a scientific and technological achievement intelligent recommendation method based on big data, which comprises the steps of obtaining a user name and current demand information of a user to be recommended, and determining a first attention field, a second attention field and a third attention field of the user to be recommended; calculating the matching degree to be recommended, and sorting the corresponding scientific and technological achievements to be recommended according to the matching degree to be recommended; sorting the actual recommendation sequence of each concerned field; and determining the actual recommendation quantity of each attention field, and recommending the sequenced scientific and technological achievements to be recommended according to the actual recommendation quantity and the actual recommendation sequence. According to the method, the technological achievements to be recommended in each concerned field are selected and arranged according to the obtained actual recommendation sequence and the actual recommendation quantity, and then the recommendation is sent to the corresponding users to be recommended, so that the attraction of the related technological achievements recommended earlier to potential clients is improved, and the conversion process of the technological achievements is further accelerated.
Description
Technical Field
The invention relates to the technical field of intelligent recommendation, in particular to a scientific and technological achievement intelligent recommendation method based on big data.
Background
The scientific achievements refer to achievements with a certain innovation and practical value, including theoretical achievements, technical achievements, soft scientific achievements and the like, which are obtained through technical research and development activities such as scientific research and technical development, are core achievements of the scientific activities, and have important promotion effects on technological progress and economic and social development.
The forms of technological achievements are various, the related fields are different, along with the development of internet and big data technology, people also rely on technological products and related services in life more and more, however, facing massive technological products and information, how to recommend technological achievements which are more in line with the requirements and interests of users becomes a great challenge in the prior art, and random recommendation or massive listing is not only unfavorable for users to learn about information of required technological achievements, but also can further reduce the knowledge interests of users on related technological achievements, thereby causing adverse effects on the conversion process of the technological achievements, accelerating the conversion process of the technological achievements, and promoting the deep fusion of the technological achievements and industries, so that the technological achievements are recommended to potential users.
Disclosure of Invention
Therefore, the invention provides a scientific and technological achievement intelligent recommending method based on big data, which is used for solving the problems that in the prior art, scientific and technological achievement which is difficult to be recommended according to users and meets relevant requirements and interests is difficult to attract deep attention of potential customers, and the conversion process of the scientific and technological achievement is reduced.
In order to achieve the above object, the present invention provides, on the one hand, a technological achievement intelligent recommendation method based on big data, comprising,
Step S1, obtaining a user name and current demand information of a user to be recommended;
acquiring historical demand information of a current user to be recommended in a first time period, historical demand information of the current user to be recommended in a second time period and personal tag information according to the user name;
Step S2, a first attention field is determined according to the current demand information, a second attention field is determined according to the history demand information in the first time period, and a third attention field is determined according to the history demand information and the personal tag information in the second time period;
step S3, retrieving technological achievements to be recommended in each concerned field, and calculating the matching degree to be recommended according to the recent click heat value and the recent recommendation heat value of each technological achievements to be recommended;
S4, ordering the corresponding scientific and technological achievements to be recommended according to the matching degree to be recommended in any attention field;
step S5, sorting the actual recommendation sequence of each attention field according to the actual attention degree of each attention field;
Setting that the actual attention of the first attention area is larger than the actual attention of the second attention area and the actual attention of the third attention area;
Step S6, determining the actual recommended quantity of the technological achievements to be recommended corresponding to each attention field according to the preset recommended proportion and the preset recommended quantity;
And S7, recommending the sequenced technical achievements to be recommended to the user to be recommended according to the actual recommendation quantity and the actual recommendation sequence corresponding to the attention areas.
Further, in the step S3, a preset collection date is further set, the recent click times and the recent recommendation times of the technological achievement to be recommended in the preset collection date are obtained according to the preset collection date, the recent click heat value is obtained by calculating according to the preset collection date and the recent click times, and the recent recommendation heat value is obtained by calculating according to the preset collection date and the recent recommendation times;
Wherein, r1=q1/D, r2=q2/D, R1 is a recent click heat value, R2 is a recent recommended heat value, Q1 is a recent click frequency of a technological result to be recommended within a preset collection date, Q2 is a recent recommendation frequency of the technological result to be recommended within the preset collection date, and D is a preset collection date.
Further, calculating according to the recent click heat value and the recent recommendation heat value, and obtaining the degree of matching to be recommended of the technological achievement to be recommended;
wherein, p=r1/R2, and P is the matching degree to be recommended for the scientific and technological achievement to be recommended.
Further, in the step S4, the degree of matching to be recommended of each technical result to be recommended is compared, and each technical result to be recommended is ranked according to the value of the degree of matching to be recommended from large to small.
Further, in the step S6, the preset recommendation ratio includes a first preset recommendation ratio and a second preset recommendation ratio, where the first preset recommendation ratio is a number ratio between a first preset recommendation number of the first field of interest and a first preset recommendation number of the second field of interest and a first preset recommendation number of the third field of interest, and the second preset recommendation ratio is a number ratio between a second preset recommendation number of the second field of interest and a second preset recommendation number of the third field of interest;
Wherein k1=n1: n2: n3, k2=n2': n3', K1 is a first preset recommendation ratio, K2 is a second preset recommendation ratio, N1 is a first preset recommendation number of the first attention area, N2 is a first preset recommendation number of the second attention area, N3 is a first preset recommendation number of the third attention area, N2' is a second preset recommendation number of the second attention area, and N3' is a second preset recommendation number of the third attention area.
Further, in the step S6, the method further includes determining whether the first field of interest exists, where the preset recommended number includes a first preset recommended number and a second preset recommended number, and when it is determined that the first field of interest exists, calculating, by the first preset recommended proportion and the first preset recommended number, the actual recommended number of the technological achievements to be recommended in each field of interest;
Wherein nis=nx [ Ni/(n1+n2+n3) ], ni is a first preset recommended number of the ith field of interest, nis is an actual recommended number of the ith field of interest at the first preset recommended ratio, i is 1, 2 or 3, and N is the first preset recommended number.
Further, in the step S6, according to the determination of whether the first field of interest exists;
If the first attention area is judged to be absent, calculating the second preset recommendation proportion and the second preset recommendation number to obtain the actual recommendation number of the technological achievements to be recommended in each attention area;
Wherein Nis ' =n ' × [ Ni '/(N2 ' +n3 ') ] where Ni ' is a second preset recommended number of the i ' th field of interest, nis ' is an actual recommended number of the i ' th field of interest at the second preset recommended ratio, i ' is 2 or 3, and N ' is the second preset recommended number.
Further, the acquisition duration of the first time period is smaller than the acquisition duration of the second time period, and the first time period is not included in the second time period.
Further, the current demand information is search information of the current user to be recommended in the current time period.
Further, in the step S7, the scientific and technological achievements to be recommended in the areas of interest ordered in the step S4 are sequentially selected from front to back according to the actual recommended number of the areas of interest calculated in the step S6, and the selected scientific and technological achievements to be recommended are sequentially recommended according to the actual recommended sequence ordered in the step S5.
Compared with the prior art, the method has the beneficial effects that the information of each requirement of the users to be recommended in the current time period is acquired through the big data platform, so that each attention area of the users to be recommended in the current time period is determined, the technical achievements to be recommended in each attention area are ordered through calculating the matching degree of each attention to be recommended of the technical achievements to be recommended, the related technical achievements in each attention area can be prioritized according to the personal interests and the requirements of the users to be recommended, the actual recommendation sequence of the technical achievements to be recommended in each attention area is obtained through ordering the technical achievements to be recommended in the real attention areas according to the actual attention degree of the users to be recommended, the actual recommendation quantity of the technical achievements to be recommended in each attention area is calculated through the preset recommendation proportion and the preset recommendation quantity, the recommendation sequence and the actual recommendation quantity of the technical achievements to be recommended in each attention area are selected and arranged, the recommendation is sent to the users to be recommended, the related technical achievements to be recommended by the users to be attractive and the related technical achievements to be more attractive to the users to be more attractive, the related technical achievements to be more attractive to the users to be interested in the related requirements of the users to be more attractive, and the users to be more attractive to the users to be interested in the users to be more attractive to the users to the potential to the users to be better.
Further, by calculating the recent recommendation hotness value and the recent recommendation hotness value of each technological achievement to be recommended in any concerned field, the subsequent calculation of the matching degree to be recommended of each recommendation achievement in the concerned field is facilitated, and the actual attractiveness of each recommendation achievement to the recommended user in the past is represented by the calculated matching degree to be recommended.
In particular, by calculating the degree of matching to be recommended of each technical result to be recommended, each technical result to be recommended in the current field of interest is ranked according to the degree of matching to be recommended of each technical result to be recommended, so that the more attractive the technical result to be recommended in the current field of interest is to the current user, the more attractive the technical result to be recommended is, and the more attractive the technical result to be recommended is to the current user to be recommended.
Further, whether the first attention area exists or not is judged, so that proper preset recommendation proportion and preset recommendation number are selected, and finally recommended technological achievements to be recommended can be more in line with actual relevant requirements of users to be recommended.
In particular, the actual recommended number of technological achievements to be recommended in each attention field under the condition that the first attention field exists in each attention field is obtained through calculation of the first preset proportion and the corresponding preset recommended number, so that the finally recommended relevant technological achievements more accord with the actual demands and the relevant interests of users to be recommended with current demands.
Further, the actual recommended number of the technological achievements to be recommended in each attention area when the first attention area does not exist is obtained through calculation of the second preset proportion and the corresponding preset recommended number, so that the finally recommended relevant technological achievements more accord with the actual demands and the relevant interests of the users to be recommended, wherein the actual demands and the relevant interests of the users to be recommended do not exist.
Drawings
FIG. 1 is a flowchart of a technological achievement intelligent recommendation method based on big data in the embodiment;
FIG. 2 is a logic diagram of determining a recommended ratio according to the present embodiment;
FIG. 3 is a flowchart showing the steps for calculating the actual recommended number of each field of interest when it is determined that the first field of interest exists in the present embodiment;
fig. 4 is a flowchart showing specific steps of calculating the actual recommended number of each attention area when it is determined that the first attention area does not exist in the present embodiment.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, as shown in fig. 1, a flowchart of a technological achievement intelligent recommendation method based on big data in this embodiment is shown;
Specifically, the intelligent recommending method for technological achievements based on big data provided by the embodiment of the invention comprises the following steps,
Step S1, obtaining a user name and current demand information of a user to be recommended;
acquiring historical demand information of a current user to be recommended in a first time period, historical demand information of the current user to be recommended in a second time period and personal tag information according to the user name;
Step S2, a first attention field is determined according to the current demand information, a second attention field is determined according to the history demand information in the first time period, and a third attention field is determined according to the history demand information and the personal tag information in the second time period;
step S3, retrieving technological achievements to be recommended in each concerned field, and calculating the matching degree to be recommended according to the recent click heat value and the recent recommendation heat value of each technological achievements to be recommended;
Searching related scientific and technological achievements in the corresponding field of each concerned field through a big data platform, and taking the searched related scientific and technological achievements as the scientific and technological achievements to be recommended;
S4, ordering the corresponding scientific and technological achievements to be recommended according to the matching degree to be recommended in any attention field;
step S5, sorting the actual recommendation sequence of each attention field according to the actual attention degree of each attention field;
Setting that the actual attention of the first attention area is larger than that of the second attention area and the actual attention of the third attention area;
Step S6, determining the actual recommended quantity of the technological achievements to be recommended corresponding to each attention field according to the preset recommended proportion and the preset recommended quantity;
And S7, recommending the sequenced technical achievements to be recommended to the user to be recommended according to the actual recommendation quantity and the actual recommendation sequence corresponding to the attention areas.
The method comprises the steps of obtaining information of all demands of users to be recommended in a current time period through a big data platform, determining all concerned fields of the users to be recommended in the current time period, sorting the technological achievements to be recommended in all concerned fields through calculating the matching degree of the technological achievements to be recommended in all concerned fields, enabling the related technological achievements in all concerned fields to be preferentially sorted according to personal interests and demands of the users to be recommended, sorting all concerned fields according to the actual attention degree of the users to obtain the actual recommending order of the technological achievements to be recommended in all concerned fields, calculating the selection number of the technological achievements to be recommended in all concerned fields through preset recommending proportion and preset recommending number, obtaining the actual recommending number of the technological achievements to be recommended in all concerned fields, and sending the recommended to the users to be recommended after the obtained actual recommending order and the actual recommending number of the technological achievements to be recommended, enabling the related technological achievements to be easily attracted to the users to the related interests of the users the higher the related technological achievements, and accelerating the potential technological processes of the technological achievements to be recommended to the customers.
Specifically, in the step S3, a preset collection date is further provided, the recent click times and the recent recommendation times of the scientific and technological achievements to be recommended in the preset collection date are obtained according to the preset collection date, the recent click times are calculated according to the preset collection date and the recent click times, the recent click heat value is obtained, and the recent recommendation heat value is obtained by calculating according to the preset collection date and the recent recommendation times;
Wherein, r1=q1/D, r2=q2/D, R1 is a recent click heat value, R2 is a recent recommended heat value, Q1 is a recent click frequency of a technological result to be recommended within a preset collection date, Q2 is a recent recommendation frequency of the technological result to be recommended within the preset collection date, and D is a preset collection date.
The recent recommendation heat value and the recent recommendation heat value of each technological achievement to be recommended in any concerned field are calculated, so that the subsequent calculation of the degree of matching of each recommendation achievement to be recommended in the current concerned field is facilitated, and the actual attractive force of each recommendation achievement to the recommended user in the past is represented by the calculated degree of matching of each recommendation achievement to be recommended.
In this embodiment, the selected preset collection date can be adjusted and modified to a certain extent according to the last recommended date and personal computing habit of the technological achievement to be recommended in the relevant concerned field, but in order to ensure the real-time performance of the computing result, the computing result should generally not exceed 30 days, and in order to make the computing result more objective and accurate, the influence of the computing result on the final comparison result due to a time heating value is avoided, and the selected preset collection date should not be less than 5 days;
however, the actual selection result should be selected according to the latest click date and the latest recommendation date of the technical achievements to be recommended in each of the retrieved attention areas, for example, if the determined attention areas have cooler attention areas, the number of times of recommending the related technical achievements to be recommended in the areas is less, the latest recommendation date of the latest recommendation is more than 30 days away from the latest recommendation date of the last recommendation, and the recommendation date and the current recommendation interval date of the last recommendation should be properly prolonged and adjusted;
For example, if the last recommended date in the scientific and technological achievement to be recommended related to the current attention area is 20 days ago, and the last recommended date is 60 days ago, the recommended interval between the last recommended date and the last recommended date exceeds 30 days, and the recommended times are smaller, then the recommended times can be extended backward for a certain number of times and the recommended dates can be collected, so that the collected data is more objective, the extended times can be selected according to the actual interval date between the last recommended dates, namely, the selected preset collection date is the difference between the recommended date of the last recommended date and the recommended date of the selected last recommended date, and in order to avoid the too limited collected data, the interval times between the selected last recommended date and the last recommended date should not be lower than three times.
Specifically, calculating according to the recent click heat value and the recent recommendation heat value, and obtaining the degree of matching to be recommended of the technological achievement to be recommended;
wherein, p=r1/R2, and P is the matching degree to be recommended for the scientific and technological achievement to be recommended.
The method comprises the steps of calculating the degree of matching to be recommended of each technical result to be recommended, and sorting each technical result to be recommended in the current field of interest according to the degree of matching to be recommended of each technical result to be recommended, so that the more attractive the technical result to be recommended in the current field of interest to the current user is, the more forward, and the more attractive the technical result to be recommended in the forward region to the user to be recommended in the same field of interest is, the more attractive the technical result to be recommended in the backward region is, and the attractive force of the technical result to be recommended to the current user to be recommended is improved.
For example, if the preset collection date adopted in the present embodiment is 10 days, i.e. d=10, the total number of clicks of any one of the to-be-recommended technological achievements related to the first field of interest is 30 times, the total number of clicks in the collection date is 50 times, the number of recent clicks q1=30, the number of recent recommendations q2=50, the recent click heat value r1=q1/d=30/10=3, the recent recommendation heat value r2=q2/d=50/10=5, the to-be-recommended matching degree of the current to-be-recommended technological achievements is p=r1/r2=3/5=0.6, and if the to-be-recommended matching degree P '=0.5 of another to-be-recommended technological achievements related to the first field of interest is calculated, the current to-be-recommended technological achievements is ranked behind the previous to-be-recommended technological achievements due to P' < P.
Specifically, in the step S4, the degree of matching to be recommended of each technical result to be recommended is compared, and each technical result to be recommended is ranked according to the value of the degree of matching to be recommended from large to small.
Through sequencing the matched technical achievements to be recommended in the same field, the related technical achievements with higher click times after recommendation are properly advanced, namely the related technical achievements which are easier to attract the user to be recommended to pay attention to browse are sequenced forwards, so that the related technical achievements which are recommended to the user later are related technical achievements which are easier to cause the user to know interests in the current field of interest.
Referring to fig. 2, as shown in fig. 2, a logic diagram of determining what preset recommendation ratio is adopted in the present embodiment;
Specifically, in the step S6, the preset recommendation ratio includes a first preset recommendation ratio and a second preset recommendation ratio, where the first preset recommendation ratio is a number ratio between a first preset recommendation number of the first field of interest and a first preset recommendation number of the second field of interest and a first preset recommendation number of the third field of interest, and the second preset recommendation ratio is a number ratio between a second preset recommendation number of the second field of interest and a second preset recommendation number of the third field of interest;
Wherein k1=n1: n2: n3, k2=n2': n3', K1 is a first preset recommendation ratio, K2 is a second preset recommendation ratio, N1 is a first preset recommendation number of the first attention area, N2 is a first preset recommendation number of the second attention area, N3 is a first preset recommendation number of the third attention area, N2' is a second preset recommendation number of the second attention area, and N3' is a second preset recommendation number of the third attention area.
And judging whether the first attention area exists or not so as to select proper preset recommendation proportion and preset recommendation number, so that the finally recommended scientific and technological achievements to be recommended can be more in line with the actual related requirements of users to be recommended.
The method for judging whether the first attention area exists is to determine whether the current user to be recommended has active searching behavior in the current time period or not by determining whether the current user to be recommended has active demand information in the current time period or not, and the active demand information is used as the current demand information.
If the current user to be recommended has active searching behaviors, determining that the user to be recommended has active demand information, determining that the user to be recommended has a first attention area, and taking the active demand information as the current demand information to determine the first attention area;
if the current user to be recommended does not have active searching behaviors, determining that the user does not have active demand information, and determining that the user does not have the first field of interest;
In this embodiment, the set first preset recommendation proportion and second preset recommendation proportion are different preset measures used when different judgment conditions are met, that is, when the first attention area is judged to exist, the user to be recommended currently is represented to actively search and inquire related scientific and technological achievements in a specific area in the current time period, that is, the user to be recommended needs to know the related scientific and technological achievements in the first attention area in the current time period, so that the related scientific and technological achievements corresponding to the first attention area are mainly recommended, and the related scientific and technological achievements corresponding to the second attention area and the third attention area are supplementary to perform related recommendation;
When it is determined that the first area of interest does not exist, that is, there is no scientific and technological effort that the user to be recommended does not want to actively query in the current time period, the user should recommend mainly the related interests that can attract their attention when recommending the user, and recommend mainly the related scientific and technological effort in the second area of interest corresponding to their recent related interests, and recommend mainly the related scientific and technological effort in the third area of interest corresponding to their long-term related interests, so as to attract the user to click on the recommended technological effort, so that in this embodiment, the selected N1 ∈ (N2+n3), N2' ∈n3' should be greater than N2, N3' should be greater than N3 under the same preset total recommended number.
Referring to fig. 3, as shown in fig. 3, a flowchart of a specific step of calculating an actual recommended number of each field of interest when it is determined that the first field of interest exists in the present embodiment is shown;
Specifically, in the step S6, the method further includes determining whether the first field of interest exists, where the preset recommended number includes a first preset recommended number and a second preset recommended number, and when it is determined that the first field of interest exists, calculating, by using a first preset recommended proportion and the preset recommended number, an actual recommended number of the technological achievements to be recommended in each field of interest;
Wherein nis=nx [ Ni/(n1+n2+n3) ], ni is a first preset recommended number of the ith field of interest, nis is an actual recommended number of the ith field of interest at the first preset recommended ratio, i is 1, 2 or 3, and N is the first preset recommended number.
The actual recommendation quantity of technological achievements to be recommended of all the attention areas under the condition that the first attention area exists is obtained through calculation of the first preset proportion and the first preset recommendation quantity corresponding to the first preset proportion, and therefore the finally recommended relevant technological achievements are more in line with the actual demands and the relevant interests of users to be recommended with current demands.
In this embodiment, the selected preset recommended number should also be selected according to whether the user has an active demand, so that the user is divided into a first preset recommended number and a second preset recommended number according to whether the active demand exists, where the first preset recommended number is the preset recommended number when the active demand exists, and the second preset recommended number is the preset recommended number when the active demand does not exist, that is, the first preset recommended number corresponds to the first preset recommended proportion, the second preset recommended number corresponds to the second preset recommended proportion, and the first preset recommended number should be greater than the second preset recommended number, for example, when the user has an active demand, i.e. when the first field of interest determines that the active demand exists, in order to help the user search for the desired related technological result, the user should be provided with as many related technological results as possible, and simultaneously in order to avoid "aesthetic fatigue" and help the user to quickly locate the related technological result, the selected first preset recommended number should be within 10-50, so as to avoid that the recommendation is easy to select and the user to judge and the influence the emotional result is reduced due to excessive;
That is, when it is determined that the first field of interest exists, if the first preset recommended ratio adopted in the present embodiment is k1=3: 2:1, when the first preset recommended number is n=20, n1s=20× [ 3/(3+2+1) ]=10, n2s=20× [ 2/(3+2+1) ]=8, n3s=20× [ 1/(3+2+1) ]=2, and when N1s, N2s or N3s is not an integer, the number is automatically rounded up.
Referring to fig. 4, as shown in fig. 4, a flowchart of a specific step of calculating an actual recommended number of each field of interest when the first field of interest is determined to be absent in the present embodiment is shown;
specifically, in the step S6, a determination is made as to whether or not the first field of interest exists;
If the first attention area is judged to be absent, calculating the actual recommended number of the technological achievements to be recommended in each attention area according to the second preset recommended proportion and the second preset recommended number;
Wherein Nis '=n× [ Ni'/(N2 '+n3') ], ni 'is a second preset recommended number of the i' th field of interest, nis 'is an actual recommended number of the i' th field of interest at the second preset recommended ratio, i 'is 2 or 3, and N' is the second preset recommended number.
And calculating the actual recommended quantity of the technological achievements to be recommended in each attention field when the first attention field does not exist through the second preset proportion and the corresponding preset recommended quantity, so that the finally recommended relevant technological achievements more accord with the actual demands and the relevant interests of the users to be recommended without the current demands.
In this embodiment, when the user does not have active demand, that is, when the first attention area determines that there is no active demand, in order to avoid the possibility of user dislikeness caused by excessive recommended content, the recommended amount should be reduced as much as possible while the user recommends according to the interests of the user, and considering that most of the receiving terminals currently used in the market are mobile phones, the second preset recommended number should be selected within 2-5;
That is, when it is determined that the first field of interest exists, and when the second preset recommended ratio employed in the present embodiment is k2=3: 2, when the second preset recommended number is N ' =5, N2s ' =5× [ 3/(3+2) ]=3, N3s ' =5× [ 2/(3+2) ]=2 is calculated, and when N2s ' or N3s ' is not an integer, the whole is automatically rounded up.
Specifically, the acquisition duration of the first time period is smaller than the acquisition duration of the second time period, and the first time period is not included in the second time period.
That is, the first period of time is a period of time relatively near to the current period of time, the second period of time is a period of time relatively near to the current period of time for the user to be recommended, the first period of time is not included in the second period of time, for example, the current period of time is set to be today, the first period of time can be set to be a period of time less than seven days from the current period of time except for today, the second period of time is a period of time less than thirty days from the current period of time except for the first period of time, a common search keyword of the user to be recommended in a period of time relatively near to the current period of time is acquired through a big data platform, short-term requirement information of the user to be recommended in a period of time relatively near to the current period of time is determined, the recent attention area is determined as a second attention area of the user according to the short-term requirement information of the user to be recommended in a period of time relatively long to the current period of time is acquired, the common search keyword of the user to be used in a period of time relatively near to the current period of time is acquired, and interests set in a personal tag are determined, the long-term requirement information of the user to be required in a period of time is acquired, and the long-term requirement information of the user in a long-term requirement information of the current period of time is determined according to the long-term requirement of the current requirement information of the user in the current period of time is determined in a period of time, the current requirement of time is determined in the current requirement of time is determined, including the following the short-term requirement information is determined:
When the common search keywords of the user to be recommended in a period of time longer than the current period of time are consistent with the interests and hobbies set in the personal tag of the user to be recommended and are not the same as the keywords corresponding to the recently focused field, the interests and hobbies set in the personal tag of the user to be recommended are used as long-term requirement information to determine the long-term focused field of the user to be recommended so as to determine the third focused field of the user to be recommended;
When the common search keywords of the user to be recommended in a period of time longer than the current period of time are not consistent with the interests and hobbies set in the personal tag of the user to be recommended and are not the same as the keywords corresponding to the recently focused field, determining the long-term focused field of the user to be recommended by taking the common search keywords in the long-term period of time as long-term requirement information so as to determine a third focused field of the user to be recommended;
When the common search keywords of the user to be recommended in a period longer than the current period are not consistent with the interests and hobbies set in the personal tag of the user to be recommended and are the same as the keywords corresponding to the recently focused fields, the interests and hobbies set in the personal tag of the user to be recommended are used as long-term requirement information to determine the long-term focused fields of the user to be recommended so as to determine the third focused fields of the user to be recommended.
Specifically, the current demand information is search information of the current user to be recommended in the current time period.
The method comprises the steps that a keyword that a user to be recommended actively searches information in a current time period is obtained through a big data platform, so that information of the active demand of the user to be recommended in the current time period is determined, and further the current urgent needed related technical field is determined to be used as a second concerned field.
Specifically, in the step S7, the technical achievements to be recommended in the attention areas sorted in the step S4 are sequentially selected from front to back according to the actual recommended number of the attention areas calculated in the step S6, and the selected technical achievements to be recommended are sequentially recommended according to the actual recommended sequence sorted in the step S5.
The technical achievements to be recommended in all the attention areas after internal sequencing are sequentially selected from front to back according to the calculated actual recommended quantity of all the attention areas, so that the technical achievements to be recommended in all the selected attention areas are related technical achievements which are easier to attract the attention of users under the current attention area, and the technical achievements to be recommended are sequentially recommended to the users to be recommended after being sequenced according to the actual recommended sequence of all the attention areas according to the requirement interests of the users to be recommended, so that the technical achievements to be recommended are more attractive to the related interests of the users than the related technical achievements to be recommended first, and the technical achievements to be recommended are attracted to be focused and known.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A scientific and technological achievement intelligent recommendation method based on big data is characterized by comprising the following steps of,
Step S1, obtaining a user name and current demand information of a user to be recommended;
acquiring historical demand information of a current user to be recommended in a first time period, historical demand information of the current user to be recommended in a second time period and personal tag information according to the user name;
Step S2, a first attention field is determined according to the current demand information, a second attention field is determined according to the history demand information in the first time period, and a third attention field is determined according to the history demand information and the personal tag information in the second time period;
step S3, retrieving technological achievements to be recommended in each concerned field, and calculating the matching degree to be recommended according to the recent click heat value and the recent recommendation heat value of each technological achievements to be recommended;
S4, ordering the corresponding scientific and technological achievements to be recommended according to the matching degree to be recommended in any attention field;
step S5, sorting the actual recommendation sequence of each attention field according to the actual attention degree of each attention field;
Setting that the actual attention of the first attention area is larger than the actual attention of the second attention area and the actual attention of the third attention area;
Step S6, determining the actual recommended quantity of the technological achievements to be recommended corresponding to each attention field according to the preset recommended proportion and the preset recommended quantity;
And S7, recommending the sequenced technical achievements to be recommended to the user to be recommended according to the actual recommendation quantity and the actual recommendation sequence corresponding to each attention field.
2. The intelligent recommendation method for technological achievements based on big data according to claim 1, wherein in the step S3, a preset collection date is further provided, the recent click times and the recent recommendation times of the technological achievements to be recommended in the preset collection date are obtained according to the preset collection date, the recent click times are calculated according to the preset collection date and the recent click times, the recent click heat value is obtained, and the recent recommendation heat value is obtained by calculating according to the preset collection date and the recent recommendation times;
Wherein, r1=q1/D, r2=q2/D, R1 is a recent click heat value, R2 is a recent recommended heat value, Q1 is a recent click frequency of a technological result to be recommended within a preset collection date, Q2 is a recent recommendation frequency of the technological result to be recommended within the preset collection date, and D is a preset collection date.
3. The big data-based intelligent scientific and technological achievement recommending method according to claim 2, wherein the degree of matching to be recommended of the scientific and technological achievement to be recommended is obtained by calculating according to the recent click heat value and the recent recommendation heat value;
wherein, p=r1/R2, and P is the matching degree to be recommended for the scientific and technological achievement to be recommended.
4. The intelligent recommending method for technological achievements based on big data according to claim 3, wherein in the step S4, the degree of matching to be recommended of each technological achievements to be recommended is compared, and each technological achievements to be recommended are ranked according to the value of the degree of matching to be recommended from big to small.
5. The intelligent recommendation method for technological achievements based on big data according to claim 4, wherein in the step S6, the preset recommendation ratio includes a first preset recommendation ratio and a second preset recommendation ratio, the first preset recommendation ratio is a number ratio between a first preset recommendation number of the first attention area and a first preset recommendation number of the second attention area and a first preset recommendation number of the third attention area, and the second preset recommendation ratio is a number ratio between a second preset recommendation number of the second attention area and a second preset recommendation number of the third attention area;
Wherein k1=n1: n2: n3, k2=n2': n3', K1 is a first preset recommendation ratio, K2 is a second preset recommendation ratio, N1 is a first preset recommendation number of the first attention area, N2 is a first preset recommendation number of the second attention area, N3 is a first preset recommendation number of the third attention area, N2' is a second preset recommendation number of the second attention area, and N3' is a second preset recommendation number of the third attention area.
6. The intelligent recommendation method for technological achievements based on big data according to claim 5, wherein in the step S6, the method further comprises determining whether the first attention area exists, the preset recommendation number includes a first preset recommendation number and a second preset recommendation number, and when the first attention area is determined to exist, the actual recommendation number of the technological achievements to be recommended in each attention area is obtained through calculation of the first preset recommendation proportion and the first preset recommendation number;
Wherein nis=nx [ Ni/(n1+n2+n3) ], ni is a first preset recommended number of the ith field of interest, nis is an actual recommended number of the ith field of interest at the first preset recommended ratio, i is 1, 2 or 3, and N is the first preset recommended number.
7. The intelligent recommendation method for technological achievements based on big data according to claim 6, wherein in the step S6, according to the determination of whether the first attention area exists;
If the first attention area is judged to be absent, calculating the second preset recommendation proportion and the second preset recommendation number to obtain the actual recommendation number of the technological achievements to be recommended in each attention area;
Wherein Nis ' =n ' × [ Ni '/(N2 ' +n3 ') ] where Ni ' is a second preset recommended number of the i ' th field of interest, nis ' is an actual recommended number of the i ' th field of interest at the second preset recommended ratio, i ' is 2 or 3, and N ' is the second preset recommended number.
8. The intelligent big data based technological achievement recommendation method according to claim 7, wherein the collection duration of the first time period is smaller than the collection duration of the second time period, and the first time period is not included in the second time period.
9. The intelligent recommending method of technological achievements based on big data according to claim 8, wherein the current demand information is search information of a current user to be recommended in a current time period.
10. The intelligent recommending method of technological achievements based on big data according to claim 9, wherein in the step S7, the technological achievements to be recommended in each field of interest ordered in the step S4 are sequentially selected from front to back according to the actual recommended number of each field of interest calculated in the step S6, and the selected technological achievements to be recommended are sequentially recommended according to the actual recommended order ordered in the step S5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410393742.9A CN117992676B (en) | 2024-04-02 | 2024-04-02 | Intelligent scientific and technological achievement recommendation method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410393742.9A CN117992676B (en) | 2024-04-02 | 2024-04-02 | Intelligent scientific and technological achievement recommendation method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117992676A true CN117992676A (en) | 2024-05-07 |
| CN117992676B CN117992676B (en) | 2024-06-07 |
Family
ID=90900750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410393742.9A Active CN117992676B (en) | 2024-04-02 | 2024-04-02 | Intelligent scientific and technological achievement recommendation method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117992676B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150278351A1 (en) * | 2012-10-05 | 2015-10-01 | S.I.Sv.El Societa' Italiana Per Lo Sviluppo Dell'elettronica S.P.A. | Method and system for recommending multimedia contents through a multimedia platform |
| CN110457589A (en) * | 2019-08-19 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of vehicle recommended method, device, equipment and storage medium |
| CN112559879A (en) * | 2020-12-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Interest model training method, interest point recommendation method, device and equipment |
| CN114238615A (en) * | 2021-12-14 | 2022-03-25 | 淄博天大创新科技服务有限公司 | Enterprise service achievement data processing method and system |
| CN114943582A (en) * | 2022-05-13 | 2022-08-26 | 中信建投证券股份有限公司 | Information recommendation method and system and recommendation server |
| CN115358821A (en) * | 2022-08-24 | 2022-11-18 | 杭州正策信息科技有限公司 | Intelligent recommendation method and system for improving conversion rate of scientific and technological achievements |
| CN116976995A (en) * | 2023-07-31 | 2023-10-31 | 平安银行股份有限公司 | Multi-target recommendation processing method and device |
| CN117422182A (en) * | 2023-12-18 | 2024-01-19 | 保大坊科技有限公司 | Data prediction method, device and storage medium |
-
2024
- 2024-04-02 CN CN202410393742.9A patent/CN117992676B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150278351A1 (en) * | 2012-10-05 | 2015-10-01 | S.I.Sv.El Societa' Italiana Per Lo Sviluppo Dell'elettronica S.P.A. | Method and system for recommending multimedia contents through a multimedia platform |
| CN110457589A (en) * | 2019-08-19 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of vehicle recommended method, device, equipment and storage medium |
| CN112559879A (en) * | 2020-12-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Interest model training method, interest point recommendation method, device and equipment |
| CN114238615A (en) * | 2021-12-14 | 2022-03-25 | 淄博天大创新科技服务有限公司 | Enterprise service achievement data processing method and system |
| CN114943582A (en) * | 2022-05-13 | 2022-08-26 | 中信建投证券股份有限公司 | Information recommendation method and system and recommendation server |
| CN115358821A (en) * | 2022-08-24 | 2022-11-18 | 杭州正策信息科技有限公司 | Intelligent recommendation method and system for improving conversion rate of scientific and technological achievements |
| CN116976995A (en) * | 2023-07-31 | 2023-10-31 | 平安银行股份有限公司 | Multi-target recommendation processing method and device |
| CN117422182A (en) * | 2023-12-18 | 2024-01-19 | 保大坊科技有限公司 | Data prediction method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵海燕，周萍， 陈庆奎，曹健: "推荐***公平性评价方法:现状与展望", 《小型微型计算机***》, vol. 43, no. 3, 23 February 2022 (2022-02-23), pages 1 - 10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117992676B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11556544B2 (en) | Search system and methods with integration of user annotations from a trust network | |
| US10255353B2 (en) | Individualized detailed program recommendations with active updating of viewer preferences | |
| US8666979B2 (en) | Recommending interesting content using messages containing URLs | |
| US9177063B2 (en) | Endorsing search results | |
| US8880516B2 (en) | Endorsing local search results | |
| US20070233736A1 (en) | Method and system for social and leisure life management | |
| US8909683B1 (en) | Method and system for communicating with internet resources to identify and supply content for webpage construction | |
| EP1804179A1 (en) | Service recommendation system and service recommendation method | |
| EP1933530A2 (en) | Information distribution system, information distribution apparatus and information distribution method | |
| EP3355213A1 (en) | Search system and methods with integration of user annotations from a trust network | |
| US20060059159A1 (en) | Online dating service providing response status tracking for a service subscriber | |
| US20090006371A1 (en) | System and method for recommending information resources to user based on history of user's online activity | |
| RU2008134151A (en) | SCALABLE SEARCH SYSTEM USING SEARCH SPECIALISTS | |
| EP2048612A1 (en) | System and method for searching network users | |
| JP2009545810A (en) | Temporal ranking of search results | |
| TW200816008A (en) | Adaptive dissemination of personalized and contextually relevant information | |
| WO2011011398A2 (en) | Systems and methods for utilizing and searching social network information | |
| JP2013149140A (en) | Information processing device and information processing method | |
| KR101151176B1 (en) | The Content Recommendation Method by Using Menu Preferences | |
| WO2008028150A2 (en) | Method and apparatus of obtaining or providing search results using user-based biases | |
| CN117992676B (en) | Intelligent scientific and technological achievement recommendation method based on big data | |
| US20220027976A1 (en) | Dynamically creating electronic events based on user product preferences and identified user location | |
| CN114302182B (en) | Push method, device, equipment and storage medium for television programs | |
| CN110737754A (en) | message response method, device, equipment and storage medium | |
| CN113194360B (en) | Video recommendation method and device, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240621 Address after: Room 105 and 106, Building 92, Lvyan New Village, No. 2 Jinsong Road, Sanyuan District, Sanming City, Fujian Province, 365000 yuan Patentee after: Fujian Junnuo Technology Achievement Transformation Service Co.,Ltd. Country or region after: China Patentee after: Fujian Junnuo Intellectual Property Operation Co.,Ltd. Address before: Room 105 and 106, Building 92, Lvyan New Village, No. 2 Jinsong Road, Sanyuan District, Sanming City, Fujian Province, 365000 yuan Patentee before: Fujian Junnuo Technology Achievement Transformation Service Co.,Ltd. Country or region before: China |