CN118096325B - Enterprise safety product recommendation method, device, equipment and storage medium - Google Patents
Enterprise safety product recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN118096325B CN118096325B CN202410502552.6A CN202410502552A CN118096325B CN 118096325 B CN118096325 B CN 118096325B CN 202410502552 A CN202410502552 A CN 202410502552A CN 118096325 B CN118096325 B CN 118096325B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- safety
- product
- security
- products
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000006399 behavior Effects 0.000 claims abstract description 56
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 230000015654 memory Effects 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of intelligent recommendation, and discloses an enterprise safety product recommendation method, device, equipment and storage medium, wherein the method comprises the following steps: acquiring the weak points of the track job of the current enterprise according to a preset enterprise main body responsibility track job point evaluation system; matching the weak points of the track with different types of safety products to obtain the original scores of the safety products of the different types; calculating the demand level of the safety product according to the original score and the enterprise historical behaviors; according to the method and the system, the first preset number of types of safety products are recommended for the current enterprise according to the demand level, and the real demands of the enterprise can be obtained by combining the weak points of the track of the enterprise and the historical behaviors, so that the accuracy of recommendation is improved.
Description
Technical Field
The invention relates to the technical field of intelligent recommendation, in particular to an enterprise safety product recommendation method, device, equipment and storage medium.
Background
With the continuous development of economy, the demands of enterprises on safe products and services are continuously increased, the safe emergency industry is vigorously developed, then, no recommendation method and system specially aiming at the enterprise safe products exist at present, in the prior art, a recommendation method for general products mostly adopts collaborative recommendation based on products and users, and the demands of enterprise users are difficult to meet.
For the recommendation of the safety products, currently, mainly, enterprises search product suppliers scattered in the market according to the self requirements of the enterprises on the safety products, and only users and the products are considered in the recommendation method aiming at the general products, and the recommendation is not carried out aiming at weak points of the enterprise performing staff, so that the recommendation accuracy is low, and the requirements of the enterprise users are difficult to adapt. The enterprise actively searches for the safe product suppliers, which has low efficiency, small range and fuzzy demand, and it is difficult to find suppliers with accurate matching demands.
Therefore, there is a need for an intelligent recommendation method suitable for enterprise security products, thereby improving the accuracy of recommendation.
Disclosure of Invention
In view of the above, the invention provides a method, a device, equipment and a storage medium for recommending enterprise safety products, so as to solve the technical problem that the existing intelligent recommending method has low recommending accuracy for safety products.
In a first aspect, the present invention provides an enterprise security product recommendation method, including: acquiring the weak points of the track job of the current enterprise according to a preset enterprise main body responsibility track job point evaluation system; matching the track points with different types of safety products to obtain the original scores of the safety products of each type; calculating the demand level of the safety product according to the original score and the enterprise historical behaviors; recommending a first preset number of types of safety products for the current enterprise according to the demand.
According to the enterprise safety product recommendation method, the enterprise main body responsibility score evaluation system is preset to obtain the current enterprise's score points, the score points are matched with different types of safety products to obtain the original scores of the safety products of all types, the demand of the safety products is calculated according to the original scores and the enterprise historical behaviors, a first preset number of safety products of all types are recommended for the current enterprise according to the demand, and the enterprise real demands can be calculated by combining the score points and the historical behaviors of the enterprise, so that the recommendation accuracy is improved.
Optionally, the matching the performing weak points with different types of security products, obtaining the original scores of the security products of the respective types includes: sequencing enterprise track task items corresponding to the track points from low to high according to the security scores; extracting keywords from enterprise performing task items to obtain first keywords; matching the enterprise role-playing task item with the type of the safety product according to the first keyword; and obtaining the original scores of the safety products of all types according to the matching result, wherein the lower the score of the enterprise performing task item matched with the safety product is, the higher the original score is.
The method has the advantages that the type of the security product aiming at the weak points of the track is provided for the enterprise by matching the weak points of the track with the type of the security product and determining the original score, so that the recommended security product can meet the real requirements of the enterprise.
Optionally, the enterprise historical behaviors include a current enterprise actively searching for a security product, a current enterprise actively clicking to browse the security product, a historical purchasing behavior of an associated enterprise, a historical purchasing behavior of the current enterprise, and a historical collection behavior of the current enterprise;
the calculating the demand level of the security product according to the original score and the enterprise historical behavior comprises the following steps:
The desirability of the security product is calculated according to the following formula:
Wherein, For the desirability of a target type of security product,For the original score of the target type of security product,The score added for the security product of the target type is actively searched for by the current enterprise,The score added for the current enterprise to actively click through the target type of security product,For the number of active clicks on the security product of the type of the browse target by the current enterprise,Increased scores for target types of security products purchased by the associated enterprise,Purchasing a target type of security product several times for an associated enterprise,Increased points for current businesses to purchase target types of security products,The increased score for the target type of security product is collected for the current enterprise.
The accuracy of recommendation can be further improved by reasonably calculating the demand level of the safety product by combining the enterprise historical behaviors and the original scores.
Optionally, the enterprise security product recommendation method further includes: extracting second keywords in a outbound safety protocol file and/or an occurring safety production accident and/or a safety supervision punishment promulgation within a first preset time; matching a second preset number of types of security products according to the second keywords; recommending the second preset number of types of safety products within the preset recommending duration.
The embodiment of the invention can carry out policy recommendation on the safety products by combining the real-time safety protocol file, the safety production accident and the supervision condition, can recommend corresponding products or services aiming at the issued safety policies, accident investigation results and administrative punishment results, improves the policy sensitivity, avoids enterprises from being punished because of unresponsive policy requirements, enriches recommendation types, increases recommendation dimension, and improves the recommendation accuracy and the possibility of enterprise purchase.
Optionally, the enterprise security product recommendation method further includes: recommending a third preset number of types of security products associated with the preferred security product types according to the preferences of the current enterprise by adopting a collaborative filtering algorithm based on the articles.
Through collaborative filtering algorithm based on the articles, the security products of the types related to the interests of the enterprises can be recommended, the recommendation types are enriched, the recommendation dimension is increased, and the accuracy of the recommendation and the possibility of purchasing the enterprises are improved.
Optionally, after recommending the first preset number of types of security products for the current enterprise according to the demand level, the method further comprises: if the current enterprise does not click to browse the recommended safety products, the safety product type searched by the current enterprise is replaced by the safety product type with the minimum requirement degree in the recommended safety product types to be recommended.
The recommended safety products are correspondingly modified through click browsing of the current enterprise, so that the recommended safety products can meet the enterprise requirements better.
Optionally, after recommending the first preset number of types of security products for the current enterprise according to the demand level, the method further comprises: acquiring the number of safety products of each recommended type; when the number of the safety products of any recommended type is greater than the preset recommended number, evaluating the recommended score of the safety product according to the credit level of the supplier of the safety product, the point of use of the purchased safety product, the sales quantity of the safety product and the refund rate of the safety product; and sorting the safety products according to the recommendation scores and recommending the safety products ranked within a preset recommendation number.
According to the embodiment of the invention, when the number of the products in a certain type is excessive, the credit level of the provider, the point of use of the purchased safety products, the sales quantity of the safety products and the refund rate of the safety products are comprehensively considered, the optimal products are recommended to enterprises, and the accuracy of recommendation and the possibility of user purchase are improved.
In a second aspect, the present invention provides an enterprise security product recommendation apparatus, comprising: the weak point acquisition module is used for acquiring the weak points of the enterprise according to a preset enterprise main body responsibility score evaluation system of the enterprise; the original score acquisition module is used for matching the performing weak points with different types of safety products to obtain the original scores of the safety products of all types; the demand computing module is used for computing the demand of the safety product according to the original score and the enterprise historical behaviors; and the first recommending module is used for recommending a first preset number of types of safety products for the current enterprise according to the demand.
In a third aspect, the present invention provides a computer device comprising: the enterprise security product recommendation method comprises the steps of storing computer instructions in a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores the computer instructions, and the processor executes the computer instructions to execute the enterprise security product recommendation method according to the first aspect or any corresponding implementation mode.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the enterprise security product recommendation method of the first aspect or any of its corresponding embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an enterprise security product recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another enterprise security product recommendation method in accordance with an embodiment of the present invention;
FIG. 3 is a block diagram of an enterprise security product recommendation apparatus in accordance with an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The recommendation method for the general products only considers users and products, does not conduct targeted recommendation for weak points of enterprise performance, is difficult to adjust and recommend along with policy changes, and is difficult to adapt to requirements of enterprise users.
In accordance with an embodiment of the present invention, there is provided an enterprise security product recommendation method embodiment, it being noted that the steps shown in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order other than that shown or described herein.
In this embodiment, an enterprise security product recommendation method is provided, which may be used for a mobile terminal, such as a mobile phone, a tablet computer, etc., fig. 1 is a flowchart of an enterprise security product recommendation method according to an embodiment of the present invention, and as shown in fig. 1, the flowchart includes the following steps:
step S101, acquiring the weak points of the track job of the current enterprise according to a preset enterprise main body responsibility track job point evaluation system.
It is to be understood that security products, including physical products, may also be security services.
The preset enterprise principal responsibility and score evaluation system is a system for extracting the safety production responsibility and obligation which the enterprise should fulfill and scoring the safety responsibility and the obligation of the enterprise by using natural language according to the rules of laws, regulations and regulations, and the enterprise gives the enterprise score according to the degree of the enterprise completing the task after the enterprise completes the task according to the task requirement of the principal responsibility and score evaluation system, and the score can be exchanged for the safety products in the supermarket of the safety products.
The enterprise principal responsibility score evaluation system is provided with a plurality of enterprise role-playing task items, each enterprise role-playing task item is evaluated according to the role-playing condition of the current enterprise, and the role-playing weak points of the current enterprise are obtained according to the score condition.
Step S102, matching the weak points of the track job with different types of safety products to obtain the original scores of the safety products of the different types.
Specifically, matching questions between the weak points of the track and text descriptions of different types of security products, the closer the matching degree is, the higher the original score of the type of security product is.
Step S103, calculating the demand level of the security product according to the original score and the enterprise historical behaviors.
Specifically, the enterprise historical behavior includes at least one of a current enterprise actively searching for a historical behavior of the security product, a current enterprise actively clicking to browse the historical behavior of the security product, a historical purchasing behavior of an associated enterprise, a current enterprise's historical purchasing behavior, and a current enterprise's historical collection behavior. Associated businesses refer to businesses of the same business scale and the same industry type. For the security products actively searched by enterprises, the security products purchased by the related enterprises and the security products purchased by the enterprises after clicking and browsing the security products for more than 15 seconds, the score can be increased on the basis of the original score, and the demand of the security products of the type can be obtained.
Step S104, recommending a first preset number of types of safety products for the current enterprise according to the demand level.
Specifically, a first preset numberThe method can be set according to practical conditions, for example, 8, and the first 8 security product types with higher demand degree are recommended for the current enterprise.
According to the enterprise safety product recommendation method, the enterprise main body responsibility score evaluation system is preset to obtain the current enterprise's weak points of the track, and then the weak points of the track are matched with different types of safety products to obtain the original scores of the safety products of all types, the demand of the safety products is calculated according to the original scores and the historical behaviors of the enterprise, the first preset number of safety products of all types are recommended for the current enterprise according to the demand, and the real demands of the enterprise can be calculated by combining the weak points of the track and the historical behaviors of the enterprise, so that the recommendation accuracy is improved.
In this embodiment, an enterprise security product recommendation method is provided, which may be used in the above mobile terminal, such as a mobile phone, a tablet computer, etc., fig. 2 is a flowchart of an enterprise security product recommendation method according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
Step S201, acquiring the weak points of the track job of the current enterprise according to a preset enterprise main body responsibility track job point evaluation system. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S202, matching the weak points of the track job with different types of safety products to obtain the original scores of the safety products of the different types.
Specifically, the step S202 includes:
Step S2021, ordering the enterprise performance task items corresponding to the performance weak points according to the security scores from low to high.
The corresponding relation between the enterprise role-playing task item and the role-playing weak point is set in a preset enterprise main body responsibility role-playing score evaluation system in advance, so that the corresponding enterprise role-playing task item can be obtained according to the role-playing weak point.
Step S2022, extracting keywords from the enterprise job performance task item to obtain a first keyword.
And sequencing the enterprise track task items according to the scores from low to high, and extracting keywords to obtain a first keyword.
Step S2023, matching the enterprise role task item with the type of the security product according to the first keyword.
Text matching is carried out on the first keywords and the types of the security products, so that enterprise role-carrying task items can be matched with the classified security product types to obtain a matching result, and each type of security product is at least matched with one corresponding enterprise role-carrying task item.
Step S2024, obtaining the original scores of the security products of all types according to the matching result, wherein the lower the security score ranking of the enterprise performance task item matched by the security product is, the higher the original score is.
According to the matching result, the lower the security score ranking of the enterprise performing task item matched with the security product is, the higher the original score is, and the original score of the type of the matched security product is set as，，……Wherein。
Step S203, the demand level of the security product is calculated according to the original score and the enterprise historical behavior.
Specifically, the enterprise historical behaviors include a current enterprise actively searching for a historical behavior of a security product, a current enterprise actively clicking to browse a historical behavior of a security product, a historical purchasing behavior of an associated enterprise, a current enterprise's historical purchasing behavior, and a current enterprise's historical collection behavior.
Correspondingly, the demand level of the safety product is calculated according to the following formula:
Wherein, For the desirability of a target type of security product,As an original score for the target type of security product,The score added for the security product of the target type is actively searched for by the current enterprise,The score added for the current enterprise to actively click through the target type of security product,For the number of active clicks on the security product of the type of the browse target by the current enterprise,Increased scores for target types of security products purchased by the associated enterprise,Purchasing a target type of security product several times for an associated enterprise,Increased points for current businesses to purchase target types of security products,The increased score for the target type of security product is collected for the current enterprise.
Illustratively, the following enterprise historic behaviors are combined to increase the corresponding score on the basis of the original score to obtain the demand level of the security product:
Security product for enterprise active search: keyword extraction is carried out on products searched by enterprises, matching can be carried out on the products with the classified safe product types according to the extraction result, and the product types actively searched by the enterprises are increased by a score B;
The enterprise clicks to browse the security product for more than 15 seconds: keyword extraction is carried out on products clicked and browsed by enterprises, matching can be carried out with the types of the divided commodities according to the extraction result, and a score is increased when one type of commodity is clicked once When the enterprise clicks onNext, a product type of a certain class is added with a score of；
Associating a security product purchased by an enterprise: keyword extraction is carried out on products purchased by related enterprises, a plurality of safety product types are determined according to extraction results, and a score is increased for each time a certain type of safety product is purchasedWhen all the associated enterprises co-purchaseA next class of security products, with an added score of；
Enterprises purchase a certain type of security products: keyword extraction is carried out on security products purchased by enterprises, a plurality of security product types are determined according to extraction results, and when the enterprises purchase a certain type of security products, a score is increased；
Enterprises collect certain types of security products: and extracting keywords from the security products collected by the enterprise, determining a plurality of security product types according to the extraction result, and increasing a score F when the enterprise collects a certain type of security product.
Step S204, recommending a first preset number of types of security products for the current enterprise according to the demand level. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
According to the embodiment of the invention, the type of the security product aiming at the weak points of the track is provided for the enterprise by matching the weak points of the track with the type of the security product and determining the original score, so that the recommended security product can meet the actual requirements of the enterprise.
The accuracy of recommendation can be further improved by reasonably calculating the demand level of the safety product by combining the historical behaviors of the enterprise and the original scores.
In one embodiment, the enterprise security product recommendation method further comprises:
Step S1051, extracting second keywords in the outbound safety protocol file and/or the generated safety production accident and/or the safety supervision punishment publicity in the first preset time;
step S1052, matching a second preset number of types of security products according to the second keywords;
in step S1053, a second preset number of types of security products are recommended within a preset recommended period.
Specifically, the first preset time may be 5 days, 10 days, etc., and the policy instantaneity may be ensured by extracting the file or event recently coming out.
The safety protocol files include files of laws and regulations, industry standards, and the like.
The preset recommended duration is M days, and the number of days can be set according to actual demands.
The method comprises the steps of extracting keywords from new regulations and policies related to new regulations, and determining a plurality of safety product types according to extraction results;
Keyword extraction is carried out on the reasons of the oversized safety production accidents published by the authorities, and a plurality of safety product types are determined according to the extraction results;
Keyword extraction is carried out on enterprise administrative punishment publicity published in daily law enforcement of the security supervision department of the enterprise, and a plurality of security product types are determined according to the extraction result;
A total of the second preset number is confirmed according to the method And recommending the determined safety product types by the safety products of the types, wherein the recommending duration is M days.
The embodiment of the invention can carry out policy recommendation on the safety products by combining the real-time safety protocol file, the safety production accident and the supervision condition, can recommend corresponding products aiming at the outbound safety policy, improves the policy sensitivity, avoids the punishment of enterprises because the enterprises do not respond to the policy requirements, enriches recommendation types, increases recommendation dimension, and improves the recommendation accuracy and the enterprise purchase possibility.
Further, the enterprise security product recommendation method further comprises:
step S106, recommending a third preset number of types of security products associated with the preferred security product types according to the preferences of the current enterprise by adopting a collaborative filtering algorithm based on the articles.
A third preset numberThe types of security products are products of the type associated with the enterprise preferences, and the recommended associated type of products logic is: class a and class b products are purchased by three or more businesses simultaneously, and are considered to be related because of their high co-occurrence times. If a fourth and above business in addition purchases a class a product, a class b product associated with the class a product may be recommended to the business. The logic computes through an Item-based collaborative filtering (Item-CollaborativeFiltering, item-CF) algorithm.
The calculation method is exemplified as follows:
co-occurrence matrix for finishing products
Co-occurrence means that: two types of products are liked by the same enterprise (liked is defined as the demand degreeThe P-type product with the highest value), such as the a-type product and the b-type product, the co-occurrence times of the a-type product and the b-type product are 3 because they are simultaneously liked by the user A, B, C, and the co-occurrence matrix of the enterprise purchasing the product types at the same time is constructed by adopting the statistical method.
Calculating an association matrix of an item
The following formula is adopted:
Indicating a like The number of businesses in the class of products,Indicating a likeThe number of businesses in the class of products,AndIs indicative of simultaneous likingClass productThe larger the intersection, the higher the association of the product types,Representing a productAnd productsIs a similarity of (3).
Recommended product types
Representing an enterpriseFor a pair ofThe greater the level of interest, the more worth the class product is worth recommending,Representing an enterpriseA collection of products of interest is provided,Representation and productMost similar frontThe product of the process is a product,Representing an enterpriseFor a pair ofInterestingness of the class product.
According to the demand of the P-class products before the demand of enterprises on the product typesValue calculation interest levelIs a value of (2).
Let p=3, the first three categories of recommendations (let us assume、、Class product) D values of 8, 6 and 2, respectively, then the enterpriseFor a pair ofInterestingness of class productAn enterpriseFor a pair ofInterest level of productAn enterpriseFor a pair ofInterestingness of class product。
Examples: assume that A, B, C, D, E enterprises are provided, wherein enterprise A likes a, B and C products, enterprise B likes article a, B products, enterprise C likes a, B and D products, enterprise D likes a, C products, and enterprise E likes B and C products.
The co-occurrence matrix of the article is:
The favorite people number matrix of each type of product is as follows:
the association degree matrix of the product is as follows:
Assuming that enterprise E is recommended for items, we have previously known that enterprise E likes class b and class c products, assuming a likeness level of 0.6 and 0.4, respectively. Then, the recommended result calculated using the above formula is as follows:
Interest value for class a product: 0.6×0.75+0.4×0.58=0.682
Interest value for class d product: 0.6×0.5+0.4×0=0.3
Finally, the interest degree of the enterprise E on the class a products and the class d products is compared, and the class a products are selected and recommended because the interest degree of the enterprise E is 0.682> 0.3.
Through collaborative filtering algorithm based on the articles, the security products of the types related to the interests of the enterprises can be recommended, the recommendation types are enriched, the recommendation dimension is increased, and the accuracy of the recommendation and the possibility of purchasing the enterprises are improved.
In an embodiment, keyword extraction is performed on products on shelves of a security product supermarket, and a plurality of commodity types are divided according to extraction results, wherein the product type is Z. The total recommended number of product types is(E.g.)、、If there is a cross-over, repeat class, thenEqual to、、Number addition after deduplication), whereinTo recommend the number of product types based on the enterprise's desirability of product types,To make a policy-based recommendation of the number of product types,The method has the advantages that the number of the product types recommended for the security products of the types associated with the enterprise preferences is increased, the security products are recommended in combination with various dimensions such as products of the types associated with the enterprise requirements, policy requirements and enterprise interests, and the accuracy of recommendation and the possibility of enterprise purchase are improved.
In one embodiment, after recommending the first preset number of types of security products for the current enterprise according to the demand level, the method further comprises:
in step S107, if the current enterprise does not click to browse the recommended security products, the security product type searched by the current enterprise is recommended instead of the security product type with the minimum requirement among the recommended security product types.
Specifically, after recommending the safe products according to the above algorithm, the enterprise does not click to browse any one product, actively searches for other product types, and improves the recommended product typesThe product type with the smallest demand is replaced by the product type searched by the enterprise.
The recommended safety products are correspondingly modified through click browsing of the current enterprise, so that the recommended safety products can meet the enterprise requirements better.
In one embodiment, after recommending the first preset number of types of security products for the current enterprise according to the demand level, the method further comprises:
step S1081, obtaining the number of safety products of each recommended type;
step S1082, when the number of the safety products of any recommended type is larger than the preset recommended number, evaluating the recommended score of the safety product according to the credit level of the supplier of the safety product, the point of use of the purchased safety product, the sales of the safety product and the refund rate of the safety product;
step S1083, sorting the safety products according to the recommendation scores and recommending the safety products ranked within the preset recommendation number.
Specifically, when screening the number of products in a recommended typeAt time of the seed, the recommended score of the security product is evaluated according to the vendor credit level of the security product, the points of purchase of the security product, the sales amount of the security product, and the refund rate of the security productEach security product is distributed according to the recommended scoreSorting from high to low, and screening out the first I products for recommendation.
Wherein,，Taking an integer from 1 to 5,AndTaking integers from 1 to 4, the formula has the following meaning:
Credit level of the provider: the credit comprehensive level is evaluated as five stars (excellent), four stars (good), three stars (general), two stars (poor) and one star (very poor), and the scores are set as follows 、、、And (3) sum,Wherein the method comprises the steps ofEach security product increases a score based on the credit level of the vendor；
Points used to purchase the product: the point required for purchasing the product is increased by a fraction within the range of points already obtained by the enterprise；
Sales of products: When the sales of the product is 0 to less than or equal toWhen less than 10, increase by one fractionWhen (when)At the time, a fraction is increasedWhen 0.ltoreq.2When the value is less than 50, the value is increased by one fractionWhen (when)At the time, a fraction is increased，；
Product refund rate: Refund rate when productWhen not adding, whenWhen a score is buckledWhen (when)When a score is buckledWhen (when)When a score is buckledWhen (when)When a score is buckledWherein。
According to the embodiment of the invention, when the number of the products in a certain type is excessive, the credit level of the provider, the point of use of the purchased safety products, the sales quantity of the safety products and the refund rate of the safety products are comprehensively considered, the optimal products are recommended to enterprises, and the accuracy of recommendation and the possibility of user purchase are improved.
At present, the field of recommending safety products lacks intelligent recommending modes, and enterprises themselves are not clear about required safety products, so that the enterprises are uncertain about how to select products suitable for themselves to improve production safety.
Aiming at the situation that security fines exist in the security field, the embodiment of the invention can carry out policy recommendation on security products by combining real-time security protocol files, security production accidents and supervision conditions, can recommend corresponding products aiming at outbound security policies, improves policy sensitivity, and avoids enterprises from being penalized because of unresponsiveness to the requirements of the policies.
In addition, the embodiment of the invention can recommend the security products of the type related to the enterprise interests based on the collaborative filtering algorithm of the articles, and the recommendation dimension is increased.
The embodiment of the invention integrally combines various dimensions such as products of the related types of enterprise requirements, policy requirements and enterprise interests to recommend the security products, and improves the accuracy of recommended products and the possibility of enterprise purchase.
The invention also provides an enterprise safety product recommendation device, as shown in fig. 3, comprising:
The weak point acquisition module 301 is configured to acquire a weak point of a role of the enterprise according to a preset enterprise main body responsibility role score evaluation system;
The original score obtaining module 302 is configured to match the performing weak points with different types of security products to obtain original scores of the security products of the different types;
A demand computation module 303, configured to compute a demand of the security product according to the original score and the historical behavior of the enterprise;
The first recommending module 304 is configured to recommend a first preset number of types of security products for the current enterprise according to the demand level.
Further, the raw score acquisition module 302 includes:
the task item ordering module is used for ordering the enterprise track task items corresponding to the track points from low to high according to the security scores;
The first keyword extraction module is used for extracting keywords from enterprise performing task items to obtain first keywords;
The first matching module is used for matching the enterprise role-playing task item with the type of the safety product according to the first keyword;
And the result analysis module is used for obtaining the original scores of the safety products of all types according to the matching result, wherein the lower the safety score ranking of the enterprise performance task item matched with the safety product is, the higher the original score is.
Further, the enterprise historical behaviors include a current enterprise actively searching for a historical behavior of a security product, a current enterprise actively clicking to browse a historical behavior of the security product, a historical purchasing behavior of an associated enterprise, a current enterprise's historical purchasing behavior and a current enterprise's historical collection behavior;
calculating the demand level of the security product according to the original score and the enterprise historical behavior, comprising:
The desirability of the security product is calculated according to the following formula:
Wherein, For the desirability of a target type of security product,For the original score of the target type of security product,The score added for the security product of the target type is actively searched for by the current enterprise,The score added for the current enterprise to actively click through the target type of security product,For the number of active clicks on the security product of the type of the browse target by the current enterprise,Increased scores for target types of security products purchased by the associated enterprise,Purchasing a target type of security product several times for an associated enterprise,Increased points for current businesses to purchase target types of security products,The increased score for the target type of security product is collected for the current enterprise.
Further, the enterprise security product recommendation apparatus further includes:
The second keyword extraction module is used for extracting second keywords in the outbound safety protocol file and/or the generated safety production accidents and/or the safety supervision punishment publicity in the first preset time;
The second matching module is used for matching a second preset number of types of security products according to the second keywords;
the second recommending module is used for recommending a second preset number of types of safety products within a preset recommending duration.
Further, the enterprise security product recommendation apparatus further includes:
And the third recommendation module is used for recommending a third preset number of types of security products associated with the type of the preferred security products according to the preference of the current enterprise by adopting a collaborative filtering algorithm based on the articles.
Further, the enterprise security product recommendation apparatus further includes:
And the replacing module is used for replacing the safety product type with the minimum requirement degree in the recommended safety product types with the safety product type searched by the current enterprise to recommend if the current enterprise does not click to browse the recommended safety products.
Further, the enterprise security product recommendation apparatus further includes:
The quantity acquisition module is used for acquiring the quantity of the safety products of each recommended type;
The recommendation score calculating module is used for evaluating the recommendation score of the security product according to the credit level of the provider of the security product, the point of use of the purchased security product, the sales volume of the security product and the refund rate of the security product when the number of the security products of any recommendation type is larger than the preset recommendation number;
and the recommendation improvement module is used for sequencing the safety products according to the recommendation scores and recommending the safety products ranked within the preset recommendation quantity.
According to the enterprise safety product recommendation device provided by the embodiment of the invention, the enterprise principal responsibility score evaluation system is preset to obtain the current enterprise role weak points, and then the role weak points are matched with different types of safety products to obtain the original scores of the safety products of all types, the demand of the safety products is calculated according to the original scores and the enterprise historical behaviors, the first preset number of safety products of all types are recommended for the current enterprise according to the demand, and the enterprise real demands can be calculated by combining the role weak points and the historical behaviors of the enterprise, so that the recommendation accuracy is improved.
The embodiment of the invention also provides a schematic structural diagram of a computer device, as shown in fig. 4, where the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 4.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device further comprises input means 30 and output means 40. The processor 10, memory 20, input device 30, and output device 40 may be connected by a bus or other means, for example in fig. 4.
The input device 30 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointer stick, one or more mouse buttons, a trackball, a joystick, and the like. The output means 40 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays, light emitting diodes, displays and plasma displays. In some alternative implementations, the display device may be a touch screen.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Portions of the present invention may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or aspects in accordance with the present invention by way of operation of the computer. Those skilled in the art will appreciate that the form of computer program instructions present in a computer readable medium includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Herein, a computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by a computer.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (8)
1. A method for recommending an enterprise security product, comprising:
acquiring the weak points of the track job of the current enterprise according to a preset enterprise main body responsibility track job point evaluation system;
Matching the track points with different types of safety products to obtain the original scores of the safety products of each type;
calculating the demand level of the safety product according to the original score and the enterprise historical behaviors;
recommending a first preset number of types of safety products for the current enterprise according to the demand;
wherein matching the performance weak points with different types of security products, obtaining the original scores of the security products of each type comprises:
sequencing enterprise track task items corresponding to the track points from low to high according to the security scores;
extracting keywords from enterprise performing task items to obtain first keywords;
Matching the enterprise role-playing task item with the type of the safety product according to the first keyword;
Obtaining the original score of each type of safety product according to the matching result, wherein the lower the safety score ranking of the enterprise performing task item matched with the safety product is, the higher the original score is;
The enterprise historical behaviors comprise the historical behaviors of the current enterprise actively searching for the safety product, the historical behaviors of the current enterprise actively clicking to browse the safety product, the historical purchasing behaviors of the related enterprise, the historical purchasing behaviors of the current enterprise and the historical collecting behaviors of the current enterprise;
the calculating the demand level of the security product according to the original score and the enterprise historical behavior comprises the following steps:
The desirability of the security product is calculated according to the following formula:
Wherein, For the desirability of a target type of security product,For the original score of the target type of security product,The score added for the security product of the target type is actively searched for by the current enterprise,The score added for the current enterprise to actively click through the target type of security product,For the number of active clicks on the security product of the type of the browse target by the current enterprise,Increased scores for target types of security products purchased by the associated enterprise,Purchasing a target type of security product several times for an associated enterprise,Increased points for current businesses to purchase target types of security products,The increased score for the target type of security product is collected for the current enterprise.
2. The enterprise security product recommendation method of claim 1, further comprising:
extracting second keywords in a outbound safety protocol file and/or an occurring safety production accident and/or a safety supervision punishment promulgation within a first preset time;
Matching a second preset number of types of security products according to the second keywords;
recommending the second preset number of types of safety products within the preset recommending duration.
3. The enterprise security product recommendation method of claim 1, further comprising:
Recommending a third preset number of types of security products associated with the preferred security product types according to the preferences of the current enterprise by adopting a collaborative filtering algorithm based on the articles.
4. The enterprise safety product recommendation method of claim 1, further comprising, after recommending a first preset number of types of safety products for the current enterprise based on the desirability:
if the current enterprise does not click to browse the recommended safety products, the safety product type searched by the current enterprise is replaced by the safety product type with the minimum requirement degree in the recommended safety product types to be recommended.
5. The enterprise safety product recommendation method of claim 1, further comprising, after recommending a first preset number of types of safety products for the current enterprise based on the desirability:
Acquiring the number of safety products of each recommended type;
when the number of the safety products of any recommended type is greater than the preset recommended number, evaluating the recommended score of the safety product according to the credit level of the supplier of the safety product, the point of use of the purchased safety product, the sales quantity of the safety product and the refund rate of the safety product;
And sorting the safety products according to the recommendation scores and recommending the safety products ranked within a preset recommendation number.
6. An enterprise security product recommendation device, comprising:
the weak point acquisition module is used for acquiring the weak points of the enterprise according to a preset enterprise main body responsibility score evaluation system of the enterprise;
The original score acquisition module is used for matching the performing weak points with different types of safety products to obtain the original scores of the safety products of all types;
The demand computing module is used for computing the demand of the safety product according to the original score and the enterprise historical behaviors;
the first recommending module is used for recommending a first preset number of types of safety products for the current enterprise according to the demand;
wherein, the original score acquisition module includes:
the task item ordering module is used for ordering the enterprise track task items corresponding to the track points from low to high according to the security scores;
The first keyword extraction module is used for extracting keywords from enterprise performing task items to obtain first keywords;
The first matching module is used for matching the enterprise role-playing task item with the type of the safety product according to the first keyword;
the result analysis module is used for obtaining the original scores of the safety products of all types according to the matching result, wherein the lower the safety score ranking of the enterprise performance task item matched by the safety products is, the higher the original score is;
The enterprise historical behaviors comprise the historical behaviors of the current enterprise for actively searching the security product, the historical behaviors of the current enterprise for actively clicking and browsing the security product, the historical purchasing behaviors of the related enterprise, the historical purchasing behaviors of the current enterprise and the historical collecting behaviors of the current enterprise;
the calculating the demand level of the security product according to the original score and the enterprise historical behavior comprises the following steps:
The desirability of the security product is calculated according to the following formula:
Wherein, For the desirability of a target type of security product,For the original score of the target type of security product,The score added for the security product of the target type is actively searched for by the current enterprise,The score added for the current enterprise to actively click through the target type of security product,For the number of active clicks on the security product of the type of the browse target by the current enterprise,Increased scores for target types of security products purchased by the associated enterprise,Purchasing a target type of security product several times for an associated enterprise,Increased points for current businesses to purchase target types of security products,The increased score for the target type of security product is collected for the current enterprise.
7. A computer device, comprising: a memory and a processor in communication with each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the enterprise security product recommendation method of any of claims 1 to 5.
8. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the enterprise security product recommendation method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410502552.6A CN118096325B (en) | 2024-04-25 | 2024-04-25 | Enterprise safety product recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410502552.6A CN118096325B (en) | 2024-04-25 | 2024-04-25 | Enterprise safety product recommendation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118096325A CN118096325A (en) | 2024-05-28 |
| CN118096325B true CN118096325B (en) | 2024-07-26 |
Family
ID=91146152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410502552.6A Active CN118096325B (en) | 2024-04-25 | 2024-04-25 | Enterprise safety product recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096325B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN115391669A (en) * | 2022-10-31 | 2022-11-25 | 江西渊薮信息科技有限公司 | Intelligent recommendation method and device and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415063B (en) * | 2018-07-31 | 2022-07-05 | 北京京东尚科信息技术有限公司 | Commodity recommendation method and device, electronic equipment and readable medium |
| US12093979B2 (en) * | 2021-01-13 | 2024-09-17 | Walmart Apollo, Llc | Systems and methods for generating real-time recommendations |
| CN116167818A (en) * | 2023-01-06 | 2023-05-26 | 中科柏诚科技（北京）股份有限公司 | Intelligent recommendation system and method based on privacy protection and computer device |
-
2024
- 2024-04-25 CN CN202410502552.6A patent/CN118096325B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN115391669A (en) * | 2022-10-31 | 2022-11-25 | 江西渊薮信息科技有限公司 | Intelligent recommendation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118096325A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10699349B2 (en) | Computerized system and method for data field pre-filling and pre-filling prevention | |
| US10891701B2 (en) | Method and system for evaluating intellectual property | |
| US10109017B2 (en) | Web data scraping, tokenization, and classification system and method | |
| US7620651B2 (en) | System for dynamic product summary based on consumer-contributed keywords | |
| US9934293B2 (en) | Generating search results | |
| US10354308B2 (en) | Distinguishing accessories from products for ranking search results | |
| US20140279584A1 (en) | Evaluating Intellectual Property with a Mobile Device | |
| US8515889B2 (en) | Systems and methods for trend aware self-correcting entity relationship extraction | |
| CN107077486A (en) | Affective Evaluation system and method | |
| CN109636494A (en) | Drug recommended method and system | |
| US20160306890A1 (en) | Methods and systems for assessing excessive accessory listings in search results | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN112750011A (en) | Commodity recommendation method and device and electronic equipment | |
| US20150221023A1 (en) | Information providing device, information providing method, information providing program, and computer-readable storage medium storing the program | |
| CN115391669B (en) | Intelligent recommendation method and device and electronic equipment | |
| CN110852818A (en) | Commodity sorting method and device and computer-readable storage medium | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| CN111383049A (en) | Product recommendation method, device and storage medium | |
| CN118096325B (en) | Enterprise safety product recommendation method, device, equipment and storage medium | |
| CN111090805B (en) | Recommendation index attribution method and device and electronic equipment | |
| Johari et al. | The Hybrid Recommender System of the Indonesian Online Market Products using IMDb weight rating and TF-IDF | |
| US11379929B2 (en) | Advice engine | |
| Jiao | Applications of artificial intelligence in e-commerce and finance | |
| CN112016975A (en) | Product screening method and device, computer equipment and readable storage medium | |
| CN118710375B (en) | Prefabricated dish recommending method and system |
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 |