CN117035846A - Information prediction method and device and related equipment - Google Patents
Information prediction method and device and related equipment Download PDFInfo
- Publication number
- CN117035846A CN117035846A CN202311201534.6A CN202311201534A CN117035846A CN 117035846 A CN117035846 A CN 117035846A CN 202311201534 A CN202311201534 A CN 202311201534A CN 117035846 A CN117035846 A CN 117035846A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- event
- user
- model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000003993 interaction Effects 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 34
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000000875 corresponding effect Effects 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 35
- 230000005284 excitation Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013179 statistical model Methods 0.000 claims description 13
- 230000002596 correlated effect Effects 0.000 claims description 8
- 238000012905 input function Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 10
- 230000006399 behavior Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 101000822695 Clostridium perfringens (strain 13 / Type A) Small, acid-soluble spore protein C1 Proteins 0.000 description 1
- 101000655262 Clostridium perfringens (strain 13 / Type A) Small, acid-soluble spore protein C2 Proteins 0.000 description 1
- 101000655256 Paraclostridium bifermentans Small, acid-soluble spore protein alpha Proteins 0.000 description 1
- 101000655264 Paraclostridium bifermentans Small, acid-soluble spore protein beta Proteins 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides an information prediction method, an information prediction device and related equipment, and relates to the technical field of information processing. Wherein the method comprises the following steps: acquiring a plurality of event information corresponding to a target user, wherein each event information comprises data for indicating an event type of an interaction event between the target user and a target commodity and data for indicating occurrence time information of the interaction event, and the interaction event comprises a purchase event; training an initial model for indicating a time sequence point process corresponding to the purchase event based on a plurality of event information to obtain a target model; according to the target model, the purchase intention information is predicted, the purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment, and the behavior characteristics of the user can be deeply analyzed from the time dimension, so that the obtained prediction result is more reliable.
Description
Technical Field
The disclosure relates to the technical field of information processing, and in particular relates to an information prediction method, an information prediction device and related equipment.
Background
At the moment of commercial backlog and vigorous competition of large electronic commerce platforms, how to mine potential consumers in massive user data becomes a problem to be solved by related enterprises.
In order to mine potential consumers, related enterprises can conduct user purchase intention prediction, at present, the related technologies mostly adopt trained prediction models to predict the user purchase intention, and the prediction models are used for conducting intention prediction according to user portraits corresponding to purchase behaviors, but lack of deep mining on user data, so that reliability of output results of the prediction models is low.
Disclosure of Invention
The disclosure aims to provide an information prediction method, an information prediction device and related equipment, which are used for solving the technical problem that the reliability of a prediction result is low when the purchase intention of a user is predicted in the related technology.
In a first aspect, an embodiment of the present disclosure provides an information prediction method, including:
acquiring a plurality of event information corresponding to a target user, wherein each event information comprises first data and second data, the first data is used for indicating the event type of an interaction event between the target user and a target commodity, the second data is used for indicating the occurrence time information of the interaction event between the target user and the target commodity, and the interaction event comprises a purchase event;
training an initial model based on the event information to obtain a target model, wherein the initial model is used for indicating a time sequence point process corresponding to the purchase event;
and predicting purchase intention information according to a target model, wherein the purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment.
In one embodiment, the training the initial model based on the plurality of event information to obtain the target model includes:
acquiring user attributes of the target user;
determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
training an initial model based on the user information and the event information to obtain a target model.
In one embodiment, the interactive event further includes other events, the other events being events other than the purchase event, the initial model includes a first model portion for indicating a probability that the purchase event occurs independently within a target period, and a second model portion for indicating a probability that the purchase event occurs under the influence of the other events within the target period, the target period being a history period corresponding to the plurality of event information, the user information being used to train the first model portion, and the plurality of event information being used to train the second model portion.
In one embodiment, the target period includes a first sub-period and a second sub-period, the first sub-period corresponding to a time earlier than the second sub-period corresponding to a time;
the second model part comprises an excitation function, wherein the input of the excitation function is any time in the target period, the function value of the excitation function is positively correlated with the time of the input function in the first subperiod, and the function value of the excitation function is negatively correlated with the time of the input function in the second subperiod.
In one embodiment, the training the initial model based on the user information and the plurality of event information to obtain the target model includes:
performing likelihood estimation on model parameters of an initial model based on the user information and the event information to obtain target parameters;
and generating the target model according to the target parameters and the model framework of the initial model.
In one embodiment, the predicting purchase intention information according to the goal model includes:
obtaining a statistical model according to the target model, wherein the statistical model is used for indicating mathematical distribution of the purchase event in time;
and conducting derivative calculation on the statistical model based on the target moment to obtain the purchase intention information.
In a second aspect, an embodiment of the present disclosure further provides an information prediction apparatus, including:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring a plurality of event information corresponding to a target user, each event information comprises first data and second data, the first data is used for indicating the event type of an interaction event between the target user and a target commodity, the second data is used for indicating the occurrence time information of the interaction event between the target user and the target commodity, and the interaction event comprises a purchase event;
the training module is used for training an initial model based on the event information to obtain a target model, wherein the initial model is used for indicating a time sequence point process corresponding to the purchase event;
and the prediction module is used for predicting purchase intention information according to a target model, wherein the purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment.
In one embodiment, the training module comprises:
the attribute acquisition sub-module is used for acquiring the user attribute of the target user;
the information determination submodule is used for determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
and the training sub-module is used for training the initial model based on the user information and the event information to obtain a target model.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program implements the steps of the information prediction method described above when executed by the processor.
In a fourth aspect, the disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the information prediction method described above.
In the embodiment of the disclosure, compared with a mode of predicting the purchase intention of the user according to the user portrait, by analyzing the interaction event generated between the user and the commodity, namely through the event information corresponding to the target user, an initial model for indicating the time sequence point process of purchasing the target commodity by the target user is trained to obtain the target model, and the purchase intention of the target commodity by the target user at the target moment is predicted according to the target model, and the behavior characteristics of the user are deeply analyzed from the time dimension, so that the obtained prediction result is more reliable.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are needed in the description of the embodiments of the present disclosure will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
FIG. 1 is a flow chart of an information prediction method provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart of another information prediction method provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an information prediction apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some embodiments of the present disclosure, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
Referring to fig. 1, fig. 1 is a flowchart of an information prediction method provided in the present disclosure, as shown in fig. 1, including the following steps:
step S101, acquiring a plurality of event information corresponding to a target user.
Wherein each of the event information includes first data for indicating an event type of an interaction event between the target user and the target commodity and second data for indicating occurrence time information of the interaction event between the target user and the target commodity, the interaction event including a purchase event.
The target user may be understood as a user interested in the target commodity.
For example, a user who purchases a target commodity may be determined as the target user, and a user who generates a number of interaction events with the target commodity that is greater than a first preset threshold may be determined as the target user.
Such interaction events include, but are not limited to: link click events (e.g., clicking on a merchandise detail page link or a merchandise purchase link for a target merchandise), collection events (e.g., adding a target merchandise to a shopping cart or wish list), phone consultation events, store-to-store communication events, and purchase events.
In application, a plurality of event information may be recorded and stored in the form of (first data, "second data"), for example, the plurality of event information may be:
(purchase, "2017-03-15 10:30:24"), (telephone consultation, "2022-12-25 20:12:23"), (store-to-store communication, "2022-12-27 14:30:24").
It should be noted that in the present disclosure, the above-mentioned target commodity is understood to be a luxury commodity, a gold and silver jewelry, a car, a house, and the like, which are high-priced commodities.
Step S102, training an initial model based on the event information to obtain a target model.
The initial model is used for indicating a time sequence point process corresponding to the purchase event.
The time sequence point process corresponding to the purchase event is used for: and predicting the occurrence time of the next purchase event according to a plurality of interaction events of the target user and the target commodity in the history period.
Step S103, predicting purchase intention information according to the target model.
The purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment.
The target time may be adaptively selected according to actual requirements, for example: current time, or some time in the future.
In the present disclosure, compared with a method of predicting a purchase intention of a user according to a user portrait, by analyzing an interaction event generated between the user and a commodity, that is, by event information corresponding to a target user, an initial model for indicating a time sequence point process of purchasing the target commodity by the target user is trained to obtain a target model, and the purchase intention of the target commodity by the target user at a target moment is predicted according to the target model, and the behavior characteristics of the user are further analyzed from a time dimension, so that the obtained prediction result is more reliable.
In one embodiment, the training the initial model based on the plurality of event information to obtain the target model includes:
acquiring user attributes of the target user;
determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
training an initial model based on the user information and the event information to obtain a target model.
Illustratively, the user attributes include at least one of:
the gender of the target user;
age of the target user;
marital status of the target user;
revenue status of the target user (e.g., monthly or annual revenue, etc.);
the job of the target user;
number of nurturing of the target user;
credit rating of the target user.
For example, after obtaining the user attribute of the target user, the user attribute may be converted into the input data input by the adaptation network, and then the input data is input to a preset neural network model to obtain the user information;
the neural network model may be a perceptron model.
For example, the model form of the perceptron model may be as shown in formula (1):
wherein σ (-) is an activation function (e.g., sigmod function-))，X A For a feature matrix composed of a plurality of user attributes respectively corresponding to a plurality of users, < >>For a parameter matrix for normalizing a plurality of data included in a user attribute, Y A For a matrix composed of a plurality of user information corresponding to a plurality of users, Y A ＝(…,y a ,…)，y a It is understood that the user a's underlying purchase intent to the target good.
In the embodiment, in the process of carrying out deep analysis on the behavior characteristics of the target user from the time dimension according to the event information, the purchase intention of the target user is initially analyzed from the viewpoint of the user purchasing power based on the user attribute, so that the prediction of the user purchasing intention is carried out by combining the behavior characteristic analysis result of the target user, and the finally obtained purchasing intention information can be more accurate and reliable.
In some embodiments, the larger the value of the user information, the stronger the purchasing power of the user group corresponding to the target user is indicated, that is, the greater the probability of purchasing the target commodity by the user group corresponding to the target user is indicated;
after the user information of a certain target user is obtained, the user information corresponding to the target user can be compared with a second preset threshold value, and when the value of the user information corresponding to the target user is smaller than the second preset threshold value, the purchase intention prediction process of the target user is terminated, and the purchase intention prediction operation of the next target user is performed, so that the execution times of model training actions are reduced, and the prediction efficiency is improved;
and when the user information corresponding to the target user is greater than or equal to the second preset threshold value, continuing the subsequent purchase intention prediction flow.
In one embodiment, the interactive event further includes other events, the other events being events other than the purchase event, the initial model includes a first model portion for indicating a probability that the purchase event occurs independently within a target period, and a second model portion for indicating a probability that the purchase event occurs under the influence of the other events within the target period, the target period being a history period corresponding to the plurality of event information, the user information being used to train the first model portion, and the plurality of event information being used to train the second model portion.
In this embodiment, by combining the probability of occurrence of the purchase event and the probability of occurrence of the purchase event affected by other events, a time sequence point process corresponding to the purchase event is constructed, wherein the first model part is trained by using the user information, and the second model part is trained by using the plurality of event information, so that a prediction conclusion of the purchase power of the user and a prediction conclusion of the behavior characteristics of the user can be fused, and further more reliable purchase intention information is obtained.
The initial model may be calculated by weighting the first model part and the second model part, or may be calculated by adding the first model part and the second model part.
In one example, the model form of the initial model may be as shown in equation (2):
in the method, in the process of the invention,it can be understood that the aforementioned first model part, < +.>It can be understood that the aforementioned second model part, < +.>Representing the intensity function of user a with respect to interaction event i;
representing the basic strength of the interaction event i occurring for user a, when i= "buy", -j +>
Representing the causal relationship of the interaction event i to the interaction event j for the user a, i=j representing whether the interaction event i will happen by itself, +.>Indicating for user a that the interaction event i is the cause of the interaction event j, +.>Indicating that for user a, the interaction event i is not the cause of interaction event j;
representing the occurrence time of the interaction event j;
representing an excitation function, such as: hawkes process.
In this disclosure, the occurrence time of the other events may be earlier than the occurrence time of the purchase event in the plurality of event information, or may be later than the occurrence time of the purchase event in the plurality of event information, and the above arrangement may enhance the richness of the event information for training the initial model, so that the initial model may learn, in the training process, not only the relevant features of the other events that have a positive effect on the purchase behavior of the user, but also the relevant features of the other events that have a negative effect on the purchase behavior of the user, and make the final training obtain the target model more reliable.
In one embodiment, the target period includes a first sub-period and a second sub-period, the first sub-period corresponding to a time earlier than the second sub-period corresponding to a time;
the second model part comprises an excitation function, wherein the input of the excitation function is any time in the target period, the function value of the excitation function is positively correlated with the time of the input function in the first subperiod, and the function value of the excitation function is negatively correlated with the time of the input function in the second subperiod.
As described above, the target commodity is a high price commodity, so after the target user purchases the target commodity, the purchase intention of the target user is lower, at this time, the purchase intention of the target user is at a lower level, but as time is accumulated, the purchase intention of the target user increases, and after the target user increases to a maximum value, the purchase intention of the target user decreases again.
In one example, in formula (2)The corresponding excitation function may be as shown in equation (3):
in the method, in the process of the invention,incentive value for indicating the occurrence of interaction event i for user a +.>A time interval for indicating the occurrence of the interaction event i by the user a.
In one embodiment, the training the initial model based on the user information and the plurality of event information to obtain the target model includes:
performing likelihood estimation on model parameters of an initial model based on the user information and the event information to obtain target parameters;
and generating the target model according to the target parameters and the model framework of the initial model.
In this embodiment, the accuracy of the target parameters is improved by performing likelihood estimation on the model parameters of the initial model, so that the target model generated based on the model architecture of the initial model and the target parameters can be more reliable, and further, the purchase intention information predicted based on the target model can be more reliable.
Illustratively, model parameters of the initial model may be likelihood estimated by a desired maximum algorithm (Expectation Maximization Algorithm, EM) to obtain the target parameters.
It should be noted that, in this embodiment, the above model parameters include not only parameters corresponding to the first model part but also parameters corresponding to the second model part, where the parameters corresponding to the first model part may be as in formula (1)The parameters corresponding to the second model may be +_in equation (3)>And->
In one embodiment, the predicting purchase intention information according to the goal model includes:
obtaining a statistical model according to the target model, wherein the statistical model is used for indicating mathematical distribution of the purchase event in time;
and conducting derivative calculation on the statistical model based on the target moment to obtain the purchase intention information.
In the embodiment, mathematical distribution of the purchase event on the event is obtained based on the target model, and the purchase intention information prediction of the target user can be conveniently completed by combining a derivative calculation mode, so that the prediction efficiency of the method for predicting the multiple purchase intention of the multiple target users is improved.
Illustratively, when the target model is a model form represented by formula (2), the model form of the statistical model may be represented by formula (4):
in the method, in the process of the invention,a cumulative distribution function for representing the occurrence of interaction event i by user a, when i= "purchase",the derivative at time T is the predicted value of the purchase intention of the user a to the target commodity at time T, that is, the purchase intention information.
For ease of understanding, examples are illustrated below:
as shown in fig. 2, static feature data and dynamic feature data of a user are collected first, wherein the static feature data can be understood as the user attribute, and the dynamic feature data can be understood as the event information.
The static characteristic data of a plurality of users are converted into numerical values to form a characteristic matrix X A Then using the perceptron model to calculate the basic purchasing intention degree of the userWherein->Is a parameter matrix, σ (·) is an activation function (e.g., sigmod function), Y A ＝(…,y a ,…)，y a The intent degree is purchased for the basis of user a.
Then, an intensity function matrix in the time sequence point process is constructed according to the ' user ' -interactive behavior event ', wherein the intensity function matrix refers to the formula (2), and the excitation function in the formula (2) refers to the formula (3).
Performing parameter training on the formula (2) by taking the static characteristic data and the dynamic characteristic data of the user as training data to obtain a trained intensity functionAccording to->Calculating the cumulative distribution function of the interaction event i of the user a, and taking +.>The derivative at time T is taken as a predicted value of the purchase intent of user a at time T.
Referring to fig. 3, fig. 3 is an information prediction apparatus 300 provided in an embodiment of the present disclosure, and as shown in fig. 3, the information prediction apparatus 300 includes:
the acquiring module 301 is configured to acquire a plurality of event information corresponding to a target user, where each event information includes first data and second data, the first data is used to indicate an event type of an interaction event between the target user and a target commodity, the second data is used to indicate occurrence time information of the interaction event between the target user and the target commodity, and the interaction event includes a purchase event;
the training module 302 is configured to train an initial model based on the plurality of event information to obtain a target model, where the initial model is used to indicate a time sequence point process corresponding to the purchase event;
and the predicting module 303 is configured to predict purchase intention information according to a target model, where the purchase intention information is used to indicate a probability that the target user purchases the target commodity at a target moment.
In one embodiment, the training module 302 includes:
the attribute acquisition sub-module is used for acquiring the user attribute of the target user;
the information determination submodule is used for determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
and the training sub-module is used for training the initial model based on the user information and the event information to obtain a target model.
In one embodiment, the interactive event further includes other events, the other events being events other than the purchase event, the initial model includes a first model portion for indicating a probability that the purchase event occurs independently within a target period, and a second model portion for indicating a probability that the purchase event occurs under the influence of the other events within the target period, the target period being a history period corresponding to the plurality of event information, the user information being used to train the first model portion, and the plurality of event information being used to train the second model portion.
In one embodiment, the target period includes a first sub-period and a second sub-period, the first sub-period corresponding to a time earlier than the second sub-period corresponding to a time;
the second model part comprises an excitation function, wherein the input of the excitation function is any time in the target period, the function value of the excitation function is positively correlated with the time of the input function in the first subperiod, and the function value of the excitation function is negatively correlated with the time of the input function in the second subperiod.
In one embodiment, the training submodule is specifically configured to:
performing likelihood estimation on model parameters of an initial model based on the user information and the event information to obtain target parameters;
and generating the target model according to the target parameters and the model framework of the initial model.
In one embodiment, the prediction module 303 is specifically configured to:
obtaining a statistical model according to the target model, wherein the statistical model is used for indicating mathematical distribution of the purchase event in time;
and conducting derivative calculation on the statistical model based on the target moment to obtain the purchase intention information.
The information prediction apparatus 300 provided in the embodiments of the present disclosure can implement each process in the embodiments of the method, and in order to avoid repetition, a description is omitted here.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 4 illustrates a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 4, the apparatus 400 includes a computing unit 401 that can perform various appropriate actions and processes according to a computer program stored in a Read-Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access Memory (Random Access Memory, RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Various components in device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, etc.; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphic Process Unit, GPU), various dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (Digital Signal Processing, DSP), and any suitable processors, controllers, microcontrollers, etc. The computing unit 401 performs the respective methods and processes described above, such as a map information display method or a map information transmission method. For example, in some embodiments, the map information display method or the map information transmission method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the map information display method or the map information transmission method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the map information display method or the map information transmission method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuitry, field programmable gate arrays (Field-Programmable Gate Array, FPGA), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), application specific standard products (Application Specific Standard Product, ASSP), system On Chip (SOC), complex programmable logic devices (Complex Programmable Logic Device, CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. An information prediction method, the method comprising:
acquiring a plurality of event information corresponding to a target user, wherein each event information comprises first data and second data, the first data is used for indicating the event type of an interaction event between the target user and a target commodity, the second data is used for indicating the occurrence time information of the interaction event between the target user and the target commodity, and the interaction event comprises a purchase event;
training an initial model based on the event information to obtain a target model, wherein the initial model is used for indicating a time sequence point process corresponding to the purchase event;
and predicting purchase intention information according to a target model, wherein the purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment.
2. The method of claim 1, wherein training the initial model based on the plurality of event information to obtain the target model comprises:
acquiring user attributes of the target user;
determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
training an initial model based on the user information and the event information to obtain a target model.
3. The method of claim 2, wherein the interaction event further comprises other events, the other events being other than the purchase event, the initial model comprising a first model portion for indicating a probability that the purchase event occurs independently within a target period of time and a second model portion for indicating a probability that the purchase event occurs due to the other events within the target period of time, the target period of time being a historical period of time corresponding to the plurality of event information, the user information being used to train the first model portion, the plurality of event information being used to train the second model portion.
4. A method according to claim 3, wherein the target period comprises a first sub-period and a second sub-period, the second model part comprising an excitation function, the input of the excitation function being at any time within the target period, the function value of the excitation function being positively correlated with the time of the input function within the first sub-period, the function value of the excitation function being negatively correlated with the time of the input function within the second sub-period.
5. The method of claim 2, wherein the training the initial model based on the user information and the plurality of event information to obtain the target model comprises:
performing likelihood estimation on model parameters of an initial model based on the user information and the event information to obtain target parameters;
and generating the target model according to the target parameters and the model framework of the initial model.
6. The method of any one of claims 1 to 5, wherein predicting purchase intent information based on the goal model comprises:
obtaining a statistical model according to the target model, wherein the statistical model is used for indicating mathematical distribution of the purchase event in time;
and conducting derivative calculation on the statistical model based on the target moment to obtain the purchase intention information.
7. An information prediction apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring a plurality of event information corresponding to a target user, each event information comprises first data and second data, the first data is used for indicating the event type of an interaction event between the target user and a target commodity, the second data is used for indicating the occurrence time information of the interaction event between the target user and the target commodity, and the interaction event comprises a purchase event;
the training module is used for training an initial model based on the event information to obtain a target model, wherein the initial model is used for indicating a time sequence point process corresponding to the purchase event;
and the prediction module is used for predicting purchase intention information according to a target model, wherein the purchase intention information is used for indicating the probability that the target user purchases the target commodity at the target moment.
8. The apparatus of claim 7, wherein the training module comprises:
the attribute acquisition sub-module is used for acquiring the user attribute of the target user;
the information determination submodule is used for determining user information according to the user attribute, wherein the user information is used for indicating the probability that a user group corresponding to the target user purchases the target commodity;
and the training sub-module is used for training the initial model based on the user information and the event information to obtain a target model.
9. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor performs the steps of the method according to any one of claims 1 to 6.
10. A readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311201534.6A CN117035846A (en) | 2023-09-18 | 2023-09-18 | Information prediction method and device and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311201534.6A CN117035846A (en) | 2023-09-18 | 2023-09-18 | Information prediction method and device and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117035846A true CN117035846A (en) | 2023-11-10 |
Family
ID=88624723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311201534.6A Pending CN117035846A (en) | 2023-09-18 | 2023-09-18 | Information prediction method and device and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117035846A (en) |
-
2023
- 2023-09-18 CN CN202311201534.6A patent/CN117035846A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4242955A1 (en) | User profile-based object recommendation method and device | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN112598472A (en) | Product recommendation method, device, system, medium and program product | |
| CN114240555A (en) | Click rate prediction model training method and device and click rate prediction method and device | |
| CN110348999B (en) | Financial risk sensitive user identification method and device and electronic equipment | |
| CN110197317B (en) | Target user determination method and device, electronic equipment and storage medium | |
| CN114494814A (en) | Attention-based model training method and device and electronic equipment | |
| CN111199454B (en) | Real-time user conversion evaluation method and device and electronic equipment | |
| CN115759283A (en) | Model interpretation method and device, electronic equipment and storage medium | |
| CN113361621B (en) | Method and device for training model | |
| CN117035846A (en) | Information prediction method and device and related equipment | |
| CN114119107A (en) | Steel trade enterprise transaction evaluation method, device, equipment and storage medium | |
| CN113362141A (en) | Associated commodity recommendation method, device, medium and electronic equipment | |
| CN113947431A (en) | User behavior quality evaluation method, device, equipment and storage medium | |
| CN113807391A (en) | Task model training method and device, electronic equipment and storage medium | |
| CN113112311A (en) | Method for training causal inference model, information prompting method and device | |
| CN111178943A (en) | Advertisement real-time bidding method and device and electronic equipment | |
| CN114820164A (en) | Credit card limit evaluation method, device, equipment and medium | |
| CN116433284A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN113743906A (en) | Method and device for determining service processing strategy | |
| CN113011920A (en) | Conversion rate estimation model training method and device and electronic equipment | |
| CN116342253A (en) | Loan risk scoring method, device, equipment and storage medium | |
| CN117407439A (en) | Conversion data determining method, device, equipment and storage medium | |
| CN115526664A (en) | Resource quality score calculation method and device, storage medium and electronic equipment | |
| CN114969546A (en) | Object classification method, and network model training method and device |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 228, 2nd Floor, No. 5 Guanghua Road, Zhangjiawan Town, Tongzhou District, Beijing, 101113 Applicant after: BEIJING ZHONGGUANCUN KEJIN TECHNOLOGY Co.,Ltd. Address before: 130, 1st Floor, Building 5, Courtyard 1, Shangdi Fourth Street, Haidian District, Beijing, 100085 Applicant before: BEIJING ZHONGGUANCUN KEJIN TECHNOLOGY Co.,Ltd. Country or region before: China |