CN117788067A - Marketing advertisement feedback data monitoring method and system - Google Patents
Marketing advertisement feedback data monitoring method and system Download PDFInfo
- Publication number
- CN117788067A CN117788067A CN202311857245.1A CN202311857245A CN117788067A CN 117788067 A CN117788067 A CN 117788067A CN 202311857245 A CN202311857245 A CN 202311857245A CN 117788067 A CN117788067 A CN 117788067A
- Authority
- CN
- China
- Prior art keywords
- behavior
- jumping
- party
- monitoring
- path
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 160
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000009191 jumping Effects 0.000 claims abstract description 98
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 239000013598 vector Substances 0.000 claims description 23
- 230000003542 behavioural effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of feedback data monitoring, and particularly discloses a marketing advertisement feedback data monitoring method and a marketing advertisement feedback data monitoring system, wherein the method comprises the steps of sending marketing advertisements to a push engine and receiving behavior paths monitored by the push engine in real time; when the behavior path contains a jump request, inquiring whether the push engine has the data acquisition authority of a jump party or not; when the pushing engine has the data acquisition right of the jumping party, the behavior path is updated according to the monitoring record of the jumping party, otherwise, the jumping time is recorded, and the behavior path is updated according to the jumping time; and determining the evaluation value of each frame of data in the marketing advertisement according to the updated behavior path. According to the invention, the marketing advertisement is sent to the pushing engine, the operation information of the user is recorded in real time, the behavior path is constructed, and the behavior path is analyzed to obtain the evaluation condition of each frame of data, so that the evaluation fineness is greatly improved, and the guidance is stronger.
Description
Technical Field
The invention relates to the technical field of feedback data monitoring, in particular to a marketing advertisement feedback data monitoring method and system.
Background
Marketing advertisement feedback data monitoring is one of the key steps performed to evaluate advertisement campaign effectiveness and optimize advertisement strategies. The existing marketing advertisement feedback data monitoring method comprises click rate (CTR) monitoring, conversion rate monitoring, cost Per Click (CPC), cost per Conversion (CPA) monitoring and the like, wherein CTR is an index for measuring the ratio of advertisement click times to advertisement display times; conversion rate is a measure of the proportion of advertisements that trigger desired actions (e.g., purchase, registration, subscription, etc.); cost Per Click (CPC) and cost per Conversion (CPA) monitoring is used to measure advertisement cost versus corresponding clicks or conversions.
In the prior art, marketing advertisements are considered as a whole, and even if the popularization effect of one marketing advertisement is good, an advertisement provider cannot know which part of content attracts users more, so that the technical problem to be solved by the technical scheme of the invention is how to improve the monitoring evaluation precision of the marketing advertisements.
Disclosure of Invention
The invention aims to provide a marketing advertisement feedback data monitoring method and a marketing advertisement feedback data monitoring system, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a marketing advertising feedback data monitoring method, the method comprising:
sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
when the behavior path contains a jump request, inquiring whether the push engine has the data acquisition authority of a jump party or not;
when the pushing engine has the data acquisition right of the jumping party, updating the behavior path according to the monitoring record of the jumping party, and when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, and updating the behavior path according to the jumping time length;
and determining the evaluation value of each frame of data in the marketing advertisement according to the updated behavior path.
In the process of inquiring whether the push engine has the data acquisition permission of the jumping party, a permission adjustment port facing the receiving party is opened.
As a further scheme of the invention: the step of sending marketing advertisements to the push engine and receiving the behavior paths monitored by the push engine in real time comprises the following steps:
receiving a behavior table input by a management party; the behavior table comprises a behavior name item and a behavior index item;
sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time;
wherein the step of determining the behavior path by the push engine comprises:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
As a further scheme of the invention: when the push engine has the data acquisition right of the jumping party, the behavior path is updated according to the monitoring record of the jumping party, and when the push engine does not have the data acquisition right of the jumping party, the jump time length is recorded, and the step of updating the behavior path according to the jump time length comprises the following steps:
when the pushing engine has the data acquisition right of the jumping party, reading the behavior monitoring record of the jumping party and updating the behavior path; the behavior monitoring record is a phrase;
calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records according to the duration;
when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, inquiring the classified behavior monitoring records according to the jumping time length, and updating the behavior path.
As a further scheme of the invention: the step of calculating the time length of the behavior monitoring record and classifying the behavior monitoring record according to the time length comprises the following steps:
calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records with duration differences smaller than preset numerical values;
converting elements in the behavior monitoring record into Word vectors based on a Word2Vec tool;
calculating the similarity between any two behavior monitoring records in the similar behavior monitoring records based on the word vectors, performing secondary classification on the behavior monitoring records according to the similarity, and calculating the duty ratio according to the number of the behavior monitoring records subjected to secondary classification to serve as the selection probability;
the selection probability is used for adjusting the inquiring process of the behavior monitoring records after inquiring the classified behavior monitoring records according to the jumping time length; the calculation process of the similarity degree comprises the following steps:
wherein Sim is the similarity of two behavior monitoring records, alpha and beta are preset coefficients, d i E (d) is the distance between the i-th corresponding two word vectors i ) Is d i Is the average value of Var (d) i ) Is d i N is the total number of word vectors; a is that j For the jth numerical value in the ith word vector in one of the behavior monitoring records, B j For the j-th numerical value in the i-th word vector in another behavior monitoring record, p is a pre-set index, and m is the dimension of the word vector.
As a further scheme of the invention: when the push engine does not have the data acquisition right of the jumping party, recording the jumping time length, inquiring the classified behavior monitoring records according to the jumping time length, and updating the behavior path, wherein the step of updating the behavior path comprises the following steps:
recording the jumping time length when the pushing engine does not have the data acquisition right of the jumping party;
inquiring the corresponding behavior monitoring record and the selection probability thereof according to the jump time length, selecting a target record according to the selection probability, and updating the behavior path.
As a further scheme of the invention: the step of determining the evaluation value of each frame of data in the marketing advertisement according to the updated behavior path comprises the following steps:
inserting a numerical item into the behavior table by a management party, wherein the numerical item is used for representing the preference degree of a user to each element of the behavior table;
counting all behavior paths containing unique identification codes, and accumulating the sum of preference of each frame of data;
for any frame data, stacking the sum of the preference degrees of all other frame data according to preset weights to serve as an evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
The technical scheme of the invention also provides a marketing advertisement feedback data monitoring system, which comprises:
the behavior path monitoring module is used for sending marketing advertisements to the pushing engine and receiving behavior paths monitored by the pushing engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
the permission query module is used for querying whether the push engine has the data acquisition permission of the jumping party or not when the action path contains the jumping request;
the behavior path updating module is used for updating the behavior path according to the monitoring record of the jumping party when the pushing engine has the data acquisition right of the jumping party, and recording the jumping time length and updating the behavior path according to the jumping time length when the pushing engine does not have the data acquisition right of the jumping party;
and the evaluation value determining module is used for determining the evaluation value of each frame of data in the marketing advertisement according to the updated behavior path.
In the process of inquiring whether the push engine has the data acquisition permission of the jumping party, a permission adjustment port facing the receiving party is opened.
As a further scheme of the invention: the behavior path monitoring module comprises:
the behavior table receiving unit is used for receiving the behavior table input by the management party; the behavior table comprises a behavior name item and a behavior index item;
the path receiving unit is used for sending marketing advertisements to the pushing engine and receiving behavior paths monitored by the pushing engine in real time;
wherein the step of determining the behavior path by the push engine comprises:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
As a further scheme of the invention: the behavior path updating module comprises:
the first updating unit is used for reading the behavior monitoring record of the jumping party and updating the behavior path when the pushing engine has the data acquisition right of the jumping party; the behavior monitoring record is a phrase;
the classification unit is used for calculating the duration of the behavior monitoring records and classifying the behavior monitoring records according to the duration;
and the second updating unit is used for recording the jump time length when the pushing engine does not have the data acquisition right of the jump party, inquiring the classified behavior monitoring record according to the jump time length, and updating the behavior path.
As a further scheme of the invention: the evaluation value determination module includes:
the numerical item inserting unit is used for inserting a numerical item into the behavior table by the management party and used for representing the preference degree of the user to each element of the behavior table;
a preference degree accumulating unit for counting all the behavior paths containing the unique identification codes and accumulating the sum of preference degrees of the frame data;
the superposition unit is used for superposing the preference sum of all other frame data according to the preset weight on any frame data to be used as the evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, marketing advertisements are sent to the pushing engine, operation information of a user is recorded in real time, a behavior path is constructed, when skip operation exists, the information after skip is acquired or predicted according to authority grant information, a plurality of complete behavior paths are obtained, the behavior paths are analyzed, the evaluation condition of each frame of data is obtained, the evaluation fineness is greatly improved, and the guidance is stronger.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a block flow diagram of a method for marketing advertising feedback data monitoring.
FIG. 2 is a first sub-flowchart of a marketing advertising feedback data monitoring method.
FIG. 3 is a second sub-flowchart of a marketing advertising feedback data monitoring method.
FIG. 4 is a third sub-flowchart of a marketing advertising feedback data monitoring method.
FIG. 5 is a block diagram of the composition of a marketing advertising feedback data monitoring system.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flow chart of a method for monitoring feedback data of marketing advertisement, in an embodiment of the invention, a method for monitoring feedback data of marketing advertisement, the method includes:
step S100: sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
the pushing engine is an APP with advertisement pushing function and the like, and can receive and display marketing advertisements; the marketing advertisement to be pushed is sent to a pushing engine, and the pushing engine collects the operation of a user when the marketing advertisement is played, and the process requires authorization of the user; in general, when using a push engine (including a commonly used video App, an image App, an audio App, and a text App), a user grants operation collection rights in the process of registering an account.
After the push engine collects the operation of the user, connecting all the operations according to the time sequence to obtain an operation chain called a behavior path; for marketing advertisements, upon browsing by a user, a behavioral path is generated, each operation in the behavioral path containing time information.
Step S200: when the behavior path contains a jump request, inquiring whether the push engine has the data acquisition authority of a jump party or not;
in the process of users browsing marketing advertisements, one important operation is jump request, such as click request access, which represents that users are attracted by the content of the marketing advertisements and want to further inquire about related content; some providers of marketing advertisements are not the same main body as the pushing engine, at this time, a jump process will occur, the operation performed by the user after the jump belongs to the data collected by the marketing advertisement provider (called the jump party) (the operation behavior background can be monitored, no personal information of the user is involved, the operation information is generally collected in real time when the jump request is sent, the user sends a confirmation instruction), the pushing advertisement can be directly obtained if the pushing advertisement has the authority to obtain the data, the behavior path is updated, if the pushing advertisement does not have the authority to obtain the data, only how long the user jumps, and the jump time is obtained by subtracting the sending time of the jump request from the time of returning to the pushing engine.
Step S300: when the pushing engine has the data acquisition right of the jumping party, updating the behavior path according to the monitoring record of the jumping party, and when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, and updating the behavior path according to the jumping time length;
when the pushing engine has the data acquisition right of the jumping party, the monitoring record of the jumping party is read, the monitoring record is similar to the behavior path and only belongs to two acquisition main bodies, the format conversion problem is related during merging, the format conversion process is simpler, and the two parties can adopt the same protocol. When the monitoring records are read, the jump time is synchronously recorded, the monitoring records corresponding to the marketing advertisements are classified by the jump time, and a corresponding relation from the jump time to the monitoring record set is established.
When the pushing engine does not have the data acquisition right of the jumping party, the jumping time length is recorded, and according to the jumping time length and the corresponding relation generated in the content, a possible monitoring record can be selected and selected, and the behavior path is updated, so that the method is a simulation process.
Step S400: determining an evaluation value of each frame of data in the marketing advertisement according to the updated behavior path;
and determining the operation corresponding to each frame of data in the marketing advertisement according to the updated behavior path, and calculating the evaluation value of each frame of data, wherein the evaluation value is used for representing the preference influence degree of each frame of data on the user.
It should be noted that, in the process of querying whether the push engine has the data acquisition authority of the jumping party, an authority adjustment port facing the receiving party is opened.
The meaning of the open permission adjustment port is that although the data acquisition process has the permission granted by the user, the user can still upload a control instruction with a higher level, and the permission is withdrawn at any time, so that the push engine cannot acquire the monitoring record. In this case, when the jump party records only the operation, it cannot correspond to the personal information, and the information security of the user is higher. In colloquially, in the case of a jump party only record operation, if the push engine can acquire the monitoring record, the push engine and the monitoring record are easily connected, and when the user refuses the push engine to acquire the information of the jump party, the connection process cannot be completed.
FIG. 2 is a first sub-flowchart of a method for monitoring feedback data of marketing advertisements, wherein the steps of sending marketing advertisements to a push engine and receiving behavior paths monitored by the push engine in real time include:
step S101: receiving a behavior table input by a management party; the behavior table comprises a behavior name item and a behavior index item;
step S102: sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time;
the behavior path consists of various operations, the characteristics and names of the various operations are preset by a management party, the operations comprise praise, collection, forwarding, skip and the like, the characteristics are instructions or labels generated by a background when the operations are executed, the operations which the management party wants to monitor are characterized, and the behavior table is the value space of each element in the behavior path.
The marketing advertisement is sent to the push engine, the push engine is promoted to the user, in the process, the push engine monitors the behavior of the user under the authority granted by the user, and then a behavior path is generated, and the specific process is as follows:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
The above content specifically describes the working process of the pushing engine, after the pushing engine receives the marketing advertisement, the pushing engine copies multiple scores and sends the marketing advertisement to personal devices of different users, and monitors input data of the users in real time, wherein the input data is the operation of the users, the input data is compared and matched with behavior index items in a behavior table, so that the name of the operation of the users can be determined, the corresponding name is read and counted, and a behavior path can be obtained; since each user has a behavior path, an identification code needs to be inserted into the behavior path to characterize which user each behavior path corresponds to.
FIG. 3 is a block diagram of a second sub-process of a method for monitoring feedback data of a marketing advertisement, wherein when a push engine has a data acquisition right of a jumper, a behavior path is updated according to monitoring records of the jumper, and when the push engine does not have the data acquisition right of the jumper, a jump time length is recorded, and the step of updating the behavior path according to the jump time length includes:
step S301: when the pushing engine has the data acquisition right of the jumping party, reading the behavior monitoring record of the jumping party and updating the behavior path; the behavior monitoring record is a phrase;
step S302: calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records according to the duration;
step S303: when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, inquiring the classified behavior monitoring records according to the jumping time length, and updating the behavior path.
In an example of the technical solution of the present invention, when the push engine has the data acquisition right of the jumping party, the behavior monitoring record of the jumping party is directly read under the right, and the behavior monitoring record is different from the acquisition subject of the behavior path, and may have a difference in format, so that the transcoding process may be involved, but both are essentially the same and are operation names arranged in time sequence.
Step S302 is related to a parallel process in step S301, in which, each time a behavior monitoring record is obtained, the duration is calculated, the behavior monitoring records can be classified according to the duration, when the pushing engine does not have the data obtaining right of the jump party after the classification is completed, the behavior monitoring record of the corresponding class can be queried according to the jump duration, and some behavior monitoring records are randomly read to be used as data without the data obtaining right, so that the fitness is higher.
Specifically, the step of calculating the duration of the behavior monitoring record and classifying the behavior monitoring record according to the duration includes:
calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records with duration differences smaller than preset numerical values;
converting elements in the behavior monitoring record into Word vectors based on a Word2Vec tool;
calculating the similarity between any two behavior monitoring records in the similar behavior monitoring records based on the word vectors, performing secondary classification on the behavior monitoring records according to the similarity, and calculating the duty ratio according to the number of the behavior monitoring records subjected to secondary classification to serve as the selection probability;
the selection probability is used for adjusting the inquiring process of the behavior monitoring records after inquiring the classified behavior monitoring records according to the jumping time length; the calculation process of the similarity degree comprises the following steps:
wherein Sim is the similarity of two behavior monitoring records, alpha and beta are preset coefficients, d i E (d) is the distance between the i-th corresponding two word vectors i ) Is d i Is the average value of Var (d) i ) Is d i N is the total number of word vectors; a is that j Monitoring the direction of the ith word in the record for one of the behaviorsThe jth number of values in the quantity, B j For the j-th numerical value in the i-th word vector in another behavior monitoring record, p is a pre-set index, and m is the dimension of the word vector.
In an example of the technical scheme of the present invention, the process of step S302 is specifically defined, the classification process is defined as a gradient type two-stage classification process, the behavior monitoring records are classified for the first time according to the duration, then the words in the behavior monitoring records are converted into word vectors, a word vector group corresponding to the behavior monitoring records is obtained, and finally the word vector group is compared, so that multiple behavior monitoring records with the same duration can be further classified.
On the basis of the above, the selection probability is determined according to the number corresponding to each secondary classification result, when the push engine does not have the data acquisition right of the jump party, the behavior monitoring record of a certain large class (first classification) is selected according to the jump time length, and then the specific behavior monitoring record (second classification) is randomly selected according to the selection probability.
As a preferred embodiment of the present invention, when the push engine does not have the data acquisition right of the jumping party, recording the jumping time length, and querying the classified behavior monitoring record according to the jumping time length, and updating the behavior path includes:
recording the jumping time length when the pushing engine does not have the data acquisition right of the jumping party;
inquiring the corresponding behavior monitoring record and the selection probability thereof according to the jump time length, selecting a target record according to the selection probability, and updating the behavior path.
In an example of the present invention, when the push engine does not have the data acquisition right of the jump party, one of the behavior monitoring records is selected according to the jump duration and the selection probability, which is called a target record, and this is the inverse of the above-mentioned classification process.
FIG. 4 is a third sub-flowchart of a method for monitoring feedback data of a marketing advertisement, wherein the step of determining an evaluation value of each frame of data in the marketing advertisement according to an updated behavior path includes:
step S401: inserting a numerical item into the behavior table by a management party, wherein the numerical item is used for representing the preference degree of a user to each element of the behavior table;
step S402: counting all behavior paths containing unique identification codes, and accumulating the sum of preference of each frame of data;
step S403: for any frame data, stacking the sum of the preference degrees of all other frame data according to preset weights to serve as an evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
The above-mentioned contents specifically define the determination process of the evaluation value, and a numerical item is added in the behavior table by the management side, wherein the numerical item is used for representing the preference degree corresponding to each operation; counting all action paths corresponding to the same marketing advertisement, inquiring the numerical value and the frame data corresponding to each element in the action paths, accumulating the numerical value corresponding to each frame data to obtain an array corresponding to the marketing advertisement, wherein the element sequence in the array corresponds to the sequence of the frame data, and the element value is the accumulated numerical value.
Furthermore, since each frame of data is not isolated, the present application introduces a scheme for correcting each frame of data based on other values, where for a certain frame of data, the value of all other frames of data is multiplied by a weight, so as to calculate a value, which is called an evaluation value, and the weight can be independently input into a piecewise function by a manager, where an argument of the piecewise function is a frame number (distance) from the current frame of data, and a dependent variable is a weight.
In general, in order to simplify the operation, the manager directly sets the weight to a normal distribution, and the closer the weight is to the current frame data, the greater the influence is to the current frame data, and the greater the weight is.
Fig. 5 is a block diagram of a marketing advertisement feedback data monitoring system, in which the system 10 includes:
the behavior path monitoring module 11 is used for sending marketing advertisements to the pushing engine and receiving the behavior paths monitored by the pushing engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
the permission query module 12 is configured to query whether the push engine has data acquisition permission of a jumping party when the behavior path contains a jump request;
the behavior path updating module 13 is configured to update the behavior path according to the monitoring record of the jumping party when the pushing engine has the data acquisition right of the jumping party, and record the jumping duration and update the behavior path according to the jumping duration when the pushing engine does not have the data acquisition right of the jumping party;
the evaluation value determining module 14 is configured to determine an evaluation value of each frame of data in the marketing advertisement according to the updated behavior path.
In the process of inquiring whether the push engine has the data acquisition permission of the jumping party, a permission adjustment port facing the receiving party is opened.
Further, the behavior path monitoring module 11 includes:
the behavior table receiving unit is used for receiving the behavior table input by the management party; the behavior table comprises a behavior name item and a behavior index item;
the path receiving unit is used for sending marketing advertisements to the pushing engine and receiving behavior paths monitored by the pushing engine in real time;
wherein the step of determining the behavior path by the push engine comprises:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
Specifically, the behavior path updating module 13 includes:
the first updating unit is used for reading the behavior monitoring record of the jumping party and updating the behavior path when the pushing engine has the data acquisition right of the jumping party; the behavior monitoring record is a phrase;
the classification unit is used for calculating the duration of the behavior monitoring records and classifying the behavior monitoring records according to the duration;
and the second updating unit is used for recording the jump time length when the pushing engine does not have the data acquisition right of the jump party, inquiring the classified behavior monitoring record according to the jump time length, and updating the behavior path.
Furthermore, the evaluation value determination module 14 includes:
the numerical item inserting unit is used for inserting a numerical item into the behavior table by the management party and used for representing the preference degree of the user to each element of the behavior table;
a preference degree accumulating unit for counting all the behavior paths containing the unique identification codes and accumulating the sum of preference degrees of the frame data;
the superposition unit is used for superposing the preference sum of all other frame data according to the preset weight on any frame data to be used as the evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. A method of marketing advertising feedback data monitoring, the method comprising:
sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
when the behavior path contains a jump request, inquiring whether the push engine has the data acquisition authority of a jump party or not;
when the pushing engine has the data acquisition right of the jumping party, updating the behavior path according to the monitoring record of the jumping party, and when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, and updating the behavior path according to the jumping time length;
determining an evaluation value of each frame of data in the marketing advertisement according to the updated behavior path;
in the process of inquiring whether the push engine has the data acquisition permission of the jumping party, a permission adjustment port facing the receiving party is opened.
2. The method of claim 1, wherein the step of sending marketing advertisements to the push engine and receiving the behavior paths monitored by the push engine in real time comprises:
receiving a behavior table input by a management party; the behavior table comprises a behavior name item and a behavior index item;
sending marketing advertisements to a push engine, and receiving behavior paths monitored by the push engine in real time;
wherein the step of determining the behavior path by the push engine comprises:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
3. The method for monitoring feedback data of marketing advertisement according to claim 1, wherein the step of updating the behavior path according to the monitoring record of the jumping party when the pushing engine has the data acquisition right of the jumping party, and recording the jumping time length when the pushing engine does not have the data acquisition right of the jumping party, comprises:
when the pushing engine has the data acquisition right of the jumping party, reading the behavior monitoring record of the jumping party and updating the behavior path; the behavior monitoring record is a phrase;
calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records according to the duration;
when the pushing engine does not have the data acquisition right of the jumping party, recording the jumping time length, inquiring the classified behavior monitoring records according to the jumping time length, and updating the behavior path.
4. The marketing advertising feedback data monitoring method of claim 3, wherein the step of calculating a duration of the behavioral monitoring record and classifying the behavioral monitoring record according to the duration comprises:
calculating the duration of the behavior monitoring records, and classifying the behavior monitoring records with duration differences smaller than preset numerical values;
converting elements in the behavior monitoring record into Word vectors based on a Word2Vec tool;
calculating the similarity between any two behavior monitoring records in the similar behavior monitoring records based on the word vectors, performing secondary classification on the behavior monitoring records according to the similarity, and calculating the duty ratio according to the number of the behavior monitoring records subjected to secondary classification to serve as the selection probability;
the selection probability is used for adjusting the inquiring process of the behavior monitoring records after inquiring the classified behavior monitoring records according to the jumping time length; the calculation process of the similarity degree comprises the following steps:
Var(d i )＝E((d i -E(d i )) 2 )；
wherein Sim is the similarity of two behavior monitoring records, alpha and beta are preset coefficients, d i E (d) is the distance between the i-th corresponding two word vectors i ) Is d i Is the average value of Var (d) i ) Is d i N is the total number of word vectors; a is that j For the jth numerical value in the ith word vector in one of the behavior monitoring records, B j For the j-th numerical value in the i-th word vector in another behavior monitoring record, p is a pre-set index, and m is the dimension of the word vector.
5. The method for monitoring feedback data of marketing advertisement according to claim 1, wherein when the push engine does not have the data acquisition right of the jumping party, recording the jumping time length, inquiring the classified behavior monitoring record according to the jumping time length, and updating the behavior path comprises:
recording the jumping time length when the pushing engine does not have the data acquisition right of the jumping party;
inquiring the corresponding behavior monitoring record and the selection probability thereof according to the jump time length, selecting a target record according to the selection probability, and updating the behavior path.
6. The marketing advertisement feedback data monitoring method of claim 1, wherein the step of determining an evaluation value of each frame of data in the marketing advertisement based on the updated behavioral path comprises:
inserting a numerical item into the behavior table by a management party, wherein the numerical item is used for representing the preference degree of a user to each element of the behavior table;
counting all behavior paths containing unique identification codes, and accumulating the sum of preference of each frame of data;
for any frame data, stacking the sum of the preference degrees of all other frame data according to preset weights to serve as an evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
7. A marketing advertising feedback data monitoring system, the system comprising:
the behavior path monitoring module is used for sending marketing advertisements to the pushing engine and receiving behavior paths monitored by the pushing engine in real time; the behavior path contains a time tag, and the time tag is the relative time in marketing advertisements;
the permission query module is used for querying whether the push engine has the data acquisition permission of the jumping party or not when the action path contains the jumping request;
the behavior path updating module is used for updating the behavior path according to the monitoring record of the jumping party when the pushing engine has the data acquisition right of the jumping party, and recording the jumping time length and updating the behavior path according to the jumping time length when the pushing engine does not have the data acquisition right of the jumping party;
the evaluation value determining module is used for determining the evaluation value of each frame of data in the marketing advertisement according to the updated behavior path;
in the process of inquiring whether the push engine has the data acquisition permission of the jumping party, a permission adjustment port facing the receiving party is opened.
8. The marketing advertising feedback data monitoring system of claim 7, wherein the behavioral path monitoring module comprises:
the behavior table receiving unit is used for receiving the behavior table input by the management party; the behavior table comprises a behavior name item and a behavior index item;
the path receiving unit is used for sending marketing advertisements to the pushing engine and receiving behavior paths monitored by the pushing engine in real time;
wherein the step of determining the behavior path by the push engine comprises:
copying the marketing advertisement, determining a unique identification code and pushing copy content containing the unique identification code;
monitoring input data of a user in real time, matching the input data with a behavior index item, recording success time when the matching is successful, and reading a matched behavior name;
and arranging the behavior names in time sequence to obtain a behavior path, and connecting the behavior path with the unique identification code.
9. The marketing advertising feedback data monitoring system of claim 7, wherein the behavioral path update module comprises:
the first updating unit is used for reading the behavior monitoring record of the jumping party and updating the behavior path when the pushing engine has the data acquisition right of the jumping party; the behavior monitoring record is a phrase;
the classification unit is used for calculating the duration of the behavior monitoring records and classifying the behavior monitoring records according to the duration;
and the second updating unit is used for recording the jump time length when the pushing engine does not have the data acquisition right of the jump party, inquiring the classified behavior monitoring record according to the jump time length, and updating the behavior path.
10. The marketing advertising feedback data monitoring system of claim 7, wherein the evaluation value determination module comprises:
the numerical item inserting unit is used for inserting a numerical item into the behavior table by the management party and used for representing the preference degree of the user to each element of the behavior table;
a preference degree accumulating unit for counting all the behavior paths containing the unique identification codes and accumulating the sum of preference degrees of the frame data;
the superposition unit is used for superposing the preference sum of all other frame data according to the preset weight on any frame data to be used as the evaluation value of the current frame data;
wherein the weight conforms to a normal distribution centered on the frame data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311857245.1A CN117788067B (en) | 2023-12-29 | 2023-12-29 | Marketing advertisement feedback data monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311857245.1A CN117788067B (en) | 2023-12-29 | 2023-12-29 | Marketing advertisement feedback data monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117788067A true CN117788067A (en) | 2024-03-29 |
| CN117788067B CN117788067B (en) | 2024-05-31 |
Family
ID=90392488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311857245.1A Active CN117788067B (en) | 2023-12-29 | 2023-12-29 | Marketing advertisement feedback data monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117788067B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114040012A (en) * | 2021-11-01 | 2022-02-11 | 东莞深创产业科技有限公司 | Information query pushing method and device and computer equipment |
| CN116739670A (en) * | 2023-08-16 | 2023-09-12 | 北京三人行时代数字科技有限公司 | Advertisement pushing marketing system and method based on big data |
| CN117029863A (en) * | 2023-10-10 | 2023-11-10 | 中汽信息科技(天津)有限公司 | Feedback type traffic path planning method and system |
-
2023
- 2023-12-29 CN CN202311857245.1A patent/CN117788067B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114040012A (en) * | 2021-11-01 | 2022-02-11 | 东莞深创产业科技有限公司 | Information query pushing method and device and computer equipment |
| CN116739670A (en) * | 2023-08-16 | 2023-09-12 | 北京三人行时代数字科技有限公司 | Advertisement pushing marketing system and method based on big data |
| CN117029863A (en) * | 2023-10-10 | 2023-11-10 | 中汽信息科技(天津)有限公司 | Feedback type traffic path planning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117788067B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mishra et al. | A web recommendation system considering sequential information | |
| US7016889B2 (en) | System and method for identifying useful content in a knowledge repository | |
| US8560675B2 (en) | Determining projection weights based on a census data | |
| US20060195443A1 (en) | Information prioritisation system and method | |
| US20030030835A1 (en) | Printing control apparatus and a method of charging for printing | |
| CN110852852A (en) | Industrial Internet product recommendation system and method | |
| US20070094384A1 (en) | Macro information generation system, macro information generation device, macro information generation method and macro information generation program | |
| US7840578B2 (en) | Method for determining validity of command and system thereof | |
| US9183301B2 (en) | Search engine optimization performance valuation | |
| US20080243617A1 (en) | Keyword advertisement using ranking of advertisers | |
| GB2386439A (en) | Database analysis system | |
| US20020128907A1 (en) | Information delivery scheme and advertisement providing scheme using social filtering technique | |
| US20130282518A1 (en) | Method, system and controller for providing goods and/or services to consumers | |
| JP3872689B2 (en) | Security policy creation support system and security measure decision support system | |
| US20070179933A1 (en) | Method and system for providing information on article of commerce | |
| Gray et al. | Correcting for non-participation bias in health surveys using record-linkage, synthetic observations and pattern mixture modelling | |
| JP2011022675A (en) | Advertisement charging device and method | |
| KR20030007915A (en) | A system and related methods for dynamically selecting publication content | |
| JP2006053616A (en) | Server device, web site recommendation method and program | |
| CN117788067B (en) | Marketing advertisement feedback data monitoring method and system | |
| Colonna et al. | A retrospective assessment of COVID-19 model performance in the USA | |
| CN114691894B (en) | Paperless financial data management method for electronic information full-link knowledge graph | |
| Liu et al. | Exploiting semantic descriptions of products and user profiles for recommender systems | |
| KR100666201B1 (en) | Method for providing a search service and system for executing the method | |
| KR101182529B1 (en) | Method For Providing A Search Service And System For Executing The Method |
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 |