CN113590926A - User interest identification method, device, equipment and computer readable medium - Google Patents
User interest identification method, device, equipment and computer readable medium Download PDFInfo
- Publication number
- CN113590926A CN113590926A CN202010365801.3A CN202010365801A CN113590926A CN 113590926 A CN113590926 A CN 113590926A CN 202010365801 A CN202010365801 A CN 202010365801A CN 113590926 A CN113590926 A CN 113590926A
- Authority
- CN
- China
- Prior art keywords
- node
- user
- coverage rate
- interest
- interest network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012546 transfer Methods 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method, a device, equipment and a computer readable medium for identifying user interests, wherein the method comprises the following steps: selecting an optimal node in the current interest network as a first node to be displayed to a user; the interest network is a user interest transfer matrix generated based on passenger flow data; acquiring feedback information of a user aiming at a first node; updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user aiming at the first node; a calculated weighted gain to the third node; and updating the weighted gain of the third node in the interest network, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as the first node to the user until the updated interest network meets the preset condition. The purpose of quickly identifying the interest of the user is achieved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a computer-readable medium for identifying user interests.
Background
With the development of the internet and the improvement of the living standard of people, online shopping becomes an indispensable part of the life of people, and online sales becomes more and more intelligent.
In the current intelligent sales, matching different users with goods that the users may like is a very critical link, and in the matching process, the users need to be comprehensively and accurately interested in portraying. However, since the user's behavior during the actual online shopping operation is sparse and dispersed, how to collect the user's interest is a very troublesome problem.
Therefore, a method for quickly identifying the interest of the user is needed.
Disclosure of Invention
In view of the above, the present application provides a method, an apparatus, a device and a computer readable medium for identifying user interests, which are used to quickly identify user interests.
In order to achieve the above purpose, the embodiments of the present application provide the following technical solutions:
the first aspect of the present application provides a method for identifying user interests, including:
selecting an optimal node in the current interest network as a first node to be displayed to a user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network;
acquiring feedback information of a user aiming at the first node; wherein the feedback information is feedback of satisfaction of a user for a shop represented by the first node;
updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user aiming at the first node; the second node is a node connected with the first node;
calculating to obtain the weighting gain of each third node; wherein the third node is an uncovered node in the interest network;
updating the weighted gain of the first node and the weighted gain of the third node in the interest network, and returning to execute the selection of the optimal node in the current interest network, serving as the first node and showing the optimal node to a user until the updated interest network meets a preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
Optionally, the updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user for the first node includes:
judging whether the feedback information of the first node is that a user is interested in a shop represented by the first node;
if the feedback information of the first node is judged to be that the user is interested in the shop represented by the first node, updating the first coverage rate of the first node to be a first numerical value and the second coverage rate to be a second numerical value, and updating the first coverage rate of the second node by using the original numerical value of the first coverage rate of the second node and the weight from the first node to the second node;
if the feedback information of the first node is judged to be that the user is not interested in the shop represented by the first node, updating the first coverage rate of the first node to be a second numerical value, and updating the second coverage rate of the second node by using the original numerical value of the second coverage rate of the second node and the weight from the first node to the second node;
the first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninteresting of the user to the shop represented by the node; the first value is greater than the second value.
Optionally, the method for calculating the weighting gain of the third node includes:
calculating to obtain a first weighting gain of the third node by setting a first coverage and a second coverage of a user in which the shop represented by the third node is interested, a weight of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node;
calculating to obtain a second weighting gain of the third node by using a first coverage and a second coverage of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node, which are set by a user and are not interested in the shop represented by the third node;
and taking the average value of the first weighting gain and the second weighting gain as the weighting gain of the third node.
Optionally, the preset condition is that the number of times of updating the interest network reaches a preset value, and the returning is performed to select the optimal node in the current interest network, and the optimal node is used as a first node to be displayed to a user until the updated interest network meets the preset condition, and the method includes:
judging whether the updating times of the interest network are smaller than a preset value or not;
if the updating times of the interest network are judged to be equal to the preset value, the updating of the interest network is suspended;
and if the updating times of the interest network are judged to be smaller than the preset value, returning to execute the selection of the optimal node in the current interest network, and displaying the optimal node serving as the first node to the user.
Optionally, the preset condition is that the coverage of each node in the interest network is updated, and the returning is performed to select the optimal node in the current interest network, and the optimal node is used as the first node to be displayed to the user until the updated interest network meets the preset condition, and the method includes:
judging whether the coverage rate of each node in the interest network is completely updated;
if the coverage rate of each node of the interest network is judged to be completely updated, ending the updating of the interest network;
and if the coverage rate of the nodes in the interest network is not updated, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as the first node to the user.
A second aspect of the present application provides an apparatus for identifying a user interest, including:
the selection unit is used for selecting the optimal node in the current interest network as a first node to be displayed to a user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network;
the acquisition unit is used for acquiring feedback information of a user aiming at the first node; wherein the feedback information is feedback of satisfaction of a user for a shop represented by the first node;
the first updating unit is used for updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user aiming at the first node; the second node is a node connected with the first node;
the calculating unit is used for calculating and obtaining the weighting gain of each third node; wherein the third node is an uncovered node in the interest network;
the second updating unit is used for updating the weighted gain of the first node and the weighted gain of the third node in the interest network and triggering the selecting unit, the first updating unit, the obtaining unit and the calculating unit to operate until the updated interest network meets a preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
Optionally, the first updating unit includes:
the first judging unit is used for judging whether the feedback information of the first node is that a user is interested in a shop represented by the first node;
a first updating subunit, configured to update a first coverage rate of the first node to be a first numerical value and a second coverage rate to be a second numerical value if the first judging unit judges that the feedback information of the first node is that a user is interested in a store represented by the first node, and update the first coverage rate of the second node by using an original numerical value of the first coverage rate of the second node and a weight from the first node to the second node; the first judging unit is further configured to, if the first judging unit judges that the feedback information of the first node is that the user is not interested in the store represented by the first node, update the first coverage of the first node to be a second numerical value, where the second coverage is the first numerical value, and update the second coverage of the second node by using an original numerical value of the second coverage of the second node and the weight from the first node to the second node;
the first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninteresting of the user to the shop represented by the node; the first value is greater than the second value.
Optionally, when the calculating unit calculates the weighting gain of each third node, the calculating unit is configured to:
calculating to obtain a first weighting gain of the third node by setting a first coverage and a second coverage of a user in which the shop represented by the third node is interested, a weight of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node;
calculating to obtain a first weighting gain of the third node by using a first coverage and a second coverage which are set under the condition that a user does not interest a shop represented by the third node, the weight of a node connected by the third node to the third node, the weight of the node connected by the third node, and the first coverage and the second coverage of each node connected by the third node;
and taking the average value of the first weighting gain and the second weighting gain as the weighting gain of the third node.
Optionally, the second updating unit includes:
the second judging unit is used for judging whether the updating times of the interest network is smaller than a preset value or not;
a suspending unit, configured to suspend updating the interest network if the number of times of updating the interest network is equal to the preset value, which is determined by the second determining unit;
the first executing unit is configured to trigger the selecting unit, the obtaining unit, the first updating unit, and the calculating unit to operate if the number of times of updating the interest network is smaller than the preset value, which is determined by the second determining unit.
Optionally, the second updating unit includes:
a third judging unit, configured to judge whether coverage of each node in the interest network has been completely updated;
an ending unit, configured to, if the third determining unit determines that the coverage of each node of the interest network has been completely updated, end the updating of the interest network;
and the second execution unit is configured to trigger the selection unit, the acquisition unit, the first updating unit, and the calculation unit to operate if the third determination unit determines that the coverage of the node in the interest network is not updated.
A third aspect of the application provides a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any of the first aspects of the application.
A fourth aspect of the present application provides an apparatus comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of the first aspects of the present application.
According to the scheme, in the identification method, the identification device, the identification equipment and the computer readable medium for the user interest, the optimal node in the current interest network is selected and used as the first node to be displayed to the user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network; then, acquiring feedback information of a user for the first node; wherein the feedback information is feedback of satisfaction of a user for a shop represented by the first node; then, according to the feedback information of the user aiming at the first node, updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node; the second node is a node connected with the first node; then, calculating to obtain the weighting gain of each third node; wherein the third node is an uncovered node in the interest network; finally, updating the weighted gain of the first node and the weighted gain of the third node in the interest network, and returning to execute the selection of the optimal node in the current interest network, serving as the first node and showing the optimal node to a user until the updated interest network meets a preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node. When the updated interest network meets the preset conditions, the optimal node in the interest network is the store in which the user is most interested in the interest network, so that the aim of quickly identifying the interest of the user is fulfilled.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a detailed flowchart of a method for identifying user interests according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a user interest transfer matrix according to another embodiment of the present application;
fig. 3 is a detailed flowchart of a method for identifying user interests according to another embodiment of the present application;
fig. 4 is a detailed flowchart of a method for identifying user interests according to another embodiment of the present application;
FIG. 5 is a flowchart illustrating a method for identifying user interests according to another embodiment of the present application;
FIG. 6 is a flowchart illustrating a method for identifying user interests according to another embodiment of the present disclosure;
FIG. 7 is a schematic diagram of an apparatus for identifying user interests according to another embodiment of the present application;
FIG. 8 is a diagram illustrating a first update unit according to another embodiment of the present application;
FIG. 9 is a diagram illustrating a second update unit according to another embodiment of the present application;
FIG. 10 is a diagram illustrating a second update unit according to another embodiment of the present application;
fig. 11 is a schematic diagram of an apparatus for performing a method for identifying a user interest according to another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first", "second", and the like, referred to in this application, are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence of functions performed by these devices, modules or units, but the terms "include", or any other variation thereof are intended to cover a non-exclusive inclusion, so that a process, method, article, or apparatus that includes a series of elements includes not only those elements but also other elements that are not explicitly listed, or includes elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
An embodiment of the present application provides a method for identifying user interests, as shown in fig. 1, the method includes the following steps:
s101, selecting an optimal node in the current interest network as a first node to be displayed to a user.
The interest network is a user interest transfer matrix generated based on passenger flow data; as shown in fig. 2, which is a schematic diagram of a user interest transfer matrix, each node in the user interest transfer matrix represents a store, and a connecting line between the nodes is used for explaining the flow of customers between the stores; the optimal node is the node with the largest weighting gain in the current interest network.
It should be noted that, in addition to showing the optimal node in the current interest network as the first node to the user, a target node in the interest network may be selected as the first node by using other screening principles. Optionally, the screening principle may be: and screening the shop with the target type, and taking the node corresponding to the shop with the target type as a first node. For example: a delicatessen store, a clothing store, etc. Optionally, when the target type of stores are screened, attribute information of the users to be pushed can be further used.
It should be noted that, due to the asymmetry of the passenger flow, the weight from node 1 to node 2 is not necessarily equal to the weight from node 2 to node 1, i.e., the interest network is a directed network.
Specifically, an optimal node is selected from the current interest network and displayed to the user, and if the current interest network is just built, the weighting gains of all uncovered nodes in the interest network are calculated. The uncovered nodes are nodes which do not receive the exact feedback information of the user and show that the shop is interested or not interested. The weighting gains of all the uncovered nodes in the interest network may be calculated by, but not limited to, calculating and setting the weighting gains when the user is interested in the stores corresponding to the uncovered nodes, and setting and averaging the weighting gains when the user is not interested in the stores corresponding to the uncovered nodes.
And S102, acquiring feedback information of the user for the first node.
The feedback information is feedback of the satisfaction degree of the user for the shop represented by the first node.
The feedback information is not limited to whether the user is interested in the store represented by the first node, and may be information such as a comment made by the user on the store represented by the first node.
Specifically, in an actual application scenario, the feedback information of the user for the first node may be obtained in a manner of, but not limited to, a game, a questionnaire, and the like, and this is not limited here.
S103, updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user for the first node.
The second node is a node connected with the first node. As shown in fig. 2, if the first node is node 12, the second nodes are node 4, node 2, node 11, and node 8.
Specifically, if the obtained feedback information of the user for the first node is "interested" or "uninteresting", the coverage rate corresponding to the first node and the coverage rate corresponding to the second node are updated according to the specification; if the obtained feedback information of the user for the first node is not 'interested' or 'uninteresting', the interest of the user needs to be judged according to other information in the feedback information, such as comments and the like, after the conclusion that the feedback information of the user for the first node is 'interested' or 'uninteresting' is obtained, the coverage rate corresponding to the first node and the coverage rate corresponding to the second node are updated according to the specification.
Optionally, in another embodiment of the present application, an implementation manner of step S103, as shown in fig. 3, includes the following steps:
s301, judging whether the feedback information of the first node is that the user is interested in the shop represented by the first node.
Specifically, if it is determined that the feedback information of the first node is that the user is interested in the store represented by the first node, step S302 is executed; if the feedback information of the first node is determined that the user is not interested in the shop represented by the first node, step S303 is executed.
S302, updating the first coverage rate of the first node to be a first numerical value, updating the second coverage rate to be a second numerical value, and updating the first coverage rate of the second node by using the original numerical value of the first coverage rate of the second node and the weight from the first node to the second node.
The first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninterested of the user to the shop represented by the node. The first numerical value and the second numerical value are preset numerical values, and the first numerical value is larger than the second numerical value. In general, the first value is set to 1 and the second value is set to 0 for simplicity, but the first value may be set to other values and the second value may be set to other values smaller than the first value.
It should be noted that, the manner of updating the first coverage of the second node may be, but is not limited to, updating the first coverage of the second node through a preset first update rule.
The preset first updating rule is
Wherein u denotes a first node, v denotes a second node,
the updated coverage rate of the user interested in the shop represented by the second node;
coverage for the original user that is of interest to the store represented by the second node;
the weight from the first node to the second node is expressed, namely the weight from the first node to the second node is equal to the passenger flow from the first node to the second node, and accounts for the proportion of the sum of the passenger flows from the first node to all second nodes around the first node, and the physical meaning of the weight is the passenger group transfer probability of statistics; nb (u) denotes a set of all second nodes connected to the first node.
And ← in a preset first updating rule, representing that the coverage rate of the original user interested in the shop represented by the second node is added with the weight from the first node to the second node, and then updated into the latest coverage rate of the user interested in the shop represented by the second node.
S303, updating the first coverage rate of the first node to be a second numerical value, and the second coverage rate to be a first numerical value, and updating the second coverage rate of the second node by using the original numerical value of the second coverage rate of the second node and the weight from the first node to the second node.
It should be noted that, the manner of updating the second coverage rate of the second node may be, but is not limited to, updating the second coverage rate of the second node through a preset second update rule.
The preset second updating rule is
Wherein u denotes a first node, v denotes a second node,
representing updated coverage of the store represented by the second node that is not of interest to the user;
the coverage rate representing that the original user is not interested in the store represented by the second node is shown, and the explanation of p (u → v) can refer to the preset first updating rule, and is not described herein again.
And S104, calculating the weighting gain of each third node.
The third node is a node which is not covered in the interest network, that is, a node which does not receive the exact feedback information of the user and indicates that the shop is interested or not interested.
Specifically, a preset formula is used for calculating the weighting gain of each uncovered node in the interest network.
Optionally, in another embodiment of the present application, an implementation method of step S104, as shown in fig. 4, includes:
s401, calculating to obtain a first weighting gain of a third node by setting a first coverage rate and a second coverage rate of a user interested in a shop represented by the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage rate and a second coverage rate of each node connected with the third node.
It should be noted that, the first weighting gain of the third node may be calculated by, but not limited to, using a preset formula. The preset formula is as follows:
wherein,
representing the weighted gain of the third node assuming the user is interested in the store represented by the third node; when the user is interested in the shop represented by the third node, the value is assigned
It is to be noted that the same is herein provided
And
the value of (A) is a value set in advance for expressing the interest of the user in the node, and is not limited to
Other numerical values can be also adopted, and the numerical values can be preset according to the actual application condition;
and
representing the coverage rate of a fourth node, wherein the fourth node is a node connecting the third node to the third node; p (x → y) represents the weight of the third node to the fourth node; w (x) represents the weight of the third node; w (y) represents the weight of the fourth node; nb (x) represents a set of all fourth nodes connected to the third node.
S402, calculating to obtain a first weighting gain of the third node by setting a first coverage rate and a second coverage rate of the user which are not interested in the shop represented by the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage rate and a second coverage rate of each node connected with the third node.
It should be noted that, the second weighting gain of the third node may be calculated by, but not limited to, using a preset formula. The preset formula is as follows:
wherein,
representing the weighted gain of the third node assuming that the user is not interested in the store represented by the third node; when the user is interested in the shop represented by the third node, the value is assigned
It is to be noted that the same is herein provided
And
the value of (A) is a value set in advance for expressing the interest of the user in the node, and is not limited to
Other numerical values can be also adopted, and the numerical values can be preset according to the actual application condition;
and
representing the coverage of the fourth node; p (x → y) represents the weight of the third node to the fourth node; w (x) represents the weight of the third node; w (y) represents the weight of the fourth node; nb (x) represents a set of all fourth nodes connected to the third node.
S403, an average value of the first weighting gain and the second weighting gain is used as the weighting gain of the third node.
Specifically, for calculating the weighting gain for the node that is not currently covered in the interest network, that is, the third node, it is assumed that the probabilities that the user is interested in the store represented by the third node and is not interested in the store represented by the third node are equal, and the weighting gain for the third node when the user is interested in the store represented by the third node and the average value of the weighting gains for the third node when the user is not interested in the store represented by the third node are obtained through calculation, so that the weighting gain for the node that is not currently covered in the interest network, that is, the third node is obtained.
And S105, updating the weighting gain of the third node in the interest network.
And S106, judging whether the updated interest network meets a preset condition.
The preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
Specifically, if it is determined that the updated interest network does not satisfy the preset condition, the step S101 is returned to, and if it is determined that the updated interest network satisfies the preset condition, the update of the interest network is ended.
Optionally, in another embodiment of the present application, as shown in fig. 5, an implementation method of step S106 includes:
s501, judging whether the updating times of the interest network is smaller than a preset value.
In the actual application process, the service personnel can adjust the preset value according to the actual situation, and therefore, the method is not limited herein. In addition, considering the user experience, the preset value is usually much smaller than the number of nodes in the interest network, i.e. the number of stores in the interest network.
Specifically, if the number of times of updating the interest network is determined to be equal to the preset value, step S502 is executed; if the number of times of updating the interest network is less than the preset value, step S503 is executed.
And S502, suspending the updating of the interest network.
And S503, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as the first node to the user.
Optionally, in another embodiment of the present application, as shown in fig. 6, an implementation method of step S106 includes:
s601, judging whether the coverage rate of each node in the interest network is completely updated.
Specifically, if it is determined that the coverage of each node of the interest network has been completely updated, step S602 is executed; if it is determined that the coverage of the node in the interest network is not updated, step S603 is executed.
And S602, ending the updating of the interest network.
And S603, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as the first node to the user.
According to the scheme, in the user interest identification method provided by the application, the optimal node in the current interest network is selected and used as the first node to be displayed to the user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network; then, acquiring feedback information of a user for the first node; the feedback information is feedback of the satisfaction degree of the user for the shop represented by the first node; then, according to the feedback information of the user aiming at the first node, updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node; the second node is a node connected with the first node; then, calculating to obtain the weighting gain of each third node; the third node is an uncovered node in the interest network, and finally, the weighting gain of the third node in the interest network is updated, the optimal node in the current interest network is returned to be selected and used as the first node to be displayed to the user until the updated interest network meets the preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node. When the updated interest network meets the preset conditions, the optimal node in the interest network is the store in which the user is most interested in the interest network, so that the aim of quickly identifying the interest of the user is fulfilled.
Another embodiment of the present application provides an apparatus for identifying a user interest, as shown in fig. 7, specifically including:
a selecting unit 701, configured to select an optimal node in the current interest network, and display the optimal node as a first node to a user.
The interest network is a user interest transfer matrix generated based on passenger flow data; as shown in fig. 2, which is a schematic diagram of a user interest transfer matrix, each node in the user interest transfer matrix represents a store, and a connecting line between the nodes is used for explaining the flow of customers between the stores; the optimal node is the node with the largest weighting gain in the current interest network.
An obtaining unit 702, configured to obtain feedback information of a user for a first node.
Wherein the feedback information is feedback of satisfaction of the user for the shop represented by the first node.
The first updating unit 703 is configured to update the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user for the first node.
The second node is a node connected with the first node.
Optionally, in another embodiment of the present application, an implementation manner of the first updating unit 703, as shown in fig. 8, includes:
a first judging unit 801, configured to judge whether feedback information of a first node is that a user is interested in a store represented by the first node;
a first updating subunit 802, configured to update the first coverage rate of the first node to be a first numerical value and the second coverage rate to be a second numerical value if the first determining unit 801 determines that the feedback information of the first node is that the user is interested in the store represented by the first node, and update the first coverage rate of the second node by using an original numerical value of the first coverage rate of the second node and a weight from the first node to the second node; the first determining unit 801 is further configured to, if it is determined that the feedback information of the first node is that the user is not interested in the store represented by the first node, update the first coverage of the first node to be a second value, where the second coverage is the first value, and update the second coverage of the second node by using the original value of the second coverage of the second node and the weight from the first node to the second node.
The first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninterested of the user to the shop represented by the node; the first value is greater than the second value.
For a specific working process of the unit disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, as shown in fig. 3, which is not described herein again.
A calculating unit 704, configured to calculate a weighting gain of each third node.
And the third node is an uncovered node in the interest network.
Optionally, in another embodiment of the present application, when the calculating unit 704 calculates the weighting gain of each third node, it is configured to:
and calculating to obtain a first weighting gain of the third node by setting a first coverage rate and a second coverage rate of the user in the store represented by the third node, the weight of the node connected from the third node to the third node, the weight of the node connected with the third node, and the first coverage rate and the second coverage rate of each node connected with the third node.
And calculating to obtain a second weighting gain of the third node by setting a first coverage rate and a second coverage rate of the user to the shop represented by the third node without interest, a weight of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage rate and a second coverage rate of each node connected with the third node.
And taking the average value of the first weighting gain and the second weighting gain as the weighting gain of the third node.
For a specific working process of the unit disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, as shown in fig. 4, which is not described herein again.
The second updating unit 705 is configured to update the weighted gain of the first node and the weighted gain of the third node in the interest network, and trigger the selecting unit 701, the obtaining unit 702, the first updating unit 703, and the calculating unit 704 to operate until the updated interest network meets a preset condition.
The preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
For a specific working process of the unit disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, as shown in fig. 1, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation manner of the second updating unit 705, as shown in fig. 9, includes:
a second determining unit 901, configured to determine whether the number of times of updating the interest network is smaller than a preset value.
A suspending unit 902, configured to suspend updating the interest network if the number of times of updating the interest network is equal to the preset value, which is determined by the second determining unit 901.
The first executing unit 903 is configured to trigger the selecting unit 701, the obtaining unit 702, the first updating unit 703 and the calculating unit 704 to operate if the second determining unit 901 determines that the number of times of updating the interest network is smaller than the preset value.
For a specific working process of the unit disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, as shown in fig. 5, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation manner of the second updating unit 605, as shown in fig. 10, includes:
a third judging unit 1001, configured to judge whether the weighting gain of each node in the interest network has been updated completely.
An ending unit 1002, configured to, if the third determining unit 1001 determines that the weighting gain of each node of the interest network has been completely updated, end the updating of the interest network.
A second executing unit 1003, configured to trigger the selecting unit 701, the obtaining unit 702, the first updating unit 703, and the calculating unit 704 to operate if the third determining unit 1001 determines that the weighting gain of the node in the interest network is not updated.
For a specific working process of the unit disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, as shown in fig. 6, which is not described herein again.
According to the above scheme, in the identification apparatus for user interests provided by the application, the selection unit 701 selects the optimal node in the current interest network as the first node to be displayed to the user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network; then, the obtaining unit 702 is used to obtain the feedback information of the user for the first node; the feedback information is feedback of the satisfaction degree of the user for the shop represented by the first node; then, according to the feedback information of the user for the first node, the coverage rate corresponding to the first node and the coverage rate corresponding to the second node are updated by using the first updating unit 703; the second node is a node connected with the first node; then, the weighting gain of each third node is calculated by the calculating unit 704; the third node is an uncovered node in the interest network; finally, the second updating unit 705 is used for updating the weighted gain of the first node and the weighted gain of the third node in the interest network, and the selecting unit 701, the obtaining unit 702, the first updating unit 703, the first calculating unit 704 and the second calculating unit 705 are triggered to operate until the updated interest network meets the preset conditions; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node. When the updated interest network meets the preset conditions, the optimal node in the interest network is the store in which the user is most interested in the interest network, and therefore the purpose of quickly identifying the interest of the user is achieved.
Another embodiment of the present application provides a computer-readable medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method according to any one of the above embodiments.
Another embodiment of the present application provides an apparatus, as shown in fig. 11, including:
one or more processors 1101.
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as in any one of the above embodiments.
In the above embodiments disclosed in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present disclosure may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a live broadcast device, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for identifying user interests, comprising:
selecting an optimal node in the current interest network as a first node to be displayed to a user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network;
acquiring feedback information of a user aiming at the first node; wherein the feedback information is feedback of satisfaction of a user for a shop represented by the first node;
updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user aiming at the first node; the second node is a node connected with the first node;
calculating to obtain the weighting gain of each third node; wherein the third node is an uncovered node in the interest network;
updating the weighting gain of a third node in the interest network, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as a first node to a user until the updated interest network meets a preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
2. The method according to claim 1, wherein the updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user for the first node comprises:
judging whether the feedback information of the first node is that a user is interested in a shop represented by the first node;
if the feedback information of the first node is judged to be that the user is interested in the shop represented by the first node, updating the first coverage rate of the first node to be a first numerical value and the second coverage rate to be a second numerical value, and updating the first coverage rate of the second node by using the original numerical value of the first coverage rate of the second node and the weight from the first node to the second node;
if the feedback information of the first node is judged to be that the user is not interested in the shop represented by the first node, updating the first coverage rate of the first node to be a second numerical value, and updating the second coverage rate of the second node by using the original numerical value of the second coverage rate of the second node and the weight from the first node to the second node;
the first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninteresting of the user to the shop represented by the node; the first value is greater than the second value.
3. The method of claim 1, wherein the method for calculating the weighting gain of the third node comprises:
calculating to obtain a first weighting gain of the third node by setting a first coverage and a second coverage of a user in which the shop represented by the third node is interested, a weight of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node;
calculating to obtain a second weighting gain of the third node by using a first coverage and a second coverage of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node, which are set by a user and are not interested in the shop represented by the third node;
and taking the average value of the first weighting gain and the second weighting gain as the weighting gain of the third node.
4. The method according to claim 1, wherein the preset condition is that the number of times of updating the interest network reaches a preset value, and the returning is performed to select the optimal node in the current interest network, and the optimal node is used as the first node to be displayed to the user until the updated interest network meets the preset condition, including:
judging whether the updating times of the interest network are smaller than a preset value or not;
if the updating times of the interest network are judged to be equal to the preset value, the updating of the interest network is suspended;
and if the updating times of the interest network are judged to be smaller than the preset value, returning to execute the selection of the optimal node in the current interest network, and displaying the optimal node serving as the first node to the user.
5. The method according to claim 1, wherein the preset condition is that the coverage of each node in the interest network is updated, and the returning performs the selecting of the optimal node in the current interest network as the first node to be displayed to the user until the updated interest network meets the preset condition, including:
judging whether the coverage rate of each node in the interest network is completely updated;
if the coverage rate of each node of the interest network is judged to be completely updated, ending the updating of the interest network;
and if the coverage rate of the nodes in the interest network is not updated, returning to execute the selection of the optimal node in the current interest network, and showing the optimal node as the first node to the user.
6. An apparatus for identifying user interests, comprising:
the selection unit is used for selecting the optimal node in the current interest network as a first node to be displayed to a user; the interest network is a user interest transfer matrix generated based on passenger flow data; each node in the user interest transfer matrix represents a shop, and connecting lines among the nodes are used for explaining the flow of the customer groups among the shops; the optimal node is the node with the largest weighting gain in the current interest network;
the acquisition unit is used for acquiring feedback information of a user aiming at the first node; wherein the feedback information is feedback of satisfaction of a user for a shop represented by the first node;
the first updating unit is used for updating the coverage rate corresponding to the first node and the coverage rate corresponding to the second node according to the feedback information of the user aiming at the first node; the second node is a node connected with the first node;
the calculating unit is used for calculating and obtaining the weighting gain of each third node; wherein the third node is an uncovered node in the interest network;
the second updating unit is used for updating the weighted gain of the first node and the weighted gain of the third node in the interest network and triggering the selecting unit, the obtaining unit, the first updating unit, the first calculating unit and the second calculating unit to operate until the updated interest network meets a preset condition; the preset condition is that the coverage rate of each node in the interest network is updated, or the updating times of the interest network reach a preset value; and the coverage rate corresponding to each node in the interest network meeting the preset condition is used for explaining the interest degree of the user for the node.
7. The apparatus of claim 6, wherein the first updating unit comprises:
the first judging unit is used for judging whether the feedback information of the first node is that a user is interested in a shop represented by the first node;
a first updating subunit, configured to update a first coverage rate of the first node to be a first numerical value and a second coverage rate to be a second numerical value if the first judging unit judges that the feedback information of the first node is that a user is interested in a store represented by the first node, and update the first coverage rate of the second node by using an original numerical value of the first coverage rate of the second node and a weight from the first node to the second node; the first judging unit is further configured to update the first coverage rate of the first node to be a second numerical value and the second coverage rate to be the first numerical value if the first judging unit judges that the feedback information of the first node is that the user is not interested in the shop represented by the first node, and update the second coverage rate of the second node by using an original numerical value of the second coverage rate of the second node and the weight from the first node to the second node;
the first coverage rate is the coverage rate of interest of the user to the shop represented by the node, and the second coverage rate is the coverage rate of uninteresting of the user to the shop represented by the node; the first value is greater than the second value.
8. The apparatus of claim 6, wherein the computing unit, when computing the weighted gain for each third node, is configured to:
calculating to obtain a first weighting gain of the third node by setting a first coverage and a second coverage of a user in which the shop represented by the third node is interested, a weight of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node;
calculating to obtain a second weighting gain of the third node by using a first coverage and a second coverage of the third node, a weight of a node connected from the third node to the third node, a weight of a node connected with the third node, and a first coverage and a second coverage of each node connected with the third node, which are set by a user and are not interested in the shop represented by the third node;
and taking the average value of the first weighting gain and the second weighting gain as the weighting gain of the third node.
9. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1 to 4.
10. An apparatus, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010365801.3A CN113590926B (en) | 2020-04-30 | 2020-04-30 | User interest identification method, device, equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010365801.3A CN113590926B (en) | 2020-04-30 | 2020-04-30 | User interest identification method, device, equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590926A true CN113590926A (en) | 2021-11-02 |
| CN113590926B CN113590926B (en) | 2024-10-22 |
Family
ID=78237440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010365801.3A Active CN113590926B (en) | 2020-04-30 | 2020-04-30 | User interest identification method, device, equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590926B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260410A (en) * | 2015-09-22 | 2016-01-20 | 天津大学 | Microblog interestingness circle mining method based on intimacy degree and influence power and microblog interestingness circle mining device based on intimacy degree and influence power |
| WO2017075980A1 (en) * | 2015-11-06 | 2017-05-11 | 北京金山安全软件有限公司 | Information pushing method and apparatus |
| CN107391760A (en) * | 2017-08-25 | 2017-11-24 | 平安科技（深圳）有限公司 | User interest recognition methods, device and computer-readable recording medium |
| CN107562875A (en) * | 2017-08-31 | 2018-01-09 | 北京麒麟合盛网络技术有限公司 | A kind of update method of model, apparatus and system |
| CN108491540A (en) * | 2018-03-30 | 2018-09-04 | 北京百度网讯科技有限公司 | Text message method for pushing, device and intelligent terminal |
| CN108985843A (en) * | 2018-07-18 | 2018-12-11 | 天津璧合信息技术有限公司 | A kind of method and device of determining Trip distribution situation |
| CN109561350A (en) * | 2017-09-27 | 2019-04-02 | 北京国双科技有限公司 | The evaluation method and system of user interest degree |
| CN109933720A (en) * | 2019-01-29 | 2019-06-25 | 汕头大学 | A kind of dynamic recommendation method based on user interest Adaptive evolution |
| CN109992723A (en) * | 2019-02-25 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of user interest label construction method and relevant device based on social networks |
| CN110389662A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Content displaying method, device, storage medium and the computer equipment of application program |
-
2020
- 2020-04-30 CN CN202010365801.3A patent/CN113590926B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260410A (en) * | 2015-09-22 | 2016-01-20 | 天津大学 | Microblog interestingness circle mining method based on intimacy degree and influence power and microblog interestingness circle mining device based on intimacy degree and influence power |
| WO2017075980A1 (en) * | 2015-11-06 | 2017-05-11 | 北京金山安全软件有限公司 | Information pushing method and apparatus |
| CN107391760A (en) * | 2017-08-25 | 2017-11-24 | 平安科技（深圳）有限公司 | User interest recognition methods, device and computer-readable recording medium |
| CN107562875A (en) * | 2017-08-31 | 2018-01-09 | 北京麒麟合盛网络技术有限公司 | A kind of update method of model, apparatus and system |
| CN109561350A (en) * | 2017-09-27 | 2019-04-02 | 北京国双科技有限公司 | The evaluation method and system of user interest degree |
| CN108491540A (en) * | 2018-03-30 | 2018-09-04 | 北京百度网讯科技有限公司 | Text message method for pushing, device and intelligent terminal |
| CN108985843A (en) * | 2018-07-18 | 2018-12-11 | 天津璧合信息技术有限公司 | A kind of method and device of determining Trip distribution situation |
| CN109933720A (en) * | 2019-01-29 | 2019-06-25 | 汕头大学 | A kind of dynamic recommendation method based on user interest Adaptive evolution |
| CN109992723A (en) * | 2019-02-25 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of user interest label construction method and relevant device based on social networks |
| CN110389662A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Content displaying method, device, storage medium and the computer equipment of application program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590926B (en) | 2024-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163705B (en) | Method and device for pushing information | |
| US20150317659A1 (en) | Dynamic pricing systems and methods | |
| WO2011112173A1 (en) | Methods and systems for identifying customer status for developing customer retention and loyalty strategies | |
| CN108665293B (en) | Feature importance obtaining method and device | |
| CN110532467B (en) | Activity recommendation method and device based on push model, equipment and storage medium | |
| CN112000747A (en) | Data multidimensional analysis method, device and system | |
| JP6903629B2 (en) | Evaluation system, evaluation method and program | |
| CN111046082A (en) | Data source determination method, device, server and storage medium | |
| CN105930149B (en) | A kind of display methods and device | |
| JP5945206B2 (en) | Product recommendation device, method and program | |
| KR102290184B1 (en) | Apparatus, Method and System for Display Promotion Time | |
| CN113590926A (en) | User interest identification method, device, equipment and computer readable medium | |
| JP2007188285A (en) | Method and system for setting threshold | |
| JP2016192013A (en) | Sales representative candidate extraction system | |
| CN111861674B (en) | Product recommendation method and system | |
| CN110838019A (en) | Method and device for determining trial supply distribution crowd | |
| CN111784091B (en) | Method and device for processing information | |
| CN112650862B (en) | Method and device for constructing interest network, electronic equipment and computer storage medium | |
| WO2018144695A1 (en) | In-store display with selective display of products based on visibility metric | |
| KR101909970B1 (en) | Method for recommending exhibition based on rule model | |
| CN114611022A (en) | Method, device, equipment and storage medium for pushing display information | |
| WO2017072873A1 (en) | Document distribution device, document distribution method, program, and non-temporary recording medium | |
| KR102290213B1 (en) | Method for generating customer profile using card usage information and appratus for generating customer profile | |
| JP2011081451A (en) | Display data generating device and program | |
| CN110910035A (en) | Method and device for evaluating service area in bank outlet |
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 |