CN112650743B - Funnel data analysis method, system, electronic equipment and storage medium - Google Patents
Funnel data analysis method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112650743B CN112650743B CN202011614804.2A CN202011614804A CN112650743B CN 112650743 B CN112650743 B CN 112650743B CN 202011614804 A CN202011614804 A CN 202011614804A CN 112650743 B CN112650743 B CN 112650743B
- Authority
- CN
- China
- Prior art keywords
- funnel
- funnel step
- matching
- user
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007405 data analysis Methods 0.000 title claims abstract description 27
- 230000006399 behavior Effects 0.000 claims abstract description 215
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 230000014509 gene expression Effects 0.000 claims description 48
- 230000009471 action Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 13
- 238000012545 processing Methods 0.000 abstract description 12
- 230000007246 mechanism Effects 0.000 abstract description 11
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 238000006243 chemical reaction Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 7
- 230000002776 aggregation Effects 0.000 description 6
- 238000004220 aggregation Methods 0.000 description 6
- 238000007792 addition Methods 0.000 description 4
- 238000005192 partition Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2453—Query optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of data analysis, in particular to a funnel data analysis method, a system, electronic equipment and a storage medium, wherein the user behavior log data is divided into a plurality of time periods according to time, an elastic variable mechanism is supported, and only the time granularity is required to be adjusted during data processing, so that the user behaviors in the same time granularity value are unordered, and the user behaviors with different time granularity values are ordered, thereby enhancing the analysis flexibility; and counting the behavior sets in each time period, wherein one user corresponds to only one piece of data in the same time period, so that the data quantity to be processed is greatly reduced, the data is traversed once in the processes of data processing and query, the behavior sets of the user in each time period can be obtained, the behavior sets in each time period are respectively matched with the funnel step sets and then combined, the funnel step matched total set of all users can be obtained, a complicated Map/Reduce mechanism is avoided, and the query speed is accelerated.
Description
Technical Field
The embodiment of the application relates to the technical field of data analysis, in particular to a funnel data analysis method, a funnel data analysis system, electronic equipment and a storage medium.
Background
With the development of internet technology, especially the popularization of mobile internet, internet enterprises face explosive growth of mass data, and rapid and efficient data analysis is particularly important for rapid adjustment of product positioning and improvement of product smell. Funnel model analysis is a common means of user behavior analysis in the data analysis work of internet products. An effective funnel model can generally be divided into several parts, including multiple funnel steps, conversion period, time window, filtering conditions, user population, etc. The results of the analysis were: and in a certain time window, users meeting the filtering condition among users in a specific group finish the user number of each funnel step and the conversion rate of each step in the conversion period.
The funnel model can be mainly divided into an ordered funnel model and an unordered funnel model, wherein the ordered funnel model requires a user to sequentially complete appointed behaviors in a certain conversion period; the unordered funnel model does not require a time sequence of actions as long as the user completes a specified action within a certain conversion period. The prior art scheme generally adopts Map/Reduce batch processing mechanism query based on Hadoop, and for each funnel step, query statistics is required to be carried out on all user behavior data, and then filtering, synthesizing, summarizing and the like are carried out on the query results according to the need. When the funnel model is established to analyze the user behavior, a process of modeling needs to be initiated for a plurality of times, and a complicated Map/Reduce mechanism is added, so that the process of generating the funnel model is quite slow under the condition of massive data sets, and flexible analysis cannot be achieved.
Disclosure of Invention
The embodiment of the invention aims to provide a funnel data analysis method, a system, electronic equipment and a storage medium, which solve the problems that in the prior art, when user behaviors are analyzed, a one-time modeling process needs to initiate multiple queries, and under the condition of a massive data set, the process of generating a funnel model is quite slow and flexible analysis cannot be realized.
To solve the above technical problem, in a first aspect, an embodiment of the present invention provides a funnel data analysis method, including:
Determining user behaviors of a user in different time periods to form a behavior set corresponding to the user in each time period;
respectively matching a behavior set corresponding to each time period of a user with a funnel step set by taking the time period as a unit to obtain a behavior matching result of each time period;
And merging behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users.
In a second aspect, an embodiment of the present invention provides a funnel data analysis system, including:
The behavior extraction module is used for determining the behaviors of the user in different time periods to form a behavior set corresponding to each time period of the user;
the funnel step matching module is used for respectively matching the behavior set corresponding to each time period of the user with the funnel step set by taking the time period as a unit so as to obtain a behavior matching result of each time period;
And the funnel step analysis module is used for merging the behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the funnel data analysis method according to an embodiment of the first aspect of the invention.
In a fourth aspect, embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the funnel data analysis method according to the embodiments of the first aspect of the present invention.
Compared with the related art, the embodiment of the invention supports an elastic variable mechanism by dividing the user behavior log data into a plurality of time periods according to time, and only needs to adjust the time granularity during data processing, so that the user behaviors in the same time granularity value are unordered, and the user behaviors with different time granularity values are ordered, thereby enhancing the analysis flexibility; and counting the behavior sets in each time period, wherein one user corresponds to only one piece of data in the same time period, so that the data quantity to be processed is greatly reduced, the data is traversed once in the processes of data processing and query, the behavior sets of the user in each time period can be obtained, the behavior sets in each time period are respectively matched with the funnel step sets and then combined, the funnel step matched total set of each user can be obtained, and the number of users matched by any funnel step in the funnel step sets can be further obtained according to the complicated Map/Reduce mechanism, so that the query speed is accelerated.
In addition, the determining the user behavior of the user in different time periods to form a behavior set corresponding to the user in each time period specifically includes:
Receiving user behavior log data reported by different buried points, wherein the user behavior log data comprises user behavior path information;
partitioning the user behavior log data according to preset time periods to obtain user behavior log data of each time period, and extracting user behaviors in the user behavior log data of each time period to form a behavior set corresponding to each time period of a user.
The user behavior log data is divided into a plurality of time periods according to time, an elastic variable mechanism is supported, and the time granularity is only required to be adjusted when the data is processed, so that the user behaviors in the same time granularity value are unordered, and the user behaviors with different time granularity values are ordered, and the analysis flexibility is enhanced.
In addition, after receiving the user behavior log data reported by different buried points, the method further comprises the following steps:
cleaning the user behavior path information to remove repeated data and illegal data;
And extracting the unique identifier of each user action in the user action path information, uniformly encoding the unique identifiers according to a preset encoding rule, and converting the encoded unique identifiers into a preset data format.
By unifying the data content formats of massive user behaviors, occupied storage space is reduced.
In addition, the step of matching the behavior set corresponding to each time period by the user with the funnel step set by taking the time period as a unit to obtain a behavior matching result of each time period specifically comprises the following steps:
Respectively matching a behavior set corresponding to each time period of a user with a funnel step set to obtain a behavior matching result, wherein the behavior matching result is used for orderly recording whether each funnel step in the funnel step set has a funnel step matching sub-set of matching items in the corresponding time period, elements in the funnel step matching sub-set are in one-to-one correspondence with the funnel steps in the funnel step set, and the elements in the funnel step matching sub-set are in one-to-one correspondence with the funnel steps in the funnel step set,
If any funnel step in the funnel step set is judged to have a matching item in the behavior set, marking element values at corresponding positions in the funnel step matching sub-set as a first expression according to a preset rule;
And for any funnel step in the funnel step set, if no matching item is judged in the behavior set, marking the element value at the corresponding position in the funnel step matching sub-set as a second expression according to a preset rule.
And recording whether the funnel steps have matching items or not according to the funnel step sequence in the funnel step set through a unified expression, so that follow-up statistics is convenient.
In addition, the first expression and the second expression are binary expressions, wherein,
If the matching item is judged to exist in the behavior set, marking the element value at the corresponding position in the funnel step matching sub-set as 1;
If no matching item is judged in the behavior set, the element value at the corresponding position in the funnel step matching sub-set is recorded as 0.
In addition, the step of merging the behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user specifically comprises the following steps:
sequencing all the funnel step matching sub-sets according to the sequence of time periods;
Deleting useless matching sub-sets of the funnel steps:
if judging that the element value at the position corresponding to the first funnel step of the funnel step set is marked as a second expression in the first funnel step matching sub-set, discarding the first funnel step matching sub-set;
In the adjacent two funnel step matching sub-sets, if all funnel steps marked as first expressions in the former funnel step matching sub-set are judged to be marked as first expressions in the latter funnel step matching sub-set, deleting the former funnel step matching sub-set;
Orderly combining all the remaining funnel step matching sub-sets to obtain a funnel step matching total set for orderly recording whether each funnel step in the funnel step set has a matching item, wherein elements in the funnel step matching total set are in one-to-one correspondence with the funnel steps in the funnel step set,
If a certain funnel step in the funnel step matching sub-set is judged to be marked as a first expression in any funnel step matching sub-set, marking a corresponding funnel step as a first expression in the funnel step matching total set;
And if judging that a certain funnel step in the funnel step matching sub-set is marked as a second expression in all the funnel step matching sub-sets, marking the corresponding funnel step as the second expression in the funnel step matching total set.
In addition, the merging the behavior matching results of each user in different time periods specifically includes:
Matching the corresponding element values in the sub-set in the funnel step of each user in different time periods by bit or operation;
The determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users specifically comprises the following steps:
and respectively performing arithmetic addition operation on corresponding element values in the funnel step matching total set of all users to obtain the number of users matched by any funnel step in the funnel step set.
Through binary expression, when funnel step matching subset combination and funnel step matching total combination of all users are aggregated, accurate combination and aggregation statistics can be realized only through simple bitwise or arithmetic addition operation, and the calculation efficiency is improved.
Drawings
One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which the figures of the drawings are not to be taken in a limiting sense, unless otherwise indicated.
FIG. 1 is a flow chart of a method of funnel data analysis according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a pretreatment step according to an embodiment of the present invention;
FIG. 3 is a block diagram of a funnel data analysis system according to a second embodiment of the present invention;
Fig. 4 is a block diagram of a server according to a third embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings. However, those of ordinary skill in the art will understand that in various embodiments of the present application, numerous technical details have been set forth in order to provide a better understanding of the present application. The claimed application may be practiced without these specific details and with various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not be construed as limiting the specific implementation of the present application, and the embodiments can be mutually combined and referred to without contradiction.
The terms "first", "second" in embodiments of the application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the application, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a system, article, or apparatus that comprises a list of elements is not limited to only those elements or units listed but may alternatively include other elements not listed or inherent to such article, or apparatus. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
At present, a funnel analysis method is generally adopted to analyze user behavior data so as to monitor whether a user converts according to predefined behaviors and search for optimizable behaviors in each conversion process. Generally, user actions are performed according to a preset action sequence, for example: the method comprises the following steps of: the first behavior A, the second behavior B, the third behavior C, the fourth behavior D, the M behavior X, and M are greater than or equal to 5. For example, if the application scenario is that the user operates a shopping webpage, A is to purchase goods, B is to add shopping carts, C is to settle accounts of the shopping carts, D is to check order information, and X is to complete payment. The number of users operating shopping web pages is generally large, and each user performs differently, for example: the user may perform only a portion or all of his actions multiple times in the defined order of actions. Using these user-performed behaviors, the user behavior data is analyzed by the following steps to determine the conversion rate of the previous behavior into the next behavior.
Firstly, acquiring the total number of users operating shopping webpages by the users and executing data of each user behavior; then, acquiring a group of longest execution behaviors in a plurality of behaviors executed by each user; then, counting the total number of users executing the first action, the total number of users of the second action, and the total number of users of the Mth action X aiming at the longest execution action of all the users; finally, the ratio of the total number of users in the next action to the total number of users in the previous action is taken as the conversion rate of the previous action to the next action, and the loss rate is 1 minus the conversion rate difference. For example, the total number of users performing a behavior is 1000, the total number of users performing B behavior is 600, the total number of users performing C behavior is 450, the conversion rate of a behavior to B behavior is 60%, the conversion rate of B behavior to C behavior is 75%, and the conversion rate of C behavior to D behavior is 50%.
In the prior art, map/Reduce batch processing mechanism query based on Hadoop is generally adopted, query statistics is needed to be carried out on all user behavior data aiming at each funnel step, then filtering, synthesizing, summarizing and the like are carried out on query results according to requirements, and under the condition of a massive data set, the funnel model generation process is quite slow and flexible analysis cannot be achieved.
Therefore, the embodiment of the invention divides the user behavior log data into a plurality of time periods according to time, and for the behavior sets in each time period, one user only corresponds to one piece of data in the same time period, so that the data quantity to be processed is greatly reduced, the data is traversed once in the processes of data processing and query, the behavior sets of the user in each time period can be obtained, the behavior sets in each time period are respectively matched with the preset funnel step sets and then combined, the funnel step matching total sets of all users can be obtained, a complicated Map/Reduce mechanism is avoided, and the query speed is accelerated. The following description and description will be made with reference to various embodiments.
A first embodiment of the present invention relates to a funnel data analysis method, and a specific flow is shown in fig. 1, including:
step S1, determining user behaviors of a user in different time periods to form a behavior set corresponding to each time period of the user;
specifically, user behavior log data collected by buried points are imported into a Hive data warehouse for preprocessing, and data suitable for funnel analysis and modeling are generated; as shown in fig. 2, the pretreatment steps mainly include:
S11, cleaning original user behavior log data, removing repeated data and illegal data, and filtering the illegal user data; the user behavior log data comprises user behavior path information, and all user behaviors of a user are recorded in the user behavior path information;
S12, extracting unique identification of each user behavior in the user behavior path information, and uniformly coding the user behavior path information in the user behavior log data according to a preset coding rule so as to further convert the coded user behavior path information into a preset data format; errors caused by different formats are avoided, the cost is reduced, and the storage space is saved;
S13, removing fields irrelevant to funnel modeling to reduce the width of a data table;
S14, setting time periods, wherein each time period delta T is an order degree, and the order degree is used for summarizing the user behaviors in the same time period delta T to form a behavior set, and one user in the same time period delta T only corresponds to one piece of data, so that the data quantity to be processed is greatly reduced; according to the order degree requirement of the funnel, the higher the order degree precision requirement is, the smaller the time granularity (order degree) delta T is, the lower the order degree precision requirement is, the larger the time granularity delta T is, and the user behaviors are regarded as unordered within the same time granularity; specifically, the user behavior is regarded as unordered in the same degree of order, the smaller the degree of order is, the higher the order accuracy requirement of the funnel on the user behavior is, the more memory and time are required for funnel modeling, and an analyst can customize the degree of order of the funnel according to requirements and computing resources; the order is inversely proportional to the degree of order, which is the accuracy requirement of the funnel on the user behavior sequence, i.e. the higher the order of the funnel, the smaller the degree of order.
Compared with the simple ordered funnel or unordered funnel analysis in the traditional method, the funnel ordering of the embodiment supports an elastic variable mechanism, only the time granularity delta T is required to be adjusted during data processing, the user behaviors in the same time granularity are unordered, and the user behaviors in different time granularity are ordered, so that the analysis flexibility is enhanced.
Dividing the user behavior log data into a plurality of time periods according to a preset time period, and extracting a behavior set of each user in each time period;
specifically, the time period is taken as a partition basis, and partition statistics is carried out on the user behaviors of each user in different time periods, so that one piece of data can represent all behaviors of one user in one time granularity, and the data quantity is greatly reduced;
step S2, respectively matching the behavior set of each user in different time periods with the funnel step set by taking the time period as a unit to obtain a funnel step matching sub-set of each user in different time periods; the funnel step matching sub-set is used for orderly recording whether a matching item exists in a behavior set of each funnel step in the preset funnel step set in a corresponding time period;
Specifically, the ordered recording refers to recording according to the sequence of the funnel steps in the funnel step set.
Step S3, combining the funnel step matching sub-sets of each user in different time periods to obtain a funnel step matching set of each user;
Specifically, when the user behaviors are combined, when the user completes the same funnel step in different time periods, the user completes the funnel steps with overlapping, and in the funnel analysis process, the final result only needs to record whether all funnel steps in the preset funnel step set have matching items or not, so that the user only needs to take the data of the same user for completing the funnel steps once.
And carrying out aggregation statistics on the funnel step matching sets of all users to obtain the number of users who finish any funnel step in the funnel step sets.
Specifically, in the process of data processing and query, data only traverses once, a behavior set of a user in each time period can be obtained, the behavior sets in each time period are respectively matched with a preset funnel step set and then combined, so that funnel step matching sets of all users can be obtained, a complicated Map/Reduce mechanism is avoided, and the query speed is increased.
Embodiments of the invention are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable for use with the computer system/server include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, mainframe computer systems, and distributed cloud computing technology environments that include any of the foregoing, and the like.
On the basis of the foregoing embodiment, as a preferred implementation manner, in the step S1, the user behavior log data is divided into a plurality of time periods according to a preset time period, and specifically includes:
Dividing the user behavior log data into three parts, namely time, user dimension information and user behavior path information, setting a plurality of time periods according to the time as a partition basis, dividing the user behavior log data into a plurality of time periods according to the plurality of time periods, and importing the user dimension information and the user behavior path information into a distributed relational database for partition storage, such as importing an OLAP (Online Analytical Processing, online analysis processing) database; wherein the user dimension information corresponds to a user attribute field, such as: age, gender, mobile phone brands and the like, wherein the user behavior path information corresponds to user behavior identification and is used for funnel aggregation statistics. As shown in table 1, are examples of data stored in a database.
| ΔT1 | ΔT2 | ΔT3 |
| User1 female 18 years old a-b-d | User1 female 18 years old c-f | User2 Male 25 years old c-a-b-e-f |
| User2 Male 25 years old a-c-d-e-b | User2 Male 25 years old c-a-b-e-f | User3 female 26 years old b-e |
| User3 female 26 years old d-c-f | User3 female 26 years old a-c-f | User4 female 30 years old b-e-c |
| User4 female 30 years old b-a-e-a | User5 female 20 years old c-f-e-g | User5 female 20 years old c-b |
TABLE 1 user behavior analysis funnel modeling data
In table 1, Δt1, Δt2, and Δt3 each represent 3 time periods, user1 to User5 represent User identifications of different users, and character strings such as a-b-d and c-f represent User behavior path information.
A record is as follows: user1 female 18 years old a-b-d;
wherein three fields of "User1 female 18 years old" are User dimension information, user1 is User identification, a User can be uniquely determined, the "female 18 years old" is a User attribute, and a-b-d is User behavior path information of the User.
Based on the data storage mode, when the funnel model is generated, only one inquiry needs to be initiated, and each piece of data is scanned only once, and the specific process is as follows: assuming that a 3-step funnel model is required to be established, the filtering condition is that the number of the funnel model is 18-30 years old, and the codes corresponding to the 3 funnel steps are a-c-f; in the process of user behavior acquisition, there is a unique identifier for each user behavior, and the unique identifier is encoded according to a certain encoding rule (such as MD 5), so that the code can be obtained, where the letter is just an example.
On the basis of the foregoing embodiments, as a preferred implementation manner, in the step S2, the matching, in units of time periods, the behavior set corresponding to each time period by the user with the funnel step set to obtain a behavior matching result of each time period specifically includes:
Respectively matching a behavior set corresponding to each time period of a user with a funnel step set to obtain a behavior matching result of each time period, wherein the behavior matching result is used for orderly recording whether each funnel step in the funnel step set has a funnel step matching sub-set of matching items in the behavior set of the corresponding time period, elements in the funnel step matching sub-set are in one-to-one correspondence with the funnel steps in the funnel step set,
If any funnel step in the funnel step set is judged to have a matching item in the behavior set, marking element values at corresponding positions in the funnel step matching sub-set as a first expression according to a preset rule;
And for any funnel step in the funnel step set, if no matching item is judged in the behavior set, marking the element value at the corresponding position in the funnel step matching sub-set as a second expression according to a preset rule.
Specifically, in this embodiment, a behavior set of each user in each time period is regarded as unordered, and the behavior set is matched with all funnel steps in a preset funnel step set;
Specifically, the first expression and the second expression are binary expressions, wherein,
If the matching item is judged to exist in the behavior set, marking the element value at the corresponding position in the funnel step matching sub-set as 1;
If no matching item is judged in the behavior set, the element value at the corresponding position in the funnel step matching sub-set is recorded as 0.
If the matching result of the behavior set and the funnel step set in the time period is represented by a binary code (namely, the funnel steps are matched with the sub-set), the bit number of the binary code is equal to the number of the funnel steps in the funnel step set; the binary value of any bit in the binary code represents the matching result of one funnel step in the preset funnel step set, if any funnel step in the funnel step set is successfully matched in the behavior set, the binary value of the corresponding bit in the binary code is marked as 1, and if any funnel step in the funnel step set is failed to be matched in the behavior set, the binary value of the corresponding bit in the binary code is marked as 0.
Specifically, in this embodiment, for each time period Δt, each piece of data is scanned, users whose user dimension information meets the funnel filtering condition are matched, the behavior set of each user in the time period Δt is combined and matched with the funnel step set, each user obtains a binary code, any bit in the binary code (the number of bits of the binary code is determined by the funnel steps, for example, the number of the funnel steps is 5, and here, the binary code is 5 bits) corresponds to whether one funnel step occurs in the behavior set, if three funnel steps are included in the preset funnel step set, only the first funnel step occurs, the binary code is 100, if only the second funnel step occurs, the binary code is 010, for example, only the first funnel step and the second funnel step occur, the binary code is 110, and so on, the data in table 1 can be simplified as shown in table 2 after the matching according to the above rule is completed.
| ΔT1 | ΔT2 | ΔT3 |
| User1 100 | User1 011 | User3 000 |
| User3 011 | User3 111 | User4 010 |
| User4 100 | User5 011 | User5 010 |
TABLE 2 match results of user behavior set and funnel step set per unit time
Specifically, the sequence of the funnel step set is set to be a-c-f, if the behavior set is c-a-b-e-f, the matching result is that as long as the behavior set exists such as c, f and a, the corresponding path bit of the funnel step is assigned 1, and the obtained binary code is 111; or, when matching, considering the sequence of path codes in the behavior set, if the sequence is inconsistent with the sequence in the funnel step, not counting; in this embodiment, since the user behaviors set in the same time granularity value are unordered, the user behaviors of different time granularity values are ordered, so for the set funnel step set the order is a-c-f, if the order of the behavior set is c-a-b-e-f, the result value of the matching should be 111, because c-a-b-e-f is the behavior in the same time period Δt, which is regarded as unordered, that is, c-a-b-e-f is equivalent to a-b-c-e-f in the same Δt.
In this embodiment, a binary code is selected as the record of the funnel steps completed and the funnel steps not completed in each time period for each user, and in other embodiments other than this embodiment, other modes, such as a queue, may be adopted, and only the fact that any funnel step in the funnel step set has a unique identifier to record whether the funnel step is completed or not is required to be ensured, and the number of the identifiers is equal to the number of the funnel steps in the funnel step set.
Specifically, if the user does not use behaviors in a certain time period, the binary value of each bit in the binary code obtained by matching the behavior set in the corresponding time period with the preset funnel step set is recorded as 0.
On the basis of the foregoing embodiments, as a preferred implementation manner, in step S3, the merging the matching sub-sets of the funnel steps of each user in different time periods to obtain a matching total set of the funnel steps of each user specifically includes:
On the basis of the foregoing embodiments, as a preferred implementation manner, the merging the behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user specifically includes:
sequencing all the funnel step matching sub-sets according to the sequence of time periods;
Deleting useless matching sub-sets of the funnel steps:
if judging that the element value at the position corresponding to the first funnel step of the funnel step set is marked as a second expression in the first funnel step matching sub-set, discarding the first funnel step matching sub-set;
In the adjacent two funnel step matching sub-sets, if all funnel steps marked as first expressions in the former funnel step matching sub-set are judged to be marked as first expressions in the latter funnel step matching sub-set, deleting the former funnel step matching sub-set;
Orderly combining all the remaining funnel step matching sub-sets to obtain a funnel step matching total set for orderly recording whether each funnel step in the funnel step set has a matching item, wherein elements in the funnel step matching total set are in one-to-one correspondence with the funnel steps in the funnel step set,
And if the fact that a certain funnel step in the funnel step matching sub-set is marked as a first expression in any funnel step matching sub-set is judged, marking a corresponding funnel step as a first expression in the funnel step matching total set, and if the fact that a certain funnel step in the funnel step matching sub-set is marked as a second expression in all funnel step matching sub-sets is judged, marking a corresponding funnel step as a second expression in the funnel step matching total set.
Specifically, in this embodiment, it is necessary to perform preliminary merging on user behavior information of the same user in different time periods, and remove useless data, if a binary expression is adopted, each user obtains a binary code set after the preliminary merging is completed, where the size of the binary code set is equal to the number of time periods, and the number of bits of each binary code in the binary code set is equal to the number of funnel steps in a preset funnel step set, and a specific merging rule is:
a) For a certain user, assuming that the binary codes corresponding to the user in the time periods Δt1, Δt2 and Δt3 are x 1x2x3,y1y2y3,z1z2z3 (if there is no data in a certain time period Δt, the binary code corresponding to the time period Δt2 is defaulted to be 000), firstly, if the binary value of a certain Δt2 is bit-pressed or operated with the binary value of the previous Δt1 to be smaller than the value of the subsequent Δt3, discarding the binary code corresponding to the time period Δt2. For example: the values of the time period Δt1, the time period Δt2 and the time period Δt3 of User3 are 011, 111 and 000 respectively, and the time period Δt1 is the first time period, no data exists in the previous time period, and the default is 000, and the bit or calculation is performed: 0|0=1, 0|1=1, and since the value 011 corresponding to the time period Δt1 < the value 111 corresponding to Δt2, the value 011 corresponding to Δt1 is discarded; binary codes for time period Δt1 and time period Δt2 are bit-wise ored: 0|1=1, 1|1=1, the value 111 corresponding to Δt2 > the value corresponding to Δt3, the binary code corresponding to Δt2 is reserved, only 111,000 is processed, and so on.
Then, if the value of the first bit in the first binary code in the binary code set is 0, the user data (i.e., the first binary code) is discarded, for example: the values of the time period delta T1, the time period delta T2 and the time period delta T3 of the User5 are 000, 011 and 010 respectively, the binary code set is 011 and 010 after being processed according to a first rule, and the first bit of the first element 011 in the binary code set is 0 at the moment, which means that the User5 does not finish the first funnel step, and the data of the User can be abandoned; the data after completion of merging according to the above rule can be reduced to the data shown in table 3.
| User1 | 100，011，000 |
| User3 | 111，000 |
| User4 | 100，010 |
TABLE 3 binary code merging I
B) And c) merging the binary matching results of the user behaviors in the step a) again, wherein each user obtains a binary code, the number of bits of the binary code is equal to the number of funnel steps in the funnel step set, and the values of each bit in the binary code respectively correspond to whether one funnel step occurs or not. The specific merging rule is as follows: for a certain user, assume that the binary code set obtained in step a) is x1x2x3,y1y2y3,z1z2z3(x1＝1),, and the binary code values in the binary code set are subjected to bit-wise or operation, for example: the binary set for User1 is: 100, 111, 000, (bit wise or: 1-1=1, 1-0=1, 0-0=0, 110-111=111, 111-000=111) and so on, the result is 111 after bit wise or operation, and so on, the data after completion of the merging can be simplified as shown in table 4.
TABLE 4 binary code merger II
On the basis of the foregoing embodiments, as a preferred implementation manner, the determining, according to the total set of funnel step matches of all users, the number of users matched by any funnel step in the set of funnel steps specifically includes:
Carrying out aggregation statistics on the funnel step matching total set of all users to obtain the number of users completing any funnel step;
Specifically, when the binary expression is adopted, only arithmetic addition operation is needed to be respectively carried out on each binary bit in the funnel step matching set of all users, so that the number of users matched by each binary bit corresponding to the funnel step is obtained.
Specifically, in this embodiment, aggregation statistics is performed on the binary matching result of the user behavior in step b): the specific statistical method comprises the following steps: assuming that the 3 bits binary system obtained in step b) is x 1x2x3, arithmetic additions are made for the 3 binary bits, respectively, to obtain Σx 1,∑x2,∑x3, respectively, corresponding to the number of users of the three funnel steps, respectively, for example: aggregate statistics of the results in fig. 4 results in Σx 1＝3,∑x2＝3,∑x3 =2, indicating that, in the statistical range, there are 3 users who complete the funnel step 1, where there are 3 more users who complete the funnel step 2, where there are 2 more users who complete the funnel step 3, so far, the whole funnel analysis is complete, and the data can be used to construct a funnel model.
The above steps of the methods are divided, for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they include the same logic relationship, and they are all within the protection scope of this patent; it is within the scope of this patent to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.
An embodiment of the second aspect of the present invention provides a funnel data analysis system, based on the funnel data analysis method in the above embodiments, as shown in fig. 3, including a data receiving module 10, a behavior extracting module 20, a funnel step matching module 30, a funnel step merging module 40, and a funnel step analysis module 50, where:
the data receiving module 10 is used for receiving user behavior log data reported by different buried points;
The behavior extraction module 20 divides the user behavior log data into a plurality of time periods according to a preset time period, and extracts a behavior set of each user in each time period, wherein each time corresponds to one behavior set;
the funnel step matching module 30 respectively matches the behavior set of each user in different time periods with the funnel step set to obtain a funnel step matching sub-set of each user in different time periods; the funnel step matching sub-set is used for orderly recording whether each funnel step in the funnel step set has a matching item in the behavior set of the corresponding time period;
The funnel step combining module 40 combines the funnel step matching sub-sets of each user in different time periods to obtain a funnel step matching total set of each user;
And the funnel step analysis module 50 is used for carrying out aggregation statistics on the funnel step matching sets of all users to obtain the number of users who finish any funnel step matching in the preset funnel step set.
A third embodiment of the present invention relates to a server, as shown in fig. 4, including a processor 810, a communication interface (Communications Interface) 820, a memory 830, and a communication bus 840, where the processor 810, the communication interface 820, and the memory 830 complete communication with each other through the communication bus 840. Processor 810 may invoke logic instructions in memory 830 to perform the steps of the funnel data analysis method as described in the various embodiments above. Examples include:
step S1, determining user behaviors of a user in different time periods to form a behavior set corresponding to each time period of the user;
Step S2, taking time periods as units, respectively matching a behavior set corresponding to each time period of a user with a funnel step set to obtain a behavior matching result of each time period;
And step S3, combining behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users.
The memory and the processor are connected by a communication bus, which may include any number of interconnected buses and bridges, which connect various circuits of the one or more processors and the memory together. The bus may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface between a communication bus and a transceiver. The transceiver may be one element or may be a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over the wireless medium via the antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory may be used to store data used by the processor in performing operations.
A fourth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program when executed by a processor implements the steps of the funnel data analysis method as described in the above embodiments. Examples include:
step S1, determining user behaviors of a user in different time periods to form a behavior set corresponding to each time period of the user;
Step S2, taking time periods as units, respectively matching a behavior set corresponding to each time period of a user with a funnel step set to obtain a behavior matching result of each time period;
And step S3, combining behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users.
That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the invention and that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (8)
1. A method of funnel data analysis, comprising:
Determining user behaviors of a user in different time periods to form a behavior set corresponding to the user in each time period;
The method comprises the steps of taking time periods as units, respectively matching a behavior set corresponding to each time period of a user with a funnel step set to obtain a behavior matching result of each time period, wherein the behavior set of each user in each time period is regarded as unordered, and the behavior set corresponding to each time period of the user is respectively matched with the funnel step set to obtain the behavior matching result of each time period; the behavior matching result is a funnel step matching sub-set for orderly recording whether each funnel step in the funnel step set has a matching item in the behavior set of the corresponding time period, and elements in the funnel step matching sub-set are in one-to-one correspondence with the funnel steps in the funnel step set; if any funnel step in the funnel step set is judged to have a matching item in the behavior set, marking element values at corresponding positions in the funnel step matching sub-set as a first expression according to a preset rule; if no matching item is judged in the behavior set for any funnel step in the funnel step set, marking the element value at the corresponding position in the funnel step matching sub-set as a second expression according to a preset rule;
Combining behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users; sequencing all the funnel step matching sub-sets according to the sequence of time periods; deleting useless matching sub-sets of the funnel steps: if judging that the element value at the position corresponding to the first funnel step of the funnel step set is marked as a second expression in the first funnel step matching sub-set, discarding the first funnel step matching sub-set; in the adjacent two funnel step matching sub-sets, if all funnel steps marked as first expressions in the former funnel step matching sub-set are judged to be marked as first expressions in the latter funnel step matching sub-set, deleting the former funnel step matching sub-set; orderly combining all the remaining funnel step matching sub-sets to obtain a funnel step matching total set for orderly recording whether each funnel step in the funnel step set has a matching item, wherein elements in the funnel step matching total set are in one-to-one correspondence with funnel steps in the funnel step set, and if a certain funnel step in the funnel step matching sub-set is judged to be marked as a first expression in any funnel step matching sub-set, the corresponding funnel step is marked as the first expression in the funnel step matching total set; and if judging that a certain funnel step in the funnel step matching sub-set is marked as a second expression in all the funnel step matching sub-sets, marking the corresponding funnel step as the second expression in the funnel step matching total set.
2. The funnel data analysis method according to claim 1, wherein said determining user behaviors of the user in different time periods to form a corresponding behavior set of the user in each time period specifically comprises:
Receiving user behavior log data reported by different buried points, wherein the user behavior log data comprises user behavior path information;
partitioning the user behavior log data according to preset time periods to obtain user behavior log data of each time period, and extracting user behaviors in the user behavior log data of each time period to form a behavior set corresponding to each time period of a user.
3. The method for analyzing funnel data according to claim 2, wherein after receiving the user behavior log data reported by different buried points, further comprises:
cleaning the user behavior path information to remove repeated data and illegal data;
And extracting the unique identifier of each user action in the user action path information, uniformly encoding the unique identifiers according to a preset encoding rule, and converting the encoded unique identifiers into a preset data format.
4. The funnel data analysis method of claim 1, wherein the first and second expressions are binary expressions, wherein,
If the matching item is judged to exist in the behavior set, marking the element value at the corresponding position in the funnel step matching sub-set as 1;
If no matching item is judged in the behavior set, the element value at the corresponding position in the funnel step matching sub-set is recorded as 0.
5. The method for analyzing funnel data according to claim 4, wherein said merging results of behavior matching of each user in different time periods specifically comprises:
Matching the corresponding element values in the sub-set in the funnel step of each user in different time periods by bit or operation;
The determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users specifically comprises the following steps:
and respectively performing arithmetic addition operation on corresponding element values in the funnel step matching total set of all users to obtain the number of users matched by any funnel step in the funnel step set.
6. A funnel data analysis system, comprising:
The behavior extraction module is used for determining the behaviors of the user in different time periods to form a behavior set corresponding to each time period of the user;
the funnel step matching module is used for respectively matching the behavior set corresponding to each time period of the user with the funnel step set by taking the time period as a unit to obtain a behavior matching result of each time period, wherein the behavior set of each user in each time period is regarded as unordered, and the behavior set corresponding to each time period of the user is respectively matched with the funnel step set to obtain the behavior matching result of each time period; the behavior matching result is a funnel step matching sub-set for orderly recording whether each funnel step in the funnel step set has a matching item in the behavior set of the corresponding time period, and elements in the funnel step matching sub-set are in one-to-one correspondence with the funnel steps in the funnel step set; if any funnel step in the funnel step set is judged to have a matching item in the behavior set, marking element values at corresponding positions in the funnel step matching sub-set as a first expression according to a preset rule; if no matching item is judged in the behavior set for any funnel step in the funnel step set, marking the element value at the corresponding position in the funnel step matching sub-set as a second expression according to a preset rule;
The funnel step analysis module is used for merging behavior matching results of each user in different time periods to obtain a funnel step matching total set of each user, and determining the number of users matched by any funnel step in the funnel step set according to the funnel step matching total set of all users; sequencing all the funnel step matching sub-sets according to the sequence of time periods; deleting useless matching sub-sets of the funnel steps: if judging that the element value at the position corresponding to the first funnel step of the funnel step set is marked as a second expression in the first funnel step matching sub-set, discarding the first funnel step matching sub-set; in the adjacent two funnel step matching sub-sets, if all funnel steps marked as first expressions in the former funnel step matching sub-set are judged to be marked as first expressions in the latter funnel step matching sub-set, deleting the former funnel step matching sub-set; orderly combining all the remaining funnel step matching sub-sets to obtain a funnel step matching total set for orderly recording whether each funnel step in the funnel step set has a matching item, wherein elements in the funnel step matching total set are in one-to-one correspondence with funnel steps in the funnel step set, and if a certain funnel step in the funnel step matching sub-set is judged to be marked as a first expression in any funnel step matching sub-set, the corresponding funnel step is marked as the first expression in the funnel step matching total set; and if judging that a certain funnel step in the funnel step matching sub-set is marked as a second expression in all the funnel step matching sub-sets, marking the corresponding funnel step as the second expression in the funnel step matching total set.
7. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the funnel data analysis method of any one of claims 1 to 5.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the funnel data analysis method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011614804.2A CN112650743B (en) | 2020-12-30 | 2020-12-30 | Funnel data analysis method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011614804.2A CN112650743B (en) | 2020-12-30 | 2020-12-30 | Funnel data analysis method, system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112650743A CN112650743A (en) | 2021-04-13 |
| CN112650743B true CN112650743B (en) | 2024-10-15 |
Family
ID=75364369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011614804.2A Active CN112650743B (en) | 2020-12-30 | 2020-12-30 | Funnel data analysis method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112650743B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609188A (en) * | 2021-07-23 | 2021-11-05 | 恩亿科(北京)数据科技有限公司 | Funnel analysis method, system, device and medium for user behavior steps |
| CN114429360B (en) * | 2021-12-29 | 2024-09-17 | 神策网络科技（北京）有限公司 | Conversion rate determination method, conversion rate determination device, electronic device, and computer-readable storage medium |
| CN114925099A (en) * | 2022-06-08 | 2022-08-19 | 北京自如信息科技有限公司 | Funnel data query method and device and electronic equipment |
| CN116303834B (en) * | 2023-05-19 | 2024-03-08 | 北京弘维大数据技术有限公司 | Data warehouse historical data storage and processing method, system and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675194A (en) * | 2019-09-29 | 2020-01-10 | 北京思维造物信息科技股份有限公司 | Funnel analysis method, device, equipment and readable medium |
| CN111625563A (en) * | 2020-04-27 | 2020-09-04 | 苏宁云计算有限公司 | User access behavior analysis method and system based on funnel model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6784044B2 (en) * | 2016-03-24 | 2020-11-11 | カシオ計算機株式会社 | Behavior analysis device, behavior analysis method and program |
| CN111523921B (en) * | 2019-12-31 | 2023-10-20 | 支付宝实验室(新加坡)有限公司 | Funnel analysis method, analysis device, electronic device, and readable storage medium |
-
2020
- 2020-12-30 CN CN202011614804.2A patent/CN112650743B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675194A (en) * | 2019-09-29 | 2020-01-10 | 北京思维造物信息科技股份有限公司 | Funnel analysis method, device, equipment and readable medium |
| CN111625563A (en) * | 2020-04-27 | 2020-09-04 | 苏宁云计算有限公司 | User access behavior analysis method and system based on funnel model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112650743A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112650743B (en) | Funnel data analysis method, system, electronic equipment and storage medium | |
| CN112307762B (en) | Search result sorting method and device, storage medium and electronic device | |
| CN112613917B (en) | Information pushing method, device, equipment and storage medium based on user portrait | |
| CN111339427A (en) | Book information recommendation method, device and system and storage medium | |
| CN104077407A (en) | System and method for intelligent data searching | |
| CN111639700A (en) | Target similarity recognition method and device, computer equipment and readable storage medium | |
| CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN113656699A (en) | User feature vector determination method, related device and medium | |
| CN110443264A (en) | A kind of method and apparatus of cluster | |
| CN113139558A (en) | Method and apparatus for determining a multi-level classification label for an article | |
| CN112069269B (en) | Big data and multidimensional feature-based data tracing method and big data cloud server | |
| CN112100177A (en) | Data storage method and device, computer equipment and storage medium | |
| CN114282119B (en) | Scientific and technological information resource retrieval method and system based on heterogeneous information network | |
| CN112182320B (en) | Cluster data processing method, device, computer equipment and storage medium | |
| CN115470279A (en) | Data source conversion method, device, equipment and medium based on enterprise data | |
| CN112580676B (en) | Clustering method, clustering device, computer readable medium and electronic equipment | |
| CN110309235B (en) | Data processing method, device, equipment and medium | |
| CN114093447A (en) | Data asset recommendation method and device, computer equipment and storage medium | |
| TW202305613A (en) | Method for creating data warehouse, electronic device, and storage medium | |
| CN113343076A (en) | Innovative technology recommendation method and system based on feature matching degree | |
| CN111400413A (en) | Method and system for determining category of knowledge points in knowledge base | |
| CN113392105B (en) | Service data processing method and terminal equipment | |
| CN117787729B (en) | Intelligent park management method and related device based on identification analysis | |
| Li | Application and Research of Multi-Feature Fusion Tag Propagation Computer Algorithm in Image Search and Matching |
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 |