CN110866241A - Evaluation model generation and equipment association method, device and storage medium - Google Patents
Evaluation model generation and equipment association method, device and storage medium Download PDFInfo
- Publication number
- CN110866241A CN110866241A CN201910948387.6A CN201910948387A CN110866241A CN 110866241 A CN110866241 A CN 110866241A CN 201910948387 A CN201910948387 A CN 201910948387A CN 110866241 A CN110866241 A CN 110866241A
- Authority
- CN
- China
- Prior art keywords
- app
- equipment
- behavior data
- installation list
- list information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/44—Program or device authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an evaluation model generation and equipment association method, an evaluation model generation and equipment association device and a storage medium, and relates to the field of machine learning, wherein the equipment association method comprises the following steps: respectively acquiring preset equipment information of each second equipment aiming at any two pieces of second equipment to be evaluated; determining the equipment pair characteristics of a second equipment pair consisting of two pieces of second equipment according to the acquired preset equipment information; and determining whether the two second devices belong to the same user or not based on an evaluation model according to the device pair characteristics. The scheme is simple and convenient to realize, and has universal applicability and the like.
Description
[ technical field ] A method for producing a semiconductor device
The present application relates to the field of machine learning, and in particular, to a method, an apparatus, and a storage medium for generating an evaluation model and associating devices.
[ background of the invention ]
At present, user behavior data analysis is involved in various service systems such as internet search, e-commerce, content recommendation, financial wind control and the like, and whether complete and accurate user behavior data can be obtained determines the upper limit capacity of various service systems.
In practical application, the same user may have multiple devices (such as mobile devices like a mobile phone and a tablet computer), in addition, the frequency of device replacement is accelerated at present, and different devices of the same user are associated with each other in a trusted manner, that is, the association between the multiple devices and the user is realized, so that user behavior data on different devices are aggregated, and the integrity of the user behavior data can be greatly improved.
In the prior art, a way of forcing a user to log in a same account on different devices is usually adopted to realize association of different devices of the same user, that is, user behavior data on different devices are associated together through a user account identification (id), so as to achieve the purpose of aggregation.
However, the above method has at least the following problems in practical application: forcing a user to log in may lose a certain amount of new users, and the login process is relatively cumbersome, some users may give up using, and in addition, if the user does not log in, the association cannot be realized, and the like. In a word, the above manner is cumbersome to implement and does not have general applicability.
[ summary of the invention ]
In view of the above, the present application provides an evaluation model generation and device association method, apparatus and storage medium.
The specific technical scheme is as follows:
an evaluation model generation method, comprising:
respectively acquiring preset equipment information of each first equipment as an acquisition object;
combining part or all of the first equipment in pairs to obtain more than one group of first equipment pairs;
respectively constructing a training sample for each group of first equipment pairs; each training sample respectively comprises: determining device pair characteristics according to preset device information of two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to sample tags of the same user;
and training according to the training sample to obtain an evaluation model so as to determine whether two pieces of second equipment belong to the same user or not according to the evaluation model and the obtained equipment pair characteristics of the second equipment pair aiming at a second equipment pair consisting of any two pieces of second equipment to be evaluated.
According to a preferred embodiment of the present invention, the predetermined device information includes: APP behavior data and APP installation list information.
According to a preferred embodiment of the present invention, the respectively obtaining the predetermined device information of each first device as the acquisition target includes:
collecting original data of each first device within a preset time length;
extracting the APP behavior data and the APP installation list information from the original data;
and respectively aggregating the APP behavior data and the APP installation list information belonging to the same first device to obtain the preset device information of each first device.
According to a preferred embodiment of the present invention, the APP behavior data includes: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the aggregating the APP behavior data and the APP installation list information belonging to the same first device respectively comprises:
and according to the equipment identification, respectively aggregating the APP behavior data and the APP installation list information belonging to the same first equipment.
According to a preferred embodiment of the present invention, before aggregating the APP behavior data and the APP installation list information belonging to the same first device, the method further includes:
cleaning the extracted APP behavior data, and filtering out the APP behavior data which do not meet the requirement;
and/or, the APP installation list information which is extracted is cleaned, and the APP installation list information which does not meet the requirement is filtered.
According to a preferred embodiment of the present invention, after aggregating the APP behavior data and the APP installation list information belonging to the same first device, the method further includes:
for any first device, if the number of pieces of APP behavior data obtained by aggregation is greater than a predetermined threshold, only the number of pieces of APP behavior data equal to the threshold is reserved.
According to a preferred embodiment of the invention, the method further comprises: for any first equipment pair, if it is determined that the two first equipments in the first equipment pair log in the same user account identifier, it is determined that the two first equipments in the first equipment pair belong to the same user.
According to a preferred embodiment of the invention, the method further comprises: and filtering out negative samples which do not meet the requirements from the constructed training samples, wherein the negative samples are the training samples of two first devices in the corresponding first device pairs which do not belong to the same user.
A device association method, comprising:
respectively acquiring preset equipment information of each second equipment aiming at any two pieces of second equipment to be evaluated;
determining the device pair characteristics of a second device pair consisting of the two second devices according to the preset device information;
and determining whether the two second devices belong to the same user or not based on the evaluation model generated according to the evaluation model generation method according to the device pair characteristics.
According to a preferred embodiment of the present invention, the predetermined device information includes: APP behavior data and APP installation list information.
According to a preferred embodiment of the present invention, the respectively obtaining the predetermined device information of each second device includes:
collecting original data of each second device to be evaluated within a preset time length;
extracting the APP behavior data and the APP installation list information from the original data;
and respectively aggregating the APP behavior data and the APP installation list information belonging to the same second device to obtain the preset device information of each second device.
According to a preferred embodiment of the present invention, the APP behavior data includes: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the aggregating the APP behavior data and the APP installation list information belonging to the same second device respectively comprises:
and according to the equipment identification, respectively aggregating the APP behavior data and the APP installation list information belonging to the same second equipment.
According to a preferred embodiment of the present invention, before aggregating the APP behavior data and the APP installation list information belonging to the same second device, the method further includes:
cleaning the extracted APP behavior data, and filtering out the APP behavior data which do not meet the requirement;
and/or, the APP installation list information which is extracted is cleaned, and the APP installation list information which does not meet the requirement is filtered.
An evaluation model generation apparatus comprising: the device comprises a first acquisition unit, a combination unit, a construction unit and a training unit;
the first acquisition unit is used for respectively acquiring preset equipment information of each first equipment as an acquisition object;
the combination unit is used for combining part or all of the first equipment in pairs to obtain more than one group of first equipment pairs;
the construction unit is used for respectively constructing a training sample for each group of first equipment pairs; each training sample respectively comprises: determining device pair characteristics according to preset device information of two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to sample tags of the same user;
the training unit is used for training according to the training sample to obtain an evaluation model so as to determine whether two pieces of second equipment belong to the same user or not according to the evaluation model and the obtained equipment pair characteristics of the second equipment pair aiming at a second equipment pair consisting of any two pieces of second equipment to be evaluated.
According to a preferred embodiment of the present invention, the predetermined device information includes: APP behavior data and APP installation list information.
According to a preferred embodiment of the present invention, the first obtaining unit collects original data of each first device within a predetermined time, extracts APP behavior data and APP installation list information from the original data, and aggregates the APP behavior data and the APP installation list information belonging to the same first device respectively as the obtained predetermined device information of each first device.
According to a preferred embodiment of the present invention, the APP behavior data includes: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the first obtaining unit respectively aggregates the APP behavior data and the APP installation list information belonging to the same first device according to the device identifier.
According to a preferred embodiment of the present invention, the first obtaining unit is further configured to clean the extracted APP behavior data and filter out the APP behavior data that does not meet the requirement, and/or clean the extracted APP installation list information and filter out the APP installation list information that does not meet the requirement.
According to a preferred embodiment of the present invention, the first obtaining unit is further configured to, for any first device, only retain APP behavior data of the number equal to the threshold if the number of pieces of APP behavior data obtained by aggregation is greater than a predetermined threshold.
According to a preferred embodiment of the present invention, the constructing unit is further configured to, for any first device pair, determine that two first devices in the first device pair belong to the same user if it is determined that the two first devices in the first device pair have logged in the same user account id.
According to a preferred embodiment of the present invention, the constructing unit is further configured to filter out an unsatisfactory negative sample from the constructed training samples, where the negative sample is a training sample in which two first devices in the corresponding first device pair do not belong to the same user.
An apparatus associated with a device, comprising: the device comprises a second acquisition unit, an extraction unit and an evaluation unit;
the second obtaining unit is configured to obtain, for any two second devices to be evaluated, predetermined device information of each second device;
the extraction unit is used for determining the device pair characteristics of a second device pair consisting of the two second devices according to the preset device information;
and the evaluation unit is used for determining whether the two second devices belong to the same user or not according to the device pair characteristics and based on an evaluation model generated according to the evaluation model generation method or an evaluation model generated by the evaluation model generation device.
According to a preferred embodiment of the present invention, the predetermined device information includes: APP behavior data and APP installation list information.
According to a preferred embodiment of the present invention, the second obtaining unit collects original data of each second device to be evaluated within a predetermined time, extracts APP behavior data and APP installation list information from the original data, and aggregates the APP behavior data and the APP installation list information belonging to the same second device respectively as the obtained predetermined device information of each second device.
According to a preferred embodiment of the present invention, the APP behavior data includes: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
and the second acquisition unit respectively aggregates the APP behavior data and the APP installation list information belonging to the same second device according to the device identifier.
According to a preferred embodiment of the present invention, the second obtaining unit is further configured to clean the extracted APP behavior data and filter out the APP behavior data that does not meet the requirement, and/or clean the extracted APP installation list information and filter out the APP installation list information that does not meet the requirement.
An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method described above.
Based on the introduction, it can be seen that the association mode does not need to force the user to log in, is more simple and convenient to realize, and can assess whether two arbitrary devices belong to the same user based on the assessment model obtained by training, has universal applicability, and through cleaning the extracted APP behavior data and/or APP installation list information, and filtering the constructed training sample, negative effects on subsequent processing caused by abnormal data and the like are avoided as much as possible, thereby improving the accuracy and the like of the association result.
[ description of the drawings ]
The accompanying drawings are included to provide a better understanding of the present solution and are not to be considered limiting of the present application, in which:
FIG. 1 is a flow chart of an embodiment of a method for generating an assessment model according to the present application;
FIG. 2 is a flow chart of an embodiment of a device association method described herein;
FIG. 3 is a schematic diagram illustrating a structure of an evaluation model generating apparatus according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a component structure of an embodiment of an apparatus related to the present application;
FIG. 5 illustrates a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application.
[ detailed description ] embodiments
The method for associating different devices of the same user by using the machine learning model is provided, so that the user behavior data can be aggregated through device-level association, and more complete and accurate user behavior data can be provided for various service systems.
In order to make the technical solutions of the present application more clear and understandable, the solutions of the present application are further described below by referring to the drawings and examples.
It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In addition, it should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Fig. 1 is a flowchart of an embodiment of an evaluation model generation method according to the present application. As shown in fig. 1, the following detailed implementation is included.
In 101, predetermined device information of each first device as an acquisition object is acquired, respectively.
At 102, some or all of the first devices are combined pairwise to obtain more than one first device pair.
In 103, respectively constructing a training sample for each group of first device pairs; each training sample respectively comprises: and determining the device pair characteristics according to the preset device information of the two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to the sample labels of the same user.
In 104, an evaluation model is obtained according to the training of the constructed training sample, so that for a second device pair composed of any two second devices to be evaluated, whether the two second devices belong to the same user is determined according to the evaluation model and the obtained device pair characteristics of the second device pair.
Which devices are used as the acquisition objects can be determined according to actual needs, so that the acquisition objects are distinguished from the devices to be evaluated which appear subsequently, the devices to be used as the acquisition objects are called first devices, and the devices to be evaluated are called second devices.
Preferably, the acquired predetermined device information of the first device may include: application (APP) behavior data and APP installation list information.
The method can collect the original data of each first device within the preset duration, extract the APP behavior data and the APP installation list information from the original data, and further aggregate the APP behavior data and the APP installation list information belonging to the same first device respectively to serve as the preset device information of each acquired first device.
The collected original data contains various fields and may have dirty data, so that effective fields in the data need to be extracted, and the most core fields are extracted. Wherein, the extracted APP behavior data can include: the device comprises a device identification, a timestamp for generating an APP behavior and an APP identification. The extracted APP install list information may include: the device identification, the timestamp of the collected APP installation list and the APP installation list.
The specific value of the preset time length can be determined according to actual needs, such as the latest month. Assuming that the first device is a mobile phone, a user opens a certain social APP on the mobile phone to view social information, an APP behavior data is generated, a certain video APP is opened to view a video, and an APP behavior data is also generated. In addition, the APP installation list information on the mobile phone can be periodically collected once at the zero point of each day, namely, the information such as which APPs are currently installed on the mobile phone.
To the APP action data of extraction, still can wash it, filter the APP action data that does not conform to the requirement, and/or, to the APP installation list information of extraction, still can wash it, filter the APP installation list information that does not conform to the requirement. By cleaning, negative effects of dirty data on subsequent model training and the like can be avoided.
For example, for an APP behavior data, if the device identifier is a null identifier or an identifier in an illegal format, the APP behavior data may be considered to be not compliant, and may be filtered out.
For another example, for an APP behavior data, if the APP identifier is a null identifier or an identifier in an illegal format, the APP behavior data may be considered to be not compliant with the requirement, and may be filtered out.
For another example, for an APP behavior data or APP installation list information, if the timestamp is empty, or is an excessively large or excessively small timestamp, the APP behavior data or APP installation list information may be considered to be not satisfactory, and may be filtered out. Too large may mean greater than the current time, i.e., a future timestamp, and too small may mean less than the factory time of the device, etc.
For another example, for an APP installation list information, if the APP name in the APP installation list contains a messy code, etc., then the APP installation list information may be considered to be not in compliance with the requirement, and may be filtered out.
After cleaning is completed according to the above mode, the APP behavior data and the APP installation list information belonging to the same first device can be aggregated according to the device identifier, namely, the APP behavior data and the APP installation list information belonging to the first device 1 are aggregated together, the APP behavior data and the APP installation list information belonging to the first device 2 are aggregated together, and the like.
Preferably, for any first device, if the number of pieces of APP behavior data obtained by aggregation is greater than a predetermined threshold, only the number of pieces of APP behavior data equal to the threshold may be retained. The data truncation can be carried out on the equipment with the number of the APP behavior data obviously larger than the normal value, so that negative effects on subsequent model training caused by abnormal equipment are prevented, and the model can identify the abnormal equipment. For example, according to experience and the like, if it is considered that APP behavior data generated on the same device in one month under normal conditions should not be larger than X (threshold) pieces, and APP behavior data obtained by actual aggregation is 2X pieces, X pieces of APP behavior data can be randomly reserved.
Then, a part or all of the first devices as the acquisition objects may be combined two by two, thereby obtaining more than one set of first device pairs. For example, the first devices to be acquired include the first devices 1 to 3 (for example only, the actual size may be much larger), and at most three groups of first device pairs may be combined, which are the first device pair formed by the first device 1 and the first device 2, the first device pair formed by the first device 1 and the first device 3, and the first device pair formed by the first device 2 and the first device 3.
And respectively constructing a training sample for each group of first equipment pairs. Each training sample can respectively comprise: and determining the device pair characteristics according to the preset device information of the two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to the sample labels of the same user.
Preferably, for any first device pair, if it is determined that the two first devices in the first device pair have logged in the same user account id, it may be determined that the two first devices in the first device pair belong to the same user, otherwise, it may be determined that the two first devices in the first device pair do not belong to the same user.
For any first device pair, how to determine the device pair characteristics of the first device pair and which specific characteristics are included in the device pair characteristics are not limited according to the predetermined device information of two first devices in the first device pair.
For example, the device pair features may include, but are not limited to, the following: frequency relationship of daily/monthly APP behaviors of the two first devices, similarity relationship of daily/monthly APP usage of the two first devices, daily/monthly APP install/uninstall behavior relationship of the two first devices, and the like. The required features can be extracted (or calculated) by comparing the APP behavior data and the APP installation list information of the two first devices according to the preset feature extraction rule.
Preferably, an unsatisfactory negative sample can be further filtered from the constructed training samples, where the negative sample is a training sample in which two first devices in the corresponding first device pair do not belong to the same user, and conversely, a training sample in which two first devices in the corresponding first device pair belong to the same user is a positive sample.
According to the processing method in this embodiment, the number of constructed negative samples is much larger than that of the positive samples, so that the negative samples can be filtered to control the positive samples and the negative samples within a reasonable proportion range. The specific filtering of which negative samples can be determined according to actual needs. For example, negative samples that two first devices obviously do not belong to the same user can be distinguished based on the IP, Access Point (AP), geographical location, etc. of the devices, and filtered out to improve the model training effect, etc.
And (4) training to obtain an evaluation model according to the filtered positive samples and the filtered negative samples. How to perform model training is prior art. In addition, the evaluation model can be updated or optimized subsequently by using the training sample obtained latest according to actual needs.
Fig. 2 is a flowchart of an embodiment of a device association method according to the present application. As shown in fig. 2, the following detailed implementation is included.
In 201, for any two second devices to be evaluated, predetermined device information of each second device is acquired respectively.
In 202, a device pair characteristic of a second device pair composed of two second devices is determined according to the acquired predetermined device information.
In 203, it is determined whether the two second devices belong to the same user based on the pre-trained evaluation model according to the determined device pair characteristics.
The evaluation model may be an evaluation model generated according to the evaluation model generation method shown in fig. 1.
Preferably, the predetermined device information may include: APP behavior data and APP installation list information.
For each second device to be evaluated, the original data of each second device in a preset time length can be collected, APP behavior data and APP installation list information can be extracted from the original data, and then the APP behavior data and the APP installation list information belonging to the same second device can be aggregated respectively to serve as the preset device information of each obtained second device.
Wherein, the extracted APP behavior data can include: the device comprises a device identification, a timestamp for generating an APP behavior and an APP identification. The extracted APP install list information may include: the device identification, the timestamp of the collected APP installation list and the APP installation list. The APP behavior data and the APP installation list information belonging to the same second device can be aggregated according to the device identifier.
In addition, to the APP action data of extraction, still can wash it, filter the APP action data that does not conform to the requirement, and/or, to the APP installation list information of extraction, can wash it, filter the APP installation list information that does not conform to the requirement. After cleaning is completed according to the above mode, the APP behavior data and the APP installation list information belonging to the same second device can be aggregated according to the device identifier.
For each second device to be evaluated, two pairs of the second devices may be formed into a second device pair, and for any second device pair, if it can be determined explicitly in a certain manner whether two of the second devices belong to the same user, for example, it can be determined explicitly based on the IP, AP, geographical location, and the like of the device that two of the second devices do not belong to the same user, then such second device pairs may not be processed in the manner described in this embodiment.
Otherwise, for two second devices in any second device pair, it may be determined whether the two second devices belong to the same user based on the evaluation model according to the determined device pair characteristics of the second device pair.
In this way, multiple devices belonging to the same user may be associated together, for example, the second device 1, the second device 2, and the second device 3 belong to the same user, and in this embodiment, it may be determined that the second device 1 and the second device 2 belong to the same user, the second device 1 and the second device 3 belong to the same user, and the second device 2 and the second device 3 belong to the same user, so it may be determined that the second device 1, the second device 2, and the second device 3 belong to the same user.
It is noted that while for simplicity of explanation, the foregoing method embodiments are described as a series of acts or combination of acts, those skilled in the art will appreciate that the present application is not limited by the order of acts, as some steps may, in accordance with the present application, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In a word, this application the associated mode need not to force the user to log in, and it is more simple and convenient to realize, can estimate out whether two arbitrary equipment belong to same user based on the evaluation model that the training obtained moreover, has universal applicability to, through wasing APP action data and/or APP installation list information that extract, and filter etc. to the training sample who constructs, avoided abnormal data etc. to produce negative effect to subsequent processing as far as possible, thereby improved the accuracy etc. of associated result.
The above is a description of method embodiments, and the embodiments of the present application are further described below by way of apparatus embodiments.
Fig. 3 is a schematic structural diagram of an evaluation model generation apparatus according to an embodiment of the present application. As shown in fig. 3, includes: a first acquisition unit 301, a combination unit 302, a construction unit 303 and a training unit 304.
A first acquiring unit 301, configured to acquire predetermined device information of each first device as an acquisition object, respectively.
A combining unit 302, configured to combine every two or all of the first devices to obtain more than one first device pair.
A constructing unit 303, configured to construct a training sample for each group of first device pairs respectively; each training sample respectively comprises: and determining the device pair characteristics according to the preset device information of the two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to the sample labels of the same user.
The training unit 304 is configured to train according to the training sample to obtain an evaluation model, so that for a second device pair composed of any two second devices to be evaluated, whether the two second devices belong to the same user is determined according to the evaluation model and the obtained device pair characteristics of the second device pair.
Preferably, the acquired predetermined device information of the first device may include: APP behavior data and APP installation list information.
The first obtaining unit 301 may collect original data of each first device within a predetermined time, extract APP behavior data and APP installation list information from the original data, and aggregate the APP behavior data and APP installation list information belonging to the same first device respectively as predetermined device information of each obtained first device.
The APP behavior data can include: the device comprises a device identification, a timestamp for generating an APP behavior and an APP identification. The APP install list information may include: the device identification, the timestamp of the collected APP installation list and the APP installation list. The first obtaining unit 301 may respectively aggregate APP behavior data and APP installation list information belonging to the same first device according to the device identifier.
In addition, the first acquisition unit 301 may also perform the following processing: for any first device, if the number of pieces of APP behavior data obtained by aggregation is greater than a predetermined threshold, only the number of pieces of APP behavior data equal to the threshold is reserved.
After the above processing is completed, the combining unit 302 may combine some or all of the first devices two by two, so as to obtain more than one group of first device pairs.
For each first device pair, the constructing unit 303 may respectively construct a training sample, where each training sample may respectively include: and determining the device pair characteristics according to the preset device information of the two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to the sample labels of the same user.
Preferably, for any first device pair, if it is determined that the two first devices in the first device pair have logged in the same user account id, it may be determined that the two first devices in the first device pair belong to the same user, otherwise, it may be determined that the two first devices in the first device pair do not belong to the same user.
For any first device pair, how to determine the device pair characteristics of the first device pair and which specific characteristics are included in the device pair characteristics are not limited according to the predetermined device information of two first devices in the first device pair.
For example, the device pair features may include, but are not limited to, the following: frequency relationship of daily/monthly APP behaviors of the two first devices, similarity relationship of daily/monthly APP usage of the two first devices, daily/monthly APP install/uninstall behavior relationship of the two first devices, and the like. The required features can be extracted (or calculated) by comparing the APP behavior data and the APP installation list information of the two first devices according to the preset feature extraction rule.
Preferably, the constructing unit 303 may further filter out an unsatisfactory negative sample from the constructed training samples, where the negative sample is a training sample in which two first devices in the corresponding first device pair do not belong to the same user, and conversely, the training sample in which two first devices in the corresponding first device pair belong to the same user is a positive sample. According to the processing method in this embodiment, the number of constructed negative samples is much larger than that of the positive samples, so that the negative samples can be filtered to control the positive samples and the negative samples within a reasonable proportion range. The specific filtering of which negative samples can be determined according to actual needs.
According to the filtered positive sample and the filtered negative sample, the training unit 304 may train to obtain an evaluation model, so as to determine, for a second device pair composed of any two second devices to be evaluated, whether the two second devices belong to the same user according to the evaluation model and the obtained device pair characteristics of the second device pair.
Fig. 4 is a schematic structural diagram of an embodiment of an apparatus related to the present application. As shown in fig. 4, includes: a second acquisition unit 401, an extraction unit 402, and an evaluation unit 403.
A second obtaining unit 401, configured to obtain, for any two second devices to be evaluated, predetermined device information of each second device respectively.
An extracting unit 402, configured to determine, according to the obtained predetermined device information, a device pair feature of a second device pair formed by two second devices.
An evaluation unit 403, configured to determine, according to the determined device pair characteristics, whether two second devices belong to the same user based on an evaluation model generated according to the evaluation model generation method shown in fig. 1 or an evaluation model generated according to the evaluation model generation apparatus shown in fig. 3.
Preferably, the predetermined device information may include: APP behavior data and APP installation list information.
For each second device to be evaluated, the second obtaining unit 401 may collect original data of each second device within a predetermined time period, and may extract APP behavior data and APP installation list information from the original data, and may further aggregate the APP behavior data and APP installation list information belonging to the same second device, respectively, as predetermined device information of each obtained second device.
Wherein, the extracted APP behavior data can include: the device comprises a device identification, a timestamp for generating an APP behavior and an APP identification. The extracted APP install list information may include: the device identification, the timestamp of the collected APP installation list and the APP installation list. The second obtaining unit 401 may respectively aggregate APP behavior data and APP installation list information belonging to the same second device according to the device identifier.
In addition, to the extracted APP behavior data, the second obtaining unit 401 may also clean it, filtering out APP behavior data that does not meet the requirements, and/or, to the extracted APP installation list information, the second obtaining unit 401 may clean it, filtering out APP installation list information that does not meet the requirements. After the cleaning is completed in the above manner, the second obtaining unit 401 may respectively aggregate APP behavior data and APP installation list information belonging to the same second device according to the device identifier.
For each second device to be evaluated, two pairs of the second devices may be formed into a second device pair, and for any second device pair, if it can be determined explicitly in a certain manner whether two of the second devices belong to the same user, for example, it can be determined explicitly based on the IP, AP, geographical location, and the like of the device that two of the second devices do not belong to the same user, then such second device pairs may not be processed in the manner described in this embodiment.
Otherwise, for two second devices in any second device pair, the extracting unit 402 may determine, according to the obtained predetermined device information, a device pair feature of the second device pair, and the evaluating unit 403 may determine, according to the device pair feature of the second device pair, whether the two second devices belong to the same user based on an evaluation model.
For a specific work flow of the apparatus embodiments shown in fig. 3 and fig. 4, reference is made to the related description in the foregoing method embodiments, and details are not repeated.
FIG. 5 illustrates a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application. The computer system/server 12 shown in FIG. 5 is only one example and should not be taken to limit the scope of use or functionality of embodiments of the present application.
As shown in FIG. 5, computer system/server 12 is in the form of a general purpose computing device. The components of computer system/server 12 may include, but are not limited to: one or more processors (processing units) 16, a memory 28, and a bus 18 that connects the various system components, including the memory 28 and the processors 16.
Computer system/server 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The computer system/server 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
The computer system/server 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer system/server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the computer system/server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the computer system/server 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 20. As shown in FIG. 5, the network adapter 20 communicates with the other modules of the computer system/server 12 via the bus 18. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer system/server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, implementing the methods in the embodiments shown in fig. 1 or fig. 2.
The application also discloses a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, will carry out the method as in the embodiments of fig. 1 or fig. 2.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having 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. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method, etc., can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (28)
1. An evaluation model generation method, comprising:
respectively acquiring preset equipment information of each first equipment as an acquisition object;
combining part or all of the first equipment in pairs to obtain more than one group of first equipment pairs;
respectively constructing a training sample for each group of first equipment pairs; each training sample respectively comprises: determining device pair characteristics according to preset device information of two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to sample tags of the same user;
and training according to the training sample to obtain an evaluation model so as to determine whether two pieces of second equipment belong to the same user or not according to the evaluation model and the obtained equipment pair characteristics of the second equipment pair aiming at a second equipment pair consisting of any two pieces of second equipment to be evaluated.
2. The method of claim 1,
the predetermined device information includes: APP behavior data and APP installation list information.
3. The method of claim 2,
the respectively acquiring predetermined device information of each first device as an acquisition object includes:
collecting original data of each first device within a preset time length;
extracting the APP behavior data and the APP installation list information from the original data;
and respectively aggregating the APP behavior data and the APP installation list information belonging to the same first device to obtain the preset device information of each first device.
4. The method of claim 3,
the APP behavior data comprises: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the aggregating the APP behavior data and the APP installation list information belonging to the same first device respectively comprises:
and according to the equipment identification, respectively aggregating the APP behavior data and the APP installation list information belonging to the same first equipment.
5. The method of claim 3,
before aggregating the APP behavior data and the APP installation list information belonging to the same first device, respectively, the method further includes:
cleaning the extracted APP behavior data, and filtering out the APP behavior data which do not meet the requirement;
and/or, the APP installation list information which is extracted is cleaned, and the APP installation list information which does not meet the requirement is filtered.
6. The method of claim 3,
after aggregating the APP behavior data and the APP installation list information belonging to the same first device, respectively, the method further includes:
for any first device, if the number of pieces of APP behavior data obtained by aggregation is greater than a predetermined threshold, only the number of pieces of APP behavior data equal to the threshold is reserved.
7. The method of claim 1,
the method further comprises the following steps: for any first equipment pair, if it is determined that the two first equipments in the first equipment pair log in the same user account identifier, it is determined that the two first equipments in the first equipment pair belong to the same user.
8. The method of claim 1,
the method further comprises the following steps: and filtering out negative samples which do not meet the requirements from the constructed training samples, wherein the negative samples are the training samples of two first devices in the corresponding first device pairs which do not belong to the same user.
9. A device association method, comprising:
respectively acquiring preset equipment information of each second equipment aiming at any two pieces of second equipment to be evaluated;
determining the device pair characteristics of a second device pair consisting of the two second devices according to the preset device information;
determining whether the two second devices belong to the same user based on the evaluation model generated by the evaluation model generation method according to claims 1-8 according to the device pair characteristics.
10. The method of claim 9,
the predetermined device information includes: APP behavior data and APP installation list information.
11. The method of claim 10,
the respectively acquiring the predetermined device information of each second device includes:
collecting original data of each second device to be evaluated within a preset time length;
extracting the APP behavior data and the APP installation list information from the original data;
and respectively aggregating the APP behavior data and the APP installation list information belonging to the same second device to obtain the preset device information of each second device.
12. The method of claim 11,
the APP behavior data comprises: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the aggregating the APP behavior data and the APP installation list information belonging to the same second device respectively comprises:
and according to the equipment identification, respectively aggregating the APP behavior data and the APP installation list information belonging to the same second equipment.
13. The method of claim 11,
before aggregating the APP behavior data and the APP installation list information belonging to the same second device, respectively, the method further includes:
cleaning the extracted APP behavior data, and filtering out the APP behavior data which do not meet the requirement;
and/or, the APP installation list information which is extracted is cleaned, and the APP installation list information which does not meet the requirement is filtered.
14. An evaluation model generation apparatus, comprising: the device comprises a first acquisition unit, a combination unit, a construction unit and a training unit;
the first acquisition unit is used for respectively acquiring preset equipment information of each first equipment as an acquisition object;
the combination unit is used for combining part or all of the first equipment in pairs to obtain more than one group of first equipment pairs;
the construction unit is used for respectively constructing a training sample for each group of first equipment pairs; each training sample respectively comprises: determining device pair characteristics according to preset device information of two first devices in the first device pair, and judging whether the two first devices in the first device pair belong to sample tags of the same user;
the training unit is used for training according to the training sample to obtain an evaluation model so as to determine whether two pieces of second equipment belong to the same user or not according to the evaluation model and the obtained equipment pair characteristics of the second equipment pair aiming at a second equipment pair consisting of any two pieces of second equipment to be evaluated.
15. The apparatus of claim 14,
the predetermined device information includes: APP behavior data and APP installation list information.
16. The apparatus of claim 15,
the method comprises the steps that a first obtaining unit collects original data of each first device within a preset time length, APP behavior data and APP installation list information are extracted from the original data, and the APP behavior data and the APP installation list information which belong to the same first device are aggregated to serve as preset device information of each obtained first device.
17. The apparatus of claim 16,
the APP behavior data comprises: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
the first obtaining unit respectively aggregates the APP behavior data and the APP installation list information belonging to the same first device according to the device identifier.
18. The apparatus of claim 16,
the first acquisition unit is further used for cleaning the extracted APP behavior data, filtering out the APP behavior data which do not meet the requirement, and/or cleaning the extracted APP installation list information, and filtering out the APP installation list information which do not meet the requirement.
19. The apparatus of claim 16,
the first obtaining unit is further configured to, for any first device, only retain APP behavior data of a number equal to a threshold if the number of APP behavior data obtained by aggregation is greater than the predetermined threshold.
20. The apparatus of claim 14,
the construction unit is further configured to, for any first device pair, determine that two first devices in the first device pair belong to the same user if it is determined that the two first devices in the first device pair have logged in the same user account id.
21. The apparatus of claim 14,
the construction unit is further configured to filter out a negative sample that does not meet the requirement from the constructed training sample, where the negative sample is a training sample in which two first devices in the corresponding first device pair do not belong to the same user.
22. An apparatus associated with a device, comprising: the device comprises a second acquisition unit, an extraction unit and an evaluation unit;
the second obtaining unit is configured to obtain, for any two second devices to be evaluated, predetermined device information of each second device;
the extraction unit is used for determining the device pair characteristics of a second device pair consisting of the two second devices according to the preset device information;
the evaluation unit is configured to determine whether the two second devices belong to the same user according to the device pair characteristics based on an evaluation model generated by the evaluation model generation method according to claims 1 to 8 or an evaluation model generated by the evaluation model generation apparatus according to claims 14 to 21.
23. The apparatus of claim 22,
the predetermined device information includes: APP behavior data and APP installation list information.
24. The apparatus of claim 23,
the second obtaining unit collects original data of each piece of second equipment to be evaluated within a preset time, extracts the APP behavior data and the APP installation list information from the original data, and respectively aggregates the APP behavior data and the APP installation list information belonging to the same second equipment to serve as preset equipment information of each piece of obtained second equipment.
25. The apparatus of claim 24,
the APP behavior data comprises: the device comprises a device identifier, a timestamp for generating an APP behavior and an APP identifier;
the APP installation list information includes: the method comprises the steps of identifying equipment, collecting a timestamp of an APP installation list and the APP installation list;
and the second acquisition unit respectively aggregates the APP behavior data and the APP installation list information belonging to the same second device according to the device identifier.
26. The apparatus of claim 24,
the second acquisition unit is further used for cleaning the extracted APP behavior data, filtering out the APP behavior data which do not meet the requirement, and/or cleaning the extracted APP installation list information, and filtering out the APP installation list information which do not meet the requirement.
27. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.
28. A non-transitory computer readable storage medium storing computer instructions, wherein,
the computer instructions are for causing the computer to perform the method of any one of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910948387.6A CN110866241A (en) | 2019-10-08 | 2019-10-08 | Evaluation model generation and equipment association method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910948387.6A CN110866241A (en) | 2019-10-08 | 2019-10-08 | Evaluation model generation and equipment association method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866241A true CN110866241A (en) | 2020-03-06 |
Family
ID=69652340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910948387.6A Pending CN110866241A (en) | 2019-10-08 | 2019-10-08 | Evaluation model generation and equipment association method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866241A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202117A (en) * | 2015-05-07 | 2016-12-07 | 深圳市腾讯计算机***有限公司 | Data processing method, device and server |
| CN106294105A (en) * | 2015-05-22 | 2017-01-04 | 深圳市腾讯计算机***有限公司 | Brush amount tool detection method and apparatus |
| CN106445942A (en) * | 2015-08-05 | 2017-02-22 | 腾讯科技（北京）有限公司 | User cross-screen identification method and apparatus |
| CN107657048A (en) * | 2017-09-21 | 2018-02-02 | 北京麒麟合盛网络技术有限公司 | user identification method and device |
| CN109858965A (en) * | 2019-01-25 | 2019-06-07 | 上海基分文化传播有限公司 | A kind of user identification method and system |
| CN109961080A (en) * | 2017-12-26 | 2019-07-02 | 腾讯科技（深圳）有限公司 | Terminal identification method and device |
-
2019
- 2019-10-08 CN CN201910948387.6A patent/CN110866241A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202117A (en) * | 2015-05-07 | 2016-12-07 | 深圳市腾讯计算机***有限公司 | Data processing method, device and server |
| CN106294105A (en) * | 2015-05-22 | 2017-01-04 | 深圳市腾讯计算机***有限公司 | Brush amount tool detection method and apparatus |
| CN106445942A (en) * | 2015-08-05 | 2017-02-22 | 腾讯科技（北京）有限公司 | User cross-screen identification method and apparatus |
| CN107657048A (en) * | 2017-09-21 | 2018-02-02 | 北京麒麟合盛网络技术有限公司 | user identification method and device |
| CN109961080A (en) * | 2017-12-26 | 2019-07-02 | 腾讯科技（深圳）有限公司 | Terminal identification method and device |
| CN109858965A (en) * | 2019-01-25 | 2019-06-07 | 上海基分文化传播有限公司 | A kind of user identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 王晓芹等: "基于级联结构的不平衡数据集分类研究", 《计算机工程与应用》, no. 13, 1 May 2010 (2010-05-01), pages 115 - 117 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107168854B (en) | Internet advertisement abnormal click detection method, device, equipment and readable storage medium | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| CN106960143B (en) | User account identification method and device, storage medium and electronic equipment | |
| US20210035126A1 (en) | Data processing method, system and computer device based on electronic payment behaviors | |
| CN111931047B (en) | Artificial intelligence-based black product account detection method and related device | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN110162518B (en) | Data grouping method, device, electronic equipment and storage medium | |
| CN106998336B (en) | Method and device for detecting user in channel | |
| CN106301979B (en) | Method and system for detecting abnormal channel | |
| CN110675252A (en) | Risk assessment method and device, electronic equipment and storage medium | |
| CN111723083A (en) | User identity identification method and device, electronic equipment and storage medium | |
| CN108076032B (en) | Abnormal behavior user identification method and device | |
| CN110348471B (en) | Abnormal object identification method, device, medium and electronic equipment | |
| CN104731937A (en) | User behavior data processing method and device | |
| CN112347457A (en) | Abnormal account detection method and device, computer equipment and storage medium | |
| CN113010785A (en) | User recommendation method and device | |
| CN110995687B (en) | Cat pool equipment identification method, device, equipment and storage medium | |
| CN110866241A (en) | Evaluation model generation and equipment association method, device and storage medium | |
| CN110263618A (en) | The alternative manner and device of one seed nucleus body model | |
| CN113225325B (en) | IP (Internet protocol) blacklist determining method, device, equipment and storage medium | |
| CN114169451A (en) | Behavior data classification processing method, device, equipment and storage medium | |
| CN115470399A (en) | ID (identity) communication method, device, equipment and storage medium based on big data | |
| CN113065894A (en) | Data collection method and device based on user portrait and order analysis and storage medium | |
| CN108629610B (en) | Method and device for determining popularization information exposure | |
| CN109413459B (en) | User recommendation method and related equipment in live broadcast platform |
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 |