CN112685652A - Information pushing method and system for enterprise users - Google Patents
Information pushing method and system for enterprise users Download PDFInfo
- Publication number
- CN112685652A CN112685652A CN202110151042.5A CN202110151042A CN112685652A CN 112685652 A CN112685652 A CN 112685652A CN 202110151042 A CN202110151042 A CN 202110151042A CN 112685652 A CN112685652 A CN 112685652A
- Authority
- CN
- China
- Prior art keywords
- information
- label
- user
- pushed
- dimension
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000003068 static effect Effects 0.000 claims abstract description 153
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 45
- 238000010438 heat treatment Methods 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 230000010365 information processing Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 4
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000399 orthopedic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241000283973 Oryctolagus cuniculus Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005202 decontamination Methods 0.000 description 1
- 230000003588 decontaminative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an information pushing method and system for enterprise users, and relates to the technical field of information pushing. The information pushing method comprises the following steps: acquiring characteristic information of a user, and acquiring enterprise static dimension label information, user static dimension label information and user dynamic dimension label information of the user; each piece of information to be pushed in the information list to be pushed is obtained, information static dimension label information and information thermal dimension label information of the information to be pushed are obtained, label matching values are obtained by comparing the label information, and the degree of engagement between the information to be pushed and the user is obtained according to the label matching values and the information thermal dimension label information; and sequencing all the information to be pushed according to the degree of engagement, and sending the information to be pushed meeting the degree of engagement requirement to the user. The method and the device can efficiently and accurately screen the push information from the information list to be pushed, improve the user experience of enterprises and avoid the waste of bandwidth resources.
Description
Technical Field
The invention relates to the technical field of information pushing, in particular to an information pushing method and system facing enterprise users.
Background
Managers or technicians of the existing enterprises often search information related to enterprise production and enterprise research and development products on the internet in an active searching mode, and the searched data volume is large and the range is large. Taking a medical instrument production enterprise as an example, the medical instrument industry is characterized by multiple types, strong supervision, high standard, high technology and fast market change, and as a high manager or a technician of the medical instrument production enterprise, the latest information such as laws and regulations, standard standards, emerging technologies, market trends and the like of the industry generally needs to be known in time, if the information is searched in a self-searching manner, on one hand, reading and searching from massive data wastes user time, and on the other hand, if a keyword used by a user is inaccurate, the information meeting the user requirements may not be accurately searched. The information push (or called message push) refers to that the server side sends information to the client side in an active mode, so that a user is prevented from actively pulling data from the server side to access the information, and user experience is improved. The information pushing system not only displays the information to be pushed in front of the user in time, but also abandons the passive situation that the past finds the information and looks at the rabbit, and realizes the information finding by combining the technologies of data mining, Internet and the like.
At present, various technical solutions for pushing relevant information to a target user based on big data are provided in the prior art, and taking chinese patent application CN 201610133262.4 as an example, it discloses a mobile internet message pushing system facing enterprise clients: the system comprises a message pushing server, a WEB server, a user intelligent mobile terminal and an enterprise application APP; a user on behalf of an enterprise registers and uses an enterprise application APP on an intelligent mobile terminal, and a message push server has enterprise attribute information, social numbers of enterprise users and related information of the enterprise application APP; the message pushing server is connected with the enterprise application APP in a polling or long connection mode, a proper message is selected according to enterprise attributes and pushed to the enterprise application APP, the message is published to the WEB server, a URL (uniform resource locator) address is generated according to the message address and user information, the URL address and the message abstract are pushed to the user through a social number, after the user receives the message abstract, if the user is interested in the detailed message, the user clicks the URL address to check the detailed message through a browser, and the message server can acquire the message using condition of the user. Although the technical scheme realizes the information push of the whole channel, when the information push is carried out, the screening of the pushed information content is lacked, so that the information which is matched with the requirements of the user cannot be screened according to the characteristics of the user in the content push process, and the targeted push information cannot be provided for the user.
On the other hand, although the prior art also provides a scheme for pushing information according to the subscription number or the attention number of the user, all pieces of pushed information in the subscription number or the attention number are generally sent to the user according to a time sequence, frequent and blind information pushing greatly affects user experience, and unnecessary bandwidth resource waste is caused.
In summary, how to provide a technical scheme capable of intelligently matching enterprise users with push information so as to screen out information suitable for requirements of the enterprise users from an information push list is a technical problem to be solved urgently in current enterprise market activities.
Disclosure of Invention
The invention aims to: the defects of the prior art are overcome, and an enterprise user-oriented information push method and system are provided. The information pushing method provided by the invention can obtain enterprise static dimension label information, user static dimension label information and user dynamic dimension label information of a user based on a preset user label analysis module, obtain information static dimension label information and information thermal dimension label information of information to be pushed based on the preset information label analysis module, then obtain a label matching value by comparing the information static dimension label information with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information of the user, obtain the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information, and actively send the information of which the degree of engagement meets the requirement to the user. Therefore, the push information with high conformity with the enterprise user can be efficiently and accurately screened from the information list to be pushed, the enterprise user experience is improved, and the waste of bandwidth resources is avoided.
In order to achieve the above object, the present invention provides the following technical solutions:
an information pushing method facing enterprise users comprises the following steps:
s100, collecting characteristic information of a user, and obtaining enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module;
s200, acquiring information to be pushed in an information list to be pushed, acquiring information static dimension label information and information thermal dimension label information of the information to be pushed through an information label analysis module, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to acquire a label matching value, and acquiring the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information;
s300, repeating the step S200 on other information to be pushed in the information list to be pushed to obtain the fitting degree of all the information to be pushed;
s400, sequencing all the information to be pushed according to the degree of engagement, and sending the information to be pushed meeting the degree of engagement requirement to the user.
Further, the conformity requirement is as follows:
acquiring a preset conformity standard value, and sending the information to be pushed with the conformity exceeding the conformity standard value to the user;
or acquiring a preset information limit quantity value N, selecting N information to be pushed with higher degree of engagement from an information list to be pushed according to the information limit quantity value N, and sending the N information to be pushed to the user. Further, the user tag analysis module comprises an enterprise tag setting submodule, a user static tag setting submodule and a user dynamic tag setting submodule;
the enterprise tag setting submodule is used for setting enterprise static dimension tags of the user according to enterprise basic information of an enterprise to which the user belongs, wherein the enterprise static dimension tags comprise an industry tag, a region tag and a product tag; the industry labels are divided into a first type, a second type and a third type, the region labels comprise province, city and/or county information, and the product labels comprise product type information and/or product detail information;
the user static label setting submodule is used for setting a user static dimension label of the user according to basic information of the user, and comprises a position label and an attention field label, wherein the position label comprises a business owner, a technical staff, a quality staff, a production staff and a sales staff, and the attention field label comprises news, regulations, standards, quality, compliance and supervision field types;
the user dynamic label setting submodule is used for setting a user dynamic dimension label of the user according to the behavior information of the user, and comprises the step of extracting one or more keyword labels from reading records, searching records, collecting records, praise records and/or evaluation records of the user.
Further, the information label analysis module comprises an information static label setting submodule and an information thermal label setting submodule;
the information static label setting submodule is used for setting an information static dimension label according to a release object and information content of information to be pushed, and comprises a publisher label, a region label, an industry label, a product label, an information type label and an information characteristic label, wherein the publisher label comprises information of national departments, provincial departments, city departments and industry associations, the region label comprises information of national alliances, countries, regions, provinces, cities and/or counties, the industry label is divided into one type, two types and three types, the product label comprises product large-class information, product small-class information and/or product detail information, the information type label comprises news, regulations, standards, technologies and market types, and the information characteristic label comprises quality, production, supervision and inspection types;
the information heating power label setting submodule is used for setting an information heating power dimension label according to access information of information to be pushed, wherein the information heating power dimension label comprises information of reading times, forwarding times, praise times, collection times and/or reference times.
Further, the step of comparing the information static dimension label information with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value includes:
initializing a tag matching value S, and setting the tag matching value S to be 0;
extracting all information static dimension labels to construct a keyword lexicon;
sequentially extracting tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags, judging whether the tag exists in the keyword lexicon or not while extracting one tag, judging whether the tag exists in a current order S = S +1 a, wherein a represents a specific gravity coefficient of the tag, and otherwise, keeping the value of S unchanged;
when the comparison of all the tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags is judged to be completed, the scoring is finished;
and taking the current value corresponding to the S as a label matching value.
Further, the step of obtaining the degree of engagement between the information to be pushed and the user according to the tag matching value and the information thermodynamic dimension tag information includes:
acquiring the thermodynamic value of the information to be pushed based on a preset time and value mapping model according to the reading times, the forwarding times, the praise times, the collection times and/or the reference times in the information thermodynamic dimension label; the thermodynamic score is in direct proportion to the number of reading times, forwarding times, praise times, collection times and/or reference times, and the higher the times, the higher the corresponding thermodynamic score is;
and adding the label matching value of the information to be pushed and the thermal power value to obtain a value serving as a fitting degree.
Further, all the information to be pushed is arranged in a descending order according to the scores of the degrees of engagement to obtain a preset standard score of the degrees of engagement, the information to be pushed with the score exceeding the standard score is sent to the user, and the information to be pushed with the score below the standard score is deleted from the information list to be pushed.
Furthermore, the user tag analysis module and the information tag analysis module both comprise tag setting sub-modules, editing information of a user on the tags is collected through the tag setting sub-modules, and preset tags in the user tag analysis module and/or the information tag analysis module are adjusted according to the editing information;
the editing comprises changing existing label keywords, adding labels, deleting labels and/or adjusting label dimensions.
The invention also provides an information pushing system facing the enterprise users, which comprises the following structures:
the information acquisition module is used for acquiring the characteristic information of the user and the information to be pushed in the information list to be pushed;
the user tag analysis module is used for acquiring enterprise static dimension tag information of an enterprise to which the user belongs, user static dimension tag information of the user and user dynamic dimension tag information of the user according to the characteristic information of the user;
the information label analysis module is used for obtaining information static dimension label information and information thermal dimension label information of the information to be pushed according to the information to be pushed in the pushing information list;
the information processing module is used for comparing information static dimension label information of information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, and obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information; sequencing all information to be pushed according to the degree of engagement, and triggering and sending instructions for the information to be pushed which meets the degree of engagement requirement;
and the information pushing module is used for sending the corresponding information to be pushed to the user according to the sending instruction.
The invention also provides another information pushing method facing the enterprise users, which comprises the following steps:
acquiring characteristic information of a user, and acquiring enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module; acquiring information to be pushed in an information list to be pushed, and acquiring information static dimension label information and information thermal dimension label information of each information to be pushed through an information label analysis module;
and for each piece of information to be pushed, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information, and sending the information to be pushed to the user when the degree of engagement exceeds a preset degree of engagement standard.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects as examples: the method comprises the steps of obtaining enterprise static dimension label information, user static dimension label information and user dynamic dimension label information of a user based on a preset user label analysis module, obtaining information static dimension label information and information thermal dimension label information of information to be pushed based on the preset information label analysis module, then obtaining a label matching value by comparing the information static dimension label information with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information of the user, obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information, and actively sending the information with the degree of engagement meeting requirements to the user. Therefore, the push information with high conformity with the user can be efficiently and accurately screened from the information list to be pushed, the user experience is improved, and the waste of bandwidth resources is avoided.
Drawings
Fig. 1 is a flowchart of an information pushing method for enterprise users according to an embodiment of the present invention.
Fig. 2 is a diagram illustrating an example of information transmission for obtaining a degree of engagement according to an embodiment of the present invention.
Fig. 3 is a block diagram of an information push system according to an embodiment of the present invention.
Fig. 4 is a flowchart of another information pushing method for an enterprise user according to an embodiment of the present invention.
Detailed Description
The information pushing method and system for enterprise users disclosed by the invention are further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that technical features or combinations of technical features described in the following embodiments should not be considered as being isolated, and they may be combined with each other to achieve better technical effects. In the drawings of the embodiments described below, the same reference numerals appearing in the respective drawings denote the same features or components, and may be applied to different embodiments. Thus, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.
It should be noted that the structures, proportions, sizes, and other dimensions shown in the drawings and described in the specification are only for the purpose of understanding and reading the present disclosure, and are not intended to limit the scope of the invention, which is defined by the claims, and any modifications of the structures, changes in the proportions and adjustments of the sizes and other dimensions, should be construed as falling within the scope of the invention unless the function and objectives of the invention are affected. The scope of the preferred embodiments of the present invention includes additional implementations in which functions may be executed out of order from that described or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
Examples
Referring to fig. 1, an information push method for enterprise users is provided in this embodiment. The method comprises the following steps:
s100, collecting characteristic information of a user, and obtaining enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module.
The characteristic information of the user can be from active setting and/or big data analysis of the user. The active setting may be that the user inputs own characteristic information through a related user interface, or that the user uploads or imports a file in which the own characteristic information is recorded through the related user interface. The data analysis may be based on various internet information such as the user's instant messaging account, social network platform account, shopping website account, and so on.
In a preferred embodiment, the user information related to the static dimension in the feature information is from an active setting of the user. For example, but not by way of limitation, for example, a personal information setting control is set corresponding to each enterprise user as a feature information acquisition structure, after the personal information setting control is triggered, a personal information setting interface can be popped up, and the user can input enterprise basic information and personal basic information (including basic attribute information such as name, age, position, contact address, interest, and attention area) of an enterprise to which the individual belongs in the personal information setting interface. The user information related to the dynamic dimension in the characteristic information is obtained through big data analysis, and the dynamic dimension information of the user is obtained through the login behavior, the browsing behavior, the searching behavior and the like of the big data analysis user.
In this embodiment, the user tag analysis module may specifically include an enterprise tag setting sub-module, a user static tag setting sub-module, and a user dynamic tag setting sub-module.
And the enterprise label setting submodule is used for setting enterprise static dimension labels of the user according to the enterprise basic information of the enterprise to which the user belongs, wherein the enterprise static dimension labels comprise an industry label, a region label and a product label. In this embodiment, the enterprise user is a user of a medical device production enterprise, and the information to be pushed is information related to the medical device production industry.
The industry labels are preferably classified into one, two and three categories. The region label preferably includes province, city and/or county information. The product label preferably includes product type information and/or product detail information.
And the user static label setting submodule is used for setting user static dimension labels of the user according to the basic information of the user, wherein the user static dimension labels comprise position labels and attention field labels. The basic information of the user includes, but is not limited to, the name, age, position, contact address, interest, area of interest, and other basic attribute information of the user.
The job labels preferably include business owners, technicians, quality personnel, production personnel, and sales personnel. The area of interest tags preferably include news, regulatory, standards, quality, compliance, and regulatory domain types.
The user dynamic label setting submodule is used for setting a user dynamic dimension label of the user according to the behavior information of the user, and comprises the step of extracting one or more keyword labels from reading records, searching records, collecting records, praise records and/or evaluation records of the user. That is, the user dynamic tag setting sub-module may acquire and analyze the behavior information of the user, and extract one or more keyword tags from the reading record, the search record, the collection record, the approval record and/or the evaluation record of the user as the user dynamic dimension tags.
By way of example and not limitation, 3 tags are extracted from the article "hospital orthopedic laminar flow cleaning operating room design construction topic series" that the user reads historical messages: orthopedics/operating room/decontamination.
Specifically, when extracting the keyword tag, it is considered that the corresponding article in the reading record, the search record, the collection record, and the like often has a title, and a keyword may be generally arranged, in this case, when extracting the keyword tag, the title of the article may be subjected to semantic analysis directly, and then an issuer and/or a recipient of a predicate in the title may be extracted, and then the issuer and/or the recipient related to the medical device field may be used as the keyword tag; alternatively, the keyword extraction efficiency may be improved by directly using the configured keyword as the keyword tag.
For the evaluation records, considering that the evaluated sentences are often spoken, in the case of spoken sentences, in a common semantic analysis process, a predicate in a sentence may not be found, so that an issuer and an acceptor of the predicate cannot be determined, and the issuer and/or the acceptor of the predicate cannot be used as the keyword tag. At this time, the keyword tag may be extracted as follows:
firstly, acquiring text information of an evaluation record of a user, and segmenting the text information.
Then, obtaining L words through word segmentation, wherein L is more than or equal to 1; respectively acquiring the characteristics of the L words based on a preset labeling rule in the field of medical instruments; and respectively determining the information content contained in the L words according to the characteristics, and selecting at least one word containing more information content from the L words as a central word. By way of example and not limitation, when the user input text is in the chinese language, a chinese word segmentation system, such as ICTCLAS, may be used to segment the text corresponding to the user input speech. The characteristics of the words can reflect the specific part of speech, representative meaning and other named entity characteristics of the words. By way of example, and not limitation, such as product name, legal name, place name, number, part of speech (such as adjective, adverb, co-word, conjunctive, etc.), and the like.
Then, respectively taking the central words as centers to make windows, and determining context words of the central words; matching the context words with a semantic model obtained by pre-training to obtain a matching result; and analyzing semantics according to the matching result.
And finally, extracting words related to the field of the medical apparatus and instruments from the semantic content as keyword labels according to the analyzed semantic content.
S200, obtaining information to be pushed in an information list to be pushed, obtaining information static dimension label information and information thermal dimension label information of the information to be pushed through an information label analysis module, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, and obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information.
In this embodiment, the information tag analysis module may specifically include an information static tag setting submodule and an information thermal tag setting submodule.
The information static label setting submodule is used for setting information static dimension labels according to the issuing object and the information content of the information to be pushed, and the information static dimension labels comprise an issuer label, a region label, an industry label, a product label, an information type label and an information characteristic label.
The publisher tags include national, provincial, municipal, and industry association information. The region label includes national alliance, country, region, province, city and/or county information. The industry labels are classified into one type, two types, and three types. The product label includes product major category information, product minor category and/or product detail information. The information type tags include news, regulations, standards, technology, and market types. The information characteristic label comprises quality, production, supervision and inspection types.
The information heating power label setting submodule is used for setting an information heating power dimension label according to access information of information to be pushed, wherein the information heating power dimension label comprises information of reading times, forwarding times, praise times, collection times and/or reference times.
After the information static dimension label information and the information thermal dimension label information of the information to be pushed are obtained, the information static dimension label information is compared with the enterprise static dimension label information and the user static dimension label information to obtain a label matching value, which is shown in fig. 2.
The higher the matching degree of the label, the higher the label matching value. Specifically, the tag matching value can be obtained by setting a mapping relation table of the tag matching degree and the tag matching value and looking up the table according to the matching degree of the tag. The matching degree can be set to be 2 or more according to the requirement. By way of example and not limitation, such as preset to 2 — match and mismatch, the corresponding label match values (scores) are 1 score and 0 score in turn. By way of example and not limitation, for example, information region = shanghai city, business region = shanghai baoshan region, judge that the region matches and scores 1 point; enterprise.area = Hubei Wuhan city, unmatched, scored 0.
In a preferred embodiment, the step of obtaining the tag matching value may be as follows:
initializing a tag matching value S, and setting the tag matching value S to be 0;
extracting all information static dimension labels to construct a keyword lexicon;
sequentially extracting tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags, judging whether the tag exists in the keyword lexicon or not when one tag is extracted, and judging that the tag exists in the keyword lexicon by S = S +1 × a, wherein a represents a specific gravity coefficient of the tag; otherwise, keeping the value of S unchanged, namely when the label is judged not to exist in the keyword lexicon, keeping the value of S unchanged;
when the comparison of all the tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags is judged to be completed, the scoring is finished;
and taking the current value corresponding to the S as a label matching value.
In this embodiment, the specific gravity coefficient a of the tag may be set individually by the user, or may be set by default based on the system. For example, but not by way of limitation, the specific gravity coefficients a of the respective tags are uniformly set to 1 division, that is, a value of a is a numerical value greater than 0 and less than or equal to 1, or the specific gravity coefficients a of the respective tags are uniformly set to 100 divisions, that is, a value of a is a numerical value greater than 0 and less than or equal to 100.
And then, calculating the degree of engagement between the information to be pushed and the user by combining the information thermal dimension label according to the obtained label matching value, and continuing to refer to fig. 2.
In a preferred embodiment, the step of obtaining the degree of engagement may be as follows: and acquiring the thermodynamic value of the information to be pushed based on a preset time and value mapping model according to the reading times, the forwarding times, the praise times, the collection times and/or the reference times in the information thermodynamic dimension label. The thermodynamic score is in direct proportion to the number of reading times, forwarding times, praise times, collection times and/or reference times, and the higher the times, the higher the corresponding thermodynamic score is; and adding the label matching value of the information to be pushed and the thermal power value to obtain a value serving as a fitting degree.
For example, but not by way of limitation, if the thermal power score is preset to be in a positive correlation with the reference times, the corresponding thermal power score can be obtained by the reference times (which can be realized by a preset mapping table in actual operation). Such as: the quote times are between 200 and 300, and the thermal power score is 70; when the number of citations is less than 100, the thermodynamic score is 30.
And S300, repeating the step S200 for other information to be pushed in the information list to be pushed, and obtaining the fitting degree of all the information to be pushed.
S400, sequencing all the information to be pushed according to the degree of engagement, and triggering and sending instructions for the information to be pushed which meets the degree of engagement requirement.
In this embodiment, the conformity degree requirement is: and acquiring a preset conformity standard value, and sending the information to be pushed with the conformity exceeding the conformity standard value to the user.
Or, the conformity requirement is: acquiring a preset information limit quantity value N, selecting N information to be pushed with higher fitting degree from an information list to be pushed according to the information limit quantity value N, and sending the N information to be pushed to the user.
The aforesaid fitness criterion value and the information limit quantity value N may be set individually by the user, or may be set by default based on the system, and should not be taken as a limitation herein.
Preferably, all the information to be pushed can be sorted in descending order according to the scores of the degrees of engagement. And then, acquiring a preset fitness standard score, sending the information to be pushed with the score exceeding the standard score to the user, and deleting the information to be pushed with the score below the standard score from the information list to be pushed.
In another implementation manner of this embodiment, the user tag analysis module and the information tag analysis module may further include a tag setting sub-module.
Through the label setting submodule, the editing information of the user on the label can be collected, and the preset label in the user label analysis module and/or the information label analysis module is adjusted according to the editing information. The editing comprises changing existing label keywords, adding labels, deleting labels and/or adjusting label dimensions.
Through the technical scheme, the user can adjust the label information under five dimensions according to actual needs, such as changing the existing label keywords, adding new labels, deleting labels and the like.
The present embodiment is described in detail below with reference to specific applications.
For example, a public application of instant messaging tools for wechat pushes information to an enterprise user, and currently, there are 100 pieces of information to be pushed in an information list to be pushed. The value of the predetermined information limit quantity is 10.
Firstly, according to the characteristic information of an enterprise user, acquiring a plurality of tags such as an enterprise static dimension tag, a user static dimension tag and a user dynamic dimension tag of the user, specifically as follows:
static industry segment = three classes
Enterprise.static region = mountainous region of shanghai city
Static product = customized artificial tooth for enterprise
Static annual revenue =2000 RMB
User static name = zhang san
User static job = quality person in charge
User.static.concern = regulation + quality + supervision
Dynamic reading history = regulation + quality.
Then, for one piece of information in the information list to be pushed, a plurality of labels such as an information static dimension label, an information thermal dimension label and the like of the information to be pushed are obtained, which is specifically as follows:
static name = decision by the State Council on modification of medical Instrument supervision and management regulations
Static publisher = country + state
Information static region = national region
Static industry segment = all
Static product breakdown = all
Information type = regulation
Thermal citation times = 90.
Then, respectively carrying out label comparison processing on the information static dimension and the enterprise static dimension, the user static dimension and the user dynamic dimension, and scoring, wherein the obtained score is a label matching value; and independently scoring the information thermodynamic dimension, wherein the obtained score is a thermodynamic score; the scores of the tag match value and the thermodynamic score are accumulated.
Information, region & enterprise, region, 90 points
Information industry subdivision, enterprise industry subdivision and 90 points
Information product subdivision & & enterprise product, 90 points
Information, information type & & user job, 50 points
Information, information type & & user, attention, 70 points
Information, information type & & user reading history, 70 points
Number of information, heating power, quote, 30 minutes
The above score was accumulated to 490 points.
And repeating the steps of obtaining the information static dimension label and the information thermal dimension label and the step of marking aiming at each piece of other information in the information list to be pushed until the integrating degrees of all the information are completed. Thereby obtaining the degree of engagement of 100 pieces of information to be pushed to Zhang III.
And finally: and (4) arranging all the messages in a descending order according to the total score value, and pushing 10 messages to be pushed, which are 10 before the integrating degree score, in 100 messages to be pushed to Zhang III in sequence. By way of example and not limitation, the degree of engagement of the information to be pushed, such as "the decision of the State Council about modification of the medical device supervision and management regulations", is ranked first and is sent as the first push information to the user Zhang III.
Referring to fig. 3, an information pushing system for enterprise users is further provided as another embodiment of the present invention.
The system comprises the following structure: the system comprises an information acquisition module, a user label analysis module, an information processing module and an information pushing module.
The information acquisition module is used for acquiring the characteristic information of the user and the information to be pushed in the information list to be pushed.
The user tag analysis module is used for obtaining enterprise static dimension tag information of an enterprise to which the user belongs, user static dimension tag information of the user and user dynamic dimension tag information of the user according to the characteristic information of the user.
The information label analysis module is used for obtaining information static dimension label information and information thermal dimension label information of the information to be pushed according to the information to be pushed in the pushing information list.
The information processing module is used for comparing information static dimension label information of information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, and obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information; and sequencing all the information to be pushed according to the degree of engagement, and triggering and sending instructions for the information to be pushed with the degree of engagement exceeding a preset degree of engagement standard.
In one embodiment, the information processing module is configured to: and acquiring a preset conformity standard value, and sending the information to be pushed with the conformity exceeding the conformity standard value to the user.
In another embodiment, the information processing module is configured to: acquiring a preset information limit quantity value N, selecting N information to be pushed with higher fitting degree from an information list to be pushed according to the information limit quantity value N, and sending the N information to be pushed to the user.
And the information pushing module is used for sending the corresponding information to be pushed to the user according to the sending instruction.
The user tag analysis module specifically comprises an enterprise tag setting submodule, a user static tag setting submodule and a user dynamic tag setting submodule;
the enterprise tag setting submodule is used for setting enterprise static dimension tags of the user according to enterprise basic information of an enterprise to which the user belongs, wherein the enterprise static dimension tags comprise an industry tag, a region tag and a product tag; the industry labels are divided into a first type, a second type and a third type, the region labels comprise province, city and/or county information, and the product labels comprise product type information and/or product detail information;
the user static label setting submodule is used for setting a user static dimension label of the user according to basic information of the user, and comprises a position label and an attention field label, wherein the position label comprises a business owner, a technical staff, a quality staff, a production staff and a sales staff, and the attention field label comprises news, regulations, standards, quality, compliance and supervision field types;
the user dynamic label setting submodule is used for setting a user dynamic dimension label of the user according to the behavior information of the user, and comprises the step of extracting one or more keyword labels from reading records, searching records, collecting records, praise records and/or evaluation records of the user.
The information tag analysis module specifically comprises an information static tag setting submodule and an information thermal tag setting submodule;
the information static label setting submodule is used for setting an information static dimension label according to a release object and information content of information to be pushed, and comprises a publisher label, a region label, an industry label, a product label, an information type label and an information characteristic label, wherein the publisher label comprises information of national departments, provincial departments, city departments and industry associations, the region label comprises information of national alliances, countries, regions, provinces, cities and/or counties, the industry label is divided into one type, two types and three types, the product label comprises product large-class information, product small-class information and/or product detail information, the information type label comprises news, regulations, standards, technologies and market types, and the information characteristic label comprises quality, production, supervision and inspection types;
the information heating power label setting submodule is used for setting an information heating power dimension label according to access information of information to be pushed, wherein the information heating power dimension label comprises information of reading times, forwarding times, praise times, collection times and/or reference times.
The information processing module comprises a tag comparison submodule configured to: initializing a tag matching value S, and setting the tag matching value S to be 0; extracting all information static dimension labels to construct a keyword lexicon; sequentially extracting tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags, judging whether the tag exists in the keyword lexicon or not while extracting one tag, judging whether the tag exists in a current order S = S +1 a, wherein a represents a specific gravity coefficient of the tag, and otherwise, keeping the value of S unchanged; when the comparison of all the tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags is judged to be completed, the scoring is finished; and taking the current value corresponding to the S as a label matching value.
The information processing module further comprises a goodness of fit processing submodule configured to: acquiring the thermodynamic value of the information to be pushed based on a preset time and value mapping model according to the reading times, the forwarding times, the praise times, the collection times and/or the reference times in the information thermodynamic dimension label; the thermodynamic score is in direct proportion to the number of reading times, forwarding times, praise times, collection times and/or reference times, and the higher the times, the higher the corresponding thermodynamic score is; and adding the label matching value of the information to be pushed and the thermal score to obtain a score as a fitting degree.
Further, the information processing module is further configured to: and performing descending order arrangement on all the information to be pushed according to the scores of the fitness to obtain a preset standard score of the fitness, sending the information to be pushed with the score exceeding the standard score to the user, and deleting the information to be pushed with the score below the standard score from the information list to be pushed.
Other technical features are referred to in the previous embodiments and are not described herein.
Referring to fig. 4, another embodiment of the present invention further provides another information pushing method for enterprise users. The method comprises the following steps:
s100', collecting characteristic information of a user, and obtaining enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module; and acquiring information to be pushed in the information list to be pushed, and acquiring information static dimension label information and information thermal dimension label information of each information to be pushed through an information label analysis module.
S200', for each piece of information to be pushed, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information, and sending the information to be pushed to the user when the degree of engagement exceeds a preset degree of engagement standard.
Other technical features are referred to in the previous embodiments and are not described herein.
In the foregoing description, the disclosure of the present invention is not intended to limit itself to these aspects. Rather, the various components may be selectively and operatively combined in any number within the intended scope of the present disclosure. In addition, terms like "comprising," "including," and "having" should be interpreted as inclusive or open-ended, rather than exclusive or closed-ended, by default, unless explicitly defined to the contrary. All technical, scientific, or other terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. Common terms found in dictionaries should not be interpreted too ideally or too realistically in the context of related art documents unless the present disclosure expressly limits them to that. Any changes and modifications of the present invention based on the above disclosure will be within the scope of the appended claims.
Claims (10)
1. An information push method facing enterprise users is characterized by comprising the following steps:
s100, collecting characteristic information of a user, and obtaining enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module;
s200, acquiring information to be pushed in an information list to be pushed, acquiring information static dimension label information and information thermal dimension label information of the information to be pushed through an information label analysis module, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to acquire a label matching value, and acquiring the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information;
s300, repeating the step S200 on other information to be pushed in the information list to be pushed to obtain the fitting degree of all the information to be pushed;
s400, sequencing all the information to be pushed according to the degree of engagement, and sending the information to be pushed meeting the degree of engagement requirement to the user.
2. The method of claim 1, wherein: the degree of engagement requirement is that,
acquiring a preset conformity standard value, and sending the information to be pushed with the conformity exceeding the conformity standard value to the user;
or acquiring a preset information limit quantity value N, selecting N information to be pushed with higher degree of engagement from an information list to be pushed according to the information limit quantity value N, and sending the N information to be pushed to the user.
3. The method of claim 2, wherein: the user tag analysis module comprises an enterprise tag setting submodule, a user static tag setting submodule and a user dynamic tag setting submodule;
the enterprise tag setting submodule is used for setting enterprise static dimension tags of the user according to enterprise basic information of an enterprise to which the user belongs, wherein the enterprise static dimension tags comprise an industry tag, a region tag and a product tag; the industry labels are divided into a first type, a second type and a third type, the region labels comprise province, city and/or county information, and the product labels comprise product type information and/or product detail information;
the user static label setting submodule is used for setting a user static dimension label of the user according to basic information of the user, and comprises a position label and an attention field label, wherein the position label comprises a business owner, a technical staff, a quality staff, a production staff and a sales staff, and the attention field label comprises news, regulations, standards, quality, compliance and supervision field types;
the user dynamic label setting submodule is used for setting a user dynamic dimension label of the user according to the behavior information of the user, and comprises the step of extracting one or more keyword labels from reading records, searching records, collecting records, praise records and/or evaluation records of the user.
4. The method of claim 3, wherein: the information label analysis module comprises an information static label setting submodule and an information heating power label setting submodule;
the information static label setting submodule is used for setting an information static dimension label according to a release object and information content of information to be pushed, and comprises a publisher label, a region label, an industry label, a product label, an information type label and an information characteristic label, wherein the publisher label comprises information of national departments, provincial departments, city departments and industry associations, the region label comprises information of national alliances, countries, regions, provinces, cities and/or counties, the industry label is divided into one type, two types and three types, the product label comprises product large-class information, product small-class information and/or product detail information, the information type label comprises news, regulations, standards, technologies and market types, and the information characteristic label comprises quality, production, supervision and inspection types;
the information heating power label setting submodule is used for setting an information heating power dimension label according to access information of information to be pushed, wherein the information heating power dimension label comprises information of reading times, forwarding times, praise times, collection times and/or reference times.
5. The method of claim 4, wherein: the step of comparing the information static dimension label information with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value comprises,
initializing a tag matching value S, and setting the tag matching value S to be 0;
extracting all information static dimension labels to construct a keyword lexicon;
sequentially extracting tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags, judging whether the tag exists in the keyword lexicon or not while extracting one tag, judging whether the tag exists in a current order S = S +1 a, wherein a represents a specific gravity coefficient of the tag, and otherwise, keeping the value of S unchanged;
when the comparison of all the tags in the enterprise static dimension tags, the user static dimension tags and the user dynamic dimension tags is judged to be completed, the scoring is finished;
and taking the current value corresponding to the S as a label matching value.
6. The method of claim 5, wherein: the step of obtaining the fitness of the information to be pushed and the user according to the label matching value and the information thermal dimension label information comprises the steps of,
acquiring the thermodynamic value of the information to be pushed based on a preset time and value mapping model according to the reading times, the forwarding times, the praise times, the collection times and/or the reference times in the information thermodynamic dimension label; the thermodynamic score is in direct proportion to the number of reading times, forwarding times, praise times, collection times and/or reference times, and the higher the times, the higher the corresponding thermodynamic score is;
and adding the label matching value of the information to be pushed and the thermal power value to obtain a value serving as a fitting degree.
7. The method of claim 6, wherein: and performing descending order arrangement on all the information to be pushed according to the scores of the fitness to obtain a preset standard score of the fitness, sending the information to be pushed with the score exceeding the standard score to the user, and deleting the information to be pushed with the score below the standard score from the information list to be pushed.
8. The method according to any one of claims 1-7, wherein: the user tag analysis module and the information tag analysis module both comprise tag setting sub-modules, editing information of a user on tags is collected through the tag setting sub-modules, and preset tags in the user tag analysis module and/or the information tag analysis module are adjusted according to the editing information;
the editing comprises changing existing label keywords, adding labels, deleting labels and/or adjusting label dimensions.
9. An information push system facing enterprise users, characterized by comprising:
the information acquisition module is used for acquiring the characteristic information of the user and the information to be pushed in the information list to be pushed;
the user tag analysis module is used for acquiring enterprise static dimension tag information of an enterprise to which the user belongs, user static dimension tag information of the user and user dynamic dimension tag information of the user according to the characteristic information of the user;
the information label analysis module is used for obtaining information static dimension label information and information thermal dimension label information of the information to be pushed according to the information to be pushed in the pushing information list;
the information processing module is used for comparing information static dimension label information of information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, and obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information; sequencing all information to be pushed according to the degree of engagement, and triggering and sending instructions for the information to be pushed which meets the degree of engagement requirement;
and the information pushing module is used for sending the corresponding information to be pushed to the user according to the sending instruction.
10. An information push method facing enterprise users is characterized by comprising the following steps:
acquiring characteristic information of a user, and acquiring enterprise static dimension label information of an enterprise to which the user belongs, user static dimension label information of the user and user dynamic dimension label information of the user through a user label analysis module; acquiring information to be pushed in an information list to be pushed, and acquiring information static dimension label information and information thermal dimension label information of each information to be pushed through an information label analysis module;
and for each piece of information to be pushed, comparing the information static dimension label information of the information to be pushed with the enterprise static dimension label information, the user static dimension label information and the user dynamic dimension label information to obtain a label matching value, obtaining the degree of engagement between the information to be pushed and the user according to the label matching value and the information thermal dimension label information, and sending the information to be pushed to the user when the degree of engagement exceeds a preset degree of engagement standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151042.5A CN112685652A (en) | 2021-02-04 | 2021-02-04 | Information pushing method and system for enterprise users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151042.5A CN112685652A (en) | 2021-02-04 | 2021-02-04 | Information pushing method and system for enterprise users |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112685652A true CN112685652A (en) | 2021-04-20 |
Family
ID=75457878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110151042.5A Withdrawn CN112685652A (en) | 2021-02-04 | 2021-02-04 | Information pushing method and system for enterprise users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112685652A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245320A (en) * | 2023-02-02 | 2023-06-09 | 江苏强基云计算科技有限公司 | Method for intelligently pushing enterprise tasks to students |
-
2021
- 2021-02-04 CN CN202110151042.5A patent/CN112685652A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245320A (en) * | 2023-02-02 | 2023-06-09 | 江苏强基云计算科技有限公司 | Method for intelligently pushing enterprise tasks to students |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105005594B (en) | Abnormal microblog users recognition methods | |
| TWI601088B (en) | Topic management network public opinion evaluation management system and method | |
| CN104820629B (en) | A kind of intelligent public sentiment accident emergent treatment system and method | |
| US7860872B2 (en) | Automated media analysis and document management system | |
| Wilson et al. | How to find the good and avoid the bad or ugly: a short guide to tools for rating quality of health information on the internetCommentary: On the way to quality | |
| US6810394B2 (en) | Methods and apparatus for searching for and identifying information of interest to users | |
| JP4489994B2 (en) | Topic extraction apparatus, method, program, and recording medium for recording the program | |
| US8707160B2 (en) | System and method for inferring user interest based on analysis of user-generated metadata | |
| JP5160601B2 (en) | System, method and apparatus for phrase mining based on relative frequency | |
| KR102075788B1 (en) | Healthy content recommendation service system using big datas | |
| CN103399891A (en) | Method, device and system for automatic recommendation of network content | |
| CN108305180B (en) | Friend recommendation method and device | |
| Moraga et al. | SQuaRE-aligned data quality model for web portals | |
| CN113657547A (en) | Public opinion monitoring method based on natural language processing model and related equipment thereof | |
| CN112149422A (en) | Enterprise news dynamic monitoring method based on natural language | |
| TW201640383A (en) | Internet events automatic collection and analysis method and system thereof | |
| CN112685652A (en) | Information pushing method and system for enterprise users | |
| KR102413961B1 (en) | Method for providing news analysis service using robotic process automation monitoring | |
| CN113065975A (en) | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics | |
| CN112528196A (en) | Internet public opinion popularity index real-time generation automatic monitoring system and method | |
| CN117113973A (en) | Information processing method and related device | |
| Masood et al. | Semantic analysis to identify students’ feedback | |
| Trevisan et al. | Talking about mobile communication systems: verbal comments in the web as a source for acceptance research in large-scale technologies | |
| CN115796600A (en) | Public opinion risk early warning method, system, medium and electronic equipment | |
| CN116450924A (en) | Analysis module and method of intelligent environment-friendly platform ecological environment public opinion monitoring 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210420 |
|
| WW01 | Invention patent application withdrawn after publication |