CN106557410A - User behavior analysis method and apparatus based on artificial intelligence - Google Patents
User behavior analysis method and apparatus based on artificial intelligence Download PDFInfo
- Publication number
- CN106557410A CN106557410A CN201610941394.XA CN201610941394A CN106557410A CN 106557410 A CN106557410 A CN 106557410A CN 201610941394 A CN201610941394 A CN 201610941394A CN 106557410 A CN106557410 A CN 106557410A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- daily record
- scene
- filter condition
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
-
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
Abstract
The invention discloses a kind of user behavior analysis method and apparatus based on artificial intelligence, wherein, method includes：According to default Log Filter condition resolution User action log, the daily record piece segment information for meeting Log Filter condition is filtered out；User mutual scene is generated according to daily record fragment information simulation；Mark behavior evaluation information corresponding with user mutual scene.The method carries out user behavior analysis by analog subscriber interaction scenarios, and improve carries out the efficiency of user behavior analysis, is easy to be analyzed product based on Product Experience, realizes to the comprehensive of product analysis.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of user behavior analysis method based on artificial intelligence
And device.
Background technology
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is study, be developed for simulation,
Extend and extend a new technological sciences of theory, method, technology and the application system of the intelligence of people.Artificial intelligence is to calculate
One branch of machine science, it attempts the essence for understanding intelligence, and produce it is a kind of it is new can be in the way of human intelligence be similar
The intelligence machine made a response, the research in the field include robot, language identification, image recognition, natural language processing and specially
Family's system etc..
Generally, optimization and performance boost of the behavior feedback of user to product has directiveness effect, by analyzing user
User behaviors log and user feedback, related personnel can be helped to understand deficiency and impact face of the product in the experience and in performance,
To help analyze the use scene and custom that personnel understand real user, so that producing piece can bring more excellent Product Experience etc..
In correlation technique, user behavior monitoring carries out the analysis of word aspect in excel forms, it is impossible to which simulation is true to produce
The user mutual situation of product, analysis efficiency are low, and the cycle is long.
The content of the invention
The purpose of the present invention is intended at least solve one of above-mentioned technical problem to a certain extent.
For this purpose, first purpose of the present invention is to propose a kind of user behavior analysis method based on artificial intelligence, should
Method carries out user behavior analysis by analog subscriber interaction scenarios, and improve carries out the efficiency of user behavior analysis, is easy to base
Product is analyzed in Product Experience, is realized to the comprehensive of product analysis.
Second object of the present invention is to propose a kind of user behavior analysis device based on artificial intelligence.
Third object of the present invention is to propose another kind of user behavior analysis device based on artificial intelligence.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
5th purpose of the present invention is proposing a kind of computer program.
To achieve these goals, first aspect present invention embodiment proposes a kind of user behavior based on artificial intelligence
Analysis method, comprises the following steps：According to default Log Filter condition resolution User action log, filter out and meet the daily record
The daily record piece segment information of screening conditions；User mutual scene is generated according to the daily record fragment information simulation；Mark and the use
The corresponding behavior evaluation information of family interaction scenarios.
The user behavior analysis method based on artificial intelligence of the embodiment of the present invention, according to default Log Filter condition resolution
User action log, filters out the daily record piece segment information for meeting Log Filter condition, and is generated according to daily record fragment information simulation
User mutual scene, and then mark behavior evaluation information corresponding with user mutual scene.Thus, field is interacted by analog subscriber
Scape carries out user behavior analysis, and improve carries out the efficiency of user behavior analysis, is easy to carry out product point based on Product Experience
Analysis, realizes to the comprehensive of product analysis.
In addition, the user behavior analysis method based on artificial intelligence of the embodiment of the present invention, also with following additional skill
Art feature：
In one embodiment of the invention, the default Log Filter condition resolution User action log of the basis, screening
Go out to meet the daily record piece segment information of the Log Filter condition, including：
Parsing User action log obtains the unstructured information matched with parameter preset；
The unstructured information is converted into into structural data, and data directory is set up according to the structural data；
The data directory according to default Log Filter condition query, filters out the daily record for meeting the Log Filter condition
Piece segment information.
It is in one embodiment of the invention, described that user mutual scene is generated according to the daily record fragment information simulation,
Including：
Extract the text interactive information in the daily record piece segment information；
The link information in the daily record piece segment information is sent to predetermined system platform；
Receive the picture interactive information corresponding with the link information of the system platform feedback；
User mutual scene is generated according to the text interactive information and picture interactive information simulation.
In one embodiment of the invention, in mark behavior evaluation information corresponding with the user mutual scene
Afterwards, also include：
Obtain evaluation label to be checked；
Gone out and the user mutual scene for evaluating tag match according to the behavior evaluation information sifting；
Regression analysis process is done according to the user mutual scene.
In one embodiment of the invention, also include：
Show data variation trend corresponding with default index feature or temporal characteristics in system platform.
To achieve these goals, second aspect present invention embodiment proposes a kind of user behavior based on artificial intelligence
Analytical equipment, including：Screening module, for according to default Log Filter condition resolution User action log, filtering out and meeting institute
State the daily record piece segment information of Log Filter condition；Analog module, hands over for generating user according to the daily record fragment information simulation
Mutual scene；Mark module, for marking behavior evaluation information corresponding with the user mutual scene.
The user behavior analysis device based on artificial intelligence of the embodiment of the present invention, according to default Log Filter condition resolution
User action log, filters out the daily record piece segment information for meeting Log Filter condition, and is generated according to daily record fragment information simulation
User mutual scene, and then mark behavior evaluation information corresponding with user mutual scene.Thus, field is interacted by analog subscriber
Scape carries out user behavior analysis, and improve carries out the efficiency of user behavior analysis, is easy to carry out product point based on Product Experience
Analysis, realizes to the comprehensive of product analysis.
In addition, the user behavior analysis device based on artificial intelligence of the embodiment of the present invention, also with following additional skill
Art feature：
In one embodiment of the invention, the screening module includes：
Resolution unit, obtains the unstructured information matched with parameter preset for parsing User action log；
Converting unit, for the unstructured information is converted into structural data；
Unit is set up, for data directory being set up according to the structural data；
Screening unit, for the data directory according to default Log Filter condition query, filters out and meets the daily record
The daily record piece segment information of screening conditions.
In one embodiment of the invention, the analog module includes：
Extraction unit, for extracting the text interactive information in the daily record piece segment information；
Transmitting element, for the link information in the daily record piece segment information is sent to predetermined system platform；
Receiving unit, for receiving the picture interactive information corresponding with the link information of the system platform feedback；
Analogue unit, for generating user mutual field according to the text interactive information and picture interactive information simulation
Scape.
In one embodiment of the invention, also include：
Acquisition module, for obtaining evaluation label to be checked；
The screening module is additionally operable to be gone out and the user for evaluating tag match according to the behavior evaluation information sifting
Interaction scenarios；
Analysis module, for doing regression analysis process according to the user mutual scene.
In one embodiment of the invention, also include：
Display module, for showing data variation corresponding with default index feature or temporal characteristics in system platform
Trend.
To achieve these goals, third aspect present invention embodiment proposes another kind of user's row based on artificial intelligence
For analytical equipment, including：Processor；
For storing the memory of processor executable；
Wherein, the processor is configured to：According to default Log Filter condition resolution User action log, symbol is filtered out
Close the daily record piece segment information of the Log Filter condition；User mutual scene is generated according to the daily record fragment information simulation；Mark
Note behavior evaluation information corresponding with the user mutual scene.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of non-transitory computer-readable storage
Medium, when the instruction in the storage medium is performed by the processor of mobile terminal so that mobile terminal is able to carry out one
Plant for behavior analysis method, methods described includes：
According to default Log Filter condition resolution User action log, the daily record for meeting the Log Filter condition is filtered out
Piece segment information；
User mutual scene is generated according to the daily record fragment information simulation；
Mark behavior evaluation information corresponding with the user mutual scene.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program, when described
When instruction processing unit in computer program is performed, a kind of user behavior analysis method is performed, methods described includes：
According to default Log Filter condition resolution User action log, the daily record for meeting the Log Filter condition is filtered out
Piece segment information；
User mutual scene is generated according to the daily record fragment information simulation；
Mark behavior evaluation information corresponding with the user mutual scene.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
It is substantially and easy to understand, wherein：
Fig. 1 is the flow chart of the user behavior analysis method based on artificial intelligence according to an embodiment of the invention；
Fig. 2 is the scene of the daily record piece segment information for filtering out and meeting Log Filter condition according to an embodiment of the invention
Schematic diagram；
Fig. 3 is the schematic diagram of a scenario that simulation according to an embodiment of the invention generates user mutual scene；
Fig. 4 (a) is the schematic diagram of a scenario that simulation in accordance with another embodiment of the present invention generates user mutual scene；
Fig. 4 (b) is the schematic diagram of a scenario that user mutual scene is generated according to the simulation of another embodiment of the invention；
Fig. 5 is the flow chart of the user behavior analysis method based on artificial intelligence in accordance with another embodiment of the present invention；
Fig. 6 (a) is that data corresponding with default index feature or temporal characteristics according to an embodiment of the invention become
Change trend curve figure；
Fig. 6 (b) is data corresponding with default index feature or temporal characteristics in accordance with another embodiment of the present invention
Change trend curve figure；
Fig. 6 (c) is that data corresponding with default index feature or temporal characteristics according to an embodiment of the invention become
Change trend form figure；
Fig. 7 is the structural representation of the user behavior analysis device based on artificial intelligence according to an embodiment of the invention
Figure；
Fig. 8 is the structural representation of the user behavior analysis device based on artificial intelligence in accordance with another embodiment of the present invention
Figure；
Fig. 9 is the structural representation of the user behavior analysis device based on artificial intelligence according to another embodiment of the invention
Figure；
Figure 10 is that the structure of the user behavior analysis device based on artificial intelligence according to further embodiment of the present invention is shown
It is intended to；And
Figure 11 is that the structure of the user behavior analysis device based on artificial intelligence according to a still further embodiment of the present invention is shown
It is intended to.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the user behavior analysis method and apparatus based on artificial intelligence of the embodiment of the present invention is described.
It is appreciated that in order that the behavior feedback of user, can be that the optimization of product and the raising of performance are played more
Comprehensive directive function so that related personnel can be fed back according to the behavior of user, understands custom of the user using product, understands and produce
Deficiency of the product in experience and in performance and impact face, to make improvement for these deficiencies, and can face according to impact
Development function point carries out waiting, and the present invention proposes a kind of user behavior analysis method based on artificial intelligence.
Specifically, in the user behavior analysis method based on artificial intelligence of the embodiment of the present invention, in order to avoid only
By the analysis for carrying out word aspect in excel forms to user behavior, cause user behavior analysis not comprehensive enough, mould can be passed through
Intend the user mutual scene under real scene, intuitively product is analyzed in terms of Product Experience, strategy push and resource.
It is specific as follows：
Fig. 1 is the flow chart of the user behavior analysis method based on artificial intelligence according to an embodiment of the invention.
As shown in figure 1, should be may include based on the user behavior analysis method of artificial intelligence：
S110, according to default Log Filter condition resolution User action log, filters out the day for meeting Log Filter condition
Master chip segment information.
It is appreciated that user profile (age of user, user's occupation, ID, user are have recorded in the user behaviors log of user
Account etc.), user click on history, system version, retrieval city, retrieval client id, term, retrieval time, product IDs etc.
Much information, but according to the difference of analysis scene, it is different from the information in the User action log that present analysis scene is related.
Such as, when the use crowd to product is analyzed, the User action log related to present analysis scene
Information is user profile etc.；Again such as, when the use city to product is analyzed, the user related to present analysis scene
The information of user behaviors log is retrieval city etc..
Thus, Log Filter condition can be pre-set, so as in order to according to Log Filter condition resolution user behavior day
Will, filters out the daily record piece segment information for meeting Log Filter condition, in avoiding to User action log, with present analysis scene
Unrelated information is analyzed, and causes the analysis efficiency to user behavior not high.
Wherein, above-mentioned daily record piece segment information may include to meet the friendship of the texts such as term, the retrieval result of Log Filter condition
Corresponding link information of mutual information and the pictorial information of retrieval result, voice messaging etc..
It should be noted that according to the difference of concrete application scene, can be using various ways according to default Log Filter bar
Part parses User action log, filters out the daily record piece segment information for meeting Log Filter condition, is exemplified below：
As a kind of example, it is that the related data in user journal information sets up index, so as to according to default Log Filter
Condition query data directory, to filter out the daily record piece segment information for meeting Log Filter condition.
Specifically, the parameter related to properties of product is pre-set, when such as user name, User action log are generated
Between, system version, retrieval city, term, retrieval result etc., and then parse User action log and obtain and match with parameter preset
Unstructured data.
Further, for the ease of the analysis to User action log, unstructured data is converted into, bivariate table can be used
Structure carrys out the structural data of logical expression realization, and sets up data directory according to structural data.
Wherein, data element of the data directory to instruction structure data, it may include retrieval the date, retrieval client,
Retrieval city, the vertical class of system etc., meet daily record sieve in order to according to default Log Filter condition query data directory, filter out
Select the daily record piece segment information of condition.
For example, as shown in Fig. 2 it is the sieve such as " IOS " daily record that can hang down class for " film ", operating system by selection system
Select condition, filter out the daily record piece segment information for meeting Log Filter condition, the system of the daily record piece segment information hang down class be " film ",
Operating system is " IOS ".
S120, generates user mutual scene according to daily record fragment information simulation.
Specifically, after daily record piece segment information is obtained, in order to be estimated to product based on Product Experience, can be according to day
The simulation of master chip segment information generates user mutual scene.
It should be noted that under different user mutual scenes, the information type that user mutual scene is included is different, than
Text interactive information, picture interactive information, interactive voice information etc. are may include such as.And according to the difference of concrete application scene, can
User mutual scene, the letter for including with user mutual scene below are generated according to daily record fragment information simulation in different ways
Breath type, is to illustrate as a example by text interactive information and picture interactive information, is exemplified below：
The first example, pre-sets system platform, and link information and corresponding picture are stored in system platform
Interactive information.
Specifically, in this example, the text interactive information in daily record piece segment information is extracted, so it is flat to predetermined system
Platform sends the link information in daily record piece segment information, so as to predetermined system platform is obtained and feeds back figure corresponding with the link information
Piece interactive information, according to text interactive information and picture interactive information, simulation generates user mutual scene.
In this example, for example, as shown in figure 3, can be according to the interaction letter of the text in the daily record piece segment information for extracting
Breath, and the picture interactive information corresponding with link information of system platform feedback, simulation are generated according to user's request, are recommended cold
The user mutual scene of door film, user mutual scenario reduction daily record piece segment information corresponding true interaction scenarios.
Second example, in advance in Cloud Server, according to retrieval time and the client id of picture interactive information, storage
Picture interactive information, and then the text interactive information in daily record fragment is extracted, identification text interactive information corresponding retrieval time
And client id, text interactive information corresponding retrieval time and client id are sent to Cloud Server.
Further, the picture interactive information that Cloud Server feedback was matched with retrieval time and client id, in order to according to text
This interactive information and the simulation of picture interactive information generate user mutual scene.
S130, marks behavior evaluation information corresponding with user mutual scene.
Specifically, after analog subscriber interaction scenarios, behavior evaluation information corresponding with user mutual scene is marked, so as to
In being optimized to product according to behavior evaluation information, Performance Evaluation etc..Wherein, behavior evaluation information includes the use to product
Family is experienced, the satisfaction of such as user, the degree of accuracy of retrieval result, evaluation label etc..
Such as, in the user mutual scene as shown in Fig. 4 (a) left figures, due to being " the performance of the Smurfs for retrieval request
Person is certain singer ", there is provided retrieval result for the Smurfs film, it is clear that this time retrieval can not meet the inspection of user
Rope is asked, thus as shown in Fig. 4 (a) right figures, marks user satisfaction corresponding with the user mutual scene for poor, evaluation label
To recall by mistake.
Again such as, in the user mutual scene as shown in Fig. 4 (b) left figures, due to being that " I will see greatly for retrieval request
Piece ", there is provided retrieval result for entitled " sheet " film, it is clear that this time retrieve the retrieval request that can not meet user, because
And as shown in Fig. 4 (b) right figures, it is to recall to mark user satisfaction corresponding with the user mutual scene for poor, evaluation label by mistake
Deng.
In sum, the user behavior analysis method based on artificial intelligence of the embodiment of the present invention, sieves according to default daily record
Condition resolution User action log is selected, the daily record piece segment information for meeting Log Filter condition is filtered out, and is believed according to daily record fragment
Breath simulation generates user mutual scene, and then marks behavior evaluation information corresponding with user mutual scene.Thus, by simulation
User mutual scene carries out user behavior analysis, and improve carries out the efficiency of user behavior analysis, is easy to based on Product Experience pair
Product is analyzed, and realizes to the comprehensive of product analysis.
Based on above example, for the user behavior based on artificial intelligence for more comprehensively illustrating the embodiment of the present invention
Analysis method, with reference to being illustrated to the process that product is analyzed according to user behavior, is described as follows：
Fig. 5 is the flow chart of the user behavior analysis method based on artificial intelligence in accordance with another embodiment of the present invention,
As shown in figure 5, after above-mentioned steps S130, the method also includes：
S210, obtains evaluation label to be checked.
S220, goes out and the user mutual scene for evaluating tag match according to behavior evaluation information sifting.
Specifically, when performance evaluation is carried out to product, in order to improve analysis efficiency and the degree of accuracy, can be according to analysis demand
Difference, filter out user mutual scene corresponding with current demand.Can obtain to be checked consistent with present analysis scene
Evaluation label, and then, according to behavior evaluation information sifting go out and evaluate tag match user mutual scene.
For example, if current analysis scene is, the bad case of product are repaired, then inquire about evaluation mark to be checked
Sign as " recalling " by mistake, so as to go out and evaluate the user mutual scene of tag match, including Fig. 4 according to behavior evaluation information sifting
User mutual scene shown in (b) left figure etc..
S230, does regression analysis process according to user mutual scene.
Specifically, after associated user's interaction scenarios are obtained, regression analysis process is done according to user mutual scene, in order to
Understand the corresponding relation between current production each variable, in order to according to the corresponding relation between different variables, analysis correspondence
The Operational Mechanisms of product can be repaired with completing leak, perfect in shape and function etc..
In one embodiment of the invention, in order to more intuitively be analyzed to product, can also in system platform,
Show corresponding with default index feature or temporal characteristics data variation trend, so as to can be after contrast product reaches the standard grade, Qian Houte
Fix time the trend of the details and variation tendency of section corresponding index, analysis product performance and Product Experience, in order to make
Corresponding decision-making, realizes the optimization to product.
Wherein, default index feature or page browsing amount, independent pageview be may include, average interaction wheel number, average is handed over
Mutually duration, system version are distributed, retrieve the user behavior core index such as city, or may include film card clicking rate, news card
The user behavior index that clicking rate, list and conventional tab click situation etc. are segmented according to product function, temporal characteristics include
Retrieval date, the concrete time point of retrieval etc..
It should be noted that according to the difference of concrete application demand, can be shown using various ways special with default index
Levy or the corresponding data variation trend of temporal characteristics, such as can be represented in modes such as cake chart, curve, block diagram, forms, and
The default index feature of special time period can be represented, it is also possible to show default index feature of reduced time section etc..
In one embodiment of the invention, as shown in Fig. 6 (a), when default index feature refers to for user behavior core
Timestamp, in system platform in graph form, represents user's row on July 25th, 18 days 1 July 2016 time period
For core index, so as to be got information about in the time period according to the curve, the concrete trend of user behavior core index
Deng.
In one embodiment of the invention, as shown in Fig. 6 (b), when default index feature refers to for user behavior core
Timestamp, in system platform in graph form, represents time period A (on July 25,18 days to 2016 July in 2016), and right
Than the user behavior core index in time period B (on July 11,4 days to 2016 July in 2016), so as to user can be according to bit
The user behavior core index fixed time in section, weighs the function situation of product after a New Policy is reached the standard grade, with according to running feelings
Condition is optimized.
In one embodiment of the invention, as shown in Fig. 6 (c), when default index feature refers to for user behavior core
Timestamp, in system platform in the form of form, represents July 25 18 days to 2016 July 2016 time period, during with contrasting
Between the page browsing amount of user in section on July 11st, 4 days 1 July in 2016, independent pageview, average interaction duration etc. use
Family behavior core index.
In the present embodiment, in order that the content of form is directly perceived in further detail, in order to comprehensively be divided to product
Analysis, shown in such as Fig. 6 (c), shows being worth, specify time period average, reduced time section when the earning in a day, yesterday for indices in form
The index in detail such as average.
In sum, the user behavior analysis method based on artificial intelligence of the embodiment of the present invention, is handed over user in mark
Mutually after the corresponding behavior evaluation information of scene, evaluation label to be checked is obtained, is gone out and is commented according to behavior evaluation information sifting
The user mutual scene of valency tag match, does regression analysis process according to user mutual scene.Thus, based on Product Experience to producing
Product are analyzed, and are easy to carry out perfect in shape and function and performance optimization to producing piece.
For achieving the above object, the present invention also proposes a kind of user behavior analysis device based on artificial intelligence.
Fig. 7 is the structural representation of the user behavior analysis device based on artificial intelligence according to an embodiment of the invention
Figure.
As shown in fig. 7, should be may include based on the user behavior analysis device of artificial intelligence：Screening module 10, analog module
20 and mark module 30.
Wherein, screening module 10, for according to default Log Filter condition resolution User action log, filtering out and meeting day
The daily record piece segment information of will screening conditions.
In one embodiment of the invention, Fig. 8 is the use based on artificial intelligence in accordance with another embodiment of the present invention
The structural representation of family behavioural analysis device, as shown in figure 8, on the basis of as shown in Figure 7, the screening module 10 includes parsing
Unit 11, converting unit 12, set up unit 13 and screening unit 14.
Wherein, resolution unit 11, obtain the unstructured information matched with parameter preset for parsing User action log.
Converting unit 12, for unstructured information is converted into structural data.
Unit 13 is set up, for data directory being set up according to structural data.
Screening unit 14, for according to default Log Filter condition query data directory, filtering out and meeting Log Filter bar
The daily record piece segment information of part.
Analog module 20, for generating user mutual scene according to daily record fragment information simulation.
In one embodiment of the invention, Fig. 9 is the use based on artificial intelligence according to another embodiment of the invention
The structural representation of family behavioural analysis device, as shown in figure 9, on the basis of as shown in Figure 7, analog module 20 includes extracting single
Unit 21, transmitting element 22, receiving unit 23 and analogue unit 24.
Wherein, extraction unit 21, for extracting the text interactive information in daily record piece segment information.
Transmitting element 22, for the link information in daily record piece segment information is sent to predetermined system platform.
Receiving unit 23, for the picture interactive information corresponding with link information of reception system platform feedback.
Analogue unit 24, for generating user mutual scene according to text interactive information and the simulation of picture interactive information.
Mark module 30, for marking behavior evaluation information corresponding with user mutual scene.
It should be noted that the explanation of the aforementioned user behavior analysis method to based on artificial intelligence, is also applied for
The user behavior analysis device based on artificial intelligence of the embodiment of the present invention, the use based on artificial intelligence in the embodiment of the present invention
The details not disclosed in family behavioural analysis device, will not be described here.
In sum, the user behavior analysis device based on artificial intelligence of the embodiment of the present invention, sieves according to default daily record
Condition resolution User action log is selected, the daily record piece segment information for meeting Log Filter condition is filtered out, and is believed according to daily record fragment
Breath simulation generates user mutual scene, and then marks behavior evaluation information corresponding with user mutual scene.Thus, by simulation
User mutual scene carries out user behavior analysis, and improve carries out the efficiency of user behavior analysis, is easy to based on Product Experience pair
Product is analyzed, and realizes to the comprehensive of product analysis.
Figure 10 is that the structure of the user behavior analysis device based on artificial intelligence according to further embodiment of the present invention is shown
It is intended to, as shown in Figure 10, on the basis of as shown in Figure 7, the user behavior analysis device based on artificial intelligence also includes obtaining
Module 40 and analysis module 50.
Wherein, acquisition module 40, for obtaining evaluation label to be checked.
Screening module 10 is additionally operable to be gone out and the user mutual scene for evaluating tag match according to behavior evaluation information sifting.
Analysis module 50, for doing regression analysis process according to user mutual scene.
Figure 11 is that the structure of the user behavior analysis device based on artificial intelligence according to a still further embodiment of the present invention is shown
It is intended to, as shown in figure 11, on the basis of as shown in Figure 7, the user behavior analysis device based on artificial intelligence also includes showing
Module 60.
Wherein, display module 60, it is corresponding with default index feature or temporal characteristics for showing in system platform
Data variation trend.
It should be noted that the explanation of the aforementioned user behavior analysis method to based on artificial intelligence, is also applied for
The user behavior analysis device based on artificial intelligence of the embodiment of the present invention, the use based on artificial intelligence in the embodiment of the present invention
The details not disclosed in family behavioural analysis device, will not be described here.
In sum, the user behavior analysis device based on artificial intelligence of the embodiment of the present invention, is handed over user in mark
Mutually after the corresponding behavior evaluation information of scene, evaluation label to be checked is obtained, is gone out and is commented according to behavior evaluation information sifting
The user mutual scene of valency tag match, does regression analysis process according to user mutual scene.Thus, based on Product Experience to producing
Product are analyzed, and are easy to carry out perfect in shape and function and performance optimization to producing piece.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
Example ", or the description of " some examples " etc. mean specific features with reference to the embodiment or example description, structure, material or spy
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in one or more embodiments or example in an appropriate manner.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments or example described in this specification and different embodiments or example can be tied by art personnel
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of user behavior analysis method based on artificial intelligence, it is characterised in that comprise the following steps：
According to default Log Filter condition resolution User action log, the daily record fragment for meeting the Log Filter condition is filtered out
Information；
User mutual scene is generated according to the daily record fragment information simulation；
Mark behavior evaluation information corresponding with the user mutual scene.
2. the method for claim 1, it is characterised in that the basis presets Log Filter condition resolution user behavior day
Will, filters out the daily record piece segment information for meeting the Log Filter condition, including：
Parsing User action log obtains the unstructured information matched with parameter preset；
The unstructured information is converted into into structural data, and data directory is set up according to the structural data；
The data directory according to default Log Filter condition query, filters out the daily record fragment for meeting the Log Filter condition
Information.
3. the method for claim 1, it is characterised in that described user is generated according to the daily record fragment information simulation to hand over
Mutual scene, including：
Extract the text interactive information in the daily record piece segment information；
The link information in the daily record piece segment information is sent to predetermined system platform；
Receive the picture interactive information corresponding with the link information of the system platform feedback；
User mutual scene is generated according to the text interactive information and picture interactive information simulation.
4. the method for claim 1, it is characterised in that in mark behavior corresponding with the user mutual scene
After evaluation information, also include：
Obtain evaluation label to be checked；
Gone out and the user mutual scene for evaluating tag match according to the behavior evaluation information sifting；
Regression analysis process is done according to the user mutual scene.
5. the method as described in claim 1-4 is arbitrary, it is characterised in that also include：
Show data variation trend corresponding with default index feature or temporal characteristics in system platform.
6. a kind of user behavior analysis device based on artificial intelligence, it is characterised in that include：
Screening module, for according to default Log Filter condition resolution User action log, filtering out and meeting the Log Filter
The daily record piece segment information of condition；
Analog module, for generating user mutual scene according to the daily record fragment information simulation；
Mark module, for marking behavior evaluation information corresponding with the user mutual scene.
7. device as claimed in claim 6, it is characterised in that the screening module includes：
Resolution unit, obtains the unstructured information matched with parameter preset for parsing User action log；
Converting unit, for the unstructured information is converted into structural data；
Unit is set up, for data directory being set up according to the structural data；
Screening unit, for the data directory according to default Log Filter condition query, filters out and meets the Log Filter
The daily record piece segment information of condition.
8. device as claimed in claim 6, it is characterised in that the analog module includes：
Extraction unit, for extracting the text interactive information in the daily record piece segment information；
Transmitting element, for the link information in the daily record piece segment information is sent to predetermined system platform；
Receiving unit, for receiving the picture interactive information corresponding with the link information of the system platform feedback；
Analogue unit, for generating user mutual scene according to the text interactive information and picture interactive information simulation.
9. device as claimed in claim 6, it is characterised in that also include：
Acquisition module, for obtaining evaluation label to be checked；
The screening module is additionally operable to be gone out and the user mutual for evaluating tag match according to the behavior evaluation information sifting
Scene；
Analysis module, for doing regression analysis process according to the user mutual scene.
10. the device as described in claim 6-9 is arbitrary, it is characterised in that also include：
Display module, for showing that in system platform data variation corresponding with default index feature or temporal characteristics becomes
Gesture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610941394.XA CN106557410B (en) | 2016-10-25 | 2016-10-25 | User behavior analysis method and apparatus based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610941394.XA CN106557410B (en) | 2016-10-25 | 2016-10-25 | User behavior analysis method and apparatus based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106557410A true CN106557410A (en) | 2017-04-05 |
| CN106557410B CN106557410B (en) | 2019-05-31 |
Family
ID=58443592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610941394.XA Active CN106557410B (en) | 2016-10-25 | 2016-10-25 | User behavior analysis method and apparatus based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106557410B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507612A (en) * | 2017-06-30 | 2017-12-22 | 百度在线网络技术（北京）有限公司 | A kind of method for recognizing sound-groove and device |
| CN108108284A (en) * | 2017-12-26 | 2018-06-01 | 广东欧珀移动通信有限公司 | Log processing method, device, terminal device and storage medium |
| CN108153647A (en) * | 2017-12-26 | 2018-06-12 | 广东欧珀移动通信有限公司 | log processing method, device, terminal device and storage medium |
| CN108197013A (en) * | 2017-12-26 | 2018-06-22 | 广东欧珀移动通信有限公司 | log processing method, device, terminal device and storage medium |
| CN109144836A (en) * | 2018-08-06 | 2019-01-04 | 阿里巴巴集团控股有限公司 | A kind of processing method of operation log, device and electronic equipment |
| CN110585725A (en) * | 2019-09-08 | 2019-12-20 | 北京智明星通科技股份有限公司 | Mobile game user feedback information request method, device and server |
| CN110781204A (en) * | 2019-09-09 | 2020-02-11 | 腾讯大地通途（北京）科技有限公司 | Identification information determination method, device, equipment and storage medium of target object |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1168591A (en) * | 1996-03-06 | 1997-12-24 | 菲利浦电子有限公司 | Screen-phone and method of managing menu of screen-phone |
| US20140108653A1 (en) * | 2012-09-25 | 2014-04-17 | Huawei Technologies Co., Ltd. | Man-Machine Interaction Data Processing Method and Apparatus |
| CN104822156A (en) * | 2015-04-01 | 2015-08-05 | 中国联合网络通信集团有限公司 | User behavior analysis method and device |
| CN104978406A (en) * | 2015-06-11 | 2015-10-14 | 中国科学院自动化研究所 | User behavior analysis method of Internet platform |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105357584A (en) * | 2015-12-11 | 2016-02-24 | Tcl集团股份有限公司 | User behavior log classification uploading method and system based on intelligent television |
| CN105930785A (en) * | 2016-04-15 | 2016-09-07 | 丁盛 | Intelligent concealed-type interaction system |
-
2016
- 2016-10-25 CN CN201610941394.XA patent/CN106557410B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1168591A (en) * | 1996-03-06 | 1997-12-24 | 菲利浦电子有限公司 | Screen-phone and method of managing menu of screen-phone |
| US20140108653A1 (en) * | 2012-09-25 | 2014-04-17 | Huawei Technologies Co., Ltd. | Man-Machine Interaction Data Processing Method and Apparatus |
| CN104822156A (en) * | 2015-04-01 | 2015-08-05 | 中国联合网络通信集团有限公司 | User behavior analysis method and device |
| CN104978406A (en) * | 2015-06-11 | 2015-10-14 | 中国科学院自动化研究所 | User behavior analysis method of Internet platform |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105357584A (en) * | 2015-12-11 | 2016-02-24 | Tcl集团股份有限公司 | User behavior log classification uploading method and system based on intelligent television |
| CN105930785A (en) * | 2016-04-15 | 2016-09-07 | 丁盛 | Intelligent concealed-type interaction system |
Non-Patent Citations (2)
| Title |
|---|
| MATHSHELLY: "超酷算法：日志结构化存储", 《HTTP://BLOG.JOBBOLE.COM/82730/》 * |
| 私语: "用户场景神器—故事板", 《HTTPS://WWW.DOUBAN.COM/NOTE/584457773/》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507612A (en) * | 2017-06-30 | 2017-12-22 | 百度在线网络技术（北京）有限公司 | A kind of method for recognizing sound-groove and device |
| WO2019000991A1 (en) * | 2017-06-30 | 2019-01-03 | 百度在线网络技术（北京）有限公司 | Voice print recognition method and apparatus |
| CN107507612B (en) * | 2017-06-30 | 2020-08-28 | 百度在线网络技术（北京）有限公司 | Voiceprint recognition method and device |
| US11302337B2 (en) | 2017-06-30 | 2022-04-12 | Baidu Online Network Technology (Beijing.) Co., Ltd. | Voiceprint recognition method and apparatus |
| CN108108284A (en) * | 2017-12-26 | 2018-06-01 | 广东欧珀移动通信有限公司 | Log processing method, device, terminal device and storage medium |
| CN108153647A (en) * | 2017-12-26 | 2018-06-12 | 广东欧珀移动通信有限公司 | log processing method, device, terminal device and storage medium |
| CN108197013A (en) * | 2017-12-26 | 2018-06-22 | 广东欧珀移动通信有限公司 | log processing method, device, terminal device and storage medium |
| CN108197013B (en) * | 2017-12-26 | 2022-03-08 | Oppo广东移动通信有限公司 | Log processing method and device, terminal equipment and storage medium |
| CN109144836A (en) * | 2018-08-06 | 2019-01-04 | 阿里巴巴集团控股有限公司 | A kind of processing method of operation log, device and electronic equipment |
| CN110585725A (en) * | 2019-09-08 | 2019-12-20 | 北京智明星通科技股份有限公司 | Mobile game user feedback information request method, device and server |
| CN110781204A (en) * | 2019-09-09 | 2020-02-11 | 腾讯大地通途（北京）科技有限公司 | Identification information determination method, device, equipment and storage medium of target object |
| CN110781204B (en) * | 2019-09-09 | 2024-02-20 | 腾讯大地通途（北京）科技有限公司 | Identification information determining method, device, equipment and storage medium of target object |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106557410B (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106557410A (en) | User behavior analysis method and apparatus based on artificial intelligence | |
| DE112012000853B4 (en) | Discovering, recognizing and bookmarking faces in videos | |
| CN110292775B (en) | Method and device for acquiring difference data | |
| CN112073741A (en) | Live broadcast information processing method and device, electronic equipment and storage medium | |
| CN105654950A (en) | Self-adaptive voice feedback method and device | |
| CN102650999B (en) | A kind of method and system of extracting object attribute value information from webpage | |
| CN106681299A (en) | Event analysis device, event analysis system, event analysis method, and event analysis program | |
| CN107241215B (en) | User behavior prediction method and device | |
| CN103902717A (en) | System and method for personalizing internal portals of enterprises | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| CN107169002A (en) | A kind of personalized interface method for pushing and device recognized based on face | |
| CN106067897A (en) | Information-pushing method based on user terminal location and device | |
| CN104951807A (en) | Stock market emotion determining method and device | |
| CN112231563A (en) | Content recommendation method and device and storage medium | |
| CN114707474A (en) | Report generation method and device, electronic equipment and computer readable storage medium | |
| CN108959475A (en) | A kind of webpage setting method and device | |
| WO2011109195A1 (en) | System and associated method for determining and applying sociocultural characteristics | |
| CN113626624B (en) | Resource identification method and related device | |
| CN113312924A (en) | Risk rule classification method and device based on NLP high-precision analysis label | |
| CN114218514A (en) | Page generation method, device, equipment and storage medium | |
| CN116756576B (en) | Data processing method, model training method, electronic device and storage medium | |
| CN107729486A (en) | A kind of video searching method and device | |
| CN111813816A (en) | Data processing method, data processing device, computer readable storage medium and computer equipment | |
| CN108614886A (en) | A kind of generation method and device of subject of Web site | |
| CN111399731B (en) | Picture operation intention processing method, recommendation method and device, electronic equipment 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 |