CN110222257B - method and device for recommending service information and data link node - Google Patents
method and device for recommending service information and data link node Download PDFInfo
- Publication number
- CN110222257B CN110222257B CN201910394773.5A CN201910394773A CN110222257B CN 110222257 B CN110222257 B CN 110222257B CN 201910394773 A CN201910394773 A CN 201910394773A CN 110222257 B CN110222257 B CN 110222257B
- Authority
- CN
- China
- Prior art keywords
- user
- service information
- data link
- information
- preference value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and a data link node for recommending kinds of service information, wherein the method comprises the steps that the data link node inquires user information and history records corresponding to a user from a data link stored by the data link node, respectively determines the preference value of the user for each kind of service information according to the history records, acquires the preference value of a user group to which the user belongs for each kind of service information according to the user information, acquires the service information to be recommended according to the preference value of the user group to which the user belongs for each kind of service information and the preference value of the user to each kind of service information, and sends the service information to be recommended to the user.
Description
Technical Field
The invention relates to the technical field of internet communication, in particular to a method and a device for recommending service information of types and a data link node.
Background
In order to promote users to browse more service information, a server in the related art generally recommends the current latest service information or hot spot service information to the users, but the latest service information or hot spot service information is not information interested by the users, so that the users rarely browse the service information recommended by the server, the effective purpose of recommending the service information is not achieved, and the recommendation of the service information not interested by the users is disturbed.
Disclosure of Invention
The present invention provides methods, apparatuses, and data link nodes for recommending service information, so as to overcome the disadvantages of the prior art, and embodiments of the present invention mainly achieve the above objects in the following ways.
, an embodiment of the present invention provides a method for recommending service information , where the method includes:
the data link node inquires user information and history records corresponding to the user from a data link stored by the data link node;
the data link node respectively determines the preference value of the user to each service information according to the history record;
the data link node acquires the preference value of the user group to which the user belongs to each service information according to the user information;
and the data link node acquires the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sends the service information to be recommended to the user.
With reference to the aspect, an embodiment of the present invention provides a possible implementation manner of the aspect, where the querying, by the data link node, user information and history records corresponding to a user from a data link stored in the data link node includes:
when a data link point detects that a user logs in, the data link point acquires user information corresponding to the user; or, the data link point acquires user information corresponding to the user every preset time length;
the data link node locates a data block containing the user information from a data link stored by the data link node;
and the data link node reads the history record corresponding to the user from the data block.
With reference to the , an embodiment of the present invention provides a second possible implementation manner of the , where the determining, by the data link node, the preference value of the user for each service information according to the history includes:
the data link node acquires operation behavior information of each service information operated by the user from the historical record;
the data link node respectively calculates the preference value of the user to each service information through a formula (1) according to preset behavior weight information and operation behavior information corresponding to each service information, wherein the operation behavior information comprises the type of operation behavior and the operation times of each operation behavior;
in the formula (1), i is the number of service information, PiThe preference value of the user to the ith service information is represented, j is the number of the operation behavior information, omegajBehavior weight information corresponding to the jth operation behavior, AjThe operation times corresponding to the operation behavior of the jth type.
With reference to the , an embodiment of the present invention provides a third possible implementation manner of the , where the determining, by the data link node, the preference value of the user for each service information according to the history includes:
the data link points divide the historical records into a plurality of sub-records of time units according to the time sequence;
the data link node respectively acquires the operation behavior information of each service information operated by the user from each sub-record;
the data link node respectively calculates the interest degree of the user in each service information in each time unit according to preset behavior weight information and operation behavior information corresponding to each sub record;
and the data link node determines the preference value of the user to each service information according to the interest degree of the user to each service information in each time unit.
With reference to the third possible implementation manner of the , an embodiment of the present invention provides a fourth possible implementation manner of the , where the determining, by the data link node, a preference value of the user for each service information according to the interest level of the user for each service information in each time unit includes:
the data link node respectively determines the time difference coefficient between each time unit and the current time through a formula (2) according to each time unit;
the data link node respectively calculates the preference value of the user to each service information through a formula (3) according to the time difference coefficient corresponding to each time unit and the interest degree of the user to each service information in each time unit;
gt＝a-(Tt-T)…(2)
in the formulae (2) and (3), t is the number of time units, gtTime difference coefficient corresponding to the T-th time unit, TtThe time is the T-th time unit, T is the time unit closest to the current time in each time unit, and a is a preset numerical value; i is the number of the service information, PiIs the preference value of the user to the ith service information, BtAnd the interest degree of the user in the ith service information corresponding to the t-th time unit.
With reference to the , an embodiment of the present invention provides a fifth possible implementation manner of the , where the acquiring, by the data link node, a preference value of a user group to which the user belongs to for each service information according to the user information includes:
the data link nodes determine a user group to which the user belongs according to the user information;
the data link node respectively acquires the preference value of each user included in the user group to each service information;
and the data link node determines the preference value of the user group to each service information according to the preference value of each user to each service information.
With reference to the , an embodiment of the present invention provides a sixth possible implementation manner of the , where the obtaining, by the data link node, the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information includes:
the data link node determines a preset number of service information with the highest preference value corresponding to the user group;
the data link node acquires hotspot information corresponding to the preset number of service information;
the data link point determines an interest group to which the user belongs according to the preference value of the user to each service information;
and the data link node determines the service information which is operated by other group members in the interest group and is not operated by the user and the service information which is not operated by the user in the hotspot information as the service information to be recommended.
With reference to the aspect, an embodiment of the present invention provides a seventh possible implementation manner of the aspect, where the method further includes:
the data link nodes generate data blocks according to the preference value of the user to each service information and the service information to be recommended;
the data link node adds the data block to its own stored data chain, and broadcasts the data block to other data chain nodes in the consensus network for storage.
In a second aspect, an embodiment of the present invention provides an apparatus for recommending service information, where the apparatus includes:
the query module is used for querying user information and historical records corresponding to the user from a data chain stored in the query module;
the determining module is used for respectively determining the preference value of the user to each service information according to the historical records;
the acquisition module is used for acquiring the preference value of the user group to which the user belongs to each service information according to the user information;
and the recommending module is used for acquiring the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sending the service information to be recommended to the user.
In a third aspect, an embodiment of the present invention provides data link nodes, including or more memories and processors, where the memories store executable programs, and the executable programs are loaded by or more of the processors to perform the following steps:
inquiring user information and historical records corresponding to the user from a data chain stored in the data chain;
respectively determining the preference value of the user to each service information according to the historical records;
acquiring the preference value of a user group to which the user belongs to each service information according to the user information;
and acquiring the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sending the service information to be recommended to the user.
In the embodiment of the invention, the user information of the user and the history records generated by browsing the service information in the past are stored in the data chain, the data in the data chain are difficult to be tampered, and the fact that the history records based on the data chain nodes are real and reliable in the process of recommending the service information can be correctly reflected, so that the finally recommended service information is information which is interesting to the user, and the accuracy of recommending the service information is greatly improved.
Drawings
Fig. 1 is a schematic flow chart of a method for recommending types of service information according to an embodiment of the present invention;
fig. 2 is a structural diagram of an apparatus for recommending service information of types according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of data link nodes according to an embodiment of the present invention.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
The embodiment of the invention provides service information recommending methods, which are based on data chains, a plurality of data link points form a consensus network, the processing pressure of recommending service information to all users is shared by the data link points in the consensus network, the processing amount of each data link node is not too large, the processing speed is high, the service information which is possibly interested by the users can be recommended to the users in time, historical records generated by the users operating the service information in the past are stored in the data chains, the same data chain is stored in each data link node, service providers and hackers and the like cannot tamper data stored in the data chains, the data security is high, the service information which is interested by the users can be recommended by the data link points based on the real historical records, and the recommending accuracy is high.
In addition, the embodiment of the invention synthesizes the preference of the user group to the service information and the preference of the individual user to the service information to recommend the service information to the user, thereby greatly improving the possibility that the recommended service information is the service information which is interested by the user, having high possibility that the user browses, downloads or purchases the recommended service information, realizing the effective purpose of recommending the service information, not disturbing the user and improving the user experience.
Referring to fig. 1, the method specifically includes the following steps:
step 101: and the data link node inquires user information and history records corresponding to the user from the data link stored by the data link node.
In the embodiment of the invention, two occasions can be provided for recommending the service information for the user, is that when the user logs in the data link node through the client and the data link node detects that the user logs in, the data link node recommends the service information to the user according to the mode provided by the embodiment of the invention, and is that the data link node recommends the service information to the user automatically according to the mode provided by the embodiment of the invention every preset time.
The data link point acquires user information corresponding to the user when the data link point detects that the user logs in, or detects that a preset time interval is left between the data link point and last recommendation, the user information can comprise user account numbers, sexes, ages, professions, geographic positions and the like, the user account numbers can be user contact modes, identity numbers, user-defined character sequences and the like used for identifying the user only , the data link node can directly acquire the user information from login information of the user when the data link point detects that the user logs in, and the data link point can locally acquire the stored user information when the period of the recommended service information arrives.
After the data link point acquires the user information, positioning a data block containing the user information from a data chain stored by the data link point; and reading the history record corresponding to the user from the located data block. The history record comprises operation behavior information of each service information operated by the user process, and the operation behavior information comprises the type of the operation behavior and the operation times of each operation behavior. The operation behavior of the user on the service information comprises browsing, downloading, purchasing and the like.
Step 102: and the data link node respectively determines the preference value of the user to each service information according to the history.
The embodiment of the present invention provides the following th and second ways of determining a preference value, which specifically include:
, the data link node determines the user's preference value for each service information based on the history only.
In the embodiment of the invention, each data link node in the consensus network is pre-configured with behavior weight information corresponding to each type of operation behavior, and the higher the weight corresponding to the operation behavior of the service information favored by the user is, for example, the higher the purchased weight is, the lower the browsing weight is.
And the data link node acquires the operation behavior information of each service information operated by the user from the historical record, and respectively calculates the preference value of the user to each service information through a formula (1) according to the preset behavior weight information and the operation behavior information corresponding to each service information, wherein the operation behavior information comprises the type of the operation behavior and the operation times of each operation behavior.
In formula (1), i is the number of service information, PiThe preference value of the user to the ith service information is shown, j is the number of the operation behavior information, omegajBehavior weight information corresponding to the jth operation behavior, AjThe operation times corresponding to the operation behavior of the jth type.
Specifically, when the preference value is calculated, for certain service information, the product between the operation times and the behavior weight of each operation behavior is calculated to obtain the behavior coefficient corresponding to each operation behavior. And adding the behavior coefficients corresponding to each operation behavior to obtain the preference value of the user to the service information.
For example, assume that the history of the user includes 10 times that the user browses the martial arts book information, 6 times that the user downloads the martial arts book information, and 1 time that the user purchases the martial arts book information. The preset behavior weight information on the data link node comprises that the weight corresponding to the browsing behavior is 1, the weight corresponding to the downloading behavior is 5, and the weight corresponding to the purchasing behavior is 10. The data link point calculates the behavior coefficient corresponding to the browsing behavior to be 10, the behavior coefficient corresponding to the downloading behavior to be 30, and the behavior coefficient corresponding to the purchasing behavior to be 10, and further calculates the preference value of the user for the martial arts book information to be 50.
For each kind of other service information related in the history record, the preference value of the user corresponding to each kind of other service information is respectively calculated according to the above mode.
Second, the data link node determines the preference value of the user for each service information according to the change of the operation behavior of the user for each service information over time in the historical record.
The data link node acquires the operation behavior information of each service information operated by the user from each sub-record respectively, and calculates the interest degree of the user in each service information in each time unit respectively according to the preset behavior weight information and the operation behavior information corresponding to each sub-record, and the calculation of the interest degree is the same as the calculation of the preference value in the mode, and is not repeated here.
And the data link node determines the preference value of the user to each service information according to the interest degree of the user to each service information in each time unit. Specifically, the data link node determines a time difference coefficient between each time unit and the current time according to each time unit through a formula (2), and calculates a preference value of the user for each service information through a formula (3) according to the time difference coefficient corresponding to each time unit and the interest degree of the user for each service information in each time unit.
gt＝a-(Tt-T)…(2)
In the formula (2), t is the number of time units, gtTime difference coefficient corresponding to the T-th time unit, TtIs the T-th time unit, T is the time unit nearest to the current time in each time unit, and a is a preset numerical value.
Namely, when the time difference coefficient corresponding to each time unit is determined, the time unit closest to the current time in all the divided time units is called the current time unit, and the number of the time units with the difference between each other time unit and the current time unit is respectively calculated. And for a certain time unit, subtracting the preset numerical value from the time unit number of the phase difference corresponding to the time unit to obtain the time difference coefficient corresponding to the time unit. And for each other time unit, respectively determining the time difference coefficient corresponding to each other time unit according to the above mode. The preset value can be 10, 20 or 30. For the current time unit, the number of the time units with the difference from the current time unit is 0, and the time difference coefficient corresponding to the current time unit is the preset value.
After the time difference coefficient corresponding to each time unit is calculated according to the above manner, the preference value of the user for each service information is calculated through formula (3). And for certain service information, calculating the sum of the products of the time difference coefficient corresponding to each time unit and the interestingness to obtain the preference value of the user to the service information.
In the formula (3), t is the number of time units, gtIs the time difference coefficient corresponding to the t-th time unit, i is the number of the service information, PiIs the preference value of the user to the ith service information, BtAnd the interest degree of the user in the ith service information corresponding to the t-th time unit.
For example, suppose that the history of months of the user is divided into three sub-records according to time units of 10 days, and the three sub-records are respectively recorded as a sub-record 3, a sub-record 2 and a sub-record 1 from front to back according to time, wherein the sub-record 1 is closest to the current time and is the current time unit, the sub-record 2 is different from the sub-record 1 by 1 time unit, and the sub-record 3 is different from the sub-record 1 by 2 time units.
And respectively calculating the preference value of the user to each kind of other service information in the same way for each kind of other service information. In the second mode, the change of the user preference along with time is considered, so the calculated preference value can reflect the actual preference of the user better, and the accuracy is higher.
And respectively calculating the preference value of each user to each service information by the operation of the step for each user, and respectively storing the corresponding relation between the user information of each user and the preference value of each service information of the user.
Step 103: and the data link node acquires the preference value of the user group to which the user belongs to each service information according to the user information.
Specifically, the data link node determines a user group to which the user belongs according to the user information, respectively obtains a preference value of each user included in the user group for each service information, and then determines a preference value of the user group for each service information according to the preference value of each user for each service information.
In the embodiment of the present invention, the data link nodes cluster all users according to the information of gender, age, occupation, geographical location, and the like included in the user information, and divide all users into a plurality of user groups, and users included in the user group have similar user attributes, such as that the gender of users in the user group is female, the age is between 20 and 30 years, the occupation is white collar of company, and the geographical location is beijing.
And the data link point determines a user group which accords with the user attribute of the user according to the user attribute included by the user information of the user, wherein the user group is the user group to which the user belongs. And respectively acquiring the preference value of each user included in the user group to each service information according to the user information of each user included in the user group. And then for each kind of service information, the data link node calculates the preference value of the user group for the kind of service information according to the preference value of each user for the kind of service information. Specifically, the data link node calculates an average value of preference values of each user for the service information, and takes the average value as a preference value of the user group for the service information.
Through the method, the data link point can calculate the preference value of the user group to which the user belongs to each service information.
After the preference value of each service information for each individual user and the preference value of each service information for the user group to which the user belongs are calculated as groups in the above manner, the service information is recommended to the user by the following operation of step 104.
Step 104: and the data link point acquires the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sends the service information to be recommended to the user.
The data link node determines a preset number of service information with the highest preference value corresponding to a user group to which the user belongs, obtains hotspot information corresponding to the preset number of service information, and determines the service information which is not operated by the user in the hotspot information as the service information to be recommended.
Because the user and other users in the user group to which the user belongs have similar user attributes, the user is likely to have very high similarity in the preference of the service information, and the preset number of service information with the highest preference value corresponding to the user group to which the user belongs is likely to be the service information category preferred by the user. The hot spot information corresponding to the service information of these kinds is likely to be service information that is very interesting to the user, so that the service information that is not operated by the user in the hot spot information is recommended to the user, and the possibility that the user operates the information is high.
The data link node calculates the preference value of each service information of the user every time through the operation of the step 102, then obtains the preference value of each service information of other users from the currently stored data link, determines the preference similarity between the user and other users according to the preference value of each service information of the user and the preference value of each service information of other users, and further determines the interest group to which the user belongs according to the preference similarity between the user and other users.
The service information which is operated by other users similar to the user interest but not operated by the user is recommended to the user, so that the possibility that the user is interested in the recommended service information is high, and the accuracy and the effectiveness of service information recommendation are improved.
In the embodiment of the present invention, the data link node may also determine the service information to be recommended by referring to only the preference value of the user for each service information. Specifically, the data link node selects an information category meeting a preset condition according to the preference value of the user for each service information, and acquires the service information to be recommended from a service information set corresponding to the selected information category.
The method comprises the steps that a data link node is configured with a preset number of information types with the highest preference value, a service set corresponding to each information type is configured in advance in the data link node, the service set corresponding to the information type comprises a plurality of service information of the information type, and for the preset number of information types with the highest preference value, a data link node can determine the service information which is not operated by a user from the service set corresponding to the information type and randomly select fixed amount of service information from the service information which is not operated by the user as the service information to be recommended.
And step , recommending the service information with the highest degree of preference value to the user, so that the user has a higher interest rate in the recommended service, and the user is more likely to browse, download or purchase the recommended service information.
And the data link node sends the service information to be recommended to the client corresponding to the user. And the client displays the recommended service information after receiving the service information so that the user can operate the service information conveniently.
The data link node generates a data block according to the parent hash value of the data block to be generated, the preference value of the user on each kind of service information and the service information to be recommended, and the hash value of the last data blocks in the data link currently stored by the data link node is used as the parent hash value of the data block to be generated, the preference value of the user on each kind of service information and the service information to be recommended are subjected to hash operation to obtain the head hash value of the data block to be generated.
After other data chain nodes in the consensus network receive the data block, the data block is authenticated through a workload certification mechanism, a right certificate mechanism and the like, and the data block is added to the last of the data chains stored in the data chain nodes after the data block is authenticated.
In the embodiment of the invention, the user information of the user and the history records generated by browsing the service information in the past are stored in the data chain, the data in the data chain are difficult to be tampered, and the fact that the history records based on the data chain nodes are real and reliable in the process of recommending the service information can be correctly reflected, so that the finally recommended service information is information which is interesting to the user, and the accuracy of recommending the service information is greatly improved.
Referring to fig. 2, an embodiment of the present invention provides an apparatus for recommending service information, where the apparatus is configured to execute the method for recommending service information provided in the foregoing embodiment, and the apparatus includes:
the query module 20 is configured to query user information and a history record corresponding to a user from a data chain stored in the query module;
a determining module 21, configured to determine, according to the history records, preference values of the user for each type of service information respectively;
an obtaining module 22, configured to obtain, according to the user information, a preference value of a user group to which the user belongs for each service information;
and the recommending module 23 is configured to obtain the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and send the service information to be recommended to the user.
The query module 20 is configured to, when it is detected that the user logs in, obtain user information corresponding to the user; or acquiring user information corresponding to the user every preset time; positioning a data block containing user information from a data chain stored in the data block storage device; and reading the history record corresponding to the user from the data block.
The determining module 21 includes:
, an obtaining unit, for obtaining the operation behavior information of each service information operated by the user from the history record;
, a calculation unit, configured to calculate, according to preset behavior weight information and operation behavior information corresponding to each type of service information, a preference value of a user for each type of service information through a formula (1), where the operation behavior information includes a type of an operation behavior and an operation frequency of each operation behavior;
in the formula (1), i is the number of service information, PiThe preference value of the user to the ith service information is represented, j is the number of the operation behavior information, omegajBehavior weight information corresponding to the jth operation behavior, AjThe operation times corresponding to the operation behavior of the jth type.
In another embodiments, the determining module 21 includes:
the dividing unit is used for dividing the historical record into a plurality of sub-records of time units according to the time sequence;
the second acquisition unit is used for respectively acquiring the operation behavior information of each service information operated by the user from each sub-record;
the second calculating unit is used for respectively calculating the interest degree of the user in each service information in each time unit according to the preset behavior weight information and the operation behavior information corresponding to each sub record;
, a determining unit, for determining the user preference value for each service information according to the user interest level for each service information in each time unit.
The determining unit is configured to determine, according to each time unit, a time difference coefficient between each time unit and the current time by using a formula (2); respectively calculating the preference value of the user to each service information through a formula (3) according to the time difference coefficient corresponding to each time unit and the interest degree of the user to each service information in each time unit;
gt＝a-(Tt-T)…(2)
in the formulae (2) and (3), t is the number of time units, gtTime difference coefficient corresponding to the T-th time unit, TtThe time is the T-th time unit, T is the time unit closest to the current time in each time unit, and a is a preset numerical value; i is the number of the service information, PiIs the preference value of the user to the ith service information, BtAnd the interest degree of the user in the ith service information corresponding to the t-th time unit.
The obtaining module 22 is configured to determine, according to the user information, a user group to which the user belongs; respectively acquiring the preference value of each user included in the user group to each service information; and determining the preference value of the user group to each service information according to the preference value of each user to each service information.
The recommending module 23 is configured to determine a preset number of service information with the highest preference values corresponding to the user group; acquiring hotspot information corresponding to the preset number of service information; determining an interest group to which the user belongs according to the preference value of the user to each service information; and determining the service information which is operated by other group members in the interest group and is not operated by the user and the service information which is not operated by the user in the hotspot information as the service information to be recommended.
In the embodiment of the invention, the device further comprises a storage module, wherein the storage module is used for generating the data block according to the preference value of the user to each service information and the service information to be recommended, adding the data block into the data chain stored by the storage module, and broadcasting the data block to other data chain nodes in the consensus network for storage.
In the embodiment of the invention, the user information of the user and the history records generated by browsing the service information in the past are stored in the data chain, the data in the data chain are difficult to be tampered, and the fact that the history records based on the data chain nodes are real and reliable in the process of recommending the service information can be correctly reflected, so that the finally recommended service information is information which is interesting to the user, and the accuracy of recommending the service information is greatly improved.
Referring to fig. 3, an embodiment of the present invention provides data link nodes, where a consensus network is formed by a plurality of data link nodes, each data link point corresponds to a plurality of network appointments, there is no intersection between the network appointments corresponding to different data link points, the memory stores an executable program, the memory is connected to the processor through a bus communication, and the executable program is loaded by or more of the processors to perform the following steps:
inquiring user information and historical records corresponding to the user from a data chain stored in the data chain;
respectively determining the preference value of the user to each service information according to the historical records;
acquiring the preference value of a user group to which the user belongs to each service information according to the user information;
and acquiring the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sending the service information to be recommended to the user.
The method comprises the steps of , recommending service information operated by other users similar to the preference of the user to the user or analyzing the preference change of the user to each service information along with the time, recommending the service information which is possibly preferred by the user to the user, and improving the possibility that the user browses, downloads or purchases the recommended service information.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (7)
1, method for recommending service information, the method comprising:
the data link node inquires user information and history records corresponding to the user from a data link stored by the data link node;
the data link node respectively determines the preference value of the user to each service information according to the history record;
the data link node acquires the preference value of the user group to which the user belongs to each service information according to the user information;
the data link node acquires the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sends the service information to be recommended to the user,
the data link node inquires user information and history records corresponding to the user from a data link stored in the data link node, and the method comprises the following steps:
when a data link point detects that a user logs in, the data link point acquires user information corresponding to the user; or, the data link point acquires user information corresponding to the user every preset time length;
the data link node locates a data block containing the user information from a data link stored by the data link node;
the data link node reads the history record corresponding to the user from the data block;
the data link node respectively determines the preference value of the user to each service information according to the history record, and the method comprises the following steps:
the data link node acquires operation behavior information of each service information operated by the user from the historical record;
the data link node respectively calculates the preference value of the user to each service information through a formula (1) according to preset behavior weight information and operation behavior information corresponding to each service information, wherein the operation behavior information comprises the type of operation behavior and the operation times of each operation behavior;
in the formula (1), i is the number of service information, PiThe preference value of the user to the ith service information is represented, j is the number of the operation behavior information, omegajBehavior weight information corresponding to the jth operation behavior, AjThe operation times corresponding to the j operation behavior;
or, the determining, by the data link point, the preference value of the user for each service information according to the history includes:
the data link points divide the historical records into a plurality of sub-records of time units according to the time sequence;
the data link node respectively acquires the operation behavior information of each service information operated by the user from each sub-record;
the data link node respectively calculates the interest degree of the user in each service information in each time unit according to preset behavior weight information and operation behavior information corresponding to each sub record;
and the data link node determines the preference value of the user to each service information according to the interest degree of the user to each service information in each time unit.
2. The method for recommending service information according to claim 1, wherein the determining, by the data link node, the preference value of the user for each service information according to the interest level of the user for each service information in each time unit comprises:
the data link node respectively determines the time difference coefficient between each time unit and the current time through a formula (2) according to each time unit;
the data link node respectively calculates the preference value of the user to each service information through a formula (3) according to the time difference coefficient corresponding to each time unit and the interest degree of the user to each service information in each time unit;
gt＝a-(Tt-T)…(2)
in the formulae (2) and (3), t is the number of time units, gtTime difference coefficient corresponding to the T-th time unit, TtFor the t time sheetThe bit, T is the time unit nearest to the current time in each time unit, and a is a preset numerical value; i is the number of the service information, PiIs the preference value of the user to the ith service information, BtAnd the interest degree of the user in the ith service information corresponding to the t-th time unit.
3. The method for recommending service information according to claim 1, wherein the obtaining, by the data link node, the preference value of the user group to which the user belongs for each service information according to the user information comprises:
the data link nodes determine a user group to which the user belongs according to the user information;
the data link node respectively acquires the preference value of each user included in the user group to each service information;
and the data link node determines the preference value of the user group to each service information according to the preference value of each user to each service information.
4. The method for recommending service information according to claim 1, wherein the obtaining, by the data link node, the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information includes:
the data link node determines a preset number of service information with the highest preference value corresponding to the user group;
the data link node acquires hotspot information corresponding to the preset number of service information;
the data link point determines an interest group to which the user belongs according to the preference value of the user to each service information;
and the data link node determines the service information which is operated by other group members in the interest group and is not operated by the user and the service information which is not operated by the user in the hotspot information as the service information to be recommended.
5. The method for recommending service information according to claim 1, wherein said method further comprises:
the data link nodes generate data blocks according to the preference value of the user to each service information and the service information to be recommended;
the data link node adds the data block to its own stored data chain, and broadcasts the data block to other data chain nodes in the consensus network for storage.
An apparatus for recommending service information of , which is used to implement the method of any of in claims 1-5, wherein the apparatus comprises:
the query module is used for querying user information and historical records corresponding to the user from a data chain stored in the query module;
the determining module is used for respectively determining the preference value of the user to each service information according to the historical records;
the acquisition module is used for acquiring the preference value of the user group to which the user belongs to each service information according to the user information;
and the recommending module is used for acquiring the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sending the service information to be recommended to the user.
A datalink node comprising or more memories and processors, said memories storing executable programs which are loaded by or more said processors to perform the method of any of claims 1-5, comprising the steps of:
inquiring user information and historical records corresponding to the user from a data chain stored in the data chain;
respectively determining the preference value of the user to each service information according to the historical records;
acquiring the preference value of a user group to which the user belongs to each service information according to the user information; and acquiring the service information to be recommended according to the preference value of the user group to which the user belongs to each service information and the preference value of the user to each service information, and sending the service information to be recommended to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910394773.5A CN110222257B (en) | 2019-05-13 | 2019-05-13 | method and device for recommending service information and data link node |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910394773.5A CN110222257B (en) | 2019-05-13 | 2019-05-13 | method and device for recommending service information and data link node |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222257A CN110222257A (en) | 2019-09-10 |
| CN110222257B true CN110222257B (en) | 2020-01-31 |
Family
ID=67820951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910394773.5A Active CN110222257B (en) | 2019-05-13 | 2019-05-13 | method and device for recommending service information and data link node |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222257B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751219A (en) * | 2019-10-23 | 2020-02-04 | 郑州阿帕斯科技有限公司 | Content sending method and device |
| CN113536108A (en) * | 2021-05-31 | 2021-10-22 | 珠海大横琴科技发展有限公司 | Information recommendation method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164804A (en) * | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| CN103927673A (en) * | 2014-03-24 | 2014-07-16 | 腾讯科技（深圳）有限公司 | Method and device for recommending service information |
| CN104298679A (en) * | 2013-07-18 | 2015-01-21 | 腾讯科技（深圳）有限公司 | Application service recommendation method and device |
| CN105095267A (en) * | 2014-05-09 | 2015-11-25 | 阿里巴巴集团控股有限公司 | User involving project recommendation method and apparatus |
| CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
| CN108198019A (en) * | 2017-12-27 | 2018-06-22 | 网易无尾熊（杭州）科技有限公司 | Item recommendation method and device, storage medium, electronic equipment |
| WO2018112696A1 (en) * | 2016-12-19 | 2018-06-28 | 深圳大学 | Content pushing method and content pushing system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103603A (en) * | 2009-12-18 | 2011-06-22 | 百度在线网络技术（北京）有限公司 | User behavior data analysis method and device |
-
2019
- 2019-05-13 CN CN201910394773.5A patent/CN110222257B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164804A (en) * | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| CN104298679A (en) * | 2013-07-18 | 2015-01-21 | 腾讯科技（深圳）有限公司 | Application service recommendation method and device |
| CN103927673A (en) * | 2014-03-24 | 2014-07-16 | 腾讯科技（深圳）有限公司 | Method and device for recommending service information |
| CN105095267A (en) * | 2014-05-09 | 2015-11-25 | 阿里巴巴集团控股有限公司 | User involving project recommendation method and apparatus |
| CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
| WO2018112696A1 (en) * | 2016-12-19 | 2018-06-28 | 深圳大学 | Content pushing method and content pushing system |
| CN108198019A (en) * | 2017-12-27 | 2018-06-22 | 网易无尾熊（杭州）科技有限公司 | Item recommendation method and device, storage medium, electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222257A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108733706B (en) | Method and device for generating heat information | |
| US9710555B2 (en) | User profile stitching | |
| CN107851267A (en) | System and method for carrying out the synchronous data related to audio call via the virtual phone number of dynamically distributes | |
| JPWO2014049828A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN105190595A (en) | Uniquely identifying a network-connected entity | |
| CN103765456A (en) | Social networking system data exchange | |
| WO2014105622A2 (en) | Selecting an advertisement for a traffic source | |
| KR20150118587A (en) | Initiating real-time bidding based on expected revenue from bids | |
| JP6827305B2 (en) | Selection device, selection method and selection program | |
| CN110222257B (en) | method and device for recommending service information and data link node | |
| US10489828B2 (en) | Analyzing the advertisement bidding-chain | |
| EP2499607A1 (en) | Real-time online advertisement verification system and method | |
| CN109711917B (en) | Information pushing method and device | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| US20160267534A1 (en) | System and method for tracking car sales | |
| CN104765758A (en) | Systems and Methods for Search Results Targeting | |
| JP2011227721A (en) | Interest extraction device, interest extraction method, and interest extraction program | |
| CN110766489B (en) | Method for requesting content and providing content and corresponding device | |
| CN111582899B (en) | Quantification method, device and system for showing link effect and storage medium | |
| WO2017053248A1 (en) | Attributing an internet browsing session to television on-air time | |
| US8150730B2 (en) | Method and apparatus for internet sale using sale contents | |
| JP4649525B1 (en) | RECOMMENDATION DEVICE, RECOMMENDATION METHOD, AND RECOMMENDATION PROGRAM | |
| JP5824601B1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN111582901A (en) | Method, device and system for quantizing display link effect and storage medium | |
| CN115485676A (en) | User portrait based data processing method, apparatus, device, medium, and program |
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 |