CN110659419B - Method and related device for determining target user - Google Patents
Method and related device for determining target user Download PDFInfo
- Publication number
- CN110659419B CN110659419B CN201910877192.7A CN201910877192A CN110659419B CN 110659419 B CN110659419 B CN 110659419B CN 201910877192 A CN201910877192 A CN 201910877192A CN 110659419 B CN110659419 B CN 110659419B
- Authority
- CN
- China
- Prior art keywords
- user
- determining
- target
- text information
- portrait
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the disclosure provides a method for determining a target user and a related device. The method for determining the target user comprises the following steps: and determining an importance level value corresponding to the matching user based on the importance level value of the keyword in the text information, the priority score of the matching user and the importance level value of the target portrait element, and determining a target user based on the importance level value corresponding to the matching user. The technical scheme of the embodiment of the disclosure can improve the accuracy of determining the candidate users.
Description
Technical Field
The disclosure relates to the technical field of data analysis, in particular to a method for determining a target user and a related device.
Background
With the continuous development of internet science and technology, the current information volume presents explosive growth, and although user portraits are carried out on all users participating in the internet through the prior art so as to find the same or similar user groups in massive data through portrait labels in the user portraits, the data volume of the same or similar user groups determined through the manner of the portrait labels is still massive, and how to accurately determine target users meeting requirements in the massive data of the same or similar user groups is a problem to be solved.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
BRIEF SUMMARY OF THE PRESENT DISCLOSURE
The embodiment of the disclosure aims to provide a method and a device for determining a target user, so that the problem of low accuracy of determining the target user in the prior art can be solved at least to a certain extent.
According to one aspect of the disclosed embodiments, there is provided a method of determining a target user, comprising:
acquiring text information about a target user, and extracting keywords from the text information;
inputting the text information and the keywords into a preset importance degree value determining model, and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model;
obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in a pre-stored user portrait library;
searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user;
Acquiring target portrait elements matched with the keywords in each user portrait element matched with the user, and determining importance values of the target portrait elements;
determining an importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score of the matching user and the importance value of the target portrait element in the matching user;
and determining the target user based on the importance level value corresponding to the matched user.
In an embodiment of the disclosure, the extracting the keyword from the text information includes:
inputting the text information into a preset keyword extraction model, and obtaining keywords of the text information output by the keyword extraction model.
In an embodiment of the disclosure, the preset keyword extraction model is trained by:
acquiring a preset text information set;
extracting key words of each text information sample in the text information set in advance;
inputting the text information sample into the preset keyword extraction model, obtaining keywords output by the keyword extraction model, comparing the keywords output by the keyword extraction model with the keywords of the pre-extracted text information sample, and if the keywords are inconsistent, adjusting the preset keyword extraction model until the keywords output by the keyword extraction model are consistent with the keywords of the pre-extracted text information sample.
In an embodiment of the present disclosure, before the searching a pre-stored table corresponding to a specific attribute value range and a user priority score based on the specific attribute value of the matching user, the method further includes:
acquiring the user portrait of the matched user;
inputting the text information into a preset specific attribute determining model, and acquiring a specific attribute corresponding to the text information output by the preset specific attribute determining model;
and determining a specific attribute value corresponding to the matched candidate user based on the specific attribute and the user image of the matched candidate user.
In an embodiment of the present disclosure, the obtaining the target portrait elements of each of the user portrait elements of the matching user that match the keyword, and determining the importance value of the target portrait elements includes:
for each target portrait element matched with the keyword in the user portrait elements of the matched user, acquiring the execution times of the matched user in a unit period of network behaviors related to the target portrait elements and the average execution times of internet users in the unit period of the network behaviors related to the target portrait elements;
Determining the relative execution frequency of the target portrait elements of the matched user based on the execution times of the matched user of the network behavior related to the target portrait elements in a unit period and the average execution times of the internet users of the network behavior related to the target portrait elements in the unit period;
acquiring the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user;
and dividing the relative execution frequency of the target portrait elements of the matched user by the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user to obtain the importance value of the target portrait elements.
In an embodiment of the present disclosure, the determining the relative execution frequency of the target portrait elements of the matching user based on the matching user execution times of the network behavior related to the target portrait elements in a unit period and an internet user average execution times of the network behavior related to the target portrait elements in a unit period includes:
dividing the number of times of execution of the matching user in a unit period by the average number of times of execution of the internet user in the unit period by the network behavior related to the target portrait element to obtain the relative execution frequency of the target portrait element of the matching user.
In an embodiment of the disclosure, the determining the target user based on the importance value corresponding to the matching user includes:
sorting all users in the matched users based on importance values corresponding to the matched users, and obtaining the matched candidate user sequences;
and determining the users in the preset sequence range in the matched user sequence as target users.
According to an aspect of an embodiment of the present disclosure, there is provided an apparatus for determining a target user, including:
a first acquisition unit that acquires text information about a target user, and extracts keywords from the text information;
the second obtaining unit is used for inputting the text information and the keywords into a preset importance degree value determining model and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model;
the first determining unit is used for obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in the pre-stored user portrait library;
the second determining unit is used for searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user;
A third acquisition unit, configured to acquire target portrait elements, each of which matches the keyword, of the user portrait elements of the matching user, and determine a importance value of the target portrait elements;
a third determining unit, configured to determine, in the matching user, a importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score of the matching user, and the importance value of the target portrait element;
and a fourth determining unit, configured to determine a target user based on the importance level value corresponding to the matching user.
According to an aspect of the disclosed embodiments, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method of determining a target user as described in the above embodiments.
According to an aspect of an embodiment of the present disclosure, there is provided an electronic device including: one or more processors; and a storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of determining a target user as described in the above embodiments.
Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
in the technical schemes provided by some embodiments of the present disclosure, keywords are extracted from acquired text information about a target user, the text information and the keywords corresponding to the text information are input into a preset importance degree model, an importance degree value corresponding to each keyword in the plurality of keywords in the text information is obtained, then a matching user is obtained in a user image library based on the plurality of keywords, and then a priority score of the matching user is determined based on a specific attribute value corresponding to the matching user and a pre-stored specific attribute value range and user priority score corresponding table; acquiring target portrait elements matched with the keywords in each user portrait element matched with the user, and determining importance values of the target portrait elements; and then, determining the importance level value corresponding to the matching user based on the importance level value of the keyword in the text information, the user priority score and the importance level value of the target portrait element, and determining the target user based on the importance level value corresponding to the matching user. Therefore, the technical scheme of the embodiment of the disclosure can improve the accuracy of determining the target user.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort. In the drawings:
FIG. 1 illustrates a schematic diagram of an exemplary system architecture of a method of determining a target user or a device of determining a target user to which embodiments of the present disclosure may be applied;
FIG. 2 schematically illustrates a flow chart of a method of determining a target user according to one embodiment of the disclosure;
FIG. 3 schematically illustrates a flow chart of a preset keyword extraction model training process;
fig. 4 schematically shows a flow chart before step S240 shown in fig. 2;
fig. 5 schematically shows a detailed flowchart of step S250 shown in fig. 2;
fig. 6 schematically shows a detailed flowchart of step S270 shown in fig. 2;
FIG. 7 schematically illustrates a block diagram of an apparatus for determining a target user according to one embodiment of the disclosure;
FIG. 8 illustrates a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure;
FIG. 9 is a diagram of a computer-readable storage medium illustrating a determination of a target user according to an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Fig. 1 shows a schematic diagram of an exemplary system architecture 100 of a device for determining candidate users or determining candidate clients to which embodiments of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired communication links, wireless communication links, and the like.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. The terminal devices 101, 102, 103 may be various electronic devices with display screens including, but not limited to, smartphones, tablet computers, portable computers, desktop computers, and the like.
The server 105 may be a server providing various services. After obtaining text information about a target user, the server 105 extracts keywords from the text information, obtains importance values of the keywords in the text information through a preset importance value determining model, determines matching users in a pre-stored user image library based on the keywords, determines matching user priority scores based on a table corresponding to a specific attribute value of the matching users and a preset specific attribute value range and user priority score, and obtains target portrait elements matched with the keywords in each of the user portrait elements of the matching users, and determines importance values of the target portrait elements; determining importance values corresponding to the matched users based on the importance values of the keywords in the text information, the user priority scores and the importance values of the target portrait elements; and determining the target user based on the importance level value corresponding to the matched user, so that the accuracy of determining the target user can be improved.
It should be noted that, the method for determining the candidate user provided in the embodiments of the present disclosure is generally performed by the server 105, and accordingly, the device for determining the candidate user is generally disposed in the server 105. However, in other embodiments of the present disclosure, the terminal may also have a similar function as the server, so as to perform the scheme of determining candidate users provided by the embodiments of the present disclosure.
The present disclosure first provides a method of determining a target user. Fig. 2 is a flow chart illustrating a method of determining a target user according to an exemplary embodiment. As shown in fig. 2, the method comprises the steps of:
step S210: acquiring text information about a target user, and extracting keywords from the text information;
step S220: inputting the text information and the keywords into a preset importance degree value determining model, and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model;
step S230: obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in a pre-stored user portrait library;
step S240: searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user;
Step S250: acquiring target portrait elements matched with the keywords in each user portrait element matched with the user, and determining importance values of the target portrait elements;
step S260: determining an importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score of the matching user and the importance value of the target portrait element in the matching user;
step S270: and determining the target user based on the importance level value corresponding to the matched user.
Hereinafter, each step of the above-described method of determining a target user in the present exemplary embodiment will be explained and described in detail with reference to the accompanying drawings.
In step S210, text information about a target user is acquired, and keywords are extracted from the text information.
In one embodiment of the present disclosure, the text information about the target user refers to a description text about the target user group to be determined, where the description text includes feature information about the candidate user group, for example, one feature information is young, another feature information is female, and other feature information is good in learning performance, where if a plurality of feature information are combined together to form a text description about the candidate user group, the text description about the candidate user group after combining the feature information is: the young girls with excellent learning results and loving sports need to be noted that the text information about the candidate users includes at least one feature information.
In one embodiment of the present disclosure, extracting the keywords of the text information includes: inputting the text information into a preset keyword extraction model, obtaining keywords of the text information output by the keyword extraction model, determining the keywords in the text information in a machine learning model mode, and improving the accuracy of the finally determined target user, wherein the processing efficiency is higher and the standard is more uniform compared with that of manual processing.
In another embodiment of the present disclosure, extracting the keyword of the text information may further include: dividing the text information into sentences; comparing the sentences divided by the text information with each candidate user text sentence template in a preset candidate user text sentence template library, thereby determining candidate user text sentence templates matched with the sentences divided by the text information, wherein keyword positions in the candidate user text sentences are specified in the candidate user text sentence templates; and determining keywords in sentences into which the text information is divided according to keyword positions in candidate user texts specified in the candidate user text sentence templates, wherein the keyword determination accuracy is higher compared with the keyword determination by a machine learning model.
In an embodiment of the disclosure, as shown in fig. 3, the preset keyword extraction model is trained by:
step S310: acquiring a preset text information set;
step S320: extracting key words of each text information sample in the text information set in advance;
step S330: inputting the text information sample into the preset keyword extraction model, obtaining keywords output by the keyword extraction model, comparing the keywords output by the keyword extraction model with the keywords of the pre-extracted text information sample, and if the keywords are inconsistent, adjusting the preset keyword extraction model until the keywords output by the keyword extraction model are consistent with the keywords of the pre-extracted text information sample.
In an embodiment of the present disclosure, training the machine learning model through preset database data may improve accuracy of output results of the machine learning model.
With continued reference to fig. 2, in step S220, the text information and the keyword are input into a preset importance value determining model, and the importance value of the keyword output by the importance value determining model in the text information is obtained.
In an embodiment of the present disclosure, the importance value of the keyword in the text information refers to the importance of the feature information corresponding to the keyword in the text description information about the candidate user, for example, a text description information about the candidate user is: the female young who learns to be excellent and loves to exercise is preferably accompanied by the feature of being loved to assist, and the feature information of the candidate user text description information, which is loved to assist, has lower importance than the two feature information of being excellent and loving to exercise.
In an embodiment of the present disclosure, the importance value determination model may be trained by: acquiring a preset text information set about a target user; extracting keywords of each text information sample about the target user in the text information set about the target user; determining the importance value of the keywords of each text information sample about the target user in the text information sample about the target user in advance; inputting the text information sample related to the target user and the corresponding keywords into the preset importance degree value determining model, obtaining an importance degree value output by the importance degree value determining model, comparing the importance degree value output by the importance degree value determining model with a preset importance degree value of the keywords of the text information sample related to the target user in the text information sample related to the target user, and if the importance degree value is inconsistent with the preset importance degree value, adjusting the preset importance degree value determining model until the importance degree value output by the importance degree value determining model is consistent with the preset importance degree value of the keywords of the text information sample related to the target user in the text information sample related to the target user.
In an embodiment of the present disclosure, training the machine learning model through preset database data may improve accuracy of output results of the machine learning model.
With continued reference to fig. 2, in step S230, a matching user is obtained based on the matching of the keyword with the user portrait elements of each user in the pre-stored user portrait library.
In an embodiment of the present disclosure, a matching candidate user is obtained by matching a keyword with an portrait element of each candidate user in a pre-stored candidate user library, and if a logarithm of matching the keyword existing in the portrait element of the candidate user with the portrait element of the user reaches a preset logarithm, the candidate user is determined to be the matching candidate user, if the keyword is "cosmetic", the portrait element of the user is "purchase cosmetic", and the candidate user including the portrait element of "purchase cosmetic" is determined to be the matching candidate user.
In step S240, a pre-stored table of correspondence between specific attribute value ranges and user priority scores is searched based on the specific attribute values of the matching users, and the priority scores corresponding to the matching users are determined.
In an embodiment of the present disclosure, before step S240, it may further include:
step S237: acquiring the user portrait of the matched user;
step S238: inputting the text information into a preset specific attribute determining model, and acquiring a specific attribute corresponding to the text information output by the preset specific attribute determining model;
step S239: and determining a specific attribute value corresponding to the matched candidate user based on the specific attribute and the user image of the matched candidate user.
In an embodiment of the disclosure, the preset specific attribute determining model may be trained in the following manner to obtain a preset text information set about the target user; a specific attribute corresponding to each text information sample about the target user in the text information set about the target user is predetermined; inputting the text information sample related to the target user and the corresponding specific attribute into the preset specific attribute determining model, acquiring the specific attribute output by the specific attribute determining model, comparing the specific attribute output by the specific attribute determining model with the preset specific attribute corresponding to the text information sample related to the target user, and if the specific attribute is inconsistent with the preset specific attribute, adjusting the preset specific attribute determining model until the specific attribute output by the specific attribute determining model is consistent with the preset specific attribute corresponding to the text information sample related to the target user.
In an embodiment of the present disclosure, the specific attribute refers to an abstract depiction of a specific aspect of a person, e.g., the specific attribute of a user may be "consumption," "academic," "sports," etc.
In an embodiment of the present disclosure, if the acquired text information is "loving cosmetics and is willing to purchase cosmetics while being a person who prefers to watch movies at the same time," consumption "may be determined as a specific attribute corresponding to the text information, because both" purchasing cosmetics "and" watching movies "require sufficient consumption capability, and then the priority level corresponding to the candidate user determined based on the description information may be determined by an attribute value (consumption amount) corresponding to the specific attribute" consumption ", wherein the priority level may be directly represented by the priority level.
In an embodiment of the present disclosure, determining the priority score of the matching candidate user may also be by: determining intention information contained in the text information, inputting the intention information into a preset machine learning model, acquiring a specific attribute output by the machine learning model, and determining a specific attribute value corresponding to the candidate user based on the specific attribute. For example, a user image sample is female, adult, white collar, 8 thousand months of income, 30 minutes per day of average news reading, liking to watch Korean drama, 2 hours per day of average television drama. If the intention information of the candidate user is determined to be that cosmetics are promoted to the candidate user, 8 kiloof month income in the user portrait is used as a specific attribute value corresponding to the user of the user portrait, and if the intention of the candidate user is determined to be that the user is recommended to the television show, the average television show per day in the user portrait can be used as the specific attribute value corresponding to the user for 2 hours.
With continued reference to fig. 2, in step S250, a importance value of each of the user portrait elements of the matching user that matches the keyword in the user portrait elements of each of the matching users is obtained.
In an embodiment of the present disclosure, step S250 may include:
step S2501: for each target portrait element matched with the keyword in the user portrait elements of the matched user, acquiring the execution times of the matched user in a unit period of network behaviors related to the target portrait elements and the average execution times of internet users in the unit period of the network behaviors related to the target portrait elements;
step S2502: determining the relative execution frequency of the target portrait elements of the matched user based on the execution times of the matched user of the network behavior related to the target portrait elements in a unit period and the average execution times of the internet users of the network behavior related to the target portrait elements in the unit period;
step S2503: acquiring the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user;
Step S2504: and dividing the relative execution frequency of the target portrait elements of the matched user by the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user to obtain the importance value of the target portrait elements.
Wherein step S2502 may include: dividing the number of times of execution of the matching user in a unit period by the average number of times of execution of the internet user in the unit period by the network behavior related to the target portrait element to obtain the relative execution frequency of the target portrait element of the matching user.
In an embodiment of the present disclosure, the network behavior may also be other behaviors, such as a consumption behavior, a click video behavior, and the like.
In one embodiment of the disclosure, for each of the user portrayal elements of the matched candidate users that match the keyword, an average of the attribute value corresponding to the user portrayal element in a unit period and the attribute values corresponding to the portrayal elements of all users in the candidate user library in the unit period is obtained.
In an embodiment of the present disclosure, the network behavior may also be other behaviors related to the target portrait element, and is not limited to only network behavior.
In an embodiment of the present disclosure, the obtaining the sum of the relative execution frequencies of all portrait elements in the user portrait of the matching user may be performed by: acquiring the execution times of the related behavior of each portrait element in the user portrait of the matched user in a unit period, acquiring the execution times of the related behavior of each portrait element in the Internet user in the unit period, and determining the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user based on the execution times of the related behavior of each portrait element of the matched user in the unit period and the execution times of the related behavior of each portrait element in the Internet user in the unit period.
In one embodiment of the present disclosure, if the attribute value corresponding to the user portrait element is obtained, the attribute value in the unit period corresponding to the user portrait element is divided by the average value of the attribute values corresponding to the portrait elements of all users in the candidate user library in the unit period, so as to obtain the relative ratio of the user portrait element for the candidate user.
In one embodiment of the present disclosure, if a relative ratio of the user portrait elements of the matching user is obtained, the relative ratio of the user portrait of the matching user is divided by a sum of relative ratios of all user portrait elements of the matching user to obtain importance values of the user portrait elements in all portrait elements of the matching user.
In step S260, in the matching user, a importance value corresponding to the matching user is determined based on the importance value of the keyword in the text information, the priority score of the matching user, and the importance value of the target portrait element.
In an embodiment of the present disclosure, the importance value corresponding to the matching user may be determined based on the following formula:
wherein S is v A, as the importance value corresponding to the v-th matched user in the matched users i Is the importance value corresponding to the ith keyword in the text information, c iv The importance value of the portrait element corresponding to the ith keyword in the text information in all portrait elements corresponding to the v-th matched user in the matched users; b (B) v A priority score corresponding to the v-th matched user in the matched users, wherein n is the total number of keywords with corresponding importance values in the text informationA number.
In step S270, a target user is determined based on the importance level value corresponding to the matching user.
In an embodiment of the present disclosure, as shown in fig. 6, step S270 may include:
step S2701: sorting all users in the matched users based on importance values corresponding to the matched users, and obtaining the matched candidate user sequences;
Step S2702: and determining the users in the preset sequence range in the matched user sequence as target users.
In an embodiment of the present disclosure, the matching candidate users may be ranked from large to small according to their corresponding importance values in a ranking manner, and users with an order within a preset range are used as their own target users, so as to improve accuracy in determining the target users.
In another embodiment of the present disclosure, after step S270, it may further include: and responding to the request of determining the key high-quality user in the target user, and determining the key high-quality client in the candidate user based on the importance value corresponding to the target user.
The importance degree of the found candidate users is reflected through the importance degree value, so that the degree that the determined candidate users reach the requirements of the candidate users can be simply and clearly reflected, and people can simply and quickly screen out important high-quality clients from confirmed target users again.
The technical solutions of the embodiments shown in fig. 2 to fig. 6 enable determining the importance value corresponding to the matching user through deep mining analysis on the text information about the target user, and further determine the target user based on the importance value of the matching user, thereby improving accuracy of determining the target user. Meanwhile, the importance value of the matching user reflects the matching degree and the importance of the text information of the matching user and the target user, so that the importance condition of the matching user can be simply and clearly reflected through the importance value of the matching user, and the determined target user can be screened again based on the importance value of the matching user, so that the importance condition of the determined target user can be simply and clearly reflected and conveniently screened again on the premise of improving the accuracy of the determined target user.
The present disclosure also provides an apparatus for determining a target user. Referring to fig. 7, the apparatus 600 for determining a target user includes: the first acquisition unit 610, the second acquisition unit 620, the first determination unit 630, the second determination unit 640, the third acquisition unit 650, the third determination unit 660, the fourth determination unit 670. Wherein:
a first acquisition unit 610 configured to acquire text information about a target user, and extract keywords from the text information;
a second obtaining unit 620 configured to input the text information and the keyword into a preset importance value determining model, and obtain an importance value of the keyword output by the importance value determining model in the text information;
a first determining unit 630, configured to obtain a matched user based on the matching of the keyword and the user portrait elements of each user in the pre-stored user portrait library;
a second determining unit 640 configured to search a pre-stored table of specific attribute value ranges and user priority scores based on the specific attribute values of the matching users, and determine the priority scores corresponding to the matching users;
a third acquisition unit 650 configured to acquire target portrait elements each of which matches the keyword among the user portrait elements of the matching user, and determine a importance value of the target portrait elements;
A third determining unit 660 configured to determine, in the matching user, a importance value corresponding to the matching user based on the importance value of the keyword in the text information, the matching user priority score, and the importance value of the target portrait element;
and a fourth determining unit 670 configured to determine a target user based on the importance level value corresponding to the matching user.
The specific details of each module in the device for determining the target user are described in the corresponding method, so that they will not be described in detail herein.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in the particular order or that all of the illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 400 according to this embodiment of the invention is described below with reference to fig. 8. The electronic device 400 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 8, the electronic device 400 is embodied in the form of a general purpose computing device. The components of electronic device 400 may include, but are not limited to: the at least one processing unit 410, the at least one memory unit 420, and a bus 430 connecting the various system components, including the memory unit 420 and the processing unit 410.
Wherein the storage unit stores program code that is executable by the processing unit 410 such that the processing unit 410 performs steps according to various exemplary embodiments of the present invention described in the above-described "exemplary methods" section of the present specification. For example, the processing unit 410 may perform step S210 as shown in fig. 1: acquiring text information about a target user, and extracting keywords from the text information; step S220: inputting the text information and the keywords into a preset importance degree value determining model, and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model; step S230: obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in a pre-stored user portrait library; step S240: searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user; step S250: acquiring target portrait elements matched with the keywords in each user portrait element matched with the user, and determining importance values of the target portrait elements; step S260: determining an importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score of the matching user and the importance value of the target portrait element in the matching user; step S270: and determining the target user based on the importance level value corresponding to the matched user.
The storage unit 420 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 4201 and/or cache memory 4202, and may further include Read Only Memory (ROM) 4203.
The storage unit 420 may also include a program/utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 430 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 400 may also communicate with one or more external devices 500 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 400, and/or any device (e.g., router, modem, etc.) that enables the electronic device 400 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 450. Also, electronic device 400 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 over the bus 430. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 400, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
Referring to fig. 9, a program product 700 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a 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.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. 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 of the foregoing. A readable signal medium may also be any readable medium that is not a 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 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.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present application, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (8)
1. A method of determining a target user, comprising:
acquiring text information about a target user, and extracting keywords from the text information;
inputting the text information and the keywords into a preset importance degree value determining model, and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model;
Obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in a pre-stored user portrait library;
acquiring the user portrait of the matched user;
inputting the text information into a preset specific attribute determining model, and acquiring a specific attribute corresponding to the text information output by the preset specific attribute determining model;
determining a specific attribute value of the matched user based on the specific attribute and the user image of the matched user;
searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user;
for each target portrait element matched with the keyword in the user portrait elements of the matched users, acquiring the execution times of the matched users in a unit period of network behaviors related to the target portrait elements and the average execution times of internet users in the unit period of the network behaviors related to the target portrait elements;
determining the relative execution frequency of the target portrait elements of the matched user based on the matching user execution times of the network behavior related to the target portrait elements in a unit period and the average internet user execution times of the network behavior related to the target portrait elements in the unit period;
Acquiring the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user;
dividing the relative execution frequency of the target portrait elements of the matched user by the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user to obtain an importance value of the target portrait elements;
determining an importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score corresponding to the matching user and the importance value of the target portrait element in the matching user;
and determining the target user based on the importance level value corresponding to the matched user.
2. The method for determining a target user according to claim 1, wherein the extracting keywords from the text information comprises:
inputting the text information into a preset keyword extraction model, and obtaining keywords of the text information output by the keyword extraction model.
3. The method for determining a target user according to claim 2, wherein the preset keyword extraction model is trained by:
Acquiring a preset text information set;
extracting key words of each text information sample in the text information set in advance;
inputting the text information sample into the preset keyword extraction model, obtaining keywords output by the keyword extraction model, comparing the keywords output by the keyword extraction model with the keywords of the pre-extracted text information sample, and if the keywords are inconsistent, adjusting the preset keyword extraction model until the keywords output by the keyword extraction model are consistent with the keywords of the pre-extracted text information sample.
4. The method of determining a target user according to claim 1, wherein the determining the relative execution frequency of the target portrait elements for the matching user based on the number of times the matching user executes the network behavior related to the target portrait elements in a unit period and the average number of times the internet user executes the network behavior related to the target portrait elements in a unit period includes:
dividing the number of times of execution of the matching user in a unit period by the number of times of average execution of the internet user in the unit period by the network behavior related to the target portrait element to obtain the relative execution frequency of the target portrait element of the matching user.
5. The method for determining a target user according to claim 1, wherein determining the target user based on the importance value corresponding to the matching user comprises:
sorting all users in the matched users based on importance values corresponding to the matched users to obtain a matched user sequence;
and determining the users in the preset sequence range in the matched user sequence as target users.
6. An apparatus for determining a target user, comprising:
a first acquisition unit that acquires text information about a target user, and extracts keywords from the text information;
the second obtaining unit is used for inputting the text information and the keywords into a preset importance degree value determining model and obtaining the importance degree value of the keywords in the text information, which is output by the importance degree value determining model;
the first determining unit is used for obtaining a matched user based on the matching of the keyword and the user portrait elements of each user in the pre-stored user portrait library; acquiring the user portrait of the matched user; inputting the text information into a preset specific attribute determining model, and acquiring a specific attribute corresponding to the text information output by the preset specific attribute determining model; determining a specific attribute value of the matched user based on the specific attribute and the user image of the matched user;
The second determining unit is used for searching a pre-stored specific attribute value range and user priority score corresponding table based on the specific attribute value of the matched user, and determining the priority score corresponding to the matched user;
a third obtaining unit, configured to obtain, for each target portrait element that matches the keyword in the user portrait elements of the matching user, the number of times of execution of the matching user in a unit period of a network behavior related to the target portrait element, and the average number of times of execution of the internet user in the unit period of the network behavior related to the target portrait element; determining the relative execution frequency of the target portrait elements of the matched user based on the matching user execution times of the network behavior related to the target portrait elements in a unit period and the average internet user execution times of the network behavior related to the target portrait elements in the unit period; acquiring the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user; dividing the relative execution frequency of the target portrait elements of the matched user by the sum of the relative execution frequencies of all portrait elements in the user portrait of the matched user to obtain an importance value of the target portrait elements;
A third determining unit, configured to determine, in the matching user, a importance value corresponding to the matching user based on the importance value of the keyword in the text information, the priority score corresponding to the matching user, and the importance value of the target portrait element;
and a fourth determining unit, configured to determine a target user based on the importance level value corresponding to the matching user.
7. A computer readable medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of determining a target user according to any of claims 1 to 5.
8. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of determining a target user of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910877192.7A CN110659419B (en) | 2019-09-17 | 2019-09-17 | Method and related device for determining target user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910877192.7A CN110659419B (en) | 2019-09-17 | 2019-09-17 | Method and related device for determining target user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110659419A CN110659419A (en) | 2020-01-07 |
| CN110659419B true CN110659419B (en) | 2023-09-05 |
Family
ID=69037158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910877192.7A Active CN110659419B (en) | 2019-09-17 | 2019-09-17 | Method and related device for determining target user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110659419B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| CN105373584A (en) * | 2015-10-14 | 2016-03-02 | 北京乐动卓越科技有限公司 | User tag management method, user determination method and cloud server |
| CN107203894A (en) * | 2016-03-18 | 2017-09-26 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| WO2018049960A1 (en) * | 2016-09-14 | 2018-03-22 | 厦门幻世网络科技有限公司 | Method and apparatus for matching resource for text information |
| CN108415935A (en) * | 2018-01-23 | 2018-08-17 | 北京奇虎科技有限公司 | A kind of method, apparatus of push recommendation message |
| KR20180136265A (en) * | 2017-06-14 | 2018-12-24 | 주식회사 핀인사이트 | Apparatus, method and computer-readable medium for searching and providing sectional video |
-
2019
- 2019-09-17 CN CN201910877192.7A patent/CN110659419B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| CN105373584A (en) * | 2015-10-14 | 2016-03-02 | 北京乐动卓越科技有限公司 | User tag management method, user determination method and cloud server |
| CN107203894A (en) * | 2016-03-18 | 2017-09-26 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| WO2018049960A1 (en) * | 2016-09-14 | 2018-03-22 | 厦门幻世网络科技有限公司 | Method and apparatus for matching resource for text information |
| KR20180136265A (en) * | 2017-06-14 | 2018-12-24 | 주식회사 핀인사이트 | Apparatus, method and computer-readable medium for searching and providing sectional video |
| CN108415935A (en) * | 2018-01-23 | 2018-08-17 | 北京奇虎科技有限公司 | A kind of method, apparatus of push recommendation message |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110659419A (en) | 2020-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| US11714816B2 (en) | Information search method and apparatus, device and storage medium | |
| US10902077B2 (en) | Search result aggregation method and apparatus based on artificial intelligence and search engine | |
| US8782155B2 (en) | Methods and apparatus for inserting content into conversations in on-line and digital environments | |
| US9767183B2 (en) | Method and system for enhanced query term suggestion | |
| EP3729231A1 (en) | Domain-specific natural language understanding of customer intent in self-help | |
| CN110597962B (en) | Search result display method and device, medium and electronic equipment | |
| US11172040B2 (en) | Method and apparatus for pushing information | |
| CN107526846B (en) | Method, device, server and medium for generating and sorting channel sorting model | |
| CN110147494B (en) | Information searching method and device, storage medium and electronic equipment | |
| CN113688310B (en) | Content recommendation method, device, equipment and storage medium | |
| CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
| CN113301442A (en) | Method, apparatus, medium, and program product for determining live broadcast resource | |
| US10600017B2 (en) | Co-opetition index based on rival behavior in social networks | |
| CN110737811A (en) | Application classification method and device and related equipment | |
| CN113961823B (en) | News recommendation method, system, storage medium and equipment | |
| CN109472028B (en) | Method and device for generating information | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN110971973A (en) | Video pushing method and device and electronic equipment | |
| WO2022267755A1 (en) | Form processing method and apparatus, device, and storage medium | |
| CN110659419B (en) | Method and related device for determining target user | |
| CN115827978A (en) | Information recommendation method, device, equipment and computer readable storage medium | |
| CN112672202B (en) | Bullet screen processing method, equipment and storage medium | |
| CN112802454B (en) | Method and device for recommending awakening words, terminal equipment and storage medium | |
| CN112348614A (en) | Method and device for pushing information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |