CN114969566A - Distance-measuring government affair service item collaborative filtering recommendation method - Google Patents
Distance-measuring government affair service item collaborative filtering recommendation method Download PDFInfo
- Publication number
- CN114969566A CN114969566A CN202210733505.3A CN202210733505A CN114969566A CN 114969566 A CN114969566 A CN 114969566A CN 202210733505 A CN202210733505 A CN 202210733505A CN 114969566 A CN114969566 A CN 114969566A
- Authority
- CN
- China
- Prior art keywords
- user
- transaction
- portrait
- service
- government
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
A distance measurement government affair service affair collaborative filtering recommendation method comprises the steps of respectively constructing a government affair service affair portrait, a user basic portrait and a user behavior portrait; calculating the similarity between users by adopting the portrait; calculating the relative position between the user and the government affair service center according to the user position information expression mode; and calculating the quasi-recommendation score of the target user for the related matters according to the user similarity and the distance between the user and the matters, thereby recommending the related matters. The user transaction frequency calculation method provided by the invention can fully reflect the correlation degree of the user and the transaction service items, introduces the spatial neighborhood relation and the distance calculation method, and participates in item score calculation; the method can preferentially recommend items of the same place for the user, improve the accuracy of the recommendation result, make up the problem of insufficient consideration of the space position by the traditional collaborative filtering, and develop and enrich the collaborative filtering recommendation method.
Description
Technical Field
The invention belongs to the technical field of information recommendation, and particularly relates to a distance-measuring collaborative filtering recommendation method for government affair service affairs.
Background
In recent years, the work of 'internet + government affairs service' is highly emphasized by state hospitals, a series of policy documents are successively exported, and standardization, normalization and convenience of government affairs service are promoted. On one hand, all levels of government departments of the national organization comprehensively comb administrative authority items and public service items, compile and form a government affair service item catalogue list, standardize government affair service item handling guides, and lay a foundation for enterprises and masses to handle affairs conveniently. On the other hand, the construction of a government affair service network is strengthened in each region, and more government affair service events such as online handling, handheld handling and fingertip handling are promoted. At present, more and more government affair service items are put through online transaction, and the masses can directly handle the items through the network, so that the transaction flow is simplified, the transaction time is saved, the transaction efficiency is greatly improved, and the acquisition feeling of the masses of enterprises is practically enhanced.
When the business masses transact government affairs in a network mode, the business masses need to find the affairs to be transacted on the webpage. Due to the fact that the number of the online government affair service affair catalogues is large and the categories are professional, an ordinary user can hardly position needed affairs quickly and accurately. Although some websites have provided retrieval functionality, queries are primarily located in a keyword matching manner, without comprehensively considering user characteristics and historical behavior, resulting in inaccurate recommendation results. In fact, in the business or academic fields, recommendation systems have been developed to solve the problem of information overload, such as shopping websites, video websites, and academic search, and users can quickly locate desired content according to the recommendation result of the system.
Collaborative filtering is a popular algorithm applied in current recommendation methods, which assumes that two users a and B have similar behavior habits (e.g., purchase, read, look, etc.), and then they also have similar preferences on other items. The collaborative filtering algorithm does not need to know user preferences, and only uses the historical behaviors of the user to predict the scores of the unknown commodities of the user for recommendation. The method is simple and effective, and is applied to recommendation systems in many fields.
In the government affairs service item recommendation, the collaborative filtering algorithm is a good choice, but some problems exist. Firstly, the business handling scene of government affair service is different from commercial shopping, the correlation degree between the user score and the user handling is not large, and the recommendation precision can be influenced by blindly applying a score matrix to calculate the similarity of the user. Second, government services have significant spatial attributes, and in general, government service events require that users must be approved by the home location or a competent department of the home location. When a collaborative filtering algorithm is adopted, if the position information is used as a user label, effective information may be filtered, and if the position information is not considered, inaccurate recommendation results may be caused.
Therefore, how to apply the collaborative filtering method to the government affair service item recommendation, avoid filtering useful information, and improve the recommendation accuracy becomes a technical problem which needs to be solved at present.
Disclosure of Invention
The invention provides a distance measurement government affair service affair collaborative filtering recommendation method and device aiming at the requirement of online government affair service affairs handling, combines a collaborative filtering recommendation method and government affair service affair characteristics, and fully considers user position information. In order to achieve the purpose, the invention adopts the following technical scheme:
in order to achieve the purpose, the invention adopts the following technical scheme:
a distance-measuring government affair service item collaborative filtering recommendation method is characterized by comprising the following steps:
data preparation step S110:
respectively constructing a government affair service affair portrait, a user basic portrait and a user behavior portrait based on government affair service affair data, user registration data and user transaction behavior data;
user similarity calculation step S120:
calculating user by using user basic portrait, user transaction portrait and government affair service affair portrait𝑘And𝑘' similarity between them𝑠𝑖𝑚 (𝑘, 𝑘′)；
Distance calculation step S130:
selecting administrative division or Euclidean distance to calculate user according to user position information expression mode𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 ；
Recommended item score calculation step S140:
according to user similarity𝑠𝑖𝑚 (𝑘, 𝑘′) User, user𝑘Am of affairs𝑗A distance d between𝑖𝑠 𝑘𝑗 Computing target users𝑘For the quasi-recommendation score of the related matters, the formula is as follows:
wherein the content of the first and second substances,𝑠𝑐𝑜𝑟𝑒 𝑘𝑗 representing target users𝑘User of𝑘' transacted government service events𝑗Is scored, wherein𝑤Representing a weight;
result recommending step S150:
and selecting the top N items according to the item scoring result to be recommended in S140 and according to the order of the scores from high to low to recommend the items to the user.
Optionally, in the data preparation step S110:
the government affair service affair portrait is used for labeling affairs according to attribute information of the government affair service affairs and constructing a model, wherein the attribute information of the government affair service affairs comprises the following components: item name, transaction department, service object, transaction location, and item topic;
the basic portrait of the user is that the basic information filled in during user registration is utilized to perform labeling processing on the user and construct a model, the user registration data is specifically that the basic information of natural people comprises gender, age, occupation, marriage and education conditions and positions, and the basic information of legal people can comprise an operation range, an enterprise type, an affiliated industry, an enterprise scale and an enterprise address;
the user behavior portrait is user transaction behavior data, labeling processing is carried out on user transaction behaviors, and a model is constructed, wherein the user transaction behavior data comprises attribute information of user transaction items and user transaction times.
Optionally, in step S120,
similarity between users by adopting cosine similarity calculation method𝑠𝑖𝑚 (𝑘, 𝑘′) The calculation is carried out in such a way that,
wherein the content of the first and second substances,𝐿represents a collection of all user base representation tags,𝑇a particular label in the user base representation is represented,𝑀 𝑘𝑇 and𝑀 𝑘’𝑇 respectively represent users𝑘And𝑘' Pair label𝑇Is characterized by a characteristic index of (A),
representing all users to a tag𝑇Average of the characteristic indices.
Optionally, in step S120,
the user characteristic index is used for reflecting the relevance between the user label and the transaction item, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,𝑀 𝑘𝑇 representing a user𝑘Portraying a label on a user basis𝑇The index of the characteristic of the user to be made,𝐼𝑡𝑒𝑚 𝑘 representing a user𝑘The matters to be dealt with are,𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘The total number of the processed items is,𝑟 𝑘𝑗 representing a user𝑘To handle things𝑗The frequency of the transaction of (1) is,𝐼 𝑗𝑇 show transaction items𝑗User base portrait label𝑇And (4) an index.
Optionally, in step S120,
the user transaction frequency is used for reflecting the degree of association between the user and transaction items, and is calculated according to the user behavior portrait, and the formula is as follows:
wherein the content of the first and second substances,𝑟 𝑘𝑗 representing a user𝑘To item (c)𝑗The frequency of the transaction of (1) is,𝑁(𝑗 𝑘 ) Representing a user𝑘To item (c)𝑗The number of times of the handling of (c),𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘Total number of transactions.
Optionally, in step S120,
the user basic portrait label index is used for judging the relevance between the label of the user and the transaction items, and the formula is as follows:
wherein the content of the first and second substances,𝐼 𝑗𝑇 show transaction items𝑗User base portrait label𝑇The index of the said plant is,𝑁(𝑈 𝑗 ) To do things𝑗The number of all the users of the network,𝑁(𝑇 𝑗 ) Show transaction items𝑗Has a tag among users𝑇The number of users.
Alternatively, in the distance calculating step S130,
when the user position information is expressed by coordinates, the Euclidean distance is adopted to calculate the user𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 The formula is as follows:
wherein (A), (B), (C), (D), (C), (B), (C)𝑥 𝑘 ，𝑦 𝑘 ) Representing a user𝑘(ii) a coordinate position of (A), (B)𝑥 𝑗 ，𝑦 𝑗 ) Show transaction items𝑗(ii) a government services center coordinate location;
when the user position information is expressed by administrative division, according to the administrative divisionSpatial relationship computation user of zones𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 The method comprises the following steps:
wherein (A), (B), (C), (D), (C), (B), (C)𝑥 𝑎 ，𝑦 𝑎 ) Representing a user𝑘Coordinate position of the center point of the administrative division, ((ii) coordinate position of the center point of the administrative division, ((iii)𝑥 𝑏 ，𝑦 𝑏 ) Show transaction items𝑗The center point coordinate position of the area where the government affairs service center is located.
The invention further discloses a storage medium for storing computer-executable instructions which, when executed by a processor, perform the above-mentioned distance metric government affairs collaborative filtering recommendation method.
The invention has the following advantages:
firstly, when the similarity of the users is calculated, a calculation method (formula 3) of the transaction frequency of the users is provided, the user score in the traditional collaborative filtering is replaced, the association degree of the users and the transaction service items can be fully reflected, and the method is more suitable for the recommendation scene of the transaction service items.
Secondly, introducing a spatial neighborhood relationship and a distance calculation method (formulas 5-7) in the process of recommending government affair service affairs, defining the distance between a user and a transaction affair according to point coordinates or administrative divisions respectively, and participating in the calculation of affair scores.
The distance measurement provided by the invention reflects the property requirements of an administrative department when handling the matters, can preferentially recommend the matters with the same property for the user, and improves the accuracy of the recommendation result. Meanwhile, the distance measurement also makes up the problem that the traditional collaborative filtering is insufficient in consideration of the spatial position, and a collaborative filtering recommendation method is developed and enriched.
Drawings
Fig. 1 is a flowchart of a distance-metric collaborative filtering recommendation method for government affairs service affairs according to a specific embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
The invention mainly comprises the following steps: and (4) adapting the collaborative filtering algorithm to the field of government affairs services. Meanwhile, the spatial distance measurement is added in an important mode, and the user similarity and the position attribute are comprehensively considered when items are recommended, so that the recommendation accuracy is improved.
Specifically, referring to fig. 1, a flow chart of the distance metric government affairs collaborative filtering recommendation method according to the present invention is shown, which includes the following steps:
data preparation step S110:
and respectively constructing a government affair service affair portrait, a user basic portrait and a user behavior portrait based on the government affair service affair data, the user registration data and the user transaction behavior data.
Preferably, the image of the government affairs service affairs is a model constructed by labeling the affairs according to the attribute information of the government affairs service affairs. The government service events include: transaction name, transaction department, service object, transaction location, and transaction topic.
Preferably, the user basic portrait is a model constructed by tagging the user with basic information filled in during user registration. The user registration data specifically includes natural person basic information including gender, age, occupation, marriage and childbirth conditions, location, and the like, and legal person basic information may include business scope, enterprise type, affiliated industry, enterprise scale, enterprise address, and the like.
Preferably, the user behavior representation is user transaction data, labeling is carried out on user transactions, and a model is constructed, wherein the user transaction data comprises attribute information of user transactions and user transaction times.
User similarity calculation step S120:
the user similarity degree user judges the similarity degree of the basic attribute and the handling requirement between the two users, and can find similar users for the target user through the user similarity degree, so that the handling items of the similar users can be conveniently recommended to the target user.
Specifically, the method comprises the following steps:
and calculating the similarity between the users and the' by using the information such as the user basic portrait, the user transaction portrait, the government affair service affair portrait and the like.
Specifically, the similarity between users is calculated by adopting a cosine similarity calculation method𝑠𝑖𝑚 (𝑘, 𝑘′) And (6) performing calculation.
Wherein the content of the first and second substances,𝐿represents a collection of all user base representation tags,𝑇a particular label in the user base representation is represented,𝑀 𝑘𝑇 and𝑀 𝑘’𝑇 respectively representing users𝑘And𝑘' Pair label𝑇Is characterized by a characteristic index of (A),
representing all users to a tag𝑇Mean value of characteristic index.𝑠𝑖𝑚 (𝑘, 𝑘′) The larger the value of (A), the user is represented𝑘And with𝑘The more closely together.
Specifically, the user characteristic index is used for reflecting the relevance between the user tag and the transaction item, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,𝑀 𝑘𝑇 representing a user𝑘Portraying labels on a user's base𝑇And (4) user characteristic indexes.𝐼𝑡𝑒𝑚 𝑘 Representing a user𝑘The items to be dealt with are,𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘The total number of the processed items is,𝑟 𝑘𝑗 representing a user𝑘To handle things𝑗The frequency of the transaction of (1) is,𝐼 𝑗𝑇 show handlingMatters and matters𝑗User base portrait label𝑇And (4) index.𝑀 𝑘𝑇 The larger the value of (A), the user label is represented𝑇For the user𝑘The higher the relevance of the business transaction.
The user transaction frequency is used for reflecting the degree of association between the user and transaction items, and can be calculated according to the user behavior portrait, and the formula is as follows:
wherein the content of the first and second substances,𝑟 𝑘𝑗 representing a user𝑘To item (c)𝑗The frequency of the transaction of (1) is,𝑁(𝑗 𝑘 ) Representing a user𝑘To item (c)𝑗The number of times of the handling of (c),𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘Total number of transactions.𝑟 𝑘𝑗 The higher the number of transactions indicating the government affairs service affairs, the more closely the user is connected to the affairs of the affairs.
Preferably, the user base representation label index is used for judging the relevance between the label of the user and the transaction item, and the formula is as follows:
wherein the content of the first and second substances,𝐼 𝑗𝑇 show transaction items𝑗User base portrait label𝑇The index is the number of the index,𝑁(𝑈 𝑗 ) To do things𝑗The number of all the users of the network,𝑁(𝑇 𝑗 ) Show transaction items𝑗Has a tag among users𝑇The number of users of (a) is,𝐼 𝑗𝑇 the larger the value, the more the transaction is𝑗User portrait label𝑇The stronger the traffic relevance of (a).
Distance calculation step S130:
there are obvious regional requirements for users to handle government affairs, for example, some government affairs have to be handled by the user's residence or the director of the user's residence. Therefore, measuring the position relationship between the user and the event is of great significance for accurately recommending the event.
There are two ways to express the government affair service affair and the user's position, one is to adopt the administrative division name of the area to express, such as the hai lake area, the rich platform area; another is to use a specific coordinate position. Generally, both location representations of government service events are available. The distance calculation is based on the representation mode of the user position information.
Selecting administrative division or Euclidean distance to calculate user according to user position information expression mode𝑘To deal with things𝑗Relative distance d between government service centers𝑖𝑠 𝑘𝑗 。
When the user position information is expressed in coordinates, the relative distance between the user and the government affairs service center is calculated by adopting the Euclidean distance, and the formula is as follows:
wherein d is𝑖𝑠 𝑘𝑗 Representing a user𝑘To deal with things𝑗Distance between government affairs service centers of (1), (b), (c), (d)𝑥 𝑘 ，𝑦 𝑘 ) Representing a user𝑘(ii) a coordinate position of (A), (B)𝑥 𝑗 ，𝑦 𝑗 ) Show items of business𝑗The government services center coordinate location.
When the user position information is represented by an administrative division, the relative distance between the user and the government affair service center is specifically designed according to the spatial relationship of the administrative division as follows:
the same region means that the administrative division in which the user is located is the same as the administrative division in which the administrative service center transacts the matters is located, if both are located in the lake region; the adjacent area refers to an area adjacent to an administrative district where a government center handling matters is located, for example, if the user is located in a sea lake area, the administrative district handling matters is divided into a western city area, that is, the adjacent area may be eight areas, i.e., upper, lower, left, right, upper left, lower left, upper right and lower right, adjacent to the area. And j is not adjacent, which means that two administrative divisions have no adjacent relationship, such as a western city area and a rocky mountain area.
Wherein d is𝑖𝑠 𝑘𝑗 Representing a user𝑘To deal with things𝑗Distance between government affairs service centers of (1), (b), (c), (d)𝑥 𝑎 ，𝑦 𝑎 ) Representing a user𝑘Coordinate position of the center point of the administrative division, ((ii) coordinate position of the center point of the administrative division, ((iii)𝑥 𝑏 ，𝑦 𝑏 ) And (3) the coordinate position of the center point of the area where the government affairs service center for handling the affair j is positioned.
Recommended item score calculation step S140:
the main idea of recommending the government affair service affairs is to recommend the affairs transacted by the user with the same preference as the target user to the target user.
According to user similarity𝑠𝑖𝑚 (𝑘, 𝑘′) User, user𝑘Distance d from government service center handling item j𝑖𝑠 𝑘𝑗 Computing target users𝑘For the quasi-recommendation score of the related matters, the formula is as follows:
wherein the content of the first and second substances,𝑠𝑐𝑜𝑟𝑒 𝑘𝑗 representing target users𝑘User of𝑘' score of transacted government service event j, wherein𝑤The weight is represented by a weight that is,𝑠𝑖𝑚 (𝑘, 𝑘′) Representing a user𝑘And the user𝑘' similarity between them, d𝑖𝑠 𝑘𝑗 Representing a user𝑘Distance from the government service center handling item j.
Result recommending step S150:
and selecting the top N items according to the item scoring result to be recommended in S140 and according to the order of the scores from high to low to recommend the items to the user.
Further, the invention also discloses a storage medium for storing computer-executable instructions, and the computer-executable instructions, when executed by a processor, execute the distance measurement government affair collaborative filtering recommendation method.
The invention has the following advantages:
firstly, when the similarity of the users is calculated, a calculation method (formula 3) of the transaction frequency of the users is provided, the user score in the traditional collaborative filtering is replaced, the association degree of the users and the transaction service items can be fully reflected, and the method is more suitable for the recommendation scene of the transaction service items.
Secondly, introducing a spatial neighborhood relationship and a distance calculation method (formulas 5-7) in the process of recommending government affair service affairs, defining the distance between a user and a transaction affair according to point coordinates or administrative divisions respectively, and participating in the calculation of affair scores.
The distance measurement provided by the invention reflects the property requirements of an administrative department when handling the matters, can preferentially recommend the matters with the same property for the user, and improves the accuracy of the recommendation result. Meanwhile, the distance measurement also makes up the problem that the traditional collaborative filtering is insufficient in consideration of the spatial position, and a collaborative filtering recommendation method is developed and enriched.
It will be apparent to those skilled in the art that the various elements or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device, or alternatively, they may be implemented using program code that is executable by a computing device, such that they may be stored in a memory device and executed by a computing device, or they may be separately fabricated into various integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
While the invention has been described in further detail with reference to specific preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A distance-measuring government affair service item collaborative filtering recommendation method is characterized by comprising the following steps:
data preparation step S110:
respectively constructing a government affair service affair portrait, a user basic portrait and a user behavior portrait based on government affair service affair data, user registration data and user transaction behavior data;
user similarity calculation step S120:
calculating the similarity between the users and the' by adopting the user basic portrait, the user transaction portrait and the government affairs service affair portrait
𝑠𝑖𝑚 (𝑘, 𝑘′)；
Distance calculation step S130:
selecting administrative division or Euclidean distance to calculate user according to user position information expression mode𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 ；
Recommended item score calculation step S140:
according to user similarity𝑠𝑖𝑚 (𝑘, 𝑘′) User, user𝑘To deal with things𝑗A distance d between𝑖𝑠 𝑘𝑗 Computing target users𝑘The quasi-recommendation score for the related item is formulated as follows:
wherein the content of the first and second substances,𝑠𝑐𝑜𝑟𝑒 𝑘𝑗 representing target users𝑘User of𝑘' transacted government service events𝑗Is scored, wherein𝑤Representing a weight;
result recommending step S150:
and selecting the top N items according to the item scoring result to be recommended in S140 and according to the order of the scores from high to low to recommend the items to the user.
2. The recommendation method according to claim 1,
in the data preparation step S110:
the government affair service affair portrait is used for labeling affairs according to attribute information of the government affair service affairs and constructing a model, wherein the attribute information of the government affair service affairs comprises the following components: item name, transaction department, service object, transaction location, and item topic;
the basic portrait of the user is that the basic information filled in during user registration is utilized to perform labeling processing on the user and construct a model, the user registration data is specifically that the basic information of natural people comprises gender, age, occupation, marriage and education conditions and positions, and the basic information of legal people can comprise an operation range, an enterprise type, an affiliated industry, an enterprise scale and an enterprise address;
the user behavior portrait is user transaction behavior data, labeling processing is carried out on user transaction behaviors, and a model is constructed, wherein the user transaction behavior data comprises attribute information of user transaction items and user transaction times.
3. The recommendation method according to claim 1,
in the step S120, the process proceeds,
similarity between users by adopting cosine similarity calculation method𝑠𝑖𝑚(𝑘, 𝑘′) (ii) a The calculation is carried out in such a way that,
wherein the content of the first and second substances,𝐿represents a collection of all user base representation tags,𝑇a particular label in the user base representation is represented,𝑀 𝑘𝑇 and with𝑀 𝑘’𝑇 Respectively representing users𝑘And𝑘' Pair label𝑇Is characterized by a characteristic index of (A),
representing all users to a tag𝑇Mean value of characteristic index.
4. The recommendation method according to claim 3,
in the step S120, the process proceeds,
the user characteristic index is used for reflecting the relevance between the user label and the transaction item, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,𝑀 𝑘𝑇 representing a user𝑘Portraying labels on a user's base𝑇The index of the characteristic of the user to be made,𝐼𝑡𝑒𝑚 𝑘 representing a user𝑘The matters to be dealt with are,𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘The total number of the processed items is,𝑟 𝑘𝑗 representing a user𝑘To handle things𝑗The frequency of the transaction of (1) is,𝐼 𝑗𝑇 show transaction items𝑗User base portrait label𝑇And (4) index.
5. The recommendation method according to claim 3,
in the step S120, the process proceeds,
the user transaction frequency is used for reflecting the degree of association between the user and transaction items, and is calculated according to the user behavior portrait, and the formula is as follows:
wherein the content of the first and second substances,𝑟 𝑘𝑗 representing a user𝑘To item (c)𝑗The frequency of the transaction of (1) is,𝑁(𝑗 𝑘 ) Representing a user𝑘To item (c)𝑗The number of times of the handling of (c),𝑁(𝐼𝑡𝑒𝑚 𝑘 ) Representing a user𝑘The total number of items handled.
6. The recommendation method according to claim 3,
in the step S120, the process proceeds,
the user basic portrait label index is used for judging the relevance between the label of the user and the transaction items, and the formula is as follows:
wherein the content of the first and second substances,𝐼 𝑗𝑇 show transaction items𝑗User base portrait label𝑇The index is the number of the index,𝑁(𝑈 𝑗 ) To do things𝑗The number of all the users of the network,𝑁(𝑇 𝑗 ) Show transaction items𝑗Has a tag among users𝑇The number of users.
7. The recommendation method according to claim 1,
in the distance-calculating step S130,
when the user position information is expressed by coordinates, the Euclidean distance is adopted to calculate the user𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 The formula is as follows:
wherein (A), (B), (C), (D), (C), (B), (C)𝑥 𝑘 ，𝑦 𝑘 ) Representing a user𝑘(ii) a coordinate position of (A), (B)𝑥 𝑗 ，𝑦 𝑗 ) Show transaction items𝑗(ii) a government services center coordinate location;
when the user position information is represented by an administrative division, calculating the user according to the spatial relationship of the administrative division𝑘To deal with things𝑗Distance d between government affairs service centers𝑖𝑠 𝑘𝑗 The method comprises the following steps:
wherein (A), (B), (C), (D), (C), (B), (C)𝑥 𝑎 ，𝑦 𝑎 ) Representing a user𝑘Coordinate position of center point of administrative division, ((ii) coordinate position of center point of administrative division, ((iii)𝑥 𝑏 ，𝑦 𝑏 ) Show transaction items𝑗The center point coordinate position of the area where the government affairs service center is located.
8. A storage medium, characterized by:
the storage medium storing computer-executable instructions which, when executed by a processor, perform the distance metric government service event collaborative filtering recommendation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210733505.3A CN114969566B (en) | 2022-06-27 | 2022-06-27 | Distance-measuring government affair service item collaborative filtering recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210733505.3A CN114969566B (en) | 2022-06-27 | 2022-06-27 | Distance-measuring government affair service item collaborative filtering recommendation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114969566A true CN114969566A (en) | 2022-08-30 |
| CN114969566B CN114969566B (en) | 2023-03-24 |
Family
ID=82966184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210733505.3A Active CN114969566B (en) | 2022-06-27 | 2022-06-27 | Distance-measuring government affair service item collaborative filtering recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114969566B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595161A (en) * | 2023-07-13 | 2023-08-15 | 安徽省数字江淮中心 | Government affair digital scene item recommendation method, device, equipment and storage medium |
| CN117473168A (en) * | 2023-12-27 | 2024-01-30 | 中电数据产业有限公司 | Intelligent feature recommendation method, device, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110010324A1 (en) * | 2009-07-08 | 2011-01-13 | Alvaro Bolivar | Systems and methods for making contextual recommendations |
| WO2018120427A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Risk assessment method, apparatus, and device based on location service, and storage medium |
| CN109255586A (en) * | 2018-08-24 | 2019-01-22 | 安徽讯飞智能科技有限公司 | A kind of online personalized recommendation method that E-Governance Oriented is handled affairs |
| CN110377841A (en) * | 2019-06-04 | 2019-10-25 | 深思考人工智能机器人科技（北京）有限公司 | A kind of similarity calculating method applied in collaborative filtering method and system |
| CN110750699A (en) * | 2019-10-18 | 2020-02-04 | 四川大学 | Film comment emotion visualization method for box office prediction |
| WO2020224128A1 (en) * | 2019-05-08 | 2020-11-12 | 平安科技（深圳）有限公司 | News recommendation method and apparatus based on short-term interest of user, and electronic device and medium |
| CN112632405A (en) * | 2020-12-31 | 2021-04-09 | 数字广东网络建设有限公司 | Recommendation method, device, equipment and storage medium |
| CN112699297A (en) * | 2020-12-23 | 2021-04-23 | 平安银行股份有限公司 | Service recommendation method, device and equipment based on user portrait and storage medium |
| CN114066564A (en) * | 2021-11-04 | 2022-02-18 | 上海浦东发展银行股份有限公司 | Service recommendation time determination method and device, computer equipment and storage medium |
| CN114595850A (en) * | 2022-02-08 | 2022-06-07 | 厦门市民数据服务股份有限公司 | Government affair reservation service recommendation method based on machine learning |
-
2022
- 2022-06-27 CN CN202210733505.3A patent/CN114969566B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110010324A1 (en) * | 2009-07-08 | 2011-01-13 | Alvaro Bolivar | Systems and methods for making contextual recommendations |
| WO2018120427A1 (en) * | 2016-12-29 | 2018-07-05 | 平安科技（深圳）有限公司 | Risk assessment method, apparatus, and device based on location service, and storage medium |
| CN109255586A (en) * | 2018-08-24 | 2019-01-22 | 安徽讯飞智能科技有限公司 | A kind of online personalized recommendation method that E-Governance Oriented is handled affairs |
| WO2020224128A1 (en) * | 2019-05-08 | 2020-11-12 | 平安科技（深圳）有限公司 | News recommendation method and apparatus based on short-term interest of user, and electronic device and medium |
| CN110377841A (en) * | 2019-06-04 | 2019-10-25 | 深思考人工智能机器人科技（北京）有限公司 | A kind of similarity calculating method applied in collaborative filtering method and system |
| CN110750699A (en) * | 2019-10-18 | 2020-02-04 | 四川大学 | Film comment emotion visualization method for box office prediction |
| CN112699297A (en) * | 2020-12-23 | 2021-04-23 | 平安银行股份有限公司 | Service recommendation method, device and equipment based on user portrait and storage medium |
| CN112632405A (en) * | 2020-12-31 | 2021-04-09 | 数字广东网络建设有限公司 | Recommendation method, device, equipment and storage medium |
| CN114066564A (en) * | 2021-11-04 | 2022-02-18 | 上海浦东发展银行股份有限公司 | Service recommendation time determination method and device, computer equipment and storage medium |
| CN114595850A (en) * | 2022-02-08 | 2022-06-07 | 厦门市民数据服务股份有限公司 | Government affair reservation service recommendation method based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 廖开际等: "基于位置信息的协同过滤推荐算法", 《系统工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595161A (en) * | 2023-07-13 | 2023-08-15 | 安徽省数字江淮中心 | Government affair digital scene item recommendation method, device, equipment and storage medium |
| CN116595161B (en) * | 2023-07-13 | 2023-09-19 | 安徽省数字江淮中心 | Government affair digital scene item recommendation method, device, equipment and storage medium |
| CN117473168A (en) * | 2023-12-27 | 2024-01-30 | 中电数据产业有限公司 | Intelligent feature recommendation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114969566B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9569499B2 (en) | Method and apparatus for recommending content on the internet by evaluating users having similar preference tendencies | |
| US9262439B2 (en) | System for determining local intent in a search query | |
| JP5662961B2 (en) | Review processing method and system | |
| CN114969566B (en) | Distance-measuring government affair service item collaborative filtering recommendation method | |
| US8260664B2 (en) | Semantic advertising selection from lateral concepts and topics | |
| US9589277B2 (en) | Search service advertisement selection | |
| US8311957B2 (en) | Method and system for developing a classification tool | |
| CN108717407B (en) | Entity vector determination method and device, and information retrieval method and device | |
| US20130110829A1 (en) | Method and Apparatus of Ranking Search Results, and Search Method and Apparatus | |
| Bijmolt et al. | A comparison of multidimensional scaling methods for perceptual mapping | |
| US8725562B2 (en) | Keyword advertisement using ranking of advertisers | |
| US20110035329A1 (en) | Search Methods and Systems Utilizing Social Graphs as Filters | |
| WO2018040069A1 (en) | Information recommendation system and method | |
| CN108388582A (en) | The mthods, systems and devices of related entities for identification | |
| US20110213659A1 (en) | System and Method for Automatic Matching of Contracts in an Inverted Index to Impression Opportunities Using Complex Predicates and Confidence Threshold Values | |
| JP2003186907A (en) | Profile information retrieval method and device, program, and recording medium | |
| US20140172566A1 (en) | Matching of advertising sources and keyword sets in online commerce platforms | |
| US20070174133A1 (en) | Searching for a seller of a product | |
| KR101818717B1 (en) | Method, apparatus and computer readable recording medium for search with exetension data-set of concept keywords | |
| CN111310032B (en) | Resource recommendation method, device, computer equipment and readable storage medium | |
| US20110213660A1 (en) | System and Method for Automatic Matching of Contracts in an Inverted Index to Impression Opportunities Using Complex Predicates with Multi-Valued Attributes | |
| US8229933B2 (en) | System and method for automatic matching of contracts using a fixed-length predicate representation | |
| US20170193539A1 (en) | Time-value estimation method and system for sharing environment | |
| TWI547888B (en) | A method of recording user information and a search method and a server | |
| US8065311B2 (en) | Relevance score in a paid search advertisement system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |