CN109918583B - Task information processing method and device - Google Patents
Task information processing method and device Download PDFInfo
- Publication number
- CN109918583B CN109918583B CN201910205292.5A CN201910205292A CN109918583B CN 109918583 B CN109918583 B CN 109918583B CN 201910205292 A CN201910205292 A CN 201910205292A CN 109918583 B CN109918583 B CN 109918583B
- Authority
- CN
- China
- Prior art keywords
- user
- task
- information
- target
- target user
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a task information processing method and device, relates to the technical field of computers, and is mainly used for solving the problem that the requirements of a recruiter for regional job seekers and real-time job seekers cannot be met in the prior art. Examples of the present invention include: acquiring user information of a target user, wherein the user position information of the target user in a set period is in a set area range, and/or the commuting time from the user position information to a set position in the set period is less than or equal to a threshold value; calculating the similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and sorting the target users according to the similarity scores and outputting a target user list.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a task information processing method and device.
Background
With the rapid development of internet technology, more and more internet products bring great changes to the work and life of people, such as the field of recruitment. The specific implementation process is as follows: the enterprise recruiter issues the recruiting position information on the recruiting system, and the job seeker inputs the required established position keywords on the user terminal. The method comprises the steps that a user actively delivers, after the user inputs post keyword information at a search function of a post retrieval interface through a user terminal, the user terminal automatically sends a retrieval information instruction to a recruitment system server within 3 seconds through a network communication technology, the recruitment system server automatically receives the post retrieval information instruction within 3 seconds, the post keyword information sent by the user terminal is obtained through a web technology/algorithm, post keyword matching is conducted on a database, a matching result is returned to the user terminal, so that the mobile terminal presents the matching result on the post retrieval interface, the user selects a post suitable for the user, after the user selects the post, enterprise recruiters determine that job seekers accord with post requirements, determine job hunters to enter a post, and complete recruitment.
However, the recruitment system server performs search and matching according to the location information registered by the user, and cannot meet the requirements of the recruiter for the regional job seeker and the real-time job seeker, so that the matching accuracy of the result returned by the recruitment system server is low.
Disclosure of Invention
The embodiment of the invention provides a task information processing method and a task information processing device, which are used for solving the problem that the requirements of a recruiter for regional job seekers and real-time job seekers cannot be met in the prior art.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
in a first aspect of the embodiments of the present invention, a method for processing task information is provided, where the method includes:
acquiring user information of a target user, wherein the user information comprises user position information, the target user accords with a user that the user position information is in a set area range in a set period, and/or the commute time of the target user from the user position information to a set position in the set period is less than or equal to a threshold value;
calculating the similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and
and sorting the target users according to the similarity scores and outputting a target user list.
Optionally, the step of obtaining the user information of the target user includes:
acquiring first user information of a first user, wherein the first user information comprises first user position information of the first user; and
and when the first user position information is in the set area range in the set period, enabling the target user to comprise the first user.
Optionally, the step of obtaining the user information of the target user includes:
acquiring first user information of a first user, wherein the first user information comprises first user position information of the first user; and
and when the commute time from the first user position information to a set position in a set period is less than or equal to a threshold value, enabling the target user to comprise the first user.
Optionally, the step of obtaining the user information of the target user includes:
acquiring first user information of a first user, wherein the first user information comprises first user position information of the first user; and
and when the first user position information is in the range of the set area within a set period and the commute time from the first user position information to a set position within the set period is less than or equal to a threshold value, enabling the target user to comprise the first user.
Optionally, the user information further includes a personal tag, and the task information includes a geographic location where the task is located and a task tag;
the step of calculating the similarity score between each target user and the task information according to the user information and the task information of the target user comprises the following steps:
acquiring a user characteristic vector consisting of a weight value of the user position information and a weight value of the personal label, and acquiring a task characteristic vector consisting of a weight value of a geographic position where a task is located and a weight value of the task label; and
and calculating the similarity score of each target user matched with the task information according to the user feature vector and the task feature vector.
Further optionally, the method further comprises:
initializing each weight value in the user characteristic vector and each weight value in the task characteristic vector; and
inputting the initialized weight values into a neural network, and training all the weight values;
or/and, the method further comprises:
acquiring user information and task information;
extracting a first keyword of the user information and a second keyword of the task information by adopting a word segmentation algorithm, and establishing a first mapping relation between the first keyword and the user information and a second mapping relation between the second keyword and the task information; and
and acquiring the user position information and the personal label from the first mapping relation, and acquiring the geographic position of the task and the task label from the second mapping relation.
Optionally, the method further includes:
calculating the experience value score of each target user according to the user information of the target user;
calculating a comprehensive score of the target user according to the experience value score of the target user and the similarity score of each target user matched with the task information; and
sorting the target users according to the magnitude of the comprehensive scores of the target users and outputting a target user list;
preferably, the method further comprises:
and outputting a related friend list of the target user after detecting the triggering operation of checking the user information of the target user.
Optionally, the method further includes:
after receiving the triggering operation of task completion, displaying an evaluation scoring interface; and
receiving evaluation information for evaluating the target user, and displaying the evaluation information on an evaluation scoring interface;
preferably, after the step of receiving a triggering operation of task completion, the method further comprises:
verifying the cost of the target user according to the task information; and
and paying the expense of the target user to an account of the target user through a bank gateway.
Preferably, the target user list includes only a part of the target users, and the remaining target users not included in the part have a similarity score smaller than that of the target users included in the part.
In a second aspect of the embodiments of the present invention, there is provided a task information processing apparatus, including:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring user information of a target user, the user information comprises user position information, the target user accords with a user whose user position information is in a set area range in a set period, and/or the target user accords with a user whose commute time from the user position information to a set position in the set period is less than or equal to a threshold value;
the calculation module is used for calculating the similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and
and the output module is used for sorting the target users according to the similarity scores and outputting a target user list.
In a third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which stores a computer program for executing the method of the first aspect.
In a fourth aspect of the embodiments of the present invention, a method for processing task information is provided, where the method includes:
task information of a target task is obtained, the task information comprises task position information, the target task is in a set area range according with the task position information, and/or the commuting time from a set position to the task position information is smaller than or equal to a threshold value;
calculating a similarity score of each target task matched with the user information according to the task information of the target task and the user information of the first target user; and
and sequencing the target tasks according to the similarity scores and outputting a target task list.
Optionally, the step of obtaining task information of the target task includes:
acquiring first task information of a first task, wherein the first task information comprises first task position information of the first task; and
and when the first task position information is in a set area range, enabling the target task to comprise the first task.
Optionally, the step of obtaining task information of the target task includes:
acquiring first task information of a first task, wherein the first task information comprises first task position information of the first task; and
and when the commute time from the first task position information to a set position is less than a threshold value, enabling the target task to comprise the first task.
Optionally, the step of obtaining task information of the target task includes:
acquiring first task information of a first task, wherein the first task information comprises first task position information of the first task; and
when the first task position information is within a set area range and when the commute time from the first task position information to a set position is less than a threshold value, enabling the target task to comprise the first task.
Optionally, the user information includes user location information and a personal tag where the user is located, and the task information further includes a task tag; the step of calculating the similarity score of each target task matched with the user information according to the task information and the user information of the target task comprises the following steps:
acquiring a task characteristic vector consisting of a weight value of the task position information and a weight value of the task label, and acquiring a user characteristic vector consisting of a weight value of the user position information and a weight value of the personal label; and
and calculating the similarity score of each target task matched with the user information according to the task feature vector and the user feature vector.
Optionally, the user information includes a personal tag and user location information, and the method further includes:
calculating a similarity score between the first target user and the second target user according to the user feature vector;
when the similarity score between the first target user and the second target user is smaller than or equal to a threshold value, judging that the first target user and the second target user are similar users; and
and outputting the target task list corresponding to the first target user to the second target user after detecting the starting operation of the second target user for checking the target task information.
Optionally, the method further includes:
calculating a value score of each target task according to the task information of the target task;
calculating a comprehensive score of the target task according to the value score of the target task and the similarity score of each target task matched with the user information; and
and outputting the target task list according to the comprehensive score of the target task.
Optionally, the method further includes:
after receiving the triggering operation of task completion, displaying an evaluation scoring interface; and
receiving evaluation information for evaluating the target task, and displaying the evaluation information on an evaluation scoring interface;
preferably, after the triggering operation of task completion is received, the method further includes:
verifying the cost of the target user according to the task information; and
and paying the expense of the target user to an account of the target user through a bank gateway.
Preferably, the target task list includes only a part of the target tasks, and the remaining non-included parts of the target tasks have a similarity score smaller than that of the included parts of the target tasks.
In a fifth aspect of the embodiments of the present invention, there is provided a task information processing apparatus, including:
the task information comprises task position information, the target task is in accordance with the task position information and is within a set area range, and/or the commuting time of the target task from a set position to the task position information is less than or equal to a threshold value;
the calculation module is used for calculating the similarity score of each target task matched with the user information according to the task information of the target task and the user information of a target user; and
and the output module is used for sorting the target tasks according to the similarity scores and outputting a target task list.
A sixth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program for executing the method according to the fourth aspect.
Compared with the prior art, the task information processing method and the task information processing device provided by the invention have the advantages that firstly, the user information of the target user is obtained, the user position information of the target user is in the range of the set area in the set period, and/or the commuting time of the target user from the user position information to the set position in the set period is less than or equal to the threshold value; then, calculating a similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and finally, sorting the target users according to the similarity scores and outputting a target user list. Due to the fact that geographical positions and time periods are adopted for filtering the target users regionally and in real time, time spent on results returned by the server or the terminal is small, and matching accuracy is high.
Drawings
The disclosure may be better understood by reference to the following description taken in conjunction with the accompanying drawings. It should be understood that the drawings are not necessarily drawn to scale. In the drawings:
fig. 1 is a flowchart of a task information processing method according to an embodiment of the present invention;
FIG. 2 is a diagram of a task information processing apparatus according to an embodiment of the present invention;
FIG. 3 is a diagram of another task information processing apparatus according to an embodiment of the present invention;
FIG. 4 is a flowchart of another task information processing method according to an embodiment of the present invention;
FIG. 5 is a diagram of another task information processing apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of another task information processing apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
For the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", and the like are used to distinguish the same items or similar items with basically the same functions or actions, and those skilled in the art can understand that the words "first", "second", and the like do not limit the quantity and execution order.
The term "and/or" herein is merely an association describing 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.
The term "comprises/comprising" when used herein refers to the presence of a feature, element or component, but does not preclude the presence or addition of one or more other features, elements or components.
The task information related to the embodiment of the invention includes but is not limited to: temporary work, short-term work, or concurrent work, etc. Specifically, the job positions corresponding to the task information include, but are not limited to: clean keeping, driver or nurse.
An execution main body of the task information processing method provided by the embodiment of the present invention is a task information output device, and for example, the task information output device may be a terminal device, an application program (APP for short) installed on the terminal device, or a server performing background processing. The terminal device may be a smart phone, a tablet Computer, a notebook Computer, a UMPC (Ultra-mobile Personal Computer, chinese short for super mobile Personal Computer), a netbook, a PDA (Personal Digital Assistant, chinese short for Personal Digital Assistant), and the like, but is not limited thereto.
An embodiment of the present invention provides a task information processing method, as shown in fig. 1, the method includes:
101. and acquiring user information of the target user.
Preferably, the target user corresponds to a user whose user position information is within the set area range in the set period, and/or the commute time from the user position information to the set position in the set period is less than or equal to the threshold.
Illustratively, the user information includes, but is not limited to, the following: user location information, and a personal tag, wherein: personal tags are used to describe the user's relevant information, such as: age, gender, identification number, registration address, work experience, and the like; the personal tag may be one or more, for example: tag 1, tag 2, … …, tag n.
For example, the user location information may be obtained by the user terminal from the current geographical location of the user, or may be selected by the job seeker from the current geographical location of the user.
For example, in the embodiment of the present invention, the user information of the target user may be obtained by receiving text information or voice information. Preferably, for a user who is unfamiliar with the internet and has low culture degree, typing is difficult, and a mode of receiving voice information is preferably selected to obtain user information.
Optionally, before the step 101, the method further includes:
101a, screening users according to task requirements.
The task requirements are set according to the needs of enterprises or testers, and the task requirements are not unique and can be changed according to different enterprises or users. Wherein different task requirements correspond to different target users. For example, when the task requirement is nanny finding, the screened users are nanny; and when the task requirement is to find the driver, the screened user is the driver.
Illustratively, the step 101 specifically includes the following steps:
101b1, first user information of the first user is obtained.
The first user information of the first user includes first user location information of the first user.
For example, the user information of the first user may be sent through the receiving terminal, or may be input by a user (e.g., a job seeker), where: the input method by the user is not limited, and includes voice or text input.
101b2, when the first user position information is in the set area range in the set period, the target user includes the first user.
In the embodiment of the invention, the first user position information of the first user is compared with the registered address in the user information through a Geohash coding system, the user with the comparison result within a certain threshold range is determined as the first user, then the current geographic position of the first user is periodically updated, and for the first user which is within a set area range within a period of time, a good user label is added to the first user, and the first user is determined as a target user. Due to the fact that the users are screened in time and space, when the enterprise selects the appropriate users according to task requirements in the follow-up process, the regional performance and the real-time performance are fully considered, and the follow-up efficiency when the users are matched with the tasks is improved.
Further optionally, in the embodiment of the present invention, a user whose comparison result is within a certain threshold range is determined as an "accurate user", and the user is stored as a user tag, so as to update the user information.
Illustratively, the step 101 may further include the following steps:
101c1, obtaining first user information of a first user, wherein the first user information comprises first user position information of the first user.
101c2, when the commute time from the first user position information to the set position in the set period is less than or equal to the threshold value, making the target user comprise the first user.
Illustratively, the step 101 may further include the following steps:
101d1, first user information of the first user is obtained, and the first user information comprises first user position information of the first user.
101d2, when the first user position information is within the set area within the set period and when the commute time from the first user position information to the set position within the set period is less than or equal to the threshold, making the target user include the first user.
In order to further improve the matching efficiency of subsequent users and tasks, the target users are determined through the steps of 101d1-101d2 in the embodiment of the invention, and when the conditions in 101d1 and 101d2 are simultaneously met, the determined target users can better meet the requirements of the enterprise job seekers in the region and in the real-time, so that the time spent on the results returned by the server or the terminal is less, and the matching accuracy is higher.
102. And calculating the similarity score of each target user matched with the user information according to the user information of the target user and the task information of a target task.
Illustratively, the task information includes, but is not limited to, the following: the geographic location and task label that the task is located, wherein: task tags are used to describe relevant information for a task, such as: task name, task duration, task requirements, salaries and the like; the task tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Preferably, before the step 102, the method further comprises:
102a1, obtaining user information and task information.
102a2, extracting a first keyword of the user information and a second keyword of the task information by adopting a word segmentation algorithm, and establishing a first mapping relation between the first keyword and the user information and a second mapping relation between the second keyword and the task information.
102a3, obtaining user location information and personal tags from the first mapping relationship, and obtaining geographic locations and task tags where the tasks are located from the second mapping relationship.
Illustratively, the invention adopts a word segmentation algorithm to extract keywords and then respectively establishes the specific contents of the keywords, the user information and the task information as follows: preprocessing a text of user information and task information, removing redundant spaces, dividing the text into a plurality of clauses and phrases according to punctuation marks, segmenting the text, calculating the frequency value of the words by using a TF/IDF algorithm, and taking a keyword of which the frequency value is greater than a threshold value T as a candidate keyword; carrying out similarity analysis on the candidate keywords, and selecting a K-means mean clustering algorithm to carry out clustering analysis on the candidate words to screen out the candidate keywords; matching the candidate keywords with data in a keyword database, determining final target keywords, after extraction of the user information and task information keywords is completed, storing the user information and task information keywords in the keyword database, and establishing a mapping relation between the user information and the keywords and a mapping relation between the task information and the keywords.
Illustratively, the step 102 specifically includes the following steps:
102a, obtaining a user feature vector consisting of a weight value of the user position information and a weight value of the personal label, and obtaining a task feature vector consisting of a weight value of the geographic position where the task is located and a weight value of the task label.
And 102b, calculating a similarity score of each target user matched with the task information according to the user feature vector and the task feature vector.
Alternatively, the similarity score may be calculated using cosine similarity.
Illustratively, based on the contents of the above steps 102a and 102b, the following gives the above exemplary implementation: the user feature vector is Vector quantityAnd q, the correlation, i.e. the similarity, is:
optionally, the method further includes: normalizing the user characteristic vector and the task characteristic vector to obtain a normalized vector; then, calculating cosine similarity between the normalized user characteristic vector and the task characteristic vector by adopting a parallel calculation mode to obtain N cosine similarity values; and searching the cosine similarity value with the maximum value from the N cosine similarity values.
Further optionally, before the step 102a, the method further comprises the following steps:
102c, initializing each weight value in the user feature vector and each weight value in the task feature vector.
102d, inputting the initialized ownership weight values into the neural network, and training all the weight values.
Illustratively, through the steps 102c and 102d, each weight value in the user feature vector and the task feature vector can be obtained as follows: training a weight value of a current geographic position where a target user is located, a weight value of a personal label, a weight value of a geographic position where a task is located and a weight value of a task label by using a BP neural network algorithm; taking the geographic position and the personal label of each target user and the geographic position and the task label of the task as input layer node input values of the BP neural network; aiming at the requirements of real-time performance and regionality, the initial state can be a weighted value with high abundance of geographic position information; training the neural networks through samples, adjusting output layers and weights, and training the networks through training data sets until an optimal solution meeting the threshold requirement is output.
103. And sorting the target users according to the similarity scores and outputting a target user list.
Wherein the target user list includes only a part of the target users, and the remaining target users not included have similarity scores smaller than the target users included.
For example, the above target user list may be arranged in an ascending order or a descending order according to the size of the similarity score, and a different arrangement order is selected according to the actual requirement of the user. The target user list can be obtained through the above step 103, so that the enterprise can quickly find out the appropriate staff. Because the target user is the user whose current geographic position is in the set area range in the set period and/or whose commuting time from the current geographic position of the user to the set position in the set period is less than or equal to the threshold, the regional property and the real-time property are fully considered when the users are screened, the efficiency of outputting the target user list is improved, and the target user can meet the requirements of enterprises.
Further optionally, the method further comprises:
104. and calculating the experience value score of each target user according to the user information of the target user.
105. And calculating the comprehensive score of the target user according to the experience value score of the target user and the similarity score of each target user matched with the task information.
106. And sorting the target users according to the magnitude of the comprehensive scores of the target users and outputting a target user list.
For example, the experience value of the target user is used to represent the work experience of the target user. Alternatively, the experience value of the target user may be divided into working years in the user information. Or, the modulo is a vector composed of the operating age and other user information, and the other user information is not limited here.
Illustratively, the step 105 specifically includes:
and 105a, inputting the experience value score of the target user and the similarity score of the target user matched with the task information into a calculation formula to obtain the comprehensive score of the target user.
Illustratively, the above calculation formula is: scount=α*S1+β*S2Wherein: scountA composite score for the target user, S1Scoring the experience value of the target user, S2Similarity between the target user and the task information is obtained; α is a weight corresponding to the experience value of the target user, β is a weight corresponding to the similarity between the target user and the task information, and α + β is 1.
Optionally, the method further includes:
107. and outputting a related friend list of the target user after detecting the starting operation of checking the user information of the target user.
The embodiment of the invention can obtain the information of other users which is relatively related to the target user, so as to save the management cost or uniformly realize the management of personnel.
Optionally, the method further includes the following steps:
108. and after receiving the triggering operation of task completion, displaying an evaluation scoring interface.
109. And receiving evaluation information of the evaluation target user, and displaying the evaluation information on an evaluation scoring interface.
Through the content, the evaluation scoring of the enterprise on the target user can be realized after the task is completed, and the new working experience can be stored and generated, so that the target user can refer to the evaluation scoring when acquiring the next task or searching the next user by the enterprise, and a user which enables the enterprise to be more satisfied can be obtained.
Optionally, the method further includes the following steps:
110. the cost of the target user is verified based on the mission information.
111. And paying the expense of the target user to the account of the target user through the bank gateway.
Through the content, the embodiment of the invention can realize online payment after the task is completed, so that a safe and convenient payment environment can be provided for enterprises and users, and convenience is brought to the users.
A task information processing apparatus provided by an embodiment of the present invention will be described below based on a description about an embodiment of a task information processing method corresponding to fig. 1. Technical terms, concepts and the like related to the above embodiments in the following embodiments may refer to the above embodiments, and are not described in detail herein.
An embodiment of the present invention provides a task information processing apparatus, as shown in fig. 2, where the task information processing apparatus 2 includes: a first obtaining module 201, a calculating module 202 and an output module 203, wherein:
a first obtaining module 201, configured to obtain user information of a target user. The target user accords with the user whose user position information is in the set area range in the set period, and/or the commute time of the target user from the user position information to the set position in the set period is less than or equal to the threshold value.
And the calculating module 202 is configured to calculate a similarity score between each target user and task information according to the user information of the target user and the task information of a target task.
And the output module 203 is used for sorting the target users according to the similarity scores and outputting a target user list.
For example, the first obtaining module 201 is specifically configured to:
first user information of a first user is obtained, and the first user information comprises first user position information of the first user.
And when the first user position information is in the set area range in the set period, enabling the target user to comprise the first user.
For example, the first obtaining module 201 is further specifically configured to:
the method comprises the steps of obtaining first user information of a first user, wherein the first user information comprises first user position information of the first user.
And when the commute time from the first user position information to a set position in a set period is less than or equal to a threshold value, enabling the target user to comprise the first user.
For example, the first obtaining module 201 is further specifically configured to:
the method comprises the steps of obtaining first user information of a first user, wherein the first user information comprises first user position information of the first user.
And when the first user position information is in the range of the set area in the set period and the commute time from the first user position information to the set position in the set period is less than or equal to the threshold value, enabling the target user to comprise the first user.
Illustratively, the user information includes, but is not limited to, the following: user location information, and a personal tag, wherein: personal tags are used to describe the user's relevant information, such as: age, gender, identification number, registration address, work experience, and the like; the personal tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Illustratively, the task information includes, but is not limited to, the following: the geographic location and task label that the task is located, wherein: task tags are used to describe relevant information for a task, such as: task name, task duration, task requirements, salaries and the like; the task tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Preferably, the calculation module 202 is specifically configured to:
the method comprises the steps of obtaining a user feature vector consisting of a user position information weight value and a personal label weight value, and obtaining a task feature vector consisting of a task position weight value and a task label weight value.
And calculating the similarity score of each target user and the task information according to the user feature vector and the task feature vector.
Further optionally, as shown in fig. 3, the task information processing apparatus 2 further includes: an initialization module 204 and a training module 205, wherein:
an initializing module 204, configured to initialize each weight value in the user feature vector and each weight value in the task feature vector.
The training module 205 is configured to input the initialized ownership weight values to the neural network, and train all the weight values.
Further optionally, as shown in fig. 3, the task information processing module 2 further includes: a building module 206 and a second obtaining module 207, wherein:
the first obtaining module 201 is further configured to obtain user information and task information.
The establishing module 206 is configured to extract a first keyword of the user information and a second keyword of the task information by using a word segmentation algorithm, and establish a first mapping relationship between the first keyword and the user information and a second mapping relationship between the second keyword and the task information.
And a second obtaining module 207, configured to obtain the current geographic location and the personal tag where the user is located from the first mapping relationship, and obtain the geographic location and the task tag where the task is located from the second mapping relationship.
Further optional:
the calculating module 202 is further configured to calculate an experience value score of each target user according to the user information of the target user.
The calculating module 202 is further configured to calculate a comprehensive score of the targeted user according to the experience value score of the targeted user and the similarity score of each targeted user matching the task information.
The output module 203 is further configured to sort the target users according to the magnitude of the composite scores of the target users and output a target user list.
Further optionally, the output module 203 is further configured to output the related buddy list of the target user after detecting the trigger operation for viewing the user information of the target user.
Further optionally, as shown in fig. 3, the task information processing apparatus 2 further includes: a display module 208, wherein:
and the display module 208 is configured to display an evaluation scoring interface after receiving the trigger operation of task completion.
The display module 208 is further configured to receive evaluation information of the evaluation target user, and display the evaluation information on the evaluation scoring interface.
Further optionally, as shown in fig. 3, the task information processing apparatus 2 further includes: a fee verification module 209 and a payment module 210, wherein:
a fee verification module 210 for verifying the fee of the target user based on the task information.
And the payment module 211 is configured to pay the fee of the target user to an account of the target user through the bank gateway.
An embodiment of the present invention provides a computer-readable storage medium storing a computer program for executing the method described above with reference to fig. 1.
By way of example, computer-readable storage media can be any available media that can be accessed by a computer or a data storage device, such as a server, data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Compared with the prior art, the task information processing method and the task information processing device provided by the invention have the advantages that firstly, the user information of the target user is obtained, and the target user is a user of which the current geographic position of the user is in the set area range in the set period and/or the commute time from the current geographic position of the user to the set position in the set period is less than or equal to the threshold value; then, calculating the similarity score of each target user and the task information according to the user information and the task information of the target user; and finally, outputting a target user list according to the similarity score. Due to the fact that geographical positions and time periods are adopted for filtering the target users regionally and in real time, time spent on results returned by the server or the terminal is small, and matching accuracy is high.
An embodiment of the present invention provides a method for processing task information, as shown in fig. 4, the method includes:
301. and acquiring task information of the target task.
The target task meeting task position information is located in a set area range, and/or the commuting time from a set position to the task position information is smaller than or equal to a threshold value.
Illustratively, the task information includes, but is not limited to, the following: the geographic location and task label that the task is located, wherein: task tags are used to describe relevant information for a task, such as: task name, task duration, task requirements, salaries and the like; the task tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Illustratively, the above step 301 includes the following steps:
301a1, task information for a first task is obtained.
The task information of the first task comprises first task position information of the first task.
301a2, when the first task position information is within the set area range, the target task is made to include the first task.
For example, the task information of the first task may be sent through a receiving terminal, or may be input by a user (e.g., a recruiter), where: the input method by the user is not limited, and includes voice or text input.
Through the content, the target task is screened according to the geographic position, so that matching time can be saved when task information of the target task is matched with user information subsequently, matching efficiency is improved, and the requirement of an enterprise on searching for regions of operating personnel can be met.
Illustratively, the step 301 further includes the following steps:
301b1, obtaining first task information of a first task, the first task information including first task location information of the first task.
301b2, when the commute time from the first task position information to the set position is less than the threshold value, the target task is made to include the first task. Illustratively, the step 301 further includes the following steps:
301c1, first task information of the first task is obtained, the first task information including first task location information of the first task.
301c2, when the first task position information is within the set area range and when the commute time from the first task position information to the set position is less than the threshold, causing the target task to include the first task.
In order to further improve the matching efficiency of subsequent users and tasks, the target tasks are determined through the steps 301c1-301c2 in the embodiment of the invention, and when the conditions in 301c1-301c2 are simultaneously met, the determined target tasks can better meet the regional requirements of job seekers, so that the time spent on the results returned by the server or the terminal is less, and the matching accuracy is higher.
302. And calculating the similarity score of each target task matched with the user information according to the task information of the target task and the user information of the first target user.
Illustratively, the user information includes, but is not limited to, the following: user location information, and a personal tag, wherein: personal tags are used to describe the user's relevant information, such as: age, gender, identification number, registration address, work experience, and the like; the personal tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Illustratively, the step 302 includes the following steps:
302a, acquiring a task feature vector consisting of a weight value of the task position information and a weight value of the task label, and acquiring a user feature vector consisting of a weight value of the user position information and a weight value of the personal label.
And 302b, calculating a similarity score of each target task matched with the user information according to the task feature vector and the user feature vector.
Alternatively, the similarity score may be calculated using cosine similarity.
Illustratively, based on the contents of the above steps 302a and 302b, the following gives the above exemplary implementation: the user feature vector is Vector quantityAnd q, the correlation, i.e. the similarity, is:
optionally, the method further includes: normalizing the user characteristic vector and the task characteristic vector to obtain a normalized vector; then, calculating cosine similarity between the normalized user characteristic vector and the task characteristic vector by adopting a parallel calculation mode to obtain N cosine similarity values; and searching the cosine similarity value with the maximum value from the N cosine similarity values.
Further optionally, before the step 302a, the method further includes the following steps:
302c, initializing each weight value in the user feature vector and each weight value in the task feature vector.
302d, inputting the initialized ownership weight values into the neural network, and training all the weight values.
Illustratively, through the steps 302c and 302d, each weight value in the user feature vector and the task feature vector can be obtained as follows: training a weight value of a current geographic position where a target user is located, a weight value of a personal label, a weight value of a geographic position where a task is located and a weight value of a task label by using a BP neural network algorithm; taking the geographic position and the personal label of each target user and the geographic position and the task label of the task as input layer node input values of the BP neural network; aiming at the requirements of real-time performance and regionality, the initial state can be a weighted value with high abundance of geographic position information; training the neural networks through samples, adjusting output layers and weights, and training the networks through training data sets until an optimal solution meeting the threshold requirement is output.
303. And sorting the target tasks according to the similarity scores and outputting a target task list.
Wherein, the target task list only comprises part of the target tasks, and the rest of the target tasks not comprising the part have similarity scores smaller than the target tasks comprising the part.
For example, the above target user list may be arranged in an ascending order or a descending order according to the size of the similarity score, and a different arrangement order is selected according to the actual requirement of the user.
The target task list can be obtained through the above step 303, so that the job seeker can quickly find a suitable task. Because the geographical position of the target task is within the set area range and/or the commute time from the set position to the geographical position of the target task is less than or equal to the threshold value, the determined target task can better meet the regional requirement of the job seeker, so that the time spent on the result returned by the server or the terminal is less, and the matching accuracy is higher.
Further optionally, the method further comprises:
304. and calculating the value score of each target task according to the task information of the target task.
305. And calculating the comprehensive score of the target task according to the value score of the target task and the similarity score of each target task matched with the user information.
306. And outputting a target task list according to the comprehensive score of the target task.
Illustratively, the value score of the target task is used to represent the value of the target task, such as: experience or revenue due to the target mission. Optionally, the value score of the target task may be a salary condition in the task information, for example, the value score of the target task is 10 when the salary is in the first interval range, the value score of the target task is 8 when the salary condition is in the second interval range, and the value score of the target task is 6 when the salary condition is in the third interval range. Or, the model of the vector composed of the salary condition and other task information, and the other task information is not limited herein.
Illustratively, the step 305 specifically includes:
305a, inputting the value score of the target task and the similarity score of the target user matched with the task information into a calculation formula to obtain the comprehensive score of the target task.
Illustratively, the above calculation formula is: s'count=α’*S’1+β’*S’2Wherein: s'countIs the composite score, S 'of the target task'1Value score, S 'for target task'2Similarity between the target user and the task information is obtained; α 'is a weight corresponding to the value score of the target task, β' is a weight corresponding to the similarity between the target user and the task information, and α '+ β' is 1.
Optionally, the method further includes:
307. and calculating a similarity score between the first target user and the second target user according to the user feature vector.
308. And when the similarity score between the first target user and the second target user is smaller than or equal to the threshold value, judging that the first target user and the second target user are similar users.
309. And after the starting operation that the second target user checks the target task information is detected, outputting the target task list of the first target user to the second target user.
For example, in step 307, the similarity score between the first user and the second user may be determined by a cosine similarity calculation formula, or may be calculated by classifying the users using an SVM classifier.
The embodiment of the invention can obtain the task information browsed by the first target user similar to the second target user, so that on one hand, other task information can be obtained for the user to select, and on the other hand, the information concerned by the user belonging to the same type as the user can be known to be used as reference.
Optionally, the method further includes the following steps:
310. and after receiving the starting operation of the task completion, displaying an evaluation scoring interface.
311. And receiving evaluation information of the evaluation target task, and displaying the evaluation information on an evaluation scoring interface.
Through the content, the evaluation scoring of the target task by the user can be realized after the task is completed, and the new task information can be stored and generated, so that other users can refer to the evaluation scoring when selecting similar tasks, and the user can more comprehensively know the specific situation of the task to be selected.
Optionally, the method further includes:
312. the cost of the target user is verified based on the mission information.
313. And paying the expense of the target user to the account of the target user through the bank gateway.
Through the content, the embodiment of the invention can realize online payment after the task is completed, so that a safe and convenient payment environment can be provided for enterprises and users, and convenience is brought to the users.
A task information processing apparatus provided by an embodiment of the present invention will be described below based on a description about an embodiment of a task information processing method corresponding to fig. 3. Technical terms, concepts and the like related to the above embodiments in the following embodiments may refer to the above embodiments, and are not described in detail herein.
An embodiment of the present invention provides a task information processing apparatus, and as shown in fig. 5, the task information processing apparatus 4 includes: an obtaining module 401, a calculating module 402 and an output module 403, wherein:
the obtaining module 401 is configured to obtain task information of a target task.
The target task meeting task position information is in a set area range, and/or the commuting time from a set position to the task position information is smaller than or equal to a threshold value.
A calculating module 402, configured to calculate, according to the task information of the target task and the user information of the first target user, a similarity score that each target task matches the user information.
And an output module 403, configured to sort the target tasks according to the similarity scores and output a target task list.
Illustratively, the user information includes, but is not limited to, the following: user location information, and a personal tag, wherein: personal tags are used to describe the user's relevant information, such as: age, gender, identification number, registration address, work experience, and the like; the personal tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Illustratively, the task information includes, but is not limited to, the following: the geographic location and task label that the task is located, wherein: task tags are used to describe relevant information for a task, such as: task name, task duration, task requirements, salaries and the like; the task tag may be one or more, for example: tag 1, tag 2, … …, tag n.
Illustratively, the obtaining module 401 is specifically configured to:
task information of the first task is obtained, and the task information of the first task comprises first task position information of the first task.
And when the first task position information is within the set area range, enabling the target task to comprise the first task.
For example, the obtaining module 401 is further configured to:
task information of the first task is obtained, and the task information of the first task comprises first task position information of the first task.
And when the commute time from the first task position information to the set position is less than a threshold value, enabling the target task to comprise the first task.
For example, the obtaining module 401 is further configured to:
first task information of the first task is obtained, and the first task information comprises first task position information of the first task.
When the first task position information is within the set area range and when the commute time from the first task position information to the set position is less than a threshold value, the target task is made to include the first task.
Preferably, the calculating module 402 is specifically configured to:
the method comprises the steps of obtaining a task feature vector consisting of a weight value of task position information and a weight value of a task label, and obtaining a user feature vector consisting of a weight value of user position information and a weight value of a personal label.
And calculating the similarity score of each target task and the user information according to the task feature vector and the user feature vector.
Alternatively, the similarity score may be calculated using cosine similarity. Further optionally, as shown in fig. 6, the task information processing apparatus 4 further includes: an initialization module 404 and a training module 405, wherein:
an initialization module 404, configured to initialize each weight value in the user feature vector and each weight value in the task feature vector.
The training module 405 is configured to input the initialized ownership weight values to the neural network, and train all the weight values.
Further optionally, as shown in fig. 6, the task information processing apparatus 4 further includes: a decision block 406, wherein:
the calculating module 402 is further configured to calculate a similarity score between the first user and the second user according to the user feature vector.
The determining module 406 determines that the first target user and the second target user are similar users when the similarity score between the first target user and the second target user is less than or equal to the threshold.
The output module 403 is further configured to, after detecting that the second target user starts to check the target task information, output the target task list of the second target user for the first target user.
Further optional:
the calculating module 402 is further configured to calculate a value score of each target task according to the task information of the target task.
The calculating module 402 is further configured to calculate a comprehensive score of the target task according to the value score of the target task and the similarity score of each target task matching the user information.
The output module 403 is further configured to output the target task list according to the size of the composite score of the target task.
Further optionally, as shown in fig. 6, the task information processing apparatus 4 further includes: a display module 407, wherein:
and the display module 407 is configured to display an evaluation scoring interface after receiving the trigger operation of task completion.
The display module 407 is further configured to receive evaluation information of the evaluation target task, and display the evaluation information on the evaluation scoring interface.
Further optionally, as shown in fig. 6, the task information processing apparatus 4 further includes: a fee verification module 408 and a payment module 409, wherein:
a fee verification module 408 for verifying the fee of the target user based on the task information.
And the payment module 409 is used for paying the cost of the target user to the account of the target user through the bank gateway.
An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program for executing the method described above with reference to fig. 3.
By way of example, computer-readable storage media can be any available media that can be accessed by a computer or a data storage device, such as a server, data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Compared with the prior art, the task information processing method and the device provided by the invention have the advantages that firstly, the task information of the target task is obtained, the geographical position of the target task is in the range of the set area, and/or the commuting time from the set position to the geographical position of the target task is less than or equal to the threshold value; then, calculating a similarity score between each target task and the user information according to the task information and the user information of the target task; and finally, outputting a target task list according to the similarity score. Due to the fact that geographical positions are adopted to achieve regional screening of the target tasks, time spent on results returned by the server or the terminal is short, and matching accuracy is high.
Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, only the division of the functional modules is illustrated, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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, and can also be realized in a form of a software functional unit.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (11)
1. A method for processing task information, the method comprising:
acquiring user information of a user, wherein the user information comprises a user position;
comparing the user position with the registered address in the user information through a Geohash coding system, and determining the user with the comparison result within a certain threshold range as a first user; periodically updating the geographical position of the first user, and determining the first user in a set area range within a period of time as a target user;
determining the user as a target user when the commute time from the user position to a set position is less than or equal to a threshold value;
calculating the similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and
and sorting the target users according to the similarity scores and outputting a target user list.
2. The method of claim 1, wherein the user information further comprises a personal tag, and wherein the task information comprises a geographic location where the task is located and a task tag; wherein the step of calculating a similarity score comprises:
acquiring a user characteristic vector consisting of a weight value of the user position and a weight value of the personal label, and acquiring a task characteristic vector consisting of a weight value of the geographic position where the task is located and a weight value of the task label; and
and calculating the similarity score of each target user matched with the task information according to the user feature vector and the task feature vector.
3. The method of claim 2, further comprising:
initializing each weight value in the user characteristic vector and each weight value in the task characteristic vector; and
and inputting the initialized ownership weight value into the neural network, and training all weight values.
4. The method of claim 3, further comprising:
acquiring user information and task information;
extracting a first keyword of the user information and a second keyword of the task information by adopting a word segmentation algorithm, and establishing a first mapping relation between the first keyword and the user information and a second mapping relation between the second keyword and the task information; and
and acquiring the user position and the personal label from the first mapping relation, and acquiring the geographic position of the task and the task label from the second mapping relation.
5. The method of claim 1, further comprising:
calculating the experience value score of each target user according to the user information of the target user;
calculating a comprehensive score of the target user according to the experience value score of the target user and the similarity score of each target user matched with the task information; and
and sorting the target users according to the magnitude of the comprehensive scores of the target users and outputting the target user list.
6. The method of claim 1, further comprising:
and outputting a related friend list of the target user after detecting the triggering operation of checking the user information of the target user.
7. The method of claim 1, further comprising:
after receiving the triggering operation of task completion, displaying an evaluation scoring interface; and
and receiving evaluation information for evaluating the target user, and displaying the evaluation information on an evaluation scoring interface.
8. The method of claim 7, after the receiving a triggering action for task completion step, the method further comprising:
verifying the cost of the target user according to task information; and
and paying the expense of the target user to an account of the target user through a bank gateway.
9. The method of any one of claims 1-8, wherein the similarity scores of the target users in the list of target users are higher than the similarity scores of other target users.
10. A task information processing apparatus characterized by comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring user information of a user, and the user information comprises a user position;
the determining module is used for comparing the user position with the registration address in the user information through a Geohash coding system, and determining the user with the comparison result within a certain threshold range as a first user; periodically updating the geographical position of the first user, and determining the first user in a set area range within a period of time as a target user;
the determining module is further used for determining the user as a target user when the commute time from the user position to a set position is less than or equal to a threshold value;
the calculation module is used for calculating the similarity score of each target user matched with the task information according to the user information of the target user and the task information of a target task; and
and the output module is used for sorting the target users according to the similarity scores and outputting a target user list.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for performing the method of any one of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205292.5A CN109918583B (en) | 2019-03-18 | 2019-03-18 | Task information processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205292.5A CN109918583B (en) | 2019-03-18 | 2019-03-18 | Task information processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109918583A CN109918583A (en) | 2019-06-21 |
CN109918583B true CN109918583B (en) | 2020-01-24 |
Family
ID=66965411
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910205292.5A Active CN109918583B (en) | 2019-03-18 | 2019-03-18 | Task information processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109918583B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112765492B (en) * | 2020-12-31 | 2021-08-10 | 浙江省方大标准信息有限公司 | Sequencing method for inspection and detection mechanism |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104346677A (en) * | 2013-08-07 | 2015-02-11 | 优比泰克(北京)科技有限公司 | Recruitment and employment system and method based on LBS (Location Based Service) |
CN105786813A (en) * | 2014-12-17 | 2016-07-20 | 北京邮电大学 | Method and device for sending task information |
CN105989549A (en) * | 2015-02-06 | 2016-10-05 | 白忠泽 | Life service function method based on mobile Internet and system thereof |
CN106997396A (en) * | 2017-04-14 | 2017-08-01 | 徐燮鹏 | Supply and demand information interconnected method and system |
CN107220800A (en) * | 2017-04-25 | 2017-09-29 | 浙江铁牌科技有限公司 | Talent's supply and demand information system based on region |
-
2019
- 2019-03-18 CN CN201910205292.5A patent/CN109918583B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104346677A (en) * | 2013-08-07 | 2015-02-11 | 优比泰克(北京)科技有限公司 | Recruitment and employment system and method based on LBS (Location Based Service) |
CN105786813A (en) * | 2014-12-17 | 2016-07-20 | 北京邮电大学 | Method and device for sending task information |
CN105989549A (en) * | 2015-02-06 | 2016-10-05 | 白忠泽 | Life service function method based on mobile Internet and system thereof |
CN106997396A (en) * | 2017-04-14 | 2017-08-01 | 徐燮鹏 | Supply and demand information interconnected method and system |
CN107220800A (en) * | 2017-04-25 | 2017-09-29 | 浙江铁牌科技有限公司 | Talent's supply and demand information system based on region |
Also Published As
Publication number | Publication date |
---|---|
CN109918583A (en) | 2019-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145219B (en) | Method and device for judging validity of interest points based on Internet text mining | |
CN108629043B (en) | Webpage target information extraction method, device and storage medium | |
CN109947909B (en) | Intelligent customer service response method, equipment, storage medium and device | |
CN111461637A (en) | Resume screening method and device, computer equipment and storage medium | |
CN111105209A (en) | Job resume matching method and device suitable for post matching recommendation system | |
CN111125343A (en) | Text analysis method and device suitable for human-sentry matching recommendation system | |
CN110147421B (en) | Target entity linking method, device, equipment and storage medium | |
US20180181544A1 (en) | Systems for Automatically Extracting Job Skills from an Electronic Document | |
US20210349893A1 (en) | Method and system for analytic based connections among user types in an online platform | |
CN110532480B (en) | Knowledge graph construction method for recommending human-read threat information and threat information recommendation method | |
CN114238573A (en) | Information pushing method and device based on text countermeasure sample | |
CN117114514A (en) | Talent information analysis management method, system and device based on big data | |
CN115577172A (en) | Article recommendation method, device, equipment and medium | |
CN114691869A (en) | User label generation method and system | |
CN109918583B (en) | Task information processing method and device | |
CN112182390B (en) | Mail pushing method, device, computer equipment and storage medium | |
CN113569118A (en) | Self-media pushing method and device, computer equipment and storage medium | |
CN111061939B (en) | Scientific research academic news keyword matching recommendation method based on deep learning | |
CN107609921A (en) | A kind of data processing method and server | |
CN115099832B (en) | Abnormal user detection method and device, equipment, medium and product thereof | |
CN111382254A (en) | Electronic business card recommendation method, device, equipment and computer readable storage medium | |
CN116862641A (en) | Credit product recommendation method and device, electronic equipment and storage medium | |
CN115935953A (en) | False news detection method and device, electronic equipment and storage medium | |
US20230046851A1 (en) | Multi-model approach to natural language processing and recommendation generation | |
CN112084408B (en) | List data screening method, device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |