Enterprise policy automatic pushing method based on big data

Abstract

The invention relates to the technical field of information communication, and discloses an enterprise policy automatic pushing method based on big data, and the method comprises the following steps: S1, setting a policy label, a pushing grade and a tracking grade of the pushing through a policy setting module; s2, analyzing the policy label, the push level, the policy text content and the enterprise information through an analysis module to obtain a policy matching index; s3, analyzing the policy matching index through an analysis module, screening out an enterprise which carries out the pushing, and carrying out the pushing; s4, acquiring the tracking information data of each enterprise after the current pushing through a tracking module; s5, the enterprise matching level, the tracking level and the tracking information data are analyzed through an analysis module, whether pushing reaches the standard or not is judged according to the analysis result, and the pushing effect after policy information issuing is evaluated; and the pushed policies can be accurately sent to related enterprises.

Description

Technical Field

[0001] The present invention relates to the field of information communication technology, and in particular to a method for automatically pushing enterprise policies based on big data. Background Art

[0002] With the gradual maturity of mobile Internet technology and mobile devices, electronic office has gradually replaced paper office, and government departments also release policy information through government websites.

[0003] At present, various government departments release policy information on government websites. Enterprises related to the policy information cannot obtain it directly and must open the government website to view relevant information. Since there is a lot of information on government websites and the homepage space is limited, the homepage usually only displays a few recently updated information. Therefore, relevant information can only be found when enterprises actively search.

[0004] However, due to the large number of businesses, it is difficult for enterprises to log on to government websites all the time to pay attention to policy information. Therefore, enterprises may miss a lot of policy information related to their own enterprises. At the same time, after the government departments release policy information, the staff are unable to evaluate the push effect. Summary of the invention

[0005] The purpose of the present invention is to provide a method for automatically pushing enterprise policies based on big data to solve the following technical problems:

[0006] How to evaluate the push effect after policy information is released.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for automatically pushing enterprise policies based on big data, the pushing method comprising the following steps:

[0009] S1: Set the policy label, push level and tracking level of this push through the policy setting module;

[0010] S2: Analyze the policy label, push level, policy text content and enterprise information through the analysis module to obtain the policy matching index;

[0011] S3: Analyze the policy matching index through the analysis module, select the enterprises to be pushed and push them;

[0012] S4: Obtain the tracking information data of each enterprise after this push through the tracking module;

[0013] S5: Analyze the enterprise matching level, tracking level and tracking information data through the analysis module, and determine whether the push meets the standards based on the analysis results.

[0014] As a further solution of the present invention: the policy matching index is obtained by the formula:

[0015]

[0016] Calculate the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i ;

[0017] Where i is the enterprise number; P i is the actual label matching degree between the ith enterprise and the policy pushed this time; P 0 is the preset label matching degree; Q i is the keyword matching degree between the ith enterprise and the policy pushed this time; P 0 is the preset keyword matching degree; T 0 is the basic policy matching index; γ 1 is the first weight coefficient; γ 2 is the second weight coefficient; C 1 is the first preset constant; C 2 is the second preset constant; u n It is the push level coefficient of the nth level.

[0018] As a further solution of the present invention: the push level includes N levels, N≥2; n∈[1,N]; the nth level push level coefficient u n Satisfies 0=u 1 P 0 2 P 0 …u n P 0 N P 0 ≤1, and at the same time 0=u 1 Q 0 2 Q 0 …u n Q 0 N Q 0 ≤1.

[0019] As a further solution of the present invention: In step S3, the enterprise screening process for this push is:

[0020] The comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i With the preset value R 1 Make a comparison;

[0021] When T i <T 0 When , the matching level of the i-th enterprise is level 1, and no push is performed; ​​​​

[0022] When T 0 ≤T i <R 1 When , the matching level of the i-th enterprise is level 2, and push is performed;

[0023] When T i ≤R 1 When , the matching level of the i-th enterprise is level three, and push is performed.

[0024] As a further solution of the present invention: the tracking level includes multiple levels; in step S4, the tracking information data includes a reading status and a downloading status; the reading status includes read and unread; the downloading status includes downloaded and not downloaded.

[0025] As a further solution of the present invention: in step S5, the process of determining whether the push meets the standard includes the following formula:

[0026]

[0027] Calculate the judgment index C.

[0028] As a further solution of the present invention: the process of judging whether the push meets the standard also includes: when C≥1, the push meets the standard; otherwise, the push does not meet the standard.

[0029] As a further solution of the present invention: the actual label matching degree P of the i-th enterprise and the current push policy i By formula Calculate and obtain;

[0030] The actual keyword matching degree Q between the i-th enterprise and the policy pushed this time i By formula Calculate and obtain;

[0031] Among them, X A is the total number of policy labels; Xs is the number of label matches between the i-th enterprise and the policy label of this push policy; Y A is the total number of keywords pushed this time; Xs is the number of keyword matches between the ith enterprise and the keywords pushed this time.

[0032] Beneficial effects of the present invention:

[0033] The present invention sets the policy label, push level and tracking level of this push through the policy setting module; analyzes the policy label, push level, policy text content and enterprise information through the analysis module to obtain the policy matching index; analyzes the policy matching index through the analysis module, screens out the enterprises for this push and pushes them; obtains the tracking information data of each enterprise after this push through the tracking module; analyzes the enterprise matching level, tracking level and tracking information data through the analysis module, and determines whether this push meets the standards based on the analysis results; realizes the push effect after the policy information is released; and enables the pushed policy to be accurately sent to relevant enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] Figure 1 The present invention is a method flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 As shown, in one embodiment, a method for automatically pushing enterprise policies based on big data is provided, and the pushing method includes the following steps:

[0038] S1: Set the policy label, push level and tracking level of this push through the policy setting module;

[0039] S2: Analyze the policy label, push level, policy text content and enterprise information through the analysis module to obtain the policy matching index;

[0040] S3: Analyze the policy matching index through the analysis module, select the enterprises to be pushed and push them;

[0041] S4: Obtain the tracking information data of each enterprise after this push through the tracking module;

[0042] S5: Analyze the enterprise matching level, tracking level and tracking information data through the analysis module, and determine whether the push meets the standards based on the analysis results;

[0043] Through the above technical solution, this embodiment sets the policy label, push level and tracking level of this push through the policy setting module; analyzes the policy label, push level, policy text content and enterprise information through the analysis module to obtain the policy matching index; analyzes the policy matching index through the analysis module, screens out the enterprises for this push and pushes them; obtains the tracking information data of each enterprise after this push through the tracking module; analyzes the enterprise matching level, tracking level and tracking information data through the analysis module, and determines whether this push meets the standards based on the analysis results; realizes the push effect after the policy information is released; and enables the pushed policies to be accurately sent to relevant enterprises.

[0044] As an implementation mode of the present invention, the policy matching index is obtained by the formula:

[0045]

[0046] Calculate the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i ;

[0047] Where i is the enterprise number; P i is the actual label matching degree between the ith enterprise and the policy pushed this time; P 0 is the preset label matching degree; Q i is the keyword matching degree between the ith enterprise and the policy pushed this time; P 0 is the preset keyword matching degree; T 0 is the basic policy matching index; γ 1 is the first weight coefficient; γ 2 is the second weight coefficient; C 1 is the first preset constant; C 2 is the second preset constant; u n is the push level coefficient of the nth level;

[0048] Through the above technical solution, this embodiment n P 0 The preset label matching degree of the policy text type pushed this time; P i -u n P 0 is the difference between the actual label matching degree of the i-th enterprise and the policy pushed this time and the preset label matching degree; when P i -u n P 0 >0, it means that the actual label matching degree is higher than the preset label matching degree. Therefore, the label matching degree difference P between the actual label matching degree of the i-th enterprise and the current push policy and the preset label matching degree i -u n P0 The larger the value is, the better the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time is. i The larger the value, the greater the i -u n P 0 <0, it means that the actual label matching degree is lower than the preset label matching degree. Therefore, the label matching degree difference P between the actual label matching degree of the i-th enterprise and the current push policy and the preset label matching degree i -u n P 0 The larger the absolute value of i The smaller u n Q 0 The preset keyword matching degree of the policy text type pushed this time; Q i -u n Q 0 is the difference between the actual keyword matching degree of the ith enterprise and the policy pushed this time and the preset keyword matching degree; when Q i -u n Q 0 >0, it means that the actual keyword matching degree is higher than the preset keyword matching degree. Therefore, the keyword matching degree difference Q between the actual keyword matching degree of the i-th enterprise and the current push policy and the preset keyword matching degree i -u n Q 0 The larger the value is, the better the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time is. i The larger the Q i -u n Q 0 <0, it means that the actual keyword matching degree is lower than the preset keyword matching degree. Therefore, the keyword matching degree difference Q between the actual keyword matching degree of the i-th enterprise and the current push policy and the preset keyword matching degree i -u n Q 0 The larger the absolute value of i The smaller;

[0049] It should be noted that the preset label matching degree P 0 、Preset keyword matching degree P 0 , Basic policy matching index T 0 , the first weight coefficient γ 1 , the second weight coefficient γ 2 , the first preset constant C 1 and the second preset constant C 2 It is a preset value obtained based on experience and will not be described in detail here.

[0050] As an implementation mode of the present invention, the push level includes N levels, N≥2; n∈[1,N]; the nth level push level coefficient u n Satisfies 0=u 1 P 0 2 P 0 …u n P 0 N P 0 ≤1, and at the same time 0=u 1 Q 0 2 Q 0 …u n Q 0 N Q 0 ≤1;

[0051] Through the above technical solution, this embodiment sets the push level, so that the staff can set the push accuracy by setting the push level, thereby adjusting the push range; the first-level push level is smaller than the N-level push level; the smaller the push level, the lower the push accuracy and the larger the push range; the larger the push level, the higher the push accuracy and the smaller the push range;

[0052] It should be noted that the nth level push level coefficient u n It is a preset value obtained based on experience and will not be described in detail here.

[0053] As an implementation mode of the present invention, in step S3, the enterprise screening process for this push is:

[0054] The comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i With the preset value R 1 Make a comparison;

[0055] When T i <T 0 When , the matching level of the i-th enterprise is level 1, and no push is performed;

[0056] When T 0 ≤T i <R 1 When , the matching level of the i-th enterprise is level 2, and push is performed;

[0057] When T i ≤R 1 When , the matching level of the i-th enterprise is level 3, and push is performed;

[0058] Through the above technical solution, the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time in this embodiment is​​​​i With the preset value R 1 For comparison; T 0 <R 1 When T i <T 0 When T , the i-th enterprise matching level is level 1, the matching degree is low, and no push is performed; 0 ≤T i <R 1 When , the matching level of the i-th enterprise is level 2, the matching degree is high, and it is pushed; when T i ≤R 1 When , the matching level of the i-th enterprise is level three, the matching degree is very high, and it is pushed.

[0059] It should be noted that the default value R 1 This is obtained based on experience and will not be described in detail here.

[0060] As an implementation mode of the present invention, the tracking level includes multiple levels; in step S4, the tracking information data includes a reading status and a downloading status; the reading status includes read and unread; the downloading status includes downloaded and not downloaded;

[0061] Through the above technical solution, this embodiment sets multiple tracking levels, each tracking level corresponds to different secondary preset parameters and tertiary preset parameters; the secondary preset parameters are used to evaluate the tracking information data of the enterprise matching level of the second level; the tertiary preset parameters are used to evaluate the tracking information data of the enterprise matching level of the third level; the secondary preset parameters include the secondary preset reading rate and the secondary preset download rate; the tertiary preset parameters include the tertiary preset reading rate and the tertiary preset download rate; by analyzing the tracking information data of the enterprise being pushed and the secondary preset parameters and the tertiary preset parameters selected by the staff, the effect of this push is judged.

[0062] It should be noted that the second-level preset reading rate, second-level preset download rate, third-level preset reading rate and third-level preset download rate of each tracking level are preset values, which are obtained based on experience and will not be described in detail here.

[0063] As an implementation mode of the present invention, in step S5, the process of determining whether the push meets the standard includes the following formula:

[0064]

[0065] Calculate the judgment index C;

[0066] Among them, RD 2 The number of enterprises with a reading status of "read" at the second level matching level; PP 2 is the total number of enterprises at the second level of enterprise matching; ρ RD2The secondary preset reading rate for the tracking level set for the staff; ρ DL2 The secondary preset download rate for the tracking level set for the worker; RD 3 The number of enterprises with a reading status of "read" at level 3 matching level for enterprises; PP 3 is the total number of enterprises with level three matching; ρ RD3 Three levels of preset reading rates for tracking levels set for staff; ρ DL3 Three levels of preset download rates for tracking levels set for staff; DL 2 The number of downloaded enterprises with enterprise matching level 3; θ 1 is the weight coefficient No. 1; θ 2 is the second weight coefficient; μ 2 is the secondary weight coefficient; μ 3 is the third-level weight coefficient;

[0067] When C≥1, this push meets the standard; otherwise, this push does not meet the standard.

[0068] Through the above technical solution, this embodiment The actual reading rate of the enterprise matching level 2; The difference between the actual reading rate at the enterprise matching level 2 and the preset reading rate at the tracking level 2 set by the staff. When the enterprise matching level is level 2, the actual reading rate is higher than or equal to the level 2 preset reading rate, and the difference between the actual reading rate of the enterprise matching level level 2 and the level 2 preset reading rate of the tracking level set by the staff is The larger the value is, the better the push effect is, and the larger the judgment index C is; When the enterprise matching level is 2, the actual reading rate of the enterprise matching level is less than the preset reading rate of the 2nd level. The difference between the actual reading rate of the enterprise matching level 2 and the preset reading rate of the 2nd level of the tracking level set by the staff is The larger the absolute value of is, the worse the push effect is, and the smaller the judgment index C is; The actual download rate of the enterprise matching level 2; The difference between the actual download rate at the enterprise matching level 2 and the preset download rate at the tracking level 2 set by the staff. When it is ≥0, it means that the actual download rate of the enterprise matching level is higher than or equal to the preset download rate of the second level, and the difference between the actual download rate of the enterprise matching level and the preset download rate of the second level of the tracking level set by the staff The larger the value is, the better the push effect is, and the larger the judgment index C is; When the actual download rate of the enterprise matching level is lower than the preset download rate of the second level, the difference between the actual download rate of the enterprise matching level and the preset download rate of the second level of the tracking level set by the staff is The larger the absolute value of is, the worse the push effect is, and the smaller the judgment index C is; Matching level 3 actual reading rate for enterprises; The difference between the actual reading rate at level 3 of the enterprise matching level and the preset reading rate at level 3 of the tracking level set by the staff. When the enterprise matching level is level 3, the actual reading rate is higher than or equal to the level 3 preset reading rate, and the difference between the actual reading rate of the enterprise matching level 3 and the level 3 preset reading rate of the tracking level set by the staff is The larger the value is, the better the push effect is, and the larger the judgment index C is; When the enterprise matching level is level 3, the actual reading rate is lower than the level 3 preset reading rate, and the difference between the actual reading rate of the enterprise matching level 3 and the level 3 preset reading rate of the tracking level set by the staff is The larger the absolute value of is, the worse the push effect is, and the smaller the judgment index C is; The actual download rate of the enterprise matching level 3; The difference between the actual download rate at level 3 of the enterprise matching level and the preset download rate at level 3 of the tracking level set by the staff. When the actual download rate of the enterprise matching level is higher than or equal to the preset download rate of the third level, the difference between the actual download rate of the enterprise matching level and the preset download rate of the third level of the tracking level set by the staff is The larger the value is, the better the push effect is, and the larger the judgment index C is; When the actual download rate of the enterprise matching level is less than the preset download rate of the third level, the difference between the actual download rate of the enterprise matching level and the preset download rate of the third level of the tracking level set by the staff is The larger the absolute value of , the worse the push effect is, and the smaller the judgment index C is; when C ≥ 1, the push meets the standard; otherwise, the push does not meet the standard, and the user who has not read or downloaded the content can be pushed again to improve the push effect until the push meets the standard;

[0069] It should be noted that the first weight coefficient θ 1 , weight coefficient θ 2 , secondary weight coefficient μ 2 and the third-level weight coefficient μ 3 is a preset value, obtained based on experience, and satisfies θ 1 +θ 2 =1;μ2 +μ 3 =1; no further details are given.

[0070] As an implementation mode of the present invention, the actual label matching degree P of the i-th enterprise and the current push policy is i By formula Calculate and obtain;

[0071] The actual keyword matching degree Q between the i-th enterprise and the policy pushed this time i By formula Calculate and obtain;

[0072] Among them, X A is the total number of policy labels; Xs is the number of label matches between the i-th enterprise and the policy label of this push policy; Y A is the total number of keywords pushed this time; Xs is the number of keyword matches between the ith enterprise and the keywords pushed this time;

[0073] Through the above technical scheme, the policy tags of this embodiment include enterprise type, industry, enterprise scale, etc.; the number of matches between the i-th enterprise and the policy tag of the policy pushed this time can be obtained by matching the enterprise tag of the i-th enterprise with the policy tag set for this push. The obtaining method is the existing technology and will not be described in detail here; the keywords pushed this time are automatically generated according to the policy text content and title pushed this time. The generating method is the existing technology and will not be described in detail here; the number of keyword matches between the i-th enterprise and the keywords pushed this time is obtained by analyzing the business scope or business content of the i-th enterprise with the keywords pushed this time. The analysis process is the existing technology and will not be described in detail here.

[0074] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for automatically pushing enterprise policies based on big data, characterized in that: The push method comprises the following steps: S1: Set the policy label, push level and tracking level of this push through the policy setting module; S2: Analyze the policy label, push level, policy text content and enterprise information through the analysis module to obtain the policy matching index; S3: Analyze the policy matching index through the analysis module, select the enterprises to be pushed and push them; S4: Obtain the tracking information data of each enterprise after this push through the tracking module; S5: Analyze the enterprise matching level, tracking level and tracking information data through the analysis module, and determine whether the push meets the standards based on the analysis results.

2. According to the method of automatic enterprise policy push based on big data in claim 1, it is characterized in that: The policy matching index is calculated by the formula: Calculate the comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i ; Where i is the enterprise number; P i is the actual label matching degree between the ith enterprise and the policy pushed this time; P0 is the preset label matching degree; Q i is the keyword matching degree between the ith enterprise and the policy pushed this time; P0 is the preset keyword matching degree; T0 is the basic policy matching index; γ1 is the first weight coefficient; γ2 is the second weight coefficient; C1 is the first preset constant; C2 is the second preset constant; u n It is the push level coefficient of the nth level.

3. The method for automatically pushing enterprise policies based on big data according to claim 2 is characterized in that: The push level includes N levels, N≥2; n∈[1,N]; the nth level push level coefficient u n Satisfies 0=u1P0 <u2P0…u n P0 N P0≤1, and at the same time 0=u1Q0 <u2Q0…u n Q0 N Q0≤1.​​ 4. The method for automatically pushing enterprise policies based on big data according to claim 3 is characterized in that: In step S3, the enterprise screening process for this push is as follows: The comprehensive policy matching index T between the i-th enterprise and the policy pushed this time i Compare with the preset value R1; When T i <When T is less than T0, the matching level of the i-th enterprise is at the first level and no push is performed; When T0 ≤ T i <When R1, the matching level of the i-th enterprise is level two, and push is performed; When T i When ≤R1, the matching level of the i-th enterprise is level three and is pushed.

5. The method for automatically pushing enterprise policies based on big data according to claim 4 is characterized in that: The tracking level includes multiple levels; in step S4, the tracking information data includes a reading status and a downloading status; the reading status includes read and unread; the downloading status includes downloaded and not downloaded.

6. The method for automatically pushing enterprise policies based on big data according to claim 5, characterized in that: In step S5, the process of determining whether the push meets the standard includes the following formula: Calculate the judgment index C.

7. The method for automatically pushing enterprise policies based on big data according to claim 6, characterized in that: The judgment process of whether the push meets the standard also includes: when C≥1, the push meets the standard; otherwise, the push does not meet the standard.

8. The method for automatically pushing enterprise policies based on big data according to claim 7, characterized in that: The actual label matching degree P between the i-th enterprise and the policy pushed this time i By formula Calculate and obtain; The actual keyword matching degree Q between the i-th enterprise and the policy pushed this time i By formula Calculate and obtain; Among them, X A is the total number of policy labels; X S Y is the number of label matches between the i-th enterprise and the policy label of the policy pushed this time; A The total number of keywords pushed this time; X S The number of keyword matches between the ith enterprise and the keyword pushed this time.

Images