CN114610776A - Digital solution recommendation method and device based on label - Google Patents
Digital solution recommendation method and device based on label Download PDFInfo
- Publication number
- CN114610776A CN114610776A CN202210157528.4A CN202210157528A CN114610776A CN 114610776 A CN114610776 A CN 114610776A CN 202210157528 A CN202210157528 A CN 202210157528A CN 114610776 A CN114610776 A CN 114610776A
- Authority
- CN
- China
- Prior art keywords
- label
- scheme
- solution
- digital
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000002452 interceptive effect Effects 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012552 review Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a digital solution recommendation method and device based on labels, wherein the method comprises the following steps: acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to the digital solutions; according to the access history of the digital solutions of the target user, counting a plurality of scheme sub-label values corresponding to each accessed digital solution, and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; and selecting a preset number of digital solutions as a plurality of recommended solutions according to the weight value of the solution sub-label corresponding to each accessed digital solution. By adopting the recommendation method and device provided by the invention, the recommendation scheme which is in line with the expectation of the user can be quickly and accurately screened out by modeling the solution and designing the label.
Description
Technical Field
The invention relates to the field of data processing, in particular to a digital solution recommendation method and device based on a label.
Background
At present, existing forms of digital solutions are dispersed in documents of all storage systems, so that complete solutions cannot be provided for other users, the relationship between the digital solutions and users is a pull-type relationship, and when a certain digital solution needs to be called or searched, the users need to manually search a project achievement library; for enterprises with non-uniformly filed project achievements, digital practitioners find the digital solution achievements wanted by themselves difficultly.
Moreover, the existing personalized solution recommendation method and system recommendation algorithm are not comprehensive enough in consideration of factors, only basic information and problem information of a user are considered, and consideration of dynamic factors such as user behaviors and preferences is lacked, and consideration of factors of the solution and interaction factors of the user and the solution is lacked, so that the solution finally recommended to the user is not comprehensive enough, or solution content does not accord with user expectation, retrieval time of the user is influenced, and time cost is increased.
Disclosure of Invention
The embodiment of the invention provides a tag-based digital solution recommendation method and device, which can quickly and accurately screen out a recommendation scheme meeting the expectation of a user by modeling the solution and designing tags.
To achieve the above object, a first aspect of embodiments of the present application provides a tag-based digital solution recommendation method, including:
attaching a corresponding user label to each user according to the user label model, and attaching a corresponding scheme label to each digital solution according to the solution label model;
attaching an associated basic label and an associated interactive label to each digital solution according to an associated label model by combining the user label and the scheme label;
acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to the digital solutions;
according to the access history of the digital solutions of the target user, counting a plurality of scheme sub-label values corresponding to each accessed digital solution, and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values;
and selecting a preset number of digital solutions as a plurality of recommended solutions according to the weight value of the solution sub-label corresponding to each accessed digital solution.
In a possible implementation manner of the first aspect, the calculation manner of the sub-label weight value in the scheme is as follows:
counting a plurality of scheme sub-label values corresponding to each accessed digital solution;
counting the occurrence times of each scheme sub-label value according to the plurality of scheme sub-label values;
selecting a preset number of scheme sub-label values as a label reference value set according to the sequence of the occurrence frequency of each scheme sub-label value from large to small;
calculating the occurrence frequency of each scheme sub-label value according to the occurrence frequency of each scheme sub-label value and the label reference value set;
calculating a scheme sub-label weight value according to the occurrence frequency of each scheme sub-label value and the hit value of each scheme sub-label value; the hit value of each scheme sub-label value depends on the mode of the various scheme sub-label values in the label reference value set.
In a possible implementation manner of the first aspect, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further includes:
and sequencing the recommended schemes according to the sequence of the weight values of the scheme sub-labels corresponding to each accessed digital solution from large to small.
In one possible implementation manner of the first aspect, the associated interactive tags include an access tag, a like tag, an attention tag, and a comment tag.
In a possible implementation manner of the first aspect, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further includes:
acquiring access labels corresponding to a plurality of recommendation schemes, and counting the user access number of each recommendation scheme in unit time;
calculating a correlation coefficient among a plurality of recommendation schemes according to the user access number of each recommendation scheme in the unit time;
and sequencing the plurality of recommended schemes according to the sequence of the correlation coefficient values among the schemes from large to small.
In a possible implementation manner of the first aspect, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further includes:
acquiring an access tag, a praise tag, an attention tag and a comment tag corresponding to each recommendation scheme, and counting effective reading numbers, total reading time, user average reading time, review numbers, praise numbers, comment numbers and collection numbers of each recommendation scheme;
acquiring a scheme label of each recommended scheme, and evaluating a basic score of each recommended scheme according to a preset standard;
calculating the quality performance score corresponding to each solution according to the effective reading number, the total reading time, the average reading time of the user, the review number, the praise number, the comment number, the collection number and the basis of each recommended scheme;
and sequencing the plurality of recommended schemes according to the sequence from large to small of the quality performance scores corresponding to each solution.
In a possible implementation manner of the first aspect, the preset criteria include a business analysis domain, a solution domain, and a performance price domain;
the business analysis domain, the solution domain and the valence value domain are defined according to the life cycle of the digital solution in the power industry.
In a possible implementation manner of the first aspect, the service analysis domain includes a scheme summary, a service current status, a service flow, and a service pain point;
the solution domain includes a solution target and an overall solution;
the performance value field includes: system operation analysis, scheme success and value analysis.
In a possible implementation manner of the first aspect, a key technology label corresponding to each recommended scheme is obtained, recommended schemes with the same value of the key technology label are selected, and other recommended schemes are excluded; the solution tags include key technology tags.
A second aspect of an embodiment of the present application provides a tag-based digital solution recommendation apparatus, including:
the user label module is used for attaching a corresponding user label to each user according to the user label model and attaching a corresponding scheme label to each digital solution according to the solution label model;
the interactive label module is used for attaching an associated basic label and an associated interactive label to each digital solution according to an associated label model by combining the user label and the scheme label;
the access history module is used for acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to each digital solution;
the weight calculation module is used for counting a plurality of scheme sub-label values corresponding to each accessed digital solution according to the access history of the digital solution of the target user and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values;
and the scheme selection module selects a preset number of digital solutions as a plurality of recommended schemes according to the weight value of the scheme sub-label corresponding to each accessed digital solution.
According to the method and the device for recommending the digital solutions based on the labels, which are provided by the embodiment of the invention, the scheme labels and the associated interactive labels are attached to each digital solution in the database, so that the digital solutions distributed at various places are linked with each user, and the validity of each digital solution is evaluated according to the scheme labels and the preset standard, so that the scheme integrity of the recommended scheme is ensured.
And when the recommendation schemes are screened, selecting a preset number of digital solutions as a plurality of recommendation schemes according to the scheme sub-label weight value corresponding to each accessed digital solution. Because the relevance and the content accuracy of the digital solution and other schemes can be reflected by the weight value of the scheme sub-label, the recommended scheme screening is carried out according to the weight value of the scheme sub-label, the scheme content can be enabled to meet the expectation of a user, and meanwhile, related solutions cannot be omitted, and the scheme sub-label weight value is obtained by counting the occurrence frequency of each scheme sub-label representing the scheme content.
After the screening is finished, the user can sort the solution according to the user requirements by taking the quality performance scores and the relevance of the solutions as the standards, and the retrieval results meeting the expectations of the user are ranked in front, so that the retrieval efficiency of the user is further improved.
Drawings
FIG. 1 is a schematic flowchart of a tag-based digital solution recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a user tag model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the composition of a solution label model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the components of an associate label model according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a scheme sub-label weight value calculation according to an embodiment of the present invention;
FIG. 6 is a block diagram illustrating a default criteria according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a tag-based digital solution recommendation method, where the method includes:
and S10, attaching a corresponding user label to each user according to the user label model, and attaching a corresponding scheme label to each digital solution according to the solution label model.
And S11, attaching an associated basic label and an associated interactive label to each digital solution according to the associated label model by combining the user label and the scheme label.
S12, acquiring the access history of the digital solutions of the target user according to the associated basic labels and the associated interactive labels corresponding to the digital solutions.
S13, according to the access history of the digital solutions of the target users, counting a plurality of scheme sub-label values corresponding to each accessed digital solution, and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values.
S14, selecting a preset number of digital solutions as a plurality of recommended solutions according to the weight value of the sub-label of the solution corresponding to each accessed digital solution.
Different from the existing digital solution recommendation scheme, in S10-S12, the present embodiment attaches a scheme label representing the attribute of the scheme itself and an associated label representing the attribute of interaction with the user to the scheme, and by attaching the associated labels, the scheme distributed in various places is linked with the user, and the scheme label itself can facilitate the user to see the basic content of the scheme.
When the user is labeled, the user label model is used as the basis, as shown in fig. 2. Fig. 2 is a user tag model adopted in the present embodiment, where the user tag model includes: base tags, preference tags, behavior tags, capability tags. The user basic label comprises a user ID, a name, a gender, a department, an age, a duty, a driver's job number and a subordinate job number; the user ability label comprises a study calendar, a specialty, a title, the working age of the specialty, the last work specialty, the obtained honor, the obtained certificate and the obtained patent; the user preference label comprises channel preference, access path preference, service domain preference, capability domain preference and scene preference; the user behavior tags include last login time, last 30 days of login times, common login time period, active state, interaction aggressiveness, and terminal usage duration.
When a solution is labeled, a solution label model is used as a basis, as shown in fig. 3. Fig. 3 is a scenario tag model adopted in the present embodiment, and the scenario tag model includes a base tag, a dependent tag, an interactive tag, and a key technical attribute tag. The solution basic label comprises a scheme ID, a scheme name, a service pain point, a service responsible person, a technical responsible person, scheme conversion time, year, department, work group, an associated scheme and a system name; the solution dependent label comprises an affiliated scene, an affiliated business domain, an affiliated department and a construction unit; the solution evaluation labels comprise the number of praised, the number of commented, the number of collected cases, whether excellent cases exist, the attention receiving degree, the number of accessed times in the last month, the number of accessed times in the local department, the number of accessed times in other departments, the number of concerned times in the local business domain and the number of concerned times in other business domains; the key technical labels of the solution include whether artificial intelligence is involved, whether a space-time map is involved, whether RPA is involved, whether data analysis is involved, whether the Internet of things is involved, and whether a block chain is involved.
When the scheme is labeled with the associated labels (the associated base label and the associated interactive label), the scheme label model is used as a basis, as shown in fig. 4. Fig. 4 is a scheme associated label model adopted in the present embodiment, which includes a base label, an access label, a like label, an attention label, and an evaluation label. The basic labels comprise visitor IDs, visited scheme IDs, visiting time, whether to pay attention to the scheme, the number of visits in the last week, visiting paths and visiting channels; the conversion label comprises a conversion person ID, a scheme ID and conversion time; the approval tag comprises an approval person ID, a scheme ID, approval time and whether to cancel; the attention label comprises attention time, whether to cancel and personal attention entering times; the comment tag comprises a rater ID, a scheme ID, comment time, comment content, hit keywords and comment frequency.
It should be noted that the user tag model, the scheme tag model and the associated tag model are not unique, and the attributes and types of the sub-tags in the user tag model, the scheme tag model and the associated tag model can be adjusted according to the business scenario. This is only one common model that is more practical.
After the labels are attached to the user and the digital schemes, the digital schemes related to the user search target can be quickly screened out by combining the label weight values on the basis of the following recommended schemes selected for the user. The calculation of the weight value of the scheme label is essentially based on similarity calculation between schemes, and a weight calculation method is taken as an example for description below.
Illustratively, the calculation manner of the scheme sub-tag weight value is as follows:
and counting a plurality of scheme sub-label values corresponding to each accessed digital solution.
And counting the occurrence times of the sub-label value of each scheme according to the plurality of scheme sub-label values.
And selecting the multiple scheme sub-label values of preset types as a label reference value set according to the sequence of the occurrence times of each scheme sub-label value from large to small.
And calculating the occurrence frequency of each scheme sub-label value according to the occurrence frequency of each scheme sub-label value and the label reference value set.
Calculating a scheme sub-label weight value according to the occurrence frequency of each scheme sub-label value and the hit value of each scheme sub-label value; the hit value of each scheme sub-label value depends on whether the scheme sub-label value exists in the mode of various scheme sub-label values in the label reference value set.
Please refer to fig. 5. In this example, after analyzing the historical access records of the target users, the values of the sub-tags included in the scheme tags in each accessed digital solution are listed first. In the figure, "tag value 1-1" means that the first seed tag value is 1, "tag value 1-2" means that the first seed tag value is 2, "tag value 2-2" means that the second seed tag value is 2, and so on: in the label value X-Y, X represents the sub-label type, and Y represents the sub-label value. It should be noted that the historical access record used herein is obtained by performing statistics according to the associated basic tag and the associated interactive tag corresponding to each digital solution.
Assuming that a user has historically browsed n cases, each case having m sub-label attributes, an n x m label matrix is constructed. And then calculating the number of times of the occurrence of the label attribute value of each column of the matrix, and recording and storing. In this embodiment, the occurrence frequency of each scheme sub-label value is counted, and the scheme sub-label value of a preset number of types (here, the preset number is 5, which means that 5 seed labels are selected, and 5 types) is selected as the label reference value set. Calculating the proportion of the former five label values in the label reference value set, wherein the specific calculation mode is as follows: in this embodiment, the number of elements of the tag reference value set is the sum of the frequency of occurrence of the first five tag values.
And calculating the weight values of the top 5 label values of all the solutions to be recommended according to the formula of whether the sigma label weight and the label value hit (the hit is 1, and otherwise, the hit is 0). Because the first 5 tag values in each scheme are different, taking the first tag value as an example, the tag value of scheme 1 is 1, the mode of the first tag value in the tag reference value set is 1, and is the same as the mode, so the hit value is 1. The tag value of scheme 2 is 2, while the mode of the first tag value in the tag reference value set is 1, so the hit value is 0.
Illustratively, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further comprises:
and sequencing the recommended schemes according to the sequence of the weight values of the scheme sub-labels corresponding to each accessed digital solution from large to small.
Illustratively, the associated interactive tags include an access tag, a like tag, an attention tag, and a comment tag.
Illustratively, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further comprises:
acquiring access labels corresponding to a plurality of recommendation schemes, and counting the user access number of each recommendation scheme in unit time;
calculating a correlation coefficient among a plurality of recommendation schemes according to the user access number of each recommendation scheme in the unit time;
and sequencing the plurality of recommended schemes according to the sequence of the correlation coefficient values among the schemes from large to small.
Assuming that there are N (x) users browsing the current solution x and N (y) users browsing the solution y, the correlation coefficient of the solutions x and y is
And finally, recommending the scheme for the user according to the recommendation sequence of the correlation coefficient from high to low.
Illustratively, after the selecting a preset number of digital solutions as the plurality of recommended solutions, the method further comprises:
acquiring an access tag, a praise tag, an attention tag and a comment tag corresponding to each recommendation scheme, and counting effective reading numbers, total reading time, user average reading time, review numbers, praise numbers, comment numbers and collection numbers of each recommendation scheme;
acquiring a scheme label of each recommended scheme, and evaluating a basic score of each recommended scheme according to a preset standard;
calculating the quality performance score corresponding to each solution according to the effective reading number, the total reading time, the average reading time of the user, the review number, the praise number, the comment number, the collection number and the basis of each recommended scheme;
and sequencing the plurality of recommended schemes according to the sequence of the quality performance scores corresponding to each solution from big to small.
Taking a digital solution with a basic score of 60 as an example, the solution corresponds to an effective reading number B, a total reading time (minute) C, a user average reading time (minute) D, a review number E, a praise number F, a comment number G and a collection number H, and the solution quality performance score is obtained through accumulation, and a calculation formula is shown as follows: q ═ a +5B + C + D +3E +2F + G + 2H. The example A, B, C, D, E, G in the above formula can be set according to actual requirements.
Referring to fig. 6, the preset criteria illustratively include a business analysis field, a solution field, and a performance value field.
The business analysis domain, the solution domain, and the valence value domain are defined according to a power industry digital solution lifecycle.
Illustratively, the business analysis domain includes a scheme summary, a business current situation, a business process and a business pain point;
the solution domain includes a solution target and an overall solution;
the performance value field includes: system operation analysis, scheme success and value analysis.
Exemplarily, acquiring a key technology label corresponding to each recommendation scheme, selecting the recommendation scheme with the same value of the key technology label, and excluding other recommendation schemes; the solution tags include key technology tags.
The secondary screening is carried out by adopting the key technology label, so that the range of the recommendation result can be further reduced, and the reading time and the retrieval time of the user are shortened.
According to the method and the device for recommending the digital solutions based on the labels, which are provided by the embodiment of the invention, the scheme labels and the associated interactive labels are attached to each digital solution in the database, so that the digital solutions distributed at various places are linked with each user, and the validity of each digital solution is evaluated according to the scheme labels and the preset standard, so that the scheme integrity of the recommended scheme is ensured.
And when the recommendation schemes are screened, selecting a preset number of digital solutions as a plurality of recommendation schemes according to the scheme sub-label weight value corresponding to each accessed digital solution. Because the relevance and the content accuracy of the digital solution and other schemes can be reflected by the weight value of the scheme sub-label, the recommended schemes are screened according to the weight value of the scheme sub-label, so that the scheme content can meet the expectation of a user and related solutions cannot be omitted, and the scheme sub-label weight value is obtained by counting the occurrence frequency of each scheme sub-label representing the scheme content.
After the screening is finished, the user can sort the solution according to the user requirements by taking the quality performance scores and the relevance of the solutions as the standards, and the retrieval results meeting the expectations of the user are ranked in front, so that the retrieval efficiency of the user is further improved.
A second aspect of an embodiment of the present application provides a tag-based digital solution recommendation apparatus, including: the system comprises a user tag module, an interactive tag module, an access history module, a weight calculation module and a scheme selection module.
And the user label module is used for attaching a corresponding user label to each user according to the user label model and attaching a corresponding scheme label to each digital solution according to the solution label model.
And the interactive label module is used for combining the user label and the scheme label and attaching an associated basic label and an associated interactive label to each digital solution according to the associated label model.
And the access history module is used for acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to each digital solution.
The weight calculation module is used for counting a plurality of scheme sub-label values corresponding to each accessed digital solution according to the access history of the digital solution of the target user and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values.
And the scheme selection module selects a preset number of digital solutions as a plurality of recommended schemes according to the weight value of the scheme sub-label corresponding to each accessed digital solution.
According to the label-based digital solution recommendation device provided by the embodiment of the invention, the scheme label and the associated interactive label are attached to each digital solution in the database, so that the digital solutions distributed at various places are linked with each user, and the validity of each digital solution is evaluated according to the scheme label and the preset standard, so that the scheme integrity of the recommended scheme is ensured.
And when the recommendation schemes are screened, selecting a preset number of digital solutions as a plurality of recommendation schemes according to the scheme sub-label weight value corresponding to each accessed digital solution. Because the relevance and the content accuracy of the digital solution and other schemes can be reflected by the weight value of the scheme sub-label, the recommended schemes are screened according to the weight value of the scheme sub-label, so that the scheme content can meet the expectation of a user and related solutions cannot be omitted, and the scheme sub-label weight value is obtained by counting the occurrence frequency of each scheme sub-label representing the scheme content.
After the screening is finished, the user can sort the solution according to the user requirements by taking the quality performance scores and the relevance of the solutions as the standards, and the retrieval results meeting the expectations of the user are ranked in front, so that the retrieval efficiency of the user is further improved.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A label-based digital solution recommendation method is characterized in that,
attaching a corresponding user label to each user according to the user label model, and attaching a corresponding scheme label to each digital solution according to the solution label model;
attaching an associated basic label and an associated interactive label to each digital solution according to an associated label model by combining the user label and the scheme label;
acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to the digital solutions;
according to the access history of the digital solutions of the target user, counting a plurality of scheme sub-label values corresponding to each accessed digital solution, and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values;
and selecting a preset number of digital solutions as a plurality of recommended solutions according to the weight value of the solution sub-label corresponding to each accessed digital solution.
2. The tag-based digital solution recommendation method of claim 1, wherein the scheme sub-tag weight values are calculated by:
counting a plurality of scheme sub-label values corresponding to each accessed digital solution;
counting the occurrence times of each scheme sub-label value according to the plurality of scheme sub-label values;
selecting a plurality of scheme sub-label values of preset types as a label reference value set according to the sequence of the occurrence frequency of each scheme sub-label value from large to small;
calculating the occurrence frequency of each scheme sub-label value according to the occurrence frequency of each scheme sub-label value and the label reference value set;
calculating a scheme sub-label weight value according to the occurrence frequency of each scheme sub-label value and the hit value of each scheme sub-label value; the hit value of each scheme sub-label value depends on the mode of the various scheme sub-label values in the label reference value set.
3. The tag-based digitizing solution recommendation method of claim 1, further comprising, after the selecting a preset number of digitizing solutions as the plurality of recommendations:
and sequencing the recommended schemes according to the sequence of the weight values of the scheme sub-labels corresponding to each accessed digital solution from large to small.
4. The tag-based digital solution recommendation method of claim 1, wherein the associated interactive tags include an access tag, a likes tag, an concerns tag, and a comments tag.
5. The tag-based digitizing solution recommendation method of claim 4, further comprising, after the selecting a preset number of digitizing solutions as the plurality of recommendations:
acquiring access labels corresponding to a plurality of recommendation schemes, and counting the user access number of each recommendation scheme in unit time;
calculating a correlation coefficient among a plurality of recommendation schemes according to the user access number of each recommendation scheme in the unit time;
and sequencing the plurality of recommended schemes according to the sequence of the correlation coefficient values among the schemes from large to small.
6. The tag-based digitizing solution recommendation method of claim 4, further comprising, after the selecting a preset number of digitizing solutions as the plurality of recommendations:
acquiring an access tag, a praise tag, an attention tag and a comment tag corresponding to each recommendation scheme, and counting effective reading numbers, total reading time, user average reading time, review numbers, praise numbers, comment numbers and collection numbers of each recommendation scheme;
acquiring a scheme label of each recommended scheme, and evaluating a basic score of each recommended scheme according to a preset standard;
calculating the quality performance score corresponding to each solution according to the effective reading number, the total reading time, the average reading time of the user, the review number, the praise number, the comment number, the collection number and the basis of each recommended scheme;
and sequencing the plurality of recommended schemes according to the sequence of the quality performance scores corresponding to each solution from big to small.
7. The tag-based digital solution recommendation method according to claim 6, wherein the preset criteria include a business analysis field, a solution field, and a performance value field;
the business analysis domain, the solution domain and the valence value domain are defined according to the life cycle of the digital solution in the power industry.
8. The tag-based digital solution recommendation method of claim 7, wherein the business analysis domain comprises a scenario summary, a business current situation, a business process and a business pain point;
the solution domain includes a solution target and an overall solution;
the performance value field includes: system operation analysis, scheme success and value analysis.
9. The tag-based digitizing solution recommendation method of claim 1, further comprising, after the selecting a preset number of digitizing solutions as the plurality of recommendations:
acquiring a key technical label corresponding to each recommendation scheme, selecting the recommendation schemes with the same value of the key technical label, and excluding other recommendation schemes; the solution tags include key technology tags.
10. A tag-based digital solution recommendation apparatus, comprising:
the user label module is used for attaching a corresponding user label to each user according to the user label model and attaching a corresponding scheme label to each digital solution according to the solution label model;
the interactive label module is used for attaching an associated basic label and an associated interactive label to each digital solution according to an associated label model by combining the user label and the scheme label;
the access history module is used for acquiring the access history of the digital solutions of the target user according to the associated basic tags and the associated interactive tags corresponding to each digital solution;
the weight calculation module is used for counting a plurality of scheme sub-label values corresponding to each accessed digital solution according to the access history of the digital solution of the target user and calculating a scheme sub-label weight value corresponding to each accessed digital solution according to a preset matching rule; the accessed digital solution is a digital solution accessed by the target user; the scheme sub-label weight value is obtained by calculation according to the appearance frequency of all scheme sub-label values;
and the scheme selection module selects a preset number of digital solutions as a plurality of recommended schemes according to the weight value of the scheme sub-label corresponding to each accessed digital solution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157528.4A CN114610776A (en) | 2022-02-21 | 2022-02-21 | Digital solution recommendation method and device based on label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157528.4A CN114610776A (en) | 2022-02-21 | 2022-02-21 | Digital solution recommendation method and device based on label |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114610776A true CN114610776A (en) | 2022-06-10 |
Family
ID=81860064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210157528.4A Pending CN114610776A (en) | 2022-02-21 | 2022-02-21 | Digital solution recommendation method and device based on label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114610776A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115563311A (en) * | 2022-10-21 | 2023-01-03 | 中国能源建设集团广东省电力设计研究院有限公司 | Document marking and knowledge base management method and knowledge base management system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108271076A (en) * | 2017-01-03 | 2018-07-10 | 武汉斗鱼网络科技有限公司 | A kind of method and device for recommending direct broadcasting room |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
| CN112989209A (en) * | 2021-05-10 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Content recommendation method, device and storage medium |
| CN113393306A (en) * | 2021-07-09 | 2021-09-14 | 中国建设银行股份有限公司 | Product recommendation method and device, electronic equipment and computer readable medium |
-
2022
- 2022-02-21 CN CN202210157528.4A patent/CN114610776A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108271076A (en) * | 2017-01-03 | 2018-07-10 | 武汉斗鱼网络科技有限公司 | A kind of method and device for recommending direct broadcasting room |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
| CN112989209A (en) * | 2021-05-10 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Content recommendation method, device and storage medium |
| CN113393306A (en) * | 2021-07-09 | 2021-09-14 | 中国建设银行股份有限公司 | Product recommendation method and device, electronic equipment and computer readable medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115563311A (en) * | 2022-10-21 | 2023-01-03 | 中国能源建设集团广东省电力设计研究院有限公司 | Document marking and knowledge base management method and knowledge base management system |
| CN115563311B (en) * | 2022-10-21 | 2023-09-15 | 中国能源建设集团广东省电力设计研究院有限公司 | Document labeling and knowledge base management method and knowledge base management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230306046A1 (en) | Computer implemented method for quantifying the revelance of documents | |
| CN102549563B (en) | Semantic exchange | |
| US8090621B1 (en) | Method and system for associating feedback with recommendation rules | |
| TWI420329B (en) | Method for context-based community-driven suggestions for media annotation and apparatus, computer readable storage mediu, thereof | |
| US20170213272A1 (en) | Computer resource ranking for interconnected user profiles | |
| US9449078B2 (en) | Evaluating the ranking quality of a ranked list | |
| US20130086052A1 (en) | Method and System of Information Matching in Electronic Commerce Website | |
| US20040054572A1 (en) | Collaborative filtering | |
| Xu et al. | Modeling professional similarity by mining professional career trajectories | |
| TWI455051B (en) | Geographic merchandise matching system, associate apparatus and method | |
| WO2020256854A1 (en) | Data sampling for model exploration | |
| TW200915108A (en) | System and method for permitting geographically-pertinent information to be ranked by users according to users' geographic proximity to information and to each other for affecting the ranking of such information | |
| US20060036603A1 (en) | Apparatus, system, and methods for collaborative research | |
| CN108885624A (en) | Information recommendation system and method | |
| Japec et al. | AAPOR report on big data | |
| Mukherjee | Do open‐access journals in library and information science have any scholarly impact? A bibliometric study of selected open‐access journals using Google Scholar | |
| CN106354867A (en) | Multimedia resource recommendation method and device | |
| CN112148760B (en) | Big data screening method and device | |
| CN111506727A (en) | Text content category acquisition method and device, computer equipment and storage medium | |
| CN114610776A (en) | Digital solution recommendation method and device based on label | |
| Bourne | Requirements, Criteria and Measures of Performance of Information Storage and Retrieval Systems | |
| US20150142782A1 (en) | Method for associating metadata with images | |
| KR102134544B1 (en) | Method for book recommendation for purchasing in library and apparatus for performing the same | |
| US20200160359A1 (en) | User-experience development system | |
| CN113420096B (en) | Index system construction method, device, equipment 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 |