CN113569108B - Knowledge recommendation method based on project plan content and user behavior - Google Patents
Knowledge recommendation method based on project plan content and user behavior Download PDFInfo
- Publication number
- CN113569108B CN113569108B CN202111112247.9A CN202111112247A CN113569108B CN 113569108 B CN113569108 B CN 113569108B CN 202111112247 A CN202111112247 A CN 202111112247A CN 113569108 B CN113569108 B CN 113569108B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- character
- character string
- plan
- project
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a knowledge recommendation method based on project plan content and user behaviors, which belongs to the technical field of intelligent recommendation, and comprises the steps of extracting project names and plan names, respectively calculating matching degrees with knowledge names in a knowledge base, extracting project classifications and plan types to form project classification labels and plan type labels, recording the knowledge labels in the knowledge base, respectively calculating the matching degrees of the project classification labels and the plan type labels with the knowledge labels, weighting name parameters and label parameters, determining specific gravity values in the matching degree calculation, calculating weighted average matching degrees and sequencing, extracting the user behaviors, distributing weights, performing secondary sequencing, and providing knowledge recommendation according to results. According to the invention, the weighted average sorting is calculated through the matching degrees and the weights of all items, adaptive knowledge is correspondingly returned, and the accuracy of knowledge recommendation is high.
Description
Technical Field
The invention relates to a knowledge recommendation method based on project plan content and user behaviors, and belongs to the technical field of intelligent recommendation.
Background
In order to enable a user to quickly and accurately search knowledge corresponding to target information and a target project plan in a searching process, a knowledge recommendation method capable of comprehensively sequencing according to target project plan content and user behaviors is needed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a knowledge recommendation method based on project plan content and user behaviors, which comprises the following specific technical scheme: the method comprises the following steps:
step 1: extracting the project name and the plan name in the project plan content, and respectively calculating the matching degree of the project name and the plan name with the knowledge name in the knowledge base;
step 2: weighting the project name and the plan name to obtain the specific gravity value of the matching degree of the project name and the plan name with the knowledge name;
and step 3: extracting project classification and plan types in project plan contents to form project classification labels and plan type labels, recording all knowledge labels in a knowledge base, and respectively calculating the matching degrees of the project classification labels and the plan type labels with the knowledge labels;
and 4, step 4: weighting the project classification label and the plan type label to obtain the specific gravity value of the matching degree of the project classification label and the plan type label with the knowledge label;
and 5: calculating the project name, the plan name, the project classification label, the plan type label and the knowledge name and the weighted average matching degree of the label in the project plan content, and sequencing the knowledge corresponding to the project and the plan according to the weighted average matching degree;
step 6: when the project name, the plan name, the project classification label and the plan type label in the project plan content are equal to the weighted average matching degree of the names and the labels of a plurality of knowledge, acquiring user behaviors aiming at the knowledge, distributing weight, calculating knowledge heat, and performing secondary sequencing according to the knowledge heat;
and 7: and comprehensively obtaining knowledge recommendation based on project plan content and user behaviors according to the obtained weighted average matching degree and knowledge heat.
Further, if the item name, the plan name and the knowledge name in step 1 are regarded as character strings, the matching degree is defined as the longest common subsequence of the two character strings, wherein the longest common subsequence refers to a new character string formed by deleting some characters of the original character string without changing the relative sequence or deleting any characters,
the specific steps of calculating the matching degree are as follows:
step 1.1: comparing the length of the character string a with that of the character string b, when a is less than b, creating an empty array A, and recording the number of successfully matched characters as F, putting the first character in the character string a into the array A, traversing each character in the character string b, and recording F as 1 after the array A is successfully matched with the mth character in the character string b;
step 1.2: changing the character stored in the array A into a second character in the character string a, traversing from the (m + 1) th character in the character string b, if the array A is successfully matched with the h (h is more than m) th character in the character string b, marking F as 2, and if the matching is not successful, still marking F as 1;
step 1.3: changing the character stored in the array A into the third character in the character string a, traversing from the h +1 th character in the character string b, and so on until the t th character in the character string a in the array A traverses to the last character in the character string b, and recording the first traversal matching number as F 1 ；
Step 1.4: when the traversal of the character string b is completed and the character string a is not matched yet, starting the second traversal, putting the t +1 character in the character string a into the array A, traversing each character in the character string b, and marking F as 1 after the array A is successfully matched with the mth character in the character string b;
step 1.5: changing the characters stored in the array A into t +2 th characters in the character string a, traversing from the m +1 th character in the character string b, if the array A is successfully matched with the h (h is more than m) th character in the character string b, marking F as 2, and if the matching is not successful, still marking F as 1;
step 1.6: changing the character stored in the array A into the t +3 th character in the character string a, repeating the steps until the last character of the character string b is traversed, and recording the second-time traversal matching number as F 2 ；
Step 1.7: when the character string b traverses j times, the character string a completes matching, and the calculation formula of the matching number F of the character string a and the character string b is as follows: f = max (F) 1 ，F 2 ，…，F j ) The calculation formula of the matching degree f is as follows: f = (F/a + F/B)/2;
further, the matching degree of the item classification label and the plan type label with the knowledge label is calculated in the step 3, and the matching degree calculation is performed according to the method in the step 1;
each knowledgeThe number of the labels is i, the matching degree of each label of the knowledge with the item classification and the label calculated by the plan type is (F/A + F/B)/2, and then the matching degree of the label of the target item classification, the plan type and each knowledge in the knowledge base is: f = max [ (F) k /A k +F k /B k )/2] (1≤k≤i)。
Furthermore, in the step 2 and the step 4, weighting is performed, and the weights of the project name, the plan name, the project classification label and the plan type label are set to be lambda respectively 1 、λ 2 、λ 3 And λ 4 ，
The knowledge names of n pieces of knowledge in the knowledge base are sorted according to the ASCII code, and the matching degree of the item names and each piece of knowledge in the knowledge base is respectively
The matching degree of the plan name and each knowledge in the knowledge base is respectively
The matching degree of the item classification label and each knowledge label in the knowledge base is respectively
The matching degree of the plan type label and each knowledge label in the knowledge base is respectively
，
Then the weighted average degree of match
。
Further, the user behavior selected in step 5 includes: downloading, questioning, collecting, sharing and commenting, and respectively recording the times of downloading, questioning, collecting, sharing and commenting the knowledge as w 1 、w 2 、w 3 、w 4 And w 5 Weights are assigned to the standard behaviors and are recorded as μ 1 、μ 2 、μ 3 、μ 4 And mu 5 The knowledge heat of the knowledge with the same degree of matching as the weighted average of the target plan is
。
The invention has the beneficial effects that: the method calculates the matching degree of the plan and the knowledge based on the weight of the project plan content and the user behavior, calculates the weighted average value through each matching degree and the weight, sorts the knowledge according to the weighted average matching degree, and correspondingly returns the adaptive knowledge.
Drawings
Figure 1 is a flow chart of the present invention,
figure 2 is a matching degree calculation flow chart of the present invention,
in figure 3, the project information page is shown,
in figure 4, the project plan name page,
FIG. 5 is a recommendation results page.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings.
As shown in FIG. 1, the knowledge recommendation method based on project plan content and user behavior of the present invention comprises the following steps:
step 1: extracting the project name and the plan name in the project plan content, and respectively calculating the matching degree of the project name and the plan name with the knowledge name in the knowledge base; considering the project name, plan name and knowledge name as character strings, the matching degree is defined as the longest common subsequence of the two character strings, wherein the longest common subsequence refers to a new character string formed by deleting some characters of the original character string without changing the relative sequence or deleting any characters,
as shown in fig. 2, the specific steps of calculating the matching degree are:
step 1.1: comparing the lengths of the character strings a and b, when a is less than b, creating an empty array A, recording the number of successfully matched characters as F, putting the first character in the character string a into the array A, traversing each character in the character string b, and recording F as 1 when the array A is successfully matched with the mth character in the character string b;
step 1.2: changing the character stored in the array A into a second character in the character string a, traversing from the (m + 1) th character in the character string b, if the array A is successfully matched with the h (h is more than m) th character in the character string b, marking F as 2, and if the matching is not successful, still marking F as 1;
step 1.3: changing the character stored in the array A into the third character in the character string a, traversing from the h +1 th character in the character string b, and so on until the t-th character in the character string a in the array A traverses to the last character in the character string b, and marking the first traversal matching number as F 1 ；
Step 1.4: when the traversal of the character string b is completed and the character string a is not matched yet, starting the second traversal, putting the t +1 character in the character string a into the array A, traversing each character in the character string b, and marking F as 1 after the array A is successfully matched with the mth character in the character string b;
step 1.5: changing the characters stored in the array A into t +2 th characters in the character string a, traversing from the m +1 th character in the character string b, if the array A is successfully matched with the h (h is more than m) th character in the character string b, marking F as 2, and if the matching is not successful, still marking F as 1;
step 1.6: changing the character stored in the array A into the t +3 th character in the character string a, repeating the steps until the last character of the character string b is traversed, and recording the second-time traversal matching number as F 2 ；
Step 1.7: when the character string b traverses j times, the character string a completes matching, and the calculation formula of the matching number F of the character string a and the character string b is as follows: f = max (F) 1 ，F 2 ，…，F j ) The calculation formula of the matching degree f is as follows: f = (F/a + F/B)/2;
matching degree calculation example:
the character string a is 9 characters in total, the character string b1 is 16 characters in total, the character string a represents project plan content, the character string b1 and the character string b2 both represent knowledge in a knowledge base, a null array A is created, the number of characters successfully matched is marked as F,
putting the first character c in the character string a into an array A, traversing the character string b1 for the first time, recording the number of successfully matched characters as F1, successfully matching at the third character, and F1= 1;
putting a second character q in the character string a into the array A, traversing from a fourth character i of the character string b1, completing the traversal, failing to match the character q, and F1= 1;
putting the third character i in the character string a into the array A, traversing from the fourth character i of the character string b1, and successfully matching at the fourth character, F1= 2;
putting the fourth character g in the character string a into the array A, traversing from the fifth character k of the character string b1, and successfully matching at the sixth character, F1= 3;
putting the fifth character j in the character string a into the array A, traversing from the seventh character a of the character string b1, and successfully matching at the last character, F1= 4;
at this time, the character string a is not matched yet, and a second traversal is started:
putting the sixth character e in the character string a into the array A, traversing from the first character e of the character string b1, and successfully matching at the first character, F2= 1;
putting the seventh character g in the character string a into the array A, traversing from the second character s of the character string b1, and successfully matching at the sixth character, F2= 2;
putting the eighth character n in the character string a into the array A, traversing from the seventh character a of the character string b1, and successfully matching at the tenth character, wherein F2= 3;
putting the ninth character s in the character string a into the array A, traversing from the eleventh character e of the character string b1, and successfully matching at the twelfth character, F2= 4;
at this time, the character string a is matched, and the calculation formula of the matching number F is as follows: f = max (F1, F2) =4, degree of matching F = (F/a + F/B)/2= 0.347;
step 2: weighting the project name and the plan name, determining the specific gravity value of the project name and the plan name in the calculation of the matching degree with the knowledge name, and setting the weight of the project name and the plan name as lambda 1 And λ 2 ；
And step 3: extracting project classification and plan types in project plan contents to form project classification labels and plan type labels, recording all knowledge labels in a knowledge base, and respectively calculating the matching degrees of the project classification labels and the plan type labels with the knowledge labels, wherein the matching degree calculation is carried out according to the method in the step 1;
the number of the labels of each knowledge is i, the label matching degree calculated by each label of the knowledge and the item classification and the plan type is (F/A + F/B)/2, and then the label matching degree of the target item classification, the plan type and each knowledge in the knowledge base is as follows: f = max [ (F) k /A k +F k /B k )/2] (1≤k≤i)；
And 4, step 4: weighting the item classification label and the plan type label, determining the specific gravity value of the item classification label and the plan type label in the calculation of the matching degree with the knowledge label, and setting the weights of the item classification label and the plan type label as lambda respectively 3 And λ 4 ，
The knowledge names of n pieces of knowledge in the knowledge base are sorted according to the ASCII code, and the matching degree of the item names and each piece of knowledge in the knowledge base is respectively
The matching degree of the plan name and each knowledge in the knowledge base is respectively
The matching degree of the item classification label and each knowledge label in the knowledge base is respectively
The matching degree of the plan type label and each knowledge label in the knowledge base is respectively
；
And 5: calculating the weighted average matching degree of the name and the label of the project plan content and the name and the label of the knowledge, wherein the weighted average matching degree
And sorting the corresponding knowledge according to the result;
step 6: when the project plan content is equal to the weighted average matching degree of a plurality of knowledge, acquiring user behaviors aiming at the knowledge and distributing weights, wherein the selected user behaviors comprise: downloading, questioning, collecting, sharing and commenting, and respectively recording the times of downloading, questioning, collecting, sharing and commenting the knowledge as w 1 、w 2 、w 3 、w 4 And w 5 Weights are assigned to the standard behaviors and are recorded as μ 1 、μ 2 、μ 3 、μ 4 And mu 5 Then the knowledge with the same degree of matching as the weighted average of the target plan has a heat of knowledge of
Calculating knowledge heat and performing secondary sorting;
and 7: and obtaining knowledge recommendation based on project plan content and user behaviors according to the obtained weighted average matching degree and knowledge heat.
Example (b):
the project name is 'development management of hull coating based on knowledge engineering', the project is classified into 'ship class', the project comprises a plan name 'development of antirust coating process of bottom of steel high-speed ship', the plan type belongs to 'development class', the project information and the plan name are shown in figure 3 and figure 4,
in the project plan attribute, the weight of the project classification is 10%, the weight of the plan type is 10%, the weight of the project name is 30%, and the weight of the plan name is 50%; in user behaviors, the weight of downloading is 20%, the weight of questioning is 20%, the weight of collecting is 25%, the weight of sharing is 30%, and the weight of commenting is 5%;
there are several pieces of data in the knowledge base:
the number of matches between the knowledge with sequence number 1 and the item name F =1, and the degree of matching is
(ii) a The number of matches with the plan name is F =3, and the degree of matching is
(ii) a The number of matches between each knowledge tag and the item classification, F =1 and 0, and the degree of matching
，
Because of
Therefore, it is
(ii) a The number of matches of each knowledge label with the plan type F =0 and 1, and the degree of matching
，
Because of
Therefore, it is
，
Calculating the weighted average matching degree of the knowledge title with the sequence number of 1 and the label
；
The number of matches between the knowledge with sequence number 2 and the item name F =4, and the degree of matching is
(ii) a The number of matches with the plan name is F =4, and the matching degree is
(ii) a The matching number of each knowledge label and the item classification is F =0 and 1, and the matching degree is
，
Because of
Therefore, it is
(ii) a The matching number of each knowledge label and the plan type is F =0 and 3, and the matching degree is
,
Because of
Therefore, it is
，
Calculating the weighted average matching degree of the knowledge title with the sequence number of 2 and the label
；
The number of matches between the knowledge with sequence number 3 and the item name F =1, and the degree of matching is
(ii) a The number of matches with the plan name is F =3, and the degree of matching is
(ii) a The number of matches between each knowledge tag and the item classification, F =1 and 0, and the degree of matching
，
Because of
Therefore, it is
(ii) a The number of matches of each knowledge label with the plan type F =0 and 1, and the degree of matching
，
Because of
Therefore, it is
。
Calculating the weighted average matching degree of the knowledge title with the sequence number of 3 and the label
；
The weighted average matching degrees of the sequence number 1 and the sequence number 3 are equal, and the heat degrees of the two knowledge are continuously calculated;
the knowledge heat of number 1 is W =1 × 20% +2 × 25% = 0.75;
the knowledge heat of number 3 is W =3 × 25% +4 × 30% = 1.95;
according to the knowledge relevance and the knowledge heat, the knowledge recommendation sequence is 'application and popularization of the hull plate single-channel coating system construction', 'direct calculation and analysis of the strength of the steel catamaran' and 'analysis of the welding and fire stopping characteristics of the aluminum alloy high-speed ship', and the recommendation result is shown in fig. 5.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (1)
1. A knowledge recommendation method based on project plan content and user behavior is characterized in that: the method comprises the following steps:
step 1: extracting the project name and the plan name in the project plan content, and respectively calculating the matching degree of the project name and the plan name with the knowledge name in the knowledge base;
the project name, plan name and knowledge name are regarded as character strings, and the matching degree is defined as the longest common subsequence of the two character strings, wherein the longest common subsequence refers to a new character string formed by deleting some characters of the original character string without changing the relative sequence or deleting any characters,
the specific steps of calculating the matching degree are as follows:
step 1.1: comparing the length of the character string a with that of the character string b, when a is less than b, creating an empty array A, and recording the number of successfully matched characters as F, putting the first character in the character string a into the array A, traversing each character in the character string b, and recording F as 1 after the array A is successfully matched with the mth character in the character string b;
step 1.2: changing the character stored in the array A into a second character in the character string a, traversing from the (m + 1) th character in the character string b, if the array A is successfully matched with the h-th character in the character string b, h is greater than m, F is marked as 2, and if the matching is unsuccessful, F is still 1;
step 1.3: the character stored in the array A is changed into the third character in the character string a, and the h +1 th character in the character string b is usedTraversing, and so on, until the t character in the character string a in the array A traverses to the last character in the character string b, and the matching number of the first traversal is recorded as F 1 ；
Step 1.4: when the traversal of the character string b is completed and the character string a is not matched yet, starting the second traversal, putting the t +1 character in the character string a into the array A, traversing each character in the character string b, and marking F as 1 after the array A is successfully matched with the mth character in the character string b;
step 1.5: changing the characters stored in the array A into t +2 th characters in the character string a, traversing from the m +1 th character in the character string b, if the array A is successfully matched with the h-th character in the character string b, h is greater than m, F is marked as 2, and if the matching is unsuccessful, F is still 1;
step 1.6: changing the character stored in the array A into the t +3 th character in the character string a, repeating the steps until the last character of the character string b is traversed, and recording the second-time traversal matching number as F 2 ；
Step 1.7: when the character string b traverses j times, the character string a completes matching, and the calculation formula of the matching number F of the character string a and the character string b is as follows: f = max (F) 1 ，F 2 ，…，F j ) The calculation formula of the matching degree f is as follows: f = (F/a + F/B)/2;
step 2: weighting the project name and the plan name to obtain a specific gravity value of the matching degree of the project name and the plan name with the knowledge name;
and 3, step 3: extracting the project classification and the plan type in the project plan content to form a project classification label and a plan type label, recording all knowledge labels in a knowledge base, and respectively calculating the matching degree of the project classification label and the plan type label with the knowledge labels, wherein the matching degree calculation is carried out according to the method in the step 1;
the number of the labels of each knowledge is i, the label matching degree calculated by each label of the knowledge and the item classification and the plan type is (F/A + F/B)/2, and then the label matching degree of the target item classification, the plan type and each knowledge in the knowledge base is as follows: f = max [ (F) k /A k +F k /B k )/2] ，1≤k≤i；
And 4, step 4: weighting the project classification label and the plan type label to obtain the specific gravity value of the matching degree of the project classification label and the plan type label with the knowledge label;
and 5: calculating the project name, the plan name, the project classification label, the plan type label and the knowledge name and the weighted average matching degree of the label in the project plan content, and sequencing the knowledge corresponding to the project and the plan according to the weighted average matching degree;
the selected user behaviors include: downloading, questioning, collecting, sharing and commenting, and respectively recording the times of downloading, questioning, collecting, sharing and commenting the knowledge as w 1 、w 2 、w 3 、w 4 And w 5 Weights are assigned to the standard behaviors and are recorded as μ 1 、μ 2 、μ 3 、μ 4 And mu 5 The knowledge heat of the knowledge with the same degree of matching as the weighted average of the target plan is
；
Step 6: when the project name, the plan name, the project classification label and the plan type label in the project plan content are equal to the weighted average matching degree of the names and the labels of a plurality of knowledge, acquiring user behaviors aiming at the knowledge, distributing weight, calculating knowledge heat, and performing secondary sequencing according to the knowledge heat;
and 7: comprehensively obtaining knowledge recommendation based on project plan content and user behaviors according to the obtained weighted average matching degree and knowledge heat;
weighting in the step 2 and the step 4, and setting the weights of the project name, the plan name, the project classification label and the plan type label as lambda respectively 1 、λ 2 、λ 3 And λ 4 ，
The knowledge names of n pieces of knowledge in the knowledge base are sorted according to the ASCII code, and the matching degree of the item names and each piece of knowledge in the knowledge base is respectively
The matching degree of the plan name and each knowledge in the knowledge base is respectively
The matching degree of the item classification label and each knowledge label in the knowledge base is respectively
The matching degree of the plan type label and each knowledge label in the knowledge base is respectively
，
Then the weighted average degree of match
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111112247.9A CN113569108B (en) | 2021-09-23 | 2021-09-23 | Knowledge recommendation method based on project plan content and user behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111112247.9A CN113569108B (en) | 2021-09-23 | 2021-09-23 | Knowledge recommendation method based on project plan content and user behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113569108A CN113569108A (en) | 2021-10-29 |
| CN113569108B true CN113569108B (en) | 2022-08-16 |
Family
ID=78174212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111112247.9A Active CN113569108B (en) | 2021-09-23 | 2021-09-23 | Knowledge recommendation method based on project plan content and user behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113569108B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846056B (en) * | 2018-06-01 | 2021-04-23 | 云南电网有限责任公司电力科学研究院 | Scientific and technological achievement review expert recommendation method and device |
| CN112818227B (en) * | 2021-01-29 | 2024-03-19 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN112765441B (en) * | 2021-04-07 | 2021-11-02 | 北京零号窗网络信息技术有限公司 | Enterprise policy information multiple dynamic intelligent matching recommendation method for digital government affairs |
-
2021
- 2021-09-23 CN CN202111112247.9A patent/CN113569108B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113569108A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8190556B2 (en) | Intellegent data search engine | |
| CN111105209A (en) | Job resume matching method and device suitable for post matching recommendation system | |
| CN108509461A (en) | A kind of sequence learning method and server based on intensified learning | |
| CN110851590A (en) | Method for classifying texts through sensitive word detection and illegal content recognition | |
| CN110633667B (en) | Action prediction method based on multitask random forest | |
| CN110689371B (en) | Intelligent marketing cloud service platform based on AI and big data | |
| CN112685642A (en) | Label recommendation method and device, electronic equipment and storage medium | |
| CN109189892A (en) | A kind of recommended method and device based on article review | |
| CN108255881A (en) | It is a kind of to generate the method and device for launching keyword | |
| CN106951565A (en) | File classification method and the text classifier of acquisition | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN104615621B (en) | Correlation treatment method and system in search | |
| Bartlett et al. | Species determination using AI machine-learning algorithms: Hebeloma as a case study | |
| CN113569108B (en) | Knowledge recommendation method based on project plan content and user behavior | |
| WO2008062822A1 (en) | Text mining device, text mining method and text mining program | |
| CN112598405A (en) | Business project data management method and system based on big data | |
| CN111597400A (en) | Computer retrieval system and method based on way-finding algorithm | |
| CN113076490B (en) | Case-related microblog object-level emotion classification method based on mixed node graph | |
| CN115936389A (en) | Big data technology-based method for matching evaluation experts with evaluation materials | |
| CN115329169A (en) | Archive filing calculation method based on deep neural model | |
| CN111178292A (en) | Vehicle type identification method, device and equipment | |
| CN116228484B (en) | Course combination method and device based on quantum clustering algorithm | |
| JP2003108576A (en) | Database control device and database control method | |
| CN116579344B (en) | Case main body extraction method | |
| CN112463928B (en) | Technical list generation method and system for field evaluation prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |