CN117273863A - Information pushing method based on user demand prediction and electronic commerce system - Google Patents
Information pushing method based on user demand prediction and electronic commerce system Download PDFInfo
- Publication number
- CN117273863A CN117273863A CN202311461097.1A CN202311461097A CN117273863A CN 117273863 A CN117273863 A CN 117273863A CN 202311461097 A CN202311461097 A CN 202311461097A CN 117273863 A CN117273863 A CN 117273863A
- Authority
- CN
- China
- Prior art keywords
- commodity
- sequence
- subsequence
- behavior
- user
- 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 45
- 238000012545 processing Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 description 203
- 230000000694 effects Effects 0.000 description 13
- 238000004590 computer program Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an information pushing method and an electronic commerce system based on user demand prediction, wherein behavior data in the electronic commerce system are obtained in a target time period of a user, the target time period is a time period with the current time as the end time and the time length as the preset user behavior data statistics time length, the behavior data of the user is matched with a preset behavior pattern, when any behavior pattern of the behavior data of the user is matched, a target commodity sequence corresponding to the behavior pattern is obtained, the target commodity sequence is an ordered commodity sequence corresponding to the behavior pattern, the shopping demand of the user is predicted based on the target commodity sequence, pushing information is generated according to the shopping demand, and information pushing of the electronic commerce system can be enabled to be more accurately attached to the shopping demand of the user.
Description
Technical Field
The invention relates to the technical field of electronic commerce, in particular to an information pushing method based on user demand prediction and an electronic commerce system.
Background
With the increasing popularity of online shopping, electronic commerce systems have become one of the main channels for people to shop daily. In general, an e-commerce system will be configured with an inbox for receiving push information for each user, and because the information push of the e-commerce system is generally indiscriminate push, i.e. the e-commerce system will indiscriminately push some popular merchandise introduction, preferential activity information, etc. to each user, in most cases, because these information do not fit the shopping requirement of the user, they are always ignored or deleted by the user as junk information. In the prior art, the user's interest point is identified by analyzing the actions such as browsing, searching, clicking, collecting, etc. of the user on the e-commerce system, and then the commodity is recommended to the user, for example, the chinese patent CN115239412a analyzes the historical actions of the user, digs out the historical interests and the recent interests of the user to improve the accuracy of commodity recommendation, and the chinese patent CN112862007a predicts the commodity of interest to the user by inputting the commodity historical sequence of the interactive action with the user into the pre-trained sequence prediction model, so as to improve the accuracy of commodity recommendation. However, the interests of the user are not representative of the consumer demands of the user, the interests of the user are extensive, but the number of shopping behaviors which can occur in practice is limited, and the types of commodities which are interested by the user can be accurately analyzed and obtained based on various behaviors of the user on an electronic commerce system, however, the commodities which are interested by the user tend to be numerous in class and number, if push information is generated for all the commodities, a great amount of information which cannot be fully focused by the user is filled in an inbox of the user, and the user is bothered.
Disclosure of Invention
Based on the above problems, the invention provides an information pushing method and an electronic commerce system based on user demand prediction, which can enable information pushing of the electronic commerce system to be more accurately matched with shopping demands of users.
In view of this, a first aspect of the present invention proposes an information pushing method based on user demand prediction, including:
acquiring behavior data in an electronic commerce system in a user target time period, wherein the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
matching the behavior data of the user with a pre-configured behavior pattern;
when the behavior data of the user are matched with any behavior pattern, a target commodity sequence corresponding to the behavior pattern is obtained, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior pattern;
predicting shopping demands of users based on the target commodity sequence;
and generating push information according to the shopping demand.
Preferably, the step of matching the behavior data of the user with a pre-configured behavior pattern specifically includes:
generating a shopping sequence corresponding to the behavior data and a focused commodity list, wherein the shopping sequence is an ordered commodity sequence formed by commodities ordered and purchased by a user in an electronic commerce system in the target time period and the purchase time of the commodities, and the focused commodity list is an unordered commodity sequence formed by commodities focused by the user but not ordered and purchased in the electronic commerce system in the target time period;
Sequentially reading commodity sequences corresponding to each pre-configured behavior mode from a database to serve as candidate commodity sequences;
judging whether the candidate commodity sequence contains a first subsequence which is simultaneously a subset of the shopping sequence or not, wherein the first subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the first subsequence is included in the candidate commodity sequence, judging whether a second subsequence which is simultaneously a subset of the commodity list of interest is included in the commodity sequence or not, wherein the second subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the candidate commodity sequence contains the second subsequence, determining that the behavior data is matched with a corresponding behavior pattern;
and determining the candidate commodity sequence as a target commodity sequence.
Preferably, the step of determining whether the candidate commodity sequence includes a first subsequence that is simultaneously a subset of the shopping sequence specifically includes:
determining a first intersection item of the candidate item sequence and the shopping sequence;
constructing more than one third subsequence according to the sequence of the first intersection commodity in the candidate commodity sequence, wherein the third subsequence is a continuous ordered subsequence in the candidate commodity sequence;
Constructing a fourth subsequence according to the order of the first intersection commodity in the shopping sequence;
determining a largest continuous subsequence which meets the commodity order same as that of the fourth subsequence in the third subsequence;
judging whether the length of the maximum continuous subsequence is larger than a preset matching length threshold value or not;
when the length of the maximum continuous subsequence is greater than a preset matching length threshold, determining the maximum continuous subsequence with the length greater than the matching length threshold as the first subsequence;
determining that the candidate commodity sequence comprises the first subsequence.
Preferably, the step of determining whether the commodity sequence includes a second subsequence that is also a subset of the commodity list of interest specifically includes:
determining a second intersection commodity of the candidate commodity sequence and the attention commodity list;
constructing more than one fifth subsequence according to the sequence of the second intersection commodity in the candidate commodity sequence, wherein the fifth subsequence is a continuous ordered subsequence in the candidate commodity sequence;
judging whether the length of the fifth subsequence is larger than a preset matching length threshold value;
when the length of the fifth subsequence is larger than a preset matching length threshold value, determining the fifth subsequence with the length larger than the matching length threshold value as the second subsequence;
Determining that the candidate commodity sequence comprises the second subsequence.
Preferably, the step of predicting shopping requirements of the user based on the target commodity sequence specifically includes:
determining a predicted merchandise list in the target merchandise sequence;
judging whether the predicted commodity list contains movable commodities or not;
and when the predicted commodity list contains the active commodity, determining the active commodity as a pushed commodity.
Preferably, the step of determining the predicted merchandise list in the target merchandise sequence specifically includes:
determining the last commodity of the first subsequence corresponding to the target commodity sequence;
determining the position number of the last commodity in the target commodity sequence as a prediction boundary;
and adding the commodity with the position number larger than the prediction boundary in the target commodity sequence to the predicted commodity list.
Preferably, after the step of determining whether the length of the maximum continuous subsequence is greater than a preset matching length threshold, the method further includes:
when the length of the maximum continuous subsequence is smaller than a preset matching length threshold, recording a first difference value between the matching length threshold and the length of the maximum continuous subsequence:
Δl 1 ＝l max -l 0 ，
Wherein l max For the largest contiguous subsequenceLength, l 0 A threshold value for the matching length;
after the step of determining whether the length of the fifth sub-sequence is greater than the preset matching length threshold, the method further includes:
when the length of the fifth subsequence is smaller than a preset matching length threshold, recording a second difference value between the matching length threshold and the length of the fifth subsequence:
Δl 2 ＝l 5 -l 0 ，
wherein l 5 For the length of the fifth subsequence
Adding Deltal of the first difference and the second difference 1 +Δl 2 And storing the behavior data in association with the corresponding behavior mode.
Preferably, after the step of matching the behavior data of the user with a pre-configured behavior pattern, the method further comprises:
when there is no behavior pattern matching the behavior data, summing the first difference and the second difference Deltal 1 +Δl 2 A behavior pattern smaller than a preset difference threshold is determined as a similar behavior pattern of the behavior data;
the similar behavior patterns are stored in association with the behavior data;
discarding associated data of other behavior patterns than the similar behavior pattern with the behavior data.
Preferably, the step of storing the similar behavior pattern in association with the behavior data further comprises storing a list of predicted products of the similar behavior pattern in association with the behavior data;
After the step of storing the similar behavior pattern in association with the behavior data, the method further comprises:
monitoring the ordering purchasing behavior of a user;
when the commodity purchased by the user is in the predicted commodity list of any similar behavior mode, the steps of acquiring the behavior data of the user in the electronic commerce system within the target time period of the user and matching the behavior data of the user with the pre-configured behavior mode are re-executed.
A second aspect of the present invention proposes an electronic commerce system comprising:
the system comprises a behavior data acquisition module, a behavior data processing module and a behavior data processing module, wherein the behavior data acquisition module is used for acquiring behavior data in an electronic commerce system in a user target time period, the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
the behavior pattern matching module is used for matching the behavior data of the user with a pre-configured behavior pattern;
the commodity sequence acquisition module is used for acquiring a target commodity sequence corresponding to the behavior mode when the behavior data of the user are matched with any behavior mode, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior mode;
The shopping demand prediction module is used for predicting the shopping demand of the user based on the target commodity sequence;
and the push information generation module is used for generating push information according to the shopping requirements.
The invention provides an information pushing method and an electronic commerce system based on user demand prediction, wherein behavior data in the electronic commerce system are obtained in a target time period of a user, the target time period is a time period with the current time as the end time and the time length as the preset user behavior data statistics time length, the behavior data of the user is matched with a preset behavior pattern, when any behavior pattern of the behavior data of the user is matched, a target commodity sequence corresponding to the behavior pattern is obtained, the target commodity sequence is an ordered commodity sequence corresponding to the behavior pattern, the shopping demand of the user is predicted based on the target commodity sequence, pushing information is generated according to the shopping demand, and information pushing of the electronic commerce system can be enabled to be more accurately attached to the shopping demand of the user.
Drawings
FIG. 1 is a flowchart of an information pushing method based on user demand prediction according to an embodiment of the present invention;
Fig. 2 is a schematic diagram of an electronic commerce system according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
In the description of the present invention, the term "plurality" means two or more, unless explicitly defined otherwise, the orientation or positional relationship indicated by the terms "upper", "lower", etc. are based on the orientation or positional relationship shown in the drawings, merely for convenience of description of the present invention and to simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. The terms "coupled," "mounted," "secured," and the like are to be construed broadly, and may be fixedly coupled, detachably coupled, or integrally connected, for example; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", etc. may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of this specification, the terms "one embodiment," "some implementations," "particular embodiments," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
An information pushing method and an electronic commerce system based on user demand prediction according to some embodiments of the present invention are described below with reference to the accompanying drawings.
As shown in fig. 1, a first aspect of the present invention proposes an information pushing method based on user demand prediction, including:
acquiring behavior data in an electronic commerce system in a user target time period, wherein the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
matching the behavior data of the user with a pre-configured behavior pattern;
When the behavior data of the user are matched with any behavior pattern, a target commodity sequence corresponding to the behavior pattern is obtained, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior pattern;
predicting shopping demands of users based on the target commodity sequence;
and generating push information according to the shopping demand.
Specifically, the information pushing method based on user demand prediction provided by the invention is realized by executing a computer program by a server running an electronic commerce system or other computers connected with a database storing electronic commerce system data. In some embodiments, a specific program execution period may be configured to periodically run the computer program to implement the above information pushing method, or be triggered to execute the computer program to implement the above information pushing method according to a specific behavior of a user or an operation and maintenance person. In the step of acquiring behavior data in the electronic commerce system within a target time period of a user, the current time for determining the target time period is the time for realizing the information pushing method by running the computer program each time.
The behavior data of the user in the electronic commerce system comprises, but is not limited to, the behavior of the user for browsing, clicking, searching, collecting, purchasing or purchasing goods in the electronic commerce system, and the electronic commerce system stores the time of the user for generating the behavior, the behavior itself and the corresponding goods information in a database. Specific events that occur in real life by users create specific persistent shopping demands, and the merchandise corresponding to these shopping demands is strongly associated with these events, and the purchased merchandise is strongly associated with the occurrence of the events. Thus, in the technical solution of the present invention, the pre-configured behavior pattern is a set of shopping behaviors that the user exhibits on the e-commerce platform when these specific events occur in real life. The target commodity sequence corresponding to the behavior mode is a sequence formed by commodities which the user needs to purchase when the user generates the specific events in real life. Ordered sequence of items refers to the purchase of these items in the sequence of items being time-ordered in the corresponding pattern of behavior.
For convenience of understanding, in the technical solution of the present invention, the term "commodity sequence", "subsequence" and "commodity list" refer to a set of multiple commodities, where "sequence" refers to that commodities in the commodity set are arranged according to a specific time sequence, and "list" does not limit the arrangement sequence of the commodities, and although "list" necessarily has a certain arrangement sequence in the actual program implementation, in the matching process of some commodity sets of the present invention, the influence of the arrangement sequence of the commodities in "list" on the matching result is not considered.
Preferably, the step of matching the behavior data of the user with a pre-configured behavior pattern specifically includes:
generating a shopping sequence corresponding to the behavior data and a focused commodity list, wherein the shopping sequence is an ordered commodity sequence formed by commodities ordered and purchased by a user in an electronic commerce system in the target time period and the purchase time of the commodities, and the focused commodity list is an unordered commodity sequence formed by commodities focused by the user but not ordered and purchased in the electronic commerce system in the target time period;
sequentially reading commodity sequences corresponding to each pre-configured behavior mode from a database to serve as candidate commodity sequences;
Judging whether the candidate commodity sequence contains a first subsequence which is simultaneously a subset of the shopping sequence or not, wherein the first subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the first subsequence is included in the candidate commodity sequence, judging whether a second subsequence which is simultaneously a subset of the commodity list of interest is included in the commodity sequence or not, wherein the second subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the candidate commodity sequence contains the second subsequence, determining that the behavior data is matched with a corresponding behavior pattern;
and determining the candidate commodity sequence as a target commodity sequence.
In the technical solution of the above embodiment, the commodities that the user pays attention to in the electronic commerce system but does not pay attention to purchase are commodities that the user pays attention to in the time period determined according to the behavior of browsing, clicking, searching, collecting or purchasing the commodities in the electronic commerce system.
In the step of determining whether a first subsequence that is simultaneously a subset of the shopping sequence is included in the candidate merchandise sequence, the first subsequence may be a continuous ordered subsequence or a discontinuous ordered subsequence in the shopping sequence. The first subsequence is a continuous ordered subsequence in the candidate commodity sequence, specifically, commodities in the first subsequence are all present in the candidate commodity sequence, the sequence of the commodities in the candidate commodity sequence is the same as the sequence in the first subsequence, the commodities in the first subsequence are continuous in the candidate commodity sequence, and no other commodities exist between every two commodities. Similarly, the first subsequence is a subset of the shopping sequence, i.e., the items in the first subsequence are all present in the shopping sequence, in the same order as in the first subsequence in the shopping sequence, but may be discontinuous in the shopping sequence.
Likewise, in the step of determining whether the commodity sequence includes a second subsequence that is also a subset of the list of commodities of interest, the second subsequence may likewise be a continuous ordered subsequence or a discontinuous ordered subsequence in the shopping sequence, i.e., all commodities in the second subsequence are present in the candidate commodity sequence, the order of the commodities in the candidate commodity sequence is the same as that in the second subsequence, and the commodities in the second subsequence are continuous in the candidate commodity sequence, with no other commodity present therebetween. As in the case of the first sub-sequence in the shopping sequence, the second sub-sequence is also a subset of the list of items of interest, i.e. the items in the second sub-sequence are all present in the list of items of interest and may be discontinuous in the list of items of interest, except that the list of items of interest is unordered, i.e. the order of the items in the second sub-sequence in the list of items of interest may be the same or different.
It should be appreciated that the length of the first or second sub-sequence should be less than the candidate merchandise sequence, and that the behavior data is determined to be mismatched with the corresponding behavior pattern when the length of the first or second sub-sequence is equal to the candidate merchandise sub-sequence.
Preferably, the step of determining whether the candidate commodity sequence includes a first subsequence that is simultaneously a subset of the shopping sequence specifically includes:
determining a first intersection item of the candidate item sequence and the shopping sequence;
constructing more than one third subsequence according to the sequence of the first intersection commodity in the candidate commodity sequence, wherein the third subsequence is a continuous ordered subsequence in the candidate commodity sequence;
constructing a fourth subsequence according to the order of the first intersection commodity in the shopping sequence;
determining a largest continuous subsequence which meets the commodity order same as that of the fourth subsequence in the third subsequence;
judging whether the length of the maximum continuous subsequence is larger than a preset matching length threshold value or not;
when the length of the maximum continuous subsequence is greater than a preset matching length threshold, determining the maximum continuous subsequence with the length greater than the matching length threshold as the first subsequence;
determining that the candidate commodity sequence comprises the first subsequence.
In the step of determining the first intersection commodity of the candidate commodity sequence and the shopping sequence, when the intersection commodity does not exist in the candidate commodity sequence and the shopping sequence, the first subsequence is not included in the candidate commodity sequence.
In the step of constructing one or more third subsequences in the order of the first intersection item in the candidate item sequence, the "one or more" includes one, i.e., when the first intersection item forms only one continuous subsequence in the candidate item sequence, then the third subsequence is one, and when the first intersection item is separated into a plurality of continuous subsequences in the candidate item sequence, then the third subsequence is a plurality. When the third subsequences are multiple, in the step of determining a maximum continuous subsequence which meets the commodity order same as the fourth subsequence in the third subsequences, determining a maximum continuous subsequence in each third subsequence, and judging whether the lengths of the maximum continuous subsequences are larger than a preset matching length threshold value or not.
Preferably, the step of determining whether the commodity sequence includes a second subsequence that is also a subset of the commodity list of interest specifically includes:
determining a second intersection commodity of the candidate commodity sequence and the attention commodity list;
constructing more than one fifth subsequence according to the sequence of the second intersection commodity in the candidate commodity sequence, wherein the fifth subsequence is a continuous ordered subsequence in the candidate commodity sequence;
Judging whether the length of the fifth subsequence is larger than a preset matching length threshold value;
when the length of the fifth subsequence is larger than a preset matching length threshold value, determining the fifth subsequence with the length larger than the matching length threshold value as the second subsequence;
determining that the candidate commodity sequence comprises the second subsequence.
Also, in the step of determining the second intersection commodity of the candidate commodity sequence and the attention commodity list, when the intersection commodity does not exist in the candidate commodity sequence and the attention commodity list, it is determined that the second subsequence is not included in the candidate commodity sequence.
In the step of constructing one or more fifth subsequences in the order of the second intersection item in the candidate item sequence, the "one or more" includes one, i.e., when the second intersection item forms only one continuous subsequence in the candidate item sequence, the fifth subsequence is one, and when the second intersection item is separated into a plurality of continuous subsequences in the candidate item sequence, the fifth subsequence is a plurality. When the number of the fifth subsequences is plural, in the step of judging whether the length of the fifth subsequence is larger than the preset matching length threshold, judging whether the lengths of the fifth subsequences are larger than the preset matching length threshold is performed on all the fifth subsequences.
Preferably, the step of predicting shopping requirements of the user based on the target commodity sequence specifically includes:
determining a predicted merchandise list in the target merchandise sequence;
judging whether the predicted commodity list contains movable commodities or not;
and when the predicted commodity list contains the active commodity, determining the active commodity as a pushed commodity.
Specifically, the active commodity refers to a commodity currently provided with various preferential activities in the electronic commerce system, wherein the preferential activities include, but are not limited to, sales promotion activities, group purchase activities, point activities and the like. Only when the commodity has a preferential activity, the corresponding push information can be focused by the user, so in the technical scheme of the embodiment, only the active commodity in the predicted commodity list is determined to be the push commodity, namely, the corresponding push information is generated and sent to the inbox of the user.
Preferably, the step of determining the predicted merchandise list in the target merchandise sequence specifically includes:
determining the last commodity of the first subsequence corresponding to the target commodity sequence;
determining the position number of the last commodity in the target commodity sequence as a prediction boundary;
And adding the commodity with the position number larger than the prediction boundary in the target commodity sequence to the predicted commodity list.
In the technical scheme of the invention, for each commodity sequence, the positions of the commodities in the commodity sequence are numbered respectively, for example, arabic numerals can be used as the numbers of the commodities in the commodity sequence. The same commodity is individually numbered in different commodity sequences, for example, the number of the commodity in the target commodity sequence is often different from the number of the commodity in the first subsequence corresponding to the commodity. The position numbers may be used to identify the order of the items in the respective item sequences.
Preferably, after the step of determining whether the length of the maximum continuous subsequence is greater than a preset matching length threshold, the method further includes:
when the length of the maximum continuous subsequence is smaller than a preset matching length threshold, recording a first difference value between the matching length threshold and the length of the maximum continuous subsequence:
Δl 1 ＝l max -l 0 ，
wherein l max For the length of the largest contiguous subsequence, l 0 A threshold value for the matching length;
after the step of determining whether the length of the fifth sub-sequence is greater than the preset matching length threshold, the method further includes:
When the length of the fifth subsequence is smaller than a preset matching length threshold, recording a second difference value between the matching length threshold and the length of the fifth subsequence:
Δl 2 ＝l 5 -l 0 ，
wherein l 5 For the length of the fifth subsequence
Adding Deltal of the first difference and the second difference 1 +Δl 2 And storing the behavior data in association with the corresponding behavior mode.
In some embodiments of the present invention, after the step of matching the behavior data of the user with a pre-configured behavior pattern, further comprising:
discarding, when there is a behavior pattern matching the behavior data, association data of the saved other behavior pattern with the behavior data, the association data comprising a sum Δl of the first difference and the second difference 1 +Δl 2 。
Preferably, after the step of matching the behavior data of the user with a pre-configured behavior pattern, the method further comprises:
when there is no behavior pattern matching the behavior data, summing the first difference and the second difference Deltal 1 +Δl 2 A behavior pattern smaller than a preset difference threshold is determined as a similar behavior pattern of the behavior data;
the similar behavior patterns are stored in association with the behavior data;
Discarding associated data of other behavior patterns than the similar behavior pattern with the behavior data.
Specifically, in the above embodiment, when there is no behavior pattern matching with the behavior dataAdding one or more first differences to the sum Deltal of the second differences 1 +Δl 2 And determining the behavior patterns smaller than the preset difference threshold as similar behavior patterns of the behavior data, so that the electronic commerce system can determine the matched behavior patterns from the similar behavior patterns according to the behavior data of the subsequent user in the electronic commerce system.
Preferably, the step of storing the similar behavior pattern in association with the behavior data further comprises storing a list of predicted products of the similar behavior pattern in association with the behavior data;
after the step of storing the similar behavior pattern in association with the behavior data, the method further comprises:
monitoring the ordering purchasing behavior of a user;
when the commodity purchased by the user is in the predicted commodity list of any similar behavior mode, the steps of acquiring the behavior data of the user in the electronic commerce system within the target time period of the user and matching the behavior data of the user with the pre-configured behavior mode are re-executed.
Preferably, the sum Deltal of the first difference and the second difference can be calculated 1 +Δl 2 And taking the reciprocal or the opposite number of the predicted commodity list in the similar behavior mode as the matching degree of the similar behavior mode and the behavior data, when the matching degree is smaller, executing random pushing on the movable commodity in the predicted commodity list in the similar behavior mode, and when the matching degree is larger, preferentially pushing the movable commodity which is ranked ahead in the predicted commodity list.
A second aspect of the present invention proposes an electronic commerce system comprising:
the system comprises a behavior data acquisition module, a behavior data processing module and a behavior data processing module, wherein the behavior data acquisition module is used for acquiring behavior data in an electronic commerce system in a user target time period, the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
the behavior pattern matching module is used for matching the behavior data of the user with a pre-configured behavior pattern;
the commodity sequence acquisition module is used for acquiring a target commodity sequence corresponding to the behavior mode when the behavior data of the user are matched with any behavior mode, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior mode;
the shopping demand prediction module is used for predicting the shopping demand of the user based on the target commodity sequence;
And the push information generation module is used for generating push information according to the shopping requirements.
Specifically, the information pushing method based on user demand prediction provided by the invention is realized by executing a computer program by a server running an electronic commerce system or other computers connected with a database storing electronic commerce system data. In some embodiments, a specific program execution period may be configured to periodically run the computer program to implement the above information pushing method, or be triggered to execute the computer program to implement the above information pushing method according to a specific behavior of a user or an operation and maintenance person. In the step of acquiring behavior data in the electronic commerce system within a target time period of a user, the current time for determining the target time period is the time for realizing the information pushing method by running the computer program each time.
The behavior data of the user in the electronic commerce system comprises, but is not limited to, the behavior of the user for browsing, clicking, searching, collecting, purchasing or purchasing goods in the electronic commerce system, and the electronic commerce system stores the time of the user for generating the behavior, the behavior itself and the corresponding goods information in a database. Specific events that occur in real life by users create specific persistent shopping demands, and the merchandise corresponding to these shopping demands is strongly associated with these events, and the purchased merchandise is strongly associated with the occurrence of the events. Thus, in the technical solution of the present invention, the pre-configured behavior pattern is a set of shopping behaviors that the user exhibits on the e-commerce platform when these specific events occur in real life. The target commodity sequence corresponding to the behavior mode is a sequence formed by commodities which the user needs to purchase when the user generates the specific events in real life. Ordered sequence of items refers to the purchase of these items in the sequence of items being time-ordered in the corresponding pattern of behavior.
For convenience of understanding, in the technical solution of the present invention, the term "commodity sequence", "subsequence" and "commodity list" refer to a set of multiple commodities, where "sequence" refers to that commodities in the commodity set are arranged according to a specific time sequence, and "list" does not limit the arrangement sequence of the commodities, and although "list" necessarily has a certain arrangement sequence in the actual program implementation, in the matching process of some commodity sets of the present invention, the influence of the arrangement sequence of the commodities in "list" on the matching result is not considered.
Preferably, the behavior pattern matching module includes:
the shopping sequence and the focused commodity list generation module are used for generating a shopping sequence and a focused commodity list corresponding to the behavior data, wherein the shopping sequence is an ordered commodity sequence formed by commodities ordered and purchased by a user in an electronic commerce system and the purchase time of the commodities in the target time period, and the focused commodity list is an unordered commodity sequence formed by commodities focused by the user but not ordered and purchased in the electronic commerce system in the target time period;
the candidate commodity sequence acquisition module is used for sequentially reading commodity sequences corresponding to each pre-configured behavior mode from the database to serve as candidate commodity sequences;
A first subsequence judging module, configured to judge whether the candidate commodity sequence includes a first subsequence that is a subset of the shopping sequence at the same time, where the first subsequence is a consecutive ordered subsequence in the candidate commodity sequence;
a second subsequence determining module, configured to determine, when the candidate commodity sequence includes the first subsequence, whether the commodity sequence includes a second subsequence that is simultaneously a subset of the commodity list of interest, where the second subsequence is a sequential ordered subsequence in the candidate commodity sequence;
the behavior pattern matching determining module is used for determining that the behavior data is matched with the corresponding behavior pattern when the candidate commodity sequence contains the second subsequence;
and the target commodity sequence determining module is used for determining the candidate commodity sequence as a target commodity sequence.
In the technical solution of the above embodiment, the commodities that the user pays attention to in the electronic commerce system but does not pay attention to purchase are commodities that the user pays attention to in the time period determined according to the behavior of browsing, clicking, searching, collecting or purchasing the commodities in the electronic commerce system.
In the step of determining whether a first subsequence that is simultaneously a subset of the shopping sequence is included in the candidate merchandise sequence, the first subsequence may be a continuous ordered subsequence or a discontinuous ordered subsequence in the shopping sequence. The first subsequence is a continuous ordered subsequence in the candidate commodity sequence, specifically, commodities in the first subsequence are all present in the candidate commodity sequence, the sequence of the commodities in the candidate commodity sequence is the same as the sequence in the first subsequence, the commodities in the first subsequence are continuous in the candidate commodity sequence, and no other commodities exist between every two commodities. Similarly, the first subsequence is a subset of the shopping sequence, i.e., the items in the first subsequence are all present in the shopping sequence, in the same order as in the first subsequence in the shopping sequence, but may be discontinuous in the shopping sequence.
Likewise, in the step of determining whether the commodity sequence includes a second subsequence that is also a subset of the list of commodities of interest, the second subsequence may likewise be a continuous ordered subsequence or a discontinuous ordered subsequence in the shopping sequence, i.e., all commodities in the second subsequence are present in the candidate commodity sequence, the order of the commodities in the candidate commodity sequence is the same as that in the second subsequence, and the commodities in the second subsequence are continuous in the candidate commodity sequence, with no other commodity present therebetween. As in the case of the first sub-sequence in the shopping sequence, the second sub-sequence is also a subset of the list of items of interest, i.e. the items in the second sub-sequence are all present in the list of items of interest and may be discontinuous in the list of items of interest, except that the list of items of interest is unordered, i.e. the order of the items in the second sub-sequence in the list of items of interest may be the same or different.
It should be appreciated that the length of the first or second sub-sequence should be less than the candidate merchandise sequence, and that the behavior data is determined to be mismatched with the corresponding behavior pattern when the length of the first or second sub-sequence is equal to the candidate merchandise sub-sequence.
Preferably, the first subsequence determining module includes:
a first intersection item determination module for determining a first intersection item of the candidate item sequence and the shopping sequence;
a third subsequence construction module, configured to construct more than one third subsequence according to the order of the first intersection commodity in the candidate commodity sequence, where the third subsequence is a continuous ordered subsequence in the candidate commodity sequence;
a fourth subsequence construction module for constructing a fourth subsequence according to the order of the first intersection commodity in the shopping sequence;
a maximum continuous subsequence determining module, configured to determine a maximum continuous subsequence that satisfies the same commodity order as the fourth subsequence in the third subsequence;
the first matching length threshold judging module is used for judging whether the length of the maximum continuous subsequence is larger than a preset matching length threshold or not;
and the first subsequence determining module is used for determining the largest continuous subsequence with the length larger than the preset matching length threshold value as the first subsequence when the length of the largest continuous subsequence is larger than the preset matching length threshold value, and determining that the candidate commodity sequence contains the first subsequence.
In the step of determining the first intersection commodity of the candidate commodity sequence and the shopping sequence, when the intersection commodity does not exist in the candidate commodity sequence and the shopping sequence, the first subsequence is not included in the candidate commodity sequence.
In the step of constructing one or more third subsequences in the order of the first intersection item in the candidate item sequence, the "one or more" includes one, i.e., when the first intersection item forms only one continuous subsequence in the candidate item sequence, then the third subsequence is one, and when the first intersection item is separated into a plurality of continuous subsequences in the candidate item sequence, then the third subsequence is a plurality. When the third subsequences are multiple, in the step of determining a maximum continuous subsequence which meets the commodity order same as the fourth subsequence in the third subsequences, determining a maximum continuous subsequence in each third subsequence, and judging whether the lengths of the maximum continuous subsequences are larger than a preset matching length threshold value or not.
Preferably, the second subsequence determining module includes:
A second intersection item determination module for determining a second intersection item of the candidate item sequence and the attention item list;
a fifth subsequence construction module, configured to construct more than one fifth subsequence according to the order of the second intersection commodity in the candidate commodity sequence, where the fifth subsequence is a continuous ordered subsequence in the candidate commodity sequence;
the second matching length threshold judging module is used for judging whether the length of the fifth subsequence is larger than a preset matching length threshold or not;
and the second subsequence determining module is used for determining a fifth subsequence with the length larger than a preset matching length threshold value as the second subsequence when the length of the fifth subsequence is larger than the preset matching length threshold value, and determining that the candidate commodity sequence contains the second subsequence.
Also, in the step of determining the second intersection commodity of the candidate commodity sequence and the attention commodity list, when the intersection commodity does not exist in the candidate commodity sequence and the attention commodity list, it is determined that the second subsequence is not included in the candidate commodity sequence.
In the step of constructing one or more fifth subsequences in the order of the second intersection item in the candidate item sequence, the "one or more" includes one, i.e., when the second intersection item forms only one continuous subsequence in the candidate item sequence, the fifth subsequence is one, and when the second intersection item is separated into a plurality of continuous subsequences in the candidate item sequence, the fifth subsequence is a plurality. When the number of the fifth subsequences is plural, in the step of judging whether the length of the fifth subsequence is larger than the preset matching length threshold, judging whether the lengths of the fifth subsequences are larger than the preset matching length threshold is performed on all the fifth subsequences.
Preferably, the shopping demand prediction module includes:
the predicted commodity list determining module is used for determining a predicted commodity list in the target commodity sequence;
the movable commodity judging module is used for judging whether the predicted commodity list contains movable commodities or not;
and the pushed commodity determining module is used for determining the movable commodity as a pushed commodity when the predicted commodity list contains the movable commodity.
Specifically, the active commodity refers to a commodity currently provided with various preferential activities in the electronic commerce system, wherein the preferential activities include, but are not limited to, sales promotion activities, group purchase activities, point activities and the like. Only when the commodity has a preferential activity, the corresponding push information can be focused by the user, so in the technical scheme of the embodiment, only the active commodity in the predicted commodity list is determined to be the push commodity, namely, the corresponding push information is generated and sent to the inbox of the user.
Preferably, the predicted commodity list determining module includes:
the terminal commodity determining module is used for determining the last commodity of the first subsequence corresponding to the target commodity sequence;
a prediction boundary determining module, configured to determine a position number of the last commodity in the target commodity sequence as a prediction boundary;
And the list commodity adding module is used for adding commodities with position numbers larger than the prediction boundary in the target commodity sequence to the predicted commodity list.
In the technical scheme of the invention, for each commodity sequence, the positions of the commodities in the commodity sequence are numbered respectively, for example, arabic numerals can be used as the numbers of the commodities in the commodity sequence. The same commodity is individually numbered in different commodity sequences, for example, the number of the commodity in the target commodity sequence is often different from the number of the commodity in the first subsequence corresponding to the commodity. The position numbers may be used to identify the order of the items in the respective item sequences.
Preferably, the electronic commerce system further comprises:
the first difference value recording module is used for recording a first difference value between the matching length threshold and the length of the maximum continuous subsequence when the length of the maximum continuous subsequence is smaller than a preset matching length threshold:
Δl 1 ＝l max -l 0 ，
wherein l max For the length of the largest contiguous subsequence, l 0 A threshold value for the matching length;
a second difference value recording module, configured to record a second difference value between the matching length threshold and the length of the fifth subsequence when the length of the fifth subsequence is less than a preset matching length threshold:
Δl 2 ＝l 5 -l 0 ，
Wherein l 5 For the length of the fifth subsequence
A first data association holding module for adding the first difference value and the second difference value deltal 1 +Δl 2 And storing the behavior data in association with the corresponding behavior mode.
In some embodiments of the present invention, after the step of matching the behavior data of the user with a pre-configured behavior pattern, further comprising:
discarding, when there is a behavior pattern matching the behavior data, association data of the saved other behavior pattern with the behavior data, the association data comprising a sum Δl of the first difference and the second difference 1 +Δl 2 。
Preferably, the electronic commerce system further comprises:
a similar behavior pattern determining module for adding the sum Deltal of the first difference and the second difference when there is no behavior pattern matching the behavior data 1 +Δl 2 A behavior pattern smaller than a preset difference threshold is determined as a similar behavior pattern of the behavior data;
the second data association storage module is used for associating and storing the similar behavior patterns with the behavior data;
and the associated data discarding module is used for discarding associated data of other behavior patterns except the similar behavior pattern and the behavior data.
Specifically, in the above embodiment, when there is no behavior pattern matching the behavior data, one or more of the first differences and the sum Δl of the second differences 1 +Δl 2 And determining the behavior patterns smaller than the preset difference threshold as similar behavior patterns of the behavior data, so that the electronic commerce system can determine the matched behavior patterns from the similar behavior patterns according to the behavior data of the subsequent user in the electronic commerce system.
Preferably, the second data association storage module is further configured to store a predicted merchandise list of the similar behavior pattern in association with the behavior data, and the electronic commerce system further includes:
the purchasing behavior monitoring module is used for monitoring the ordering purchasing behavior of the user;
and the circulation execution module is used for re-executing the steps of acquiring the behavior data in the electronic commerce system in the target time period of the user and matching the behavior data of the user with the pre-configured behavior pattern when the commodity purchased by the user through ordering exists in the predicted commodity list of any similar behavior pattern.
Preferably, the sum Deltal of the first difference and the second difference can be calculated 1 +Δl 2 And taking the reciprocal or the opposite number of the predicted commodity list in the similar behavior mode as the matching degree of the similar behavior mode and the behavior data, when the matching degree is smaller, executing random pushing on the movable commodity in the predicted commodity list in the similar behavior mode, and when the matching degree is larger, preferentially pushing the movable commodity which is ranked ahead in the predicted commodity list.
It should be noted that in this document relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Embodiments in accordance with the present invention, as described above, are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention and various modifications as are suited to the particular use contemplated. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. An information pushing method based on user demand prediction is characterized by comprising the following steps:
acquiring behavior data in an electronic commerce system in a user target time period, wherein the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
matching the behavior data of the user with a pre-configured behavior pattern;
when the behavior data of the user are matched with any behavior pattern, a target commodity sequence corresponding to the behavior pattern is obtained, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior pattern;
predicting shopping demands of users based on the target commodity sequence;
and generating push information according to the shopping demand.
2. The information pushing method according to claim 1, wherein the step of matching the behavior data of the user with a pre-configured behavior pattern specifically comprises:
generating a shopping sequence corresponding to the behavior data and a focused commodity list, wherein the shopping sequence is an ordered commodity sequence formed by commodities ordered and purchased by a user in an electronic commerce system in the target time period and the purchase time of the commodities, and the focused commodity list is an unordered commodity sequence formed by commodities focused by the user but not ordered and purchased in the electronic commerce system in the target time period;
Sequentially reading commodity sequences corresponding to each pre-configured behavior mode from a database to serve as candidate commodity sequences;
judging whether the candidate commodity sequence contains a first subsequence which is simultaneously a subset of the shopping sequence or not, wherein the first subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the first subsequence is included in the candidate commodity sequence, judging whether a second subsequence which is simultaneously a subset of the commodity list of interest is included in the commodity sequence or not, wherein the second subsequence is a continuous ordered subsequence in the candidate commodity sequence;
when the candidate commodity sequence contains the second subsequence, determining that the behavior data is matched with a corresponding behavior pattern;
and determining the candidate commodity sequence as a target commodity sequence.
3. The information pushing method according to claim 2, wherein the step of determining whether the candidate commodity sequence includes a first sub-sequence that is simultaneously a subset of the shopping sequence specifically includes:
determining a first intersection item of the candidate item sequence and the shopping sequence;
constructing more than one third subsequence according to the sequence of the first intersection commodity in the candidate commodity sequence, wherein the third subsequence is a continuous ordered subsequence in the candidate commodity sequence;
Constructing a fourth subsequence according to the order of the first intersection commodity in the shopping sequence;
determining a largest continuous subsequence which meets the commodity order same as that of the fourth subsequence in the third subsequence;
judging whether the length of the maximum continuous subsequence is larger than a preset matching length threshold value or not;
when the length of the maximum continuous subsequence is greater than a preset matching length threshold, determining the maximum continuous subsequence with the length greater than the matching length threshold as the first subsequence;
determining that the candidate commodity sequence comprises the first subsequence.
4. The information pushing method according to claim 2, wherein the step of determining whether the commodity sequence includes a second subsequence that is also a subset of the commodity list of interest specifically includes:
determining a second intersection commodity of the candidate commodity sequence and the attention commodity list;
constructing more than one fifth subsequence according to the sequence of the second intersection commodity in the candidate commodity sequence, wherein the fifth subsequence is a continuous ordered subsequence in the candidate commodity sequence;
judging whether the length of the fifth subsequence is larger than a preset matching length threshold value;
When the length of the fifth subsequence is larger than a preset matching length threshold value, determining the fifth subsequence with the length larger than the matching length threshold value as the second subsequence;
determining that the candidate commodity sequence comprises the second subsequence.
5. The information pushing method according to claim 2, wherein the step of predicting shopping needs of the user based on the target commodity sequence specifically includes:
determining a predicted merchandise list in the target merchandise sequence;
judging whether the predicted commodity list contains movable commodities or not;
and when the predicted commodity list contains the active commodity, determining the active commodity as a pushed commodity.
6. The information pushing method according to claim 5, wherein the step of determining a predicted merchandise list in the target merchandise sequence specifically includes:
determining the last commodity of the first subsequence corresponding to the target commodity sequence;
determining the position number of the last commodity in the target commodity sequence as a prediction boundary;
and adding the commodity with the position number larger than the prediction boundary in the target commodity sequence to the predicted commodity list.
7. The information pushing method according to claim 6, further comprising, after the step of determining whether the length of the largest consecutive sub-sequence is greater than a preset matching length threshold:
when the length of the maximum continuous subsequence is smaller than a preset matching length threshold, recording a first difference value between the matching length threshold and the length of the maximum continuous subsequence:
Δl 1 ＝l max -l 0 ，
wherein l max For the length of the largest contiguous subsequence, l 0 A threshold value for the matching length;
after the step of determining whether the length of the fifth sub-sequence is greater than the preset matching length threshold, the method further includes:
when the length of the fifth subsequence is smaller than a preset matching length threshold, recording a second difference value between the matching length threshold and the length of the fifth subsequence:
Δl 2 ＝l 5 -l 0 ，
wherein l 5 For the length of the fifth subsequence
Adding Deltal of the first difference and the second difference 1 +Δl 2 And storing the behavior data in association with the corresponding behavior mode.
8. The information pushing method according to claim 7, further comprising, after the step of matching the behavior data of the user with a pre-configured behavior pattern:
When there is no behavior pattern matching the behavior data, summing the first difference and the second difference Deltal 1 +Δl 2 A behavior pattern smaller than a preset difference threshold is determined as a similar behavior pattern of the behavior data;
the similar behavior patterns are stored in association with the behavior data;
discarding associated data of other behavior patterns than the similar behavior pattern with the behavior data.
9. The information pushing method according to claim 8, wherein the step of storing the similar behavior patterns in association with the behavior data further comprises storing a predicted merchandise list of the similar behavior patterns in association with the behavior data;
after the step of storing the similar behavior pattern in association with the behavior data, the method further comprises:
monitoring the ordering purchasing behavior of a user;
when the commodity purchased by the user is in the predicted commodity list of any similar behavior mode, the steps of acquiring the behavior data of the user in the electronic commerce system within the target time period of the user and matching the behavior data of the user with the pre-configured behavior mode are re-executed.
10. An electronic commerce system, comprising:
The system comprises a behavior data acquisition module, a behavior data processing module and a behavior data processing module, wherein the behavior data acquisition module is used for acquiring behavior data in an electronic commerce system in a user target time period, the target time period is a time period taking the current time as the end time, and the time length is a preset user behavior data statistical duration;
the behavior pattern matching module is used for matching the behavior data of the user with a pre-configured behavior pattern;
the commodity sequence acquisition module is used for acquiring a target commodity sequence corresponding to the behavior mode when the behavior data of the user are matched with any behavior mode, wherein the target commodity sequence is an ordered commodity sequence corresponding to the behavior mode;
the shopping demand prediction module is used for predicting the shopping demand of the user based on the target commodity sequence; and the push information generation module is used for generating push information according to the shopping requirements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461097.1A CN117273863B (en) | 2023-11-03 | 2023-11-03 | Information pushing method based on user demand prediction and electronic commerce system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461097.1A CN117273863B (en) | 2023-11-03 | 2023-11-03 | Information pushing method based on user demand prediction and electronic commerce system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117273863A true CN117273863A (en) | 2023-12-22 |
| CN117273863B CN117273863B (en) | 2024-05-28 |
Family
ID=89212601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311461097.1A Active CN117273863B (en) | 2023-11-03 | 2023-11-03 | Information pushing method based on user demand prediction and electronic commerce system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273863B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190012683A1 (en) * | 2017-07-10 | 2019-01-10 | Sk Planet Co., Ltd. | Method for predicting purchase probability based on behavior sequence of user and apparatus for the same |
| CN112001776A (en) * | 2020-08-24 | 2020-11-27 | 上海风秩科技有限公司 | Service information pushing method and device, storage medium and electronic equipment |
| KR20220005328A (en) * | 2020-07-06 | 2022-01-13 | 아주대학교산학협력단 | Apparatus and method for recommending product based on user behavior pattern and for forecasting user preference for recommended product |
| CN114387066A (en) * | 2022-01-17 | 2022-04-22 | 携程计算机技术（上海）有限公司 | Commodity information transmission method, system, electronic device and storage medium |
| CN115204985A (en) * | 2022-07-27 | 2022-10-18 | 清华大学 | Shopping behavior prediction method, device, equipment and storage medium |
| CN115659055A (en) * | 2022-12-27 | 2023-01-31 | 易商惠众(北京)科技有限公司 | Commodity recommendation method, system, equipment and storage medium based on event sequence |
| CN116894692A (en) * | 2023-09-11 | 2023-10-17 | 北京亿家老小科技有限公司 | Method and system for analyzing and monitoring potential demands of online network sales users |
-
2023
- 2023-11-03 CN CN202311461097.1A patent/CN117273863B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190012683A1 (en) * | 2017-07-10 | 2019-01-10 | Sk Planet Co., Ltd. | Method for predicting purchase probability based on behavior sequence of user and apparatus for the same |
| KR20220005328A (en) * | 2020-07-06 | 2022-01-13 | 아주대학교산학협력단 | Apparatus and method for recommending product based on user behavior pattern and for forecasting user preference for recommended product |
| CN112001776A (en) * | 2020-08-24 | 2020-11-27 | 上海风秩科技有限公司 | Service information pushing method and device, storage medium and electronic equipment |
| CN114387066A (en) * | 2022-01-17 | 2022-04-22 | 携程计算机技术（上海）有限公司 | Commodity information transmission method, system, electronic device and storage medium |
| CN115204985A (en) * | 2022-07-27 | 2022-10-18 | 清华大学 | Shopping behavior prediction method, device, equipment and storage medium |
| CN115659055A (en) * | 2022-12-27 | 2023-01-31 | 易商惠众(北京)科技有限公司 | Commodity recommendation method, system, equipment and storage medium based on event sequence |
| CN116894692A (en) * | 2023-09-11 | 2023-10-17 | 北京亿家老小科技有限公司 | Method and system for analyzing and monitoring potential demands of online network sales users |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117273863B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11301761B2 (en) | Behavioral prediction for targeted end users | |
| CN107590675B (en) | User shopping behavior identification method based on big data, storage device and mobile terminal | |
| JP4753616B2 (en) | Product information provision system | |
| KR100961783B1 (en) | Apparatus and method for presenting personalized goods and vendors based on artificial intelligence, and recording medium thereof | |
| JP6744882B2 (en) | Action pattern search system and action pattern search method | |
| US20120303412A1 (en) | Price and model prediction system and method | |
| US10706438B2 (en) | Systems and methods for generating and recommending promotions in a design matrix | |
| EP1723596A1 (en) | System for individualized customer interaction | |
| CN102609869A (en) | Commodity purchasing system and method | |
| Kabasakal | Customer segmentation based on recency frequency monetary model: A case study in E-retailing | |
| Hemalatha | Market basket analysis–a data mining application in Indian retailing | |
| CN117350766A (en) | Data processing method, system and storage medium based on private domain e-commerce platform | |
| Prinzie et al. | Predicting home-appliance acquisition sequences: Markov/Markov for discrimination and survival analysis for modeling sequential information in NPTB models | |
| US20220414579A1 (en) | Salesperson evaluation apparatus, salesperson evaluation method, and salesperson evaluation program | |
| CN115578163A (en) | Personalized pushing method and system for combined commodity information | |
| JP2019145043A (en) | Data management device and data management system | |
| CN103597485A (en) | Pattern extraction device and method | |
| CN117745349A (en) | Personalized coupon pushing method and system based on user characteristics | |
| CN115564531A (en) | Commodity combination recommendation method and device, equipment, medium and product thereof | |
| CN113554455B (en) | Store commodity analysis method, device and storage medium based on artificial intelligence | |
| CN113592539B (en) | Store order trend prediction method and device based on artificial intelligence and storage medium | |
| CN111461846B (en) | Shopping record analysis feedback system and method thereof | |
| CN117273863B (en) | Information pushing method based on user demand prediction and electronic commerce system | |
| Zeng et al. | Location-aware real-time recommender systems for brick-and-mortar retailers | |
| CN111177657B (en) | Demand determining method, system, electronic device and storage medium |
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 |